Go to file
2024-09-18 15:13:54 +00:00
original Upload folder using huggingface_hub 2024-09-18 15:13:54 +00:00
.gitattributes initial commit 2024-09-18 15:12:47 +00:00
config.json Upload folder using huggingface_hub 2024-09-18 15:13:54 +00:00
generation_config.json Upload folder using huggingface_hub 2024-09-18 15:13:54 +00:00
model.safetensors Upload folder using huggingface_hub 2024-09-18 15:13:54 +00:00
README.md Upload folder using huggingface_hub 2024-09-18 15:13:54 +00:00
special_tokens_map.json Upload folder using huggingface_hub 2024-09-18 15:13:54 +00:00
tokenizer_config.json Upload folder using huggingface_hub 2024-09-18 15:13:54 +00:00
tokenizer.json Upload folder using huggingface_hub 2024-09-18 15:13:54 +00:00

language library_name pipeline_tag tags
en
de
fr
it
pt
hi
es
th
transformers text-generation
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

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:

huggingface-cli download nltpt/Llama-3.2-1B-Instruct --include "original/*" --local-dir Llama-3.2-1B-Instruct