Compare commits
No commits in common. "main" and "refs/deployment/triton" have entirely different histories.
main
...
refs/deplo
39
.gitattributes
vendored
39
.gitattributes
vendored
@ -1,39 +0,0 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.model filter=lfs diff=lfs merge=lfs -text
|
||||
252
1/model.py
Normal file
252
1/model.py
Normal file
@ -0,0 +1,252 @@
|
||||
"""
|
||||
[Transformer-LLM 백엔드 가이드]
|
||||
|
||||
본 파일은 NVIDIA Triton Server에서 Hugging Face `AutoModelForCausalLM` 기반 모델을 손쉽게 배포하기 위해 제공되는 커스텀 Python 백엔드 템플릿입니다.
|
||||
|
||||
1. 모델 호환성
|
||||
- Hugging Face의 `AutoModelForCausalLM` 클래스와 호환되는 모든 Causal Language Model을 지원합니다.
|
||||
- [확인] 배포할 모델 `config.json`의 `architectures` 항목이 `...ForCausalLM` 형식인지 확인.
|
||||
2. 토크나이저 호환성
|
||||
- `AutoTokenizer`와 호환되는 토크나이저를 지원하며, 모델과 동일한 경로에서 자동으로 로드됩니다.
|
||||
|
||||
3. 커스터마이징 안내
|
||||
- 본 템플릿은 범용적인 사용을 위해 작성되었습니다.
|
||||
- 특정 모델의 동작 방식이나 예외 처리가 필요한 경우, 이 파일(`model.py`)과 설정 파일(`config.pbtxt`)을 직접 수정하여 사용하시기 바랍니다.
|
||||
"""
|
||||
|
||||
import json
|
||||
import torch
|
||||
import numpy as np
|
||||
import triton_python_backend_utils as pb_utils
|
||||
import uuid
|
||||
from typing import List, Dict, Any, Union, Tuple
|
||||
|
||||
from transformers import (
|
||||
AutoModelForCausalLM,
|
||||
AutoTokenizer,
|
||||
GenerationConfig,
|
||||
BitsAndBytesConfig,
|
||||
)
|
||||
from peft import PeftModel, PeftConfig
|
||||
|
||||
class TritonPythonModel:
|
||||
def initialize(self, args: Dict[str, str]):
|
||||
"""
|
||||
모델 초기화: 설정 로드, 로거 설정, 모델 및 토크나이저 로드
|
||||
"""
|
||||
self.logger = pb_utils.Logger
|
||||
self.model_config = json.loads(args["model_config"])
|
||||
self.model_name = args["model_name"]
|
||||
|
||||
# 설정 파라미터 로드
|
||||
self.base_model_path = self._get_config_param("base_model_path")
|
||||
self.is_adapter_model = self._get_config_param("is_adapter_model", "false").lower() == "true"
|
||||
self.adapter_model_path = self._get_config_param("adapter_model_path")
|
||||
self.quantization = self._get_config_param("quantization")
|
||||
self.device = "cuda" if torch.cuda.is_available() else "cpu"
|
||||
|
||||
# 설정 로그 출력
|
||||
self.logger.log_info(f"================ {self.model_name} Setup ================")
|
||||
self.logger.log_info(f"Base Model: {self.base_model_path}")
|
||||
self.logger.log_info(f"Adapter Mode: {self.is_adapter_model} ({self.adapter_model_path})")
|
||||
self.logger.log_info(f"Quantization: {self.quantization}")
|
||||
self.logger.log_info(f"Device: {self.device}")
|
||||
|
||||
self._load_model_and_tokenizer()
|
||||
self.logger.log_info(f"Model initialized successfully.")
|
||||
|
||||
def _load_model_and_tokenizer(self):
|
||||
"""모델과 토크나이저를 로드하고 설정합니다."""
|
||||
# 1. Quantization 설정
|
||||
bnb_config = self._get_bnb_config()
|
||||
|
||||
# 2. Base Model 로드
|
||||
load_path = self.base_model_path
|
||||
if self.is_adapter_model:
|
||||
peft_config = PeftConfig.from_pretrained(self.adapter_model_path)
|
||||
load_path = peft_config.base_model_name_or_path
|
||||
|
||||
try:
|
||||
self.model = AutoModelForCausalLM.from_pretrained(
|
||||
load_path,
|
||||
torch_dtype="auto",
|
||||
quantization_config=bnb_config,
|
||||
device_map="auto",
|
||||
local_files_only=True,
|
||||
trust_remote_code=True
|
||||
)
|
||||
except Exception as e:
|
||||
self.logger.log_error(f"Failed to load base model: {e}")
|
||||
raise e
|
||||
|
||||
# 3. Adapter 병합 (필요 시)
|
||||
if self.is_adapter_model:
|
||||
self.model = PeftModel.from_pretrained(self.model, self.adapter_model_path)
|
||||
|
||||
self.model.eval()
|
||||
|
||||
# 4. Tokenizer 로드
|
||||
self.tokenizer = AutoTokenizer.from_pretrained(load_path, trust_remote_code=True)
|
||||
|
||||
if self.tokenizer.pad_token is None:
|
||||
self.tokenizer.pad_token = self.tokenizer.eos_token
|
||||
self.tokenizer.pad_token_id = self.tokenizer.eos_token_id
|
||||
self.logger.log_info("Pad token was None. Set to EOS token.")
|
||||
|
||||
self.supports_chat_template = (
|
||||
hasattr(self.tokenizer, "chat_template") and
|
||||
self.tokenizer.chat_template is not None
|
||||
)
|
||||
|
||||
self.logger.log_info(f"Supports Chat Template: {self.supports_chat_template}")
|
||||
if self.supports_chat_template:
|
||||
self.logger.log_info(f"Chat Template Content:\n{self.tokenizer.chat_template}")
|
||||
|
||||
def _get_bnb_config(self) -> Union[BitsAndBytesConfig, None]:
|
||||
if self.quantization == "int4":
|
||||
return BitsAndBytesConfig(
|
||||
load_in_4bit=True,
|
||||
bnb_4bit_use_double_quant=True,
|
||||
bnb_4bit_quant_type="nf4",
|
||||
bnb_4bit_compute_dtype=torch.float16
|
||||
)
|
||||
elif self.quantization == "int8":
|
||||
return BitsAndBytesConfig(
|
||||
load_in_8bit=True,
|
||||
llm_int8_threshold=6.0,
|
||||
llm_int8_has_fp16_weight=True
|
||||
)
|
||||
return None
|
||||
|
||||
def execute(self, requests):
|
||||
"""Triton Inference Request 처리 메인 루프"""
|
||||
responses = []
|
||||
|
||||
for request in requests:
|
||||
# [ID 생성 로직] - 로그 추적용으로 유지 (Response에는 포함 X)
|
||||
request_id = request.request_id()
|
||||
if not request_id:
|
||||
request_id = str(uuid.uuid4())
|
||||
|
||||
try:
|
||||
# 1. 입력 데이터 파싱
|
||||
input_data, is_chat = self._parse_input(request)
|
||||
|
||||
# [LOGGING] Request ID 포함하여 로그 출력
|
||||
log_input_str = json.dumps(input_data, ensure_ascii=False) if isinstance(input_data, (list, dict)) else str(input_data)
|
||||
self.logger.log_info(f"\n[RID: {request_id}] >>> [{'CHAT' if is_chat else 'TEXT'}][Input]: {log_input_str}")
|
||||
|
||||
# 2. Generation Config 생성
|
||||
gen_config = self._create_generation_config(request)
|
||||
|
||||
# 3. 토크나이징
|
||||
inputs = self._tokenize(input_data, is_chat)
|
||||
|
||||
# 4. 모델 추론 (Generate)
|
||||
output_text = self._generate(inputs, gen_config)
|
||||
|
||||
# [LOGGING] Request ID 포함하여 결과 출력
|
||||
self.logger.log_info(f"\n[RID: {request_id}] <<< [Output]: {output_text}")
|
||||
|
||||
# 5. 응답 생성
|
||||
responses.append(self._create_response(output_text, request_id))
|
||||
|
||||
except Exception as e:
|
||||
self.logger.log_error(f"[RID: {request_id}] Error during execution: {e}")
|
||||
err_tensor = pb_utils.Tensor("text_output", np.array([str(e).encode('utf-8')], dtype=np.bytes_))
|
||||
responses.append(pb_utils.InferenceResponse(output_tensors=[err_tensor]))
|
||||
|
||||
return responses
|
||||
|
||||
def _parse_input(self, request) -> Tuple[Union[str, List[Dict]], bool]:
|
||||
input_text = self._get_input_scalar(request, "text_input")
|
||||
try:
|
||||
conversation = json.loads(input_text)
|
||||
if isinstance(conversation, list):
|
||||
return conversation, True
|
||||
except (json.JSONDecodeError, TypeError):
|
||||
pass
|
||||
return input_text, False
|
||||
|
||||
def _tokenize(self, input_data, is_chat: bool):
|
||||
if self.supports_chat_template and is_chat:
|
||||
return self.tokenizer.apply_chat_template(
|
||||
input_data,
|
||||
tokenize=True,
|
||||
add_generation_prompt=True,
|
||||
return_tensors="pt",
|
||||
return_dict=True
|
||||
).to(self.device)
|
||||
else:
|
||||
if is_chat:
|
||||
input_data = str(input_data)
|
||||
return self.tokenizer(input_data, return_tensors="pt").to(self.device)
|
||||
|
||||
def _generate(self, inputs, gen_config: GenerationConfig) -> str:
|
||||
input_ids = inputs["input_ids"]
|
||||
input_len = input_ids.shape[-1]
|
||||
|
||||
with torch.no_grad():
|
||||
outputs = self.model.generate(
|
||||
**inputs,
|
||||
generation_config=gen_config,
|
||||
pad_token_id=self.tokenizer.pad_token_id,
|
||||
eos_token_id=self.tokenizer.eos_token_id
|
||||
)
|
||||
|
||||
generated_tokens = outputs[0][input_len:]
|
||||
decoded_output = self.tokenizer.decode(generated_tokens, skip_special_tokens=True)
|
||||
return decoded_output.strip()
|
||||
|
||||
def _create_generation_config(self, request) -> GenerationConfig:
|
||||
def get_param(name, default=None, cast_type=None):
|
||||
val = self._get_input_scalar(request, name, default)
|
||||
if val is not None and cast_type:
|
||||
return cast_type(val)
|
||||
return val
|
||||
|
||||
return GenerationConfig(
|
||||
max_length=get_param("max_length", 1024, int),
|
||||
max_new_tokens=get_param("max_new_tokens", 256, int),
|
||||
temperature=get_param("temperature", 1.0, float),
|
||||
do_sample=get_param("do_sample", False, bool),
|
||||
top_k=get_param("top_k", 50, int),
|
||||
top_p=get_param("top_p", 1.0, float),
|
||||
repetition_penalty=get_param("repetition_penalty", 1.0, float),
|
||||
)
|
||||
|
||||
def _create_response(self, output_text: str, request_id: str):
|
||||
"""생성된 텍스트를 Triton Response 객체로 변환"""
|
||||
output_tensor = pb_utils.Tensor(
|
||||
"text_output",
|
||||
np.array([output_text.encode('utf-8')], dtype=np.bytes_)
|
||||
)
|
||||
return pb_utils.InferenceResponse(output_tensors=[output_tensor])
|
||||
|
||||
def _get_config_param(self, key: str, default: str = None) -> str:
|
||||
params = self.model_config.get('parameters', {})
|
||||
if key in params:
|
||||
return params[key].get('string_value', default)
|
||||
return default
|
||||
|
||||
def _get_input_scalar(self, request, name: str, default=None):
|
||||
tensor = pb_utils.get_input_tensor_by_name(request, name)
|
||||
if tensor is None:
|
||||
return default
|
||||
return self._np_decoder(tensor.as_numpy()[0])
|
||||
|
||||
def _np_decoder(self, obj):
|
||||
if isinstance(obj, bytes):
|
||||
return obj.decode('utf-8')
|
||||
if np.issubdtype(obj, np.integer):
|
||||
return int(obj)
|
||||
if np.issubdtype(obj, np.floating):
|
||||
return round(float(obj), 3)
|
||||
if isinstance(obj, np.bool_):
|
||||
return bool(obj)
|
||||
|
||||
def finalize(self):
|
||||
self.logger.log_info(f"Finalizing model {self.model_name}")
|
||||
self.model = None
|
||||
self.tokenizer = None
|
||||
torch.cuda.empty_cache()
|
||||
536
README.md
536
README.md
@ -1,536 +0,0 @@
|
||||
---
|
||||
license: gemma
|
||||
library_name: transformers
|
||||
pipeline_tag: image-text-to-text
|
||||
extra_gated_heading: Access Gemma on Hugging Face
|
||||
extra_gated_prompt: To access Gemma on Hugging Face, you’re required to review and
|
||||
agree to Google’s usage license. To do this, please ensure you’re logged in to Hugging
|
||||
Face and click below. Requests are processed immediately.
