Meta Llama 3 8B Instruct GPTQ

🚀 Meta-Llama-3-8B-Instruct GPTQ Quantized Version

This is the GPTQ quantized version of the Meta-Llama-3-8B-Instