Upload folder using huggingface_hub

README.md

@@ -0,0 +1,54 @@
+---
+language:
+- en
+- de
+- fr
+- it
+- pt
+- hi
+- es
+- th
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- facebook
+- meta
+- pytorch
+- llama
+- llama-3
+---
+
+This repository is an early access checkpoint for Llama 3.2 1B Instruct.
+
+This repo contains two versions of the model, for use with `transformers` and with the original `llama3` codebase (under the `original` directory).
+
+### Use with transformers
+
+Here is an example of simple usage with `transformers`
+
+```python
+from transformers import pipeline
+import torch
+
+model_id = "nltpt/Llama-3.2-1B-Instruct"
+
+pipe = pipeline(
+    "text-generation",
+    model=model_id,
+    model_kwargs={"torch_dtype": torch.bfloat16},
+    device_map="auto"
+)
+
+messages = [
+    {"role": "user", "content": "What is the capital of France?"},
+]
+pipe(messages, max_length=50)
+```
+
+### Use with `llama3`
+
+Please follow the instructions provided for that repository. To download the checkpoints from the Hub, see this example command using `huggingface-cli`:
+
+```bash
+huggingface-cli download nltpt/Llama-3.2-1B-Instruct --include "original/*" --local-dir Llama-3.2-1B-Instruct
+```

config.json

@@ -0,0 +1,39 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.45.0.dev0"
+}

original/params.json

@@ -0,0 +1,12 @@
+{
+  "dim": 2048,
+  "n_layers": 16,
+  "n_heads": 32,
+  "n_kv_heads": 8,
+  "vocab_size": 128256,
+  "ffn_dim_multiplier": 1.5,
+  "multiple_of": 256,
+  "norm_eps": 1e-05,
+  "rope_theta": 500000.0,
+  "use_scaled_rope": true
+}

special_tokens_map.json

@@ -0,0 +1,4 @@
+{
+  "bos_token": "<|begin_of_text|>",
+  "eos_token": "<|eot_id|>"
+}