|
||||
extra_gated_button_content: Acknowledge license
|
||||
base_model: google/gemma-3-4b-pt
|
||||
---
|
||||
|
||||
# Gemma 3 model card
|
||||
|
||||
**Model Page**: [Gemma](https://ai.google.dev/gemma/docs/core)
|
||||
|
||||
**Resources and Technical Documentation**:
|
||||
|
||||
* [Gemma 3 Technical Report][g3-tech-report]
|
||||
* [Responsible Generative AI Toolkit][rai-toolkit]
|
||||
* [Gemma on Kaggle][kaggle-gemma]
|
||||
* [Gemma on Vertex Model Garden][vertex-mg-gemma3]
|
||||
|
||||
**Terms of Use**: [Terms][terms]
|
||||
|
||||
**Authors**: Google DeepMind
|
||||
|
||||
## Model Information
|
||||
|
||||
Summary description and brief definition of inputs and outputs
|
||||
|
||||
### Description
|
||||
|
||||
Gemma is a family of lightweight, state-of-the-art open models from Google,
|
||||
built from the same research and technology used to create the Gemini models.
|
||||
Gemma 3 models are multimodal, handling text and image input and generating text
|
||||
output, with open weights for both pre-trained variants and instruction-tuned
|
||||
variants. Gemma 3 has a large, 128K context window, multilingual support in over
|
||||
140 languages, and is available in more sizes than previous versions. Gemma 3
|
||||
models are well-suited for a variety of text generation and image understanding
|
||||
tasks, including question answering, summarization, and reasoning. Their
|
||||
relatively small size makes it possible to deploy them in environments with
|
||||
limited resources such as laptops, desktops or your own cloud infrastructure,
|
||||
democratizing access to state of the art AI models and helping foster innovation
|
||||
for everyone.
|
||||
|
||||
### Inputs and outputs
|
||||
|
||||
- **Input:**
|
||||
- Text string, such as a question, a prompt, or a document to be summarized
|
||||
- Images, normalized to 896 x 896 resolution and encoded to 256 tokens
|
||||
each
|
||||
- Total input context of 128K tokens for the 4B, 12B, and 27B sizes, and
|
||||
32K tokens for the 1B size
|
||||
|
||||
- **Output:**
|
||||
- Generated text in response to the input, such as an answer to a
|
||||
question, analysis of image content, or a summary of a document
|
||||
- Total output context of 8192 tokens
|
||||
|
||||
### Usage
|
||||
|
||||
Below, there are some code snippets on how to get quickly started with running the model. First, install the Transformers library. Gemma 3 is supported starting from transformers 4.50.0.
|
||||
|
||||
```sh
|
||||
$ pip install -U transformers
|
||||
```
|
||||
|
||||
Then, copy the snippet from the section that is relevant for your use case.
|
||||
|
||||
#### Running with the `pipeline` API
|
||||
|
||||
You can initialize the model and processor for inference with `pipeline` as follows.
|
||||
|
||||
```python
|
||||
from transformers import pipeline
|
||||
import torch
|
||||
|
||||
pipe = pipeline(
|
||||
"image-text-to-text",
|
||||
model="google/gemma-3-4b-it",
|
||||
device="cuda",
|
||||
torch_dtype=torch.bfloat16
|
||||
)
|
||||
```
|
||||
|
||||
With instruction-tuned models, you need to use chat templates to process our inputs first. Then, you can pass it to the pipeline.
|
||||
|
||||
```python
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": [{"type": "text", "text": "You are a helpful assistant."}]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": [
|
||||
{"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
|
||||
{"type": "text", "text": "What animal is on the candy?"}
|
||||
]
|
||||
}
|
||||
]
|
||||
|
||||
output = pipe(text=messages, max_new_tokens=200)
|
||||
print(output[0]["generated_text"][-1]["content"])
|
||||
# Okay, let's take a look!
|
||||
# Based on the image, the animal on the candy is a **turtle**.
|
||||
# You can see the shell shape and the head and legs.
|
||||
```
|
||||
|
||||
#### Running the model on a single/multi GPU
|
||||
|
||||
```python
|
||||
# pip install accelerate
|
||||
|
||||
from transformers import AutoProcessor, Gemma3ForConditionalGeneration
|
||||
from PIL import Image
|
||||
import requests
|
||||
import torch
|
||||
|
||||
model_id = "google/gemma-3-4b-it"
|
||||
|
||||
model = Gemma3ForConditionalGeneration.from_pretrained(
|
||||
model_id, device_map="auto"
|
||||
).eval()
|
||||
|
||||
processor = AutoProcessor.from_pretrained(model_id)
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": [{"type": "text", "text": "You are a helpful assistant."}]
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": [
|
||||
{"type": "image", "image": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
|
||||
{"type": "text", "text": "Describe this image in detail."}
|
||||
]
|
||||
}
|
||||
]
|
||||
|
||||
inputs = processor.apply_chat_template(
|
||||
messages, add_generation_prompt=True, tokenize=True,
|
||||
return_dict=True, return_tensors="pt"
|
||||
).to(model.device, dtype=torch.bfloat16)
|
||||
|
||||
input_len = inputs["input_ids"].shape[-1]
|
||||
|
||||
with torch.inference_mode():
|
||||
generation = model.generate(**inputs, max_new_tokens=100, do_sample=False)
|
||||
generation = generation[0][input_len:]
|
||||
|
||||
decoded = processor.decode(generation, skip_special_tokens=True)
|
||||
print(decoded)
|
||||
|
||||
# **Overall Impression:** The image is a close-up shot of a vibrant garden scene,
|
||||
# focusing on a cluster of pink cosmos flowers and a busy bumblebee.
|
||||
# It has a slightly soft, natural feel, likely captured in daylight.
|
||||
```
|
||||
|
||||
|
||||
### Citation
|
||||
|
||||
```none
|
||||
@article{gemma_2025,
|
||||
title={Gemma 3},
|
||||
url={https://goo.gle/Gemma3Report},
|
||||
publisher={Kaggle},
|
||||
author={Gemma Team},
|
||||
year={2025}
|
||||
}
|
||||
```
|
||||
|
||||
## Model Data
|
||||
|
||||
Data used for model training and how the data was processed.
|
||||
|
||||
### Training Dataset
|
||||
|
||||
These models were trained on a dataset of text data that includes a wide variety
|
||||
of sources. The 27B model was trained with 14 trillion tokens, the 12B model was
|
||||
trained with 12 trillion tokens, 4B model was trained with 4 trillion tokens and
|
||||
1B with 2 trillion tokens. Here are the key components:
|
||||
|
||||
- Web Documents: A diverse collection of web text ensures the model is
|
||||
exposed to a broad range of linguistic styles, topics, and vocabulary. The
|
||||
training dataset includes content in over 140 languages.
|
||||
- Code: Exposing the model to code helps it to learn the syntax and
|
||||
patterns of programming languages, which improves its ability to generate
|
||||
code and understand code-related questions.
|
||||
- Mathematics: Training on mathematical text helps the model learn logical
|
||||
reasoning, symbolic representation, and to address mathematical queries.
|
||||
- Images: A wide range of images enables the model to perform image
|
||||
analysis and visual data extraction tasks.
|
||||
|
||||
The combination of these diverse data sources is crucial for training a powerful
|
||||
multimodal model that can handle a wide variety of different tasks and data
|
||||
formats.
|
||||
|
||||
### Data Preprocessing
|
||||
|
||||
Here are the key data cleaning and filtering methods applied to the training
|
||||
data:
|
||||
|
||||
- CSAM Filtering: Rigorous CSAM (Child Sexual Abuse Material) filtering
|
||||
was applied at multiple stages in the data preparation process to ensure
|
||||
the exclusion of harmful and illegal content.
|
||||
- Sensitive Data Filtering: As part of making Gemma pre-trained models
|
||||
safe and reliable, automated techniques were used to filter out certain
|
||||
personal information and other sensitive data from training sets.
|
||||
- Additional methods: Filtering based on content quality and safety in
|
||||
line with [our policies][safety-policies].
|
||||
|
||||
## Implementation Information
|
||||
|
||||
Details about the model internals.
|
||||
|
||||
### Hardware
|
||||
|
||||
Gemma was trained using [Tensor Processing Unit (TPU)][tpu] hardware (TPUv4p,
|
||||
TPUv5p and TPUv5e). Training vision-language models (VLMS) requires significant
|
||||
computational power. TPUs, designed specifically for matrix operations common in
|
||||
machine learning, offer several advantages in this domain:
|
||||
|
||||
- Performance: TPUs are specifically designed to handle the massive
|
||||
computations involved in training VLMs. They can speed up training
|
||||
considerably compared to CPUs.
|
||||
- Memory: TPUs often come with large amounts of high-bandwidth memory,
|
||||
allowing for the handling of large models and batch sizes during training.
|
||||
This can lead to better model quality.
|
||||
- Scalability: TPU Pods (large clusters of TPUs) provide a scalable
|
||||
solution for handling the growing complexity of large foundation models.
|
||||
You can distribute training across multiple TPU devices for faster and more
|
||||
efficient processing.
|
||||
- Cost-effectiveness: In many scenarios, TPUs can provide a more
|
||||
cost-effective solution for training large models compared to CPU-based
|
||||
infrastructure, especially when considering the time and resources saved
|
||||
due to faster training.
|
||||
- These advantages are aligned with
|
||||
[Google's commitments to operate sustainably][sustainability].
|
||||
|
||||
### Software
|
||||
|
||||
Training was done using [JAX][jax] and [ML Pathways][ml-pathways].
|
||||
|
||||
JAX allows researchers to take advantage of the latest generation of hardware,
|
||||
including TPUs, for faster and more efficient training of large models. ML
|
||||
Pathways is Google's latest effort to build artificially intelligent systems
|
||||
capable of generalizing across multiple tasks. This is specially suitable for
|
||||
foundation models, including large language models like these ones.
|
||||
|
||||
Together, JAX and ML Pathways are used as described in the
|
||||
[paper about the Gemini family of models][gemini-2-paper]; *"the 'single
|
||||
controller' programming model of Jax and Pathways allows a single Python
|
||||
process to orchestrate the entire training run, dramatically simplifying the
|
||||
development workflow."*
|
||||
|
||||
## Evaluation
|
||||
|
||||
Model evaluation metrics and results.
|
||||
|
||||
### Benchmark Results
|
||||
|
||||
These models were evaluated against a large collection of different datasets and
|
||||
metrics to cover different aspects of text generation:
|
||||
|
||||
#### Reasoning and factuality
|
||||
|
||||
| Benchmark | Metric | Gemma 3 PT 1B | Gemma 3 PT 4B | Gemma 3 PT 12B | Gemma 3 PT 27B |
|
||||
| ------------------------------ |----------------|:--------------:|:-------------:|:--------------:|:--------------:|
|
||||
| [HellaSwag][hellaswag] | 10-shot | 62.3 | 77.2 | 84.2 | 85.6 |
|
||||
| [BoolQ][boolq] | 0-shot | 63.2 | 72.3 | 78.8 | 82.4 |
|
||||
| [PIQA][piqa] | 0-shot | 73.8 | 79.6 | 81.8 | 83.3 |
|
||||
| [SocialIQA][socialiqa] | 0-shot | 48.9 | 51.9 | 53.4 | 54.9 |
|
||||
| [TriviaQA][triviaqa] | 5-shot | 39.8 | 65.8 | 78.2 | 85.5 |
|
||||
| [Natural Questions][naturalq] | 5-shot | 9.48 | 20.0 | 31.4 | 36.1 |
|
||||
| [ARC-c][arc] | 25-shot | 38.4 | 56.2 | 68.9 | 70.6 |
|
||||
| [ARC-e][arc] | 0-shot | 73.0 | 82.4 | 88.3 | 89.0 |
|
||||
| [WinoGrande][winogrande] | 5-shot | 58.2 | 64.7 | 74.3 | 78.8 |
|
||||
| [BIG-Bench Hard][bbh] | few-shot | 28.4 | 50.9 | 72.6 | 77.7 |
|
||||
| [DROP][drop] | 1-shot | 42.4 | 60.1 | 72.2 | 77.2 |
|
||||
|
||||
[hellaswag]: https://arxiv.org/abs/1905.07830
|
||||
[boolq]: https://arxiv.org/abs/1905.10044
|
||||
[piqa]: https://arxiv.org/abs/1911.11641
|
||||
[socialiqa]: https://arxiv.org/abs/1904.09728
|
||||
[triviaqa]: https://arxiv.org/abs/1705.03551
|
||||
[naturalq]: https://github.com/google-research-datasets/natural-questions
|
||||
[arc]: https://arxiv.org/abs/1911.01547
|
||||
[winogrande]: https://arxiv.org/abs/1907.10641
|
||||
[bbh]: https://paperswithcode.com/dataset/bbh
|
||||
[drop]: https://arxiv.org/abs/1903.00161
|
||||
|
||||
#### STEM and code
|
||||
|
||||
| Benchmark | Metric | Gemma 3 PT 4B | Gemma 3 PT 12B | Gemma 3 PT 27B |
|
||||
| ------------------------------ |----------------|:-------------:|:--------------:|:--------------:|
|
||||
| [MMLU][mmlu] | 5-shot | 59.6 | 74.5 | 78.6 |
|
||||
| [MMLU][mmlu] (Pro COT) | 5-shot | 29.2 | 45.3 | 52.2 |
|
||||
| [AGIEval][agieval] | 3-5-shot | 42.1 | 57.4 | 66.2 |
|
||||
| [MATH][math] | 4-shot | 24.2 | 43.3 | 50.0 |
|
||||
| [GSM8K][gsm8k] | 8-shot | 38.4 | 71.0 | 82.6 |
|
||||
| [GPQA][gpqa] | 5-shot | 15.0 | 25.4 | 24.3 |
|
||||
| [MBPP][mbpp] | 3-shot | 46.0 | 60.4 | 65.6 |
|
||||
| [HumanEval][humaneval] | 0-shot | 36.0 | 45.7 | 48.8 |
|
||||
|
||||
[mmlu]: https://arxiv.org/abs/2009.03300
|
||||
[agieval]: https://arxiv.org/abs/2304.06364
|
||||
[math]: https://arxiv.org/abs/2103.03874
|
||||
[gsm8k]: https://arxiv.org/abs/2110.14168
|
||||
[gpqa]: https://arxiv.org/abs/2311.12022
|
||||
[mbpp]: https://arxiv.org/abs/2108.07732
|
||||
[humaneval]: https://arxiv.org/abs/2107.03374
|
||||
|
||||
#### Multilingual
|
||||
|
||||
| Benchmark | Gemma 3 PT 1B | Gemma 3 PT 4B | Gemma 3 PT 12B | Gemma 3 PT 27B |
|
||||
| ------------------------------------ |:-------------:|:-------------:|:--------------:|:--------------:|
|
||||
| [MGSM][mgsm] | 2.04 | 34.7 | 64.3 | 74.3 |
|
||||
| [Global-MMLU-Lite][global-mmlu-lite] | 24.9 | 57.0 | 69.4 | 75.7 |
|
||||
| [WMT24++][wmt24pp] (ChrF) | 36.7 | 48.4 | 53.9 | 55.7 |
|
||||
| [FloRes][flores] | 29.5 | 39.2 | 46.0 | 48.8 |
|
||||
| [XQuAD][xquad] (all) | 43.9 | 68.0 | 74.5 | 76.8 |
|
||||
| [ECLeKTic][eclektic] | 4.69 | 11.0 | 17.2 | 24.4 |
|
||||
| [IndicGenBench][indicgenbench] | 41.4 | 57.2 | 61.7 | 63.4 |
|
||||
|
||||
[mgsm]: https://arxiv.org/abs/2210.03057
|
||||
[flores]: https://arxiv.org/abs/2106.03193
|
||||
[xquad]: https://arxiv.org/abs/1910.11856v3
|
||||
[global-mmlu-lite]: https://huggingface.co/datasets/CohereForAI/Global-MMLU-Lite
|
||||
[wmt24pp]: https://arxiv.org/abs/2502.12404v1
|
||||
[eclektic]: https://arxiv.org/abs/2502.21228
|
||||
[indicgenbench]: https://arxiv.org/abs/2404.16816
|
||||
|
||||
#### Multimodal
|
||||
|
||||
| Benchmark | Gemma 3 PT 4B | Gemma 3 PT 12B | Gemma 3 PT 27B |
|
||||
| ------------------------------ |:-------------:|:--------------:|:--------------:|
|
||||
| [COCOcap][coco-cap] | 102 | 111 | 116 |
|
||||
| [DocVQA][docvqa] (val) | 72.8 | 82.3 | 85.6 |
|
||||
| [InfoVQA][info-vqa] (val) | 44.1 | 54.8 | 59.4 |
|
||||
| [MMMU][mmmu] (pt) | 39.2 | 50.3 | 56.1 |
|
||||
| [TextVQA][textvqa] (val) | 58.9 | 66.5 | 68.6 |
|
||||
| [RealWorldQA][realworldqa] | 45.5 | 52.2 | 53.9 |
|
||||
| [ReMI][remi] | 27.3 | 38.5 | 44.8 |
|
||||
| [AI2D][ai2d] | 63.2 | 75.2 | 79.0 |
|
||||
| [ChartQA][chartqa] | 63.6 | 74.7 | 76.3 |
|
||||
| [VQAv2][vqav2] | 63.9 | 71.2 | 72.9 |
|
||||
| [BLINK][blinkvqa] | 38.0 | 35.9 | 39.6 |
|
||||
| [OKVQA][okvqa] | 51.0 | 58.7 | 60.2 |
|
||||
| [TallyQA][tallyqa] | 42.5 | 51.8 | 54.3 |
|
||||
| [SpatialSense VQA][ss-vqa] | 50.9 | 60.0 | 59.4 |
|
||||
| [CountBenchQA][countbenchqa] | 26.1 | 17.8 | 68.0 |
|
||||
|
||||
[coco-cap]: https://cocodataset.org/#home
|
||||
[docvqa]: https://www.docvqa.org/
|
||||
[info-vqa]: https://arxiv.org/abs/2104.12756
|
||||
[mmmu]: https://arxiv.org/abs/2311.16502
|
||||
[textvqa]: https://textvqa.org/
|
||||
[realworldqa]: https://paperswithcode.com/dataset/realworldqa
|
||||
[remi]: https://arxiv.org/html/2406.09175v1
|
||||
[ai2d]: https://allenai.org/data/diagrams
|
||||
[chartqa]: https://arxiv.org/abs/2203.10244
|
||||
[vqav2]: https://visualqa.org/index.html
|
||||
[blinkvqa]: https://arxiv.org/abs/2404.12390
|
||||
[okvqa]: https://okvqa.allenai.org/
|
||||
[tallyqa]: https://arxiv.org/abs/1810.12440
|
||||
[ss-vqa]: https://arxiv.org/abs/1908.02660
|
||||
[countbenchqa]: https://github.com/google-research/big_vision/blob/main/big_vision/datasets/countbenchqa/
|
||||
|
||||
## Ethics and Safety
|
||||
|
||||
Ethics and safety evaluation approach and results.
|
||||
|
||||
### Evaluation Approach
|
||||
|
||||
Our evaluation methods include structured evaluations and internal red-teaming
|
||||
testing of relevant content policies. Red-teaming was conducted by a number of
|
||||
different teams, each with different goals and human evaluation metrics. These
|
||||
models were evaluated against a number of different categories relevant to
|
||||
ethics and safety, including:
|
||||
|
||||
- **Child Safety**: Evaluation of text-to-text and image to text prompts
|
||||
covering child safety policies, including child sexual abuse and
|
||||
exploitation.
|
||||
- **Content Safety:** Evaluation of text-to-text and image to text prompts
|
||||
covering safety policies including, harassment, violence and gore, and hate
|
||||
speech.
|
||||
- **Representational Harms**: Evaluation of text-to-text and image to text
|
||||
prompts covering safety policies including bias, stereotyping, and harmful
|
||||
associations or inaccuracies.
|
||||
|
||||
In addition to development level evaluations, we conduct "assurance
|
||||
evaluations" which are our 'arms-length' internal evaluations for responsibility
|
||||
governance decision making. They are conducted separately from the model
|
||||
development team, to inform decision making about release. High level findings
|
||||
are fed back to the model team, but prompt sets are held-out to prevent
|
||||
overfitting and preserve the results' ability to inform decision making.
|
||||
Assurance evaluation results are reported to our Responsibility & Safety Council
|
||||
as part of release review.
|
||||
|
||||
### Evaluation Results
|
||||
|
||||
For all areas of safety testing, we saw major improvements in the categories of
|
||||
child safety, content safety, and representational harms relative to previous
|
||||
Gemma models. All testing was conducted without safety filters to evaluate the
|
||||
model capabilities and behaviors. For both text-to-text and image-to-text, and
|
||||
across all model sizes, the model produced minimal policy violations, and showed
|
||||
significant improvements over previous Gemma models' performance with respect
|
||||
to ungrounded inferences. A limitation of our evaluations was they included only
|
||||
English language prompts.
|
||||
|
||||
## Usage and Limitations
|
||||
|
||||
These models have certain limitations that users should be aware of.
|
||||
|
||||
### Intended Usage
|
||||
|
||||
Open vision-language models (VLMs) models have a wide range of applications
|
||||
across various industries and domains. The following list of potential uses is
|
||||
not comprehensive. The purpose of this list is to provide contextual information
|
||||
about the possible use-cases that the model creators considered as part of model
|
||||
training and development.
|
||||
|
||||
- Content Creation and Communication
|
||||
- Text Generation: These models can be used to generate creative text
|
||||
formats such as poems, scripts, code, marketing copy, and email drafts.
|
||||
- Chatbots and Conversational AI: Power conversational interfaces
|
||||
for customer service, virtual assistants, or interactive applications.
|
||||
- Text Summarization: Generate concise summaries of a text corpus,
|
||||
research papers, or reports.
|
||||
- Image Data Extraction: These models can be used to extract,
|
||||
interpret, and summarize visual data for text communications.
|
||||
- Research and Education
|
||||
- Natural Language Processing (NLP) and VLM Research: These
|
||||
models can serve as a foundation for researchers to experiment with VLM
|
||||
and NLP techniques, develop algorithms, and contribute to the
|
||||
advancement of the field.
|
||||
- Language Learning Tools: Support interactive language learning
|
||||
experiences, aiding in grammar correction or providing writing practice.
|
||||
- Knowledge Exploration: Assist researchers in exploring large
|
||||
bodies of text by generating summaries or answering questions about
|
||||
specific topics.
|
||||
|
||||
### Limitations
|
||||
|
||||
- Training Data
|
||||
- The quality and diversity of the training data significantly
|
||||
influence the model's capabilities. Biases or gaps in the training data
|
||||
can lead to limitations in the model's responses.
|
||||
- The scope of the training dataset determines the subject areas
|
||||
the model can handle effectively.
|
||||
- Context and Task Complexity
|
||||
- Models are better at tasks that can be framed with clear
|
||||
prompts and instructions. Open-ended or highly complex tasks might be
|
||||
challenging.
|
||||
- A model's performance can be influenced by the amount of context
|
||||
provided (longer context generally leads to better outputs, up to a
|
||||
certain point).
|
||||
- Language Ambiguity and Nuance
|
||||
- Natural language is inherently complex. Models might struggle
|
||||
to grasp subtle nuances, sarcasm, or figurative language.
|
||||
- Factual Accuracy
|
||||
- Models generate responses based on information they learned
|
||||
from their training datasets, but they are not knowledge bases. They
|
||||
may generate incorrect or outdated factual statements.
|
||||
- Common Sense
|
||||
- Models rely on statistical patterns in language. They might
|
||||
lack the ability to apply common sense reasoning in certain situations.
|
||||
|
||||
### Ethical Considerations and Risks
|
||||
|
||||
The development of vision-language models (VLMs) raises several ethical
|
||||
concerns. In creating an open model, we have carefully considered the following:
|
||||
|
||||
- Bias and Fairness
|
||||
- VLMs trained on large-scale, real-world text and image data can
|
||||
reflect socio-cultural biases embedded in the training material. These
|
||||
models underwent careful scrutiny, input data pre-processing described
|
||||
and posterior evaluations reported in this card.
|
||||
- Misinformation and Misuse
|
||||
- VLMs can be misused to generate text that is false, misleading,
|
||||
or harmful.
|
||||
- Guidelines are provided for responsible use with the model, see the
|
||||
[Responsible Generative AI Toolkit][rai-toolkit].
|
||||
- Transparency and Accountability:
|
||||
- This model card summarizes details on the models' architecture,
|
||||
capabilities, limitations, and evaluation processes.
|
||||
- A responsibly developed open model offers the opportunity to
|
||||
share innovation by making VLM technology accessible to developers and
|
||||
researchers across the AI ecosystem.
|
||||
|
||||
Risks identified and mitigations:
|
||||
|
||||
- **Perpetuation of biases**: It's encouraged to perform continuous
|
||||
monitoring (using evaluation metrics, human review) and the exploration of
|
||||
de-biasing techniques during model training, fine-tuning, and other use
|
||||
cases.
|
||||
- **Generation of harmful content**: Mechanisms and guidelines for content
|
||||
safety are essential. Developers are encouraged to exercise caution and
|
||||
implement appropriate content safety safeguards based on their specific
|
||||
product policies and application use cases.
|
||||
- **Misuse for malicious purposes**: Technical limitations and developer
|
||||
and end-user education can help mitigate against malicious applications of
|
||||
VLMs. Educational resources and reporting mechanisms for users to flag
|
||||
misuse are provided. Prohibited uses of Gemma models are outlined in the
|
||||
[Gemma Prohibited Use Policy][prohibited-use].
|
||||
- **Privacy violations**: Models were trained on data filtered for removal
|
||||
of certain personal information and other sensitive data. Developers are
|
||||
encouraged to adhere to privacy regulations with privacy-preserving
|
||||
techniques.
|
||||
|
||||
### Benefits
|
||||
|
||||
At the time of release, this family of models provides high-performance open
|
||||
vision-language model implementations designed from the ground up for
|
||||
responsible AI development compared to similarly sized models.
|
||||
|
||||
Using the benchmark evaluation metrics described in this document, these models
|
||||
have shown to provide superior performance to other, comparably-sized open model
|
||||
alternatives.
|
||||
|
||||
[g3-tech-report]: https://goo.gle/Gemma3Report
|
||||
[rai-toolkit]: https://ai.google.dev/responsible
|
||||
[kaggle-gemma]: https://www.kaggle.com/models/google/gemma-3
|
||||
[vertex-mg-gemma3]: https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/gemma3
|
||||
[terms]: https://ai.google.dev/gemma/terms
|
||||
[safety-policies]: https://ai.google/static/documents/ai-responsibility-update-published-february-2025.pdf
|
||||
[prohibited-use]: https://ai.google.dev/gemma/prohibited_use_policy
|
||||
[tpu]: https://cloud.google.com/tpu/docs/intro-to-tpu
|
||||
[sustainability]: https://sustainability.google/operating-sustainably/
|
||||
[jax]: https://github.com/jax-ml/jax
|
||||
[ml-pathways]: https://blog.google/technology/ai/introducing-pathways-next-generation-ai-architecture/
|
||||
[sustainability]: https://sustainability.google/operating-sustainably/
|
||||
[gemini-2-paper]: https://arxiv.org/abs/2312.11805
|
||||
@ -1,3 +0,0 @@
|
||||
{
|
||||
"<image_soft_token>": 262144
|
||||
}
|
||||
@ -1,3 +0,0 @@
|
||||
{
|
||||
"chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n {%- if messages[0]['content'] is string -%}\n {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n {%- else -%}\n {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n {%- endif -%}\n {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n {%- set first_user_prefix = \"\" -%}\n {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n {%- endif -%}\n {%- if (message['role'] == 'assistant') -%}\n {%- set role = \"model\" -%}\n {%- else -%}\n {%- set role = message['role'] -%}\n {%- endif -%}\n {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n {%- if message['content'] is string -%}\n {{ message['content'] | trim }}\n {%- elif message['content'] is iterable -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'image' -%}\n {{ '<start_of_image>' }}\n {%- elif item['type'] == 'text' -%}\n {{ item['text'] | trim }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ raise_exception(\"Invalid content type\") }}\n {%- endif -%}\n {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{'<start_of_turn>model\n'}}\n{%- endif -%}\n"
|
||||
}
|
||||
38
config.json
38
config.json
@ -1,38 +0,0 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Gemma3ForConditionalGeneration"
|
||||
],
|
||||
"boi_token_index": 255999,
|
||||
"eoi_token_index": 256000,
|
||||
"eos_token_id": [
|
||||
1,
|
||||
106
|
||||
],
|
||||
"image_token_index": 262144,
|
||||
"initializer_range": 0.02,
|
||||
"mm_tokens_per_image": 256,
|
||||
"model_type": "gemma3",
|
||||
"text_config": {
|
||||
"hidden_size": 2560,
|
||||
"intermediate_size": 10240,
|
||||
"model_type": "gemma3_text",
|
||||
"num_hidden_layers": 34,
|
||||
"rope_scaling": {
|
||||
"factor": 8.0,
|
||||
"rope_type": "linear"
|
||||
},
|
||||
"sliding_window": 1024
|
||||
},
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.50.0.dev0",
|
||||
"vision_config": {
|
||||
"hidden_size": 1152,
|
||||
"image_size": 896,
|
||||
"intermediate_size": 4304,
|
||||
"model_type": "siglip_vision_model",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 27,
|
||||
"patch_size": 14,
|
||||
"vision_use_head": false
|
||||
}
|
||||
}
|
||||
131
config.pbtxt
Normal file
131
config.pbtxt
Normal file
@ -0,0 +1,131 @@
|
||||
# Triton Backend for TransformerLLM.
|
||||
backend: "python"
|
||||
max_batch_size: 0
|
||||
|
||||
# Triton should expect as input a single string
|
||||
# input of variable length named 'text_input'
|
||||
input [
|
||||
|
||||
{
|
||||
name: "text_input"
|
||||
data_type: TYPE_STRING
|
||||
dims: [ 1 ]
|
||||
|
||||
|
||||
},
|
||||
{
|
||||
name: "max_length"
|
||||
data_type: TYPE_INT32
|
||||
dims: [ 1 ]
|
||||
|
||||
optional: true
|
||||
|
||||
|
||||
},
|
||||
{
|
||||
name: "max_new_tokens"
|
||||
data_type: TYPE_INT32
|
||||
dims: [ 1 ]
|
||||
|
||||
optional: true
|
||||
|
||||
|
||||
},
|
||||
{
|
||||
name: "do_sample"
|
||||
data_type: TYPE_BOOL
|
||||
dims: [ 1 ]
|
||||
|
||||
optional: true
|
||||
|
||||
|
||||
},
|
||||
{
|
||||
name: "top_k"
|
||||
data_type: TYPE_INT32
|
||||
dims: [ 1 ]
|
||||
|
||||
optional: true
|
||||
|
||||
|
||||
},
|
||||
{
|
||||
name: "top_p"
|
||||
data_type: TYPE_FP32
|
||||
dims: [ 1 ]
|
||||
|
||||
optional: true
|
||||
|
||||
|
||||
},
|
||||
{
|
||||
name: "temperature"
|
||||
data_type: TYPE_FP32
|
||||
dims: [ 1 ]
|
||||
|
||||
optional: true
|
||||
|
||||
|
||||
},
|
||||
{
|
||||
name: "repetition_penalty"
|
||||
data_type: TYPE_FP32
|
||||
dims: [ 1 ]
|
||||
|
||||
optional: true
|
||||
|
||||
|
||||
},
|
||||
{
|
||||
name: "stream"
|
||||
data_type: TYPE_BOOL
|
||||
dims: [ 1 ]
|
||||
|
||||
optional: true
|
||||
|
||||
|
||||
}
|
||||
|
||||
]
|
||||
|
||||
|
||||
# Triton should expect to respond with a single string
|
||||
# output of variable length named 'text_output'
|
||||
output [
|
||||
|
||||
{
|
||||
name: "text_output"
|
||||
data_type: TYPE_STRING
|
||||
dims: [ 1 ]
|
||||
|
||||
}
|
||||
|
||||
]
|
||||
|
||||
parameters: [
|
||||
{
|
||||
key: "base_model_path",
|
||||
value: {string_value: "/cheetah/input/model/groupuser/gemma-3-4b-it"}
|
||||
},
|
||||
{
|
||||
key: "is_adapter_model",
|
||||
value: {string_value: "false"}
|
||||
},
|
||||
{
|
||||
key: "adapter_model_path",
|
||||
value: {string_value: ""}
|
||||
},
|
||||
|
||||
{
|
||||
key: "quantization",
|
||||
value: {string_value: "none"}
|
||||
}
|
||||
]
|
||||
|
||||
instance_group [
|
||||
{
|
||||
kind: KIND_AUTO
|
||||
count: 1
|
||||
}
|
||||
]
|
||||
|
||||
@ -1,13 +0,0 @@
|
||||
{
|
||||
"bos_token_id": 2,
|
||||
"cache_implementation": "hybrid",
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
1,
|
||||
106
|
||||
],
|
||||
"pad_token_id": 0,
|
||||
"top_k": 64,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "4.50.0.dev0"
|
||||
}
|
||||
BIN
model-00001-of-00002.safetensors
(Stored with Git LFS)
BIN
model-00001-of-00002.safetensors
(Stored with Git LFS)
Binary file not shown.
BIN
model-00002-of-00002.safetensors
(Stored with Git LFS)
BIN
model-00002-of-00002.safetensors
(Stored with Git LFS)
Binary file not shown.
@ -1,890 +0,0 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 8600158944
|
||||
},
|
||||
"weight_map": {
|
||||
"language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.10.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.10.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.11.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.11.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.12.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.12.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.13.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.13.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.15.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.15.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.16.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.16.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.17.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.18.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.19.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.19.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.20.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.20.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.21.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.21.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.22.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.22.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.23.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.23.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.24.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.24.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.25.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.25.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.26.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.26.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.27.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.27.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.28.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.28.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.29.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.29.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.30.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.30.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.31.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.31.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.32.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.32.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.33.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.33.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.7.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.8.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.8.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.9.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.9.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.norm.weight": "model-00002-of-00002.safetensors",
|
||||
"multi_modal_projector.mm_input_projection_weight": "model-00001-of-00002.safetensors",
|
||||
"multi_modal_projector.mm_soft_emb_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
@ -1,29 +0,0 @@
|
||||
{
|
||||
"do_convert_rgb": null,
|
||||
"do_normalize": true,
|
||||
"do_pan_and_scan": null,
|
||||
"do_rescale": true,
|
||||
"do_resize": true,
|
||||
"image_mean": [
|
||||
0.5,
|
||||
0.5,
|
||||
0.5
|
||||
],
|
||||
"image_processor_type": "Gemma3ImageProcessor",
|
||||
"image_seq_length": 256,
|
||||
"image_std": [
|
||||
0.5,
|
||||
0.5,
|
||||
0.5
|
||||
],
|
||||
"pan_and_scan_max_num_crops": null,
|
||||
"pan_and_scan_min_crop_size": null,
|
||||
"pan_and_scan_min_ratio_to_activate": null,
|
||||
"processor_class": "Gemma3Processor",
|
||||
"resample": 2,
|
||||
"rescale_factor": 0.00392156862745098,
|
||||
"size": {
|
||||
"height": 896,
|
||||
"width": 896
|
||||
}
|
||||
}
|
||||
@ -1,4 +0,0 @@
|
||||
{
|
||||
"image_seq_length": 256,
|
||||
"processor_class": "Gemma3Processor"
|
||||
}
|
||||
@ -1,33 +0,0 @@
|
||||
{
|
||||
"boi_token": "<start_of_image>",
|
||||
"bos_token": {
|
||||
"content": "<bos>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eoi_token": "<end_of_image>",
|
||||
"eos_token": {
|
||||
"content": "<eos>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"image_token": "<image_soft_token>",
|
||||
"pad_token": {
|
||||
"content": "<pad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
BIN
tokenizer.json
(Stored with Git LFS)
BIN
tokenizer.json
(Stored with Git LFS)
Binary file not shown.
BIN
tokenizer.model
(Stored with Git LFS)
BIN
tokenizer.model
(Stored with Git LFS)
Binary file not shown.
51346
tokenizer_config.json
51346
tokenizer_config.json
File diff suppressed because it is too large
Load Diff
Loading…
Reference in New Issue
Block a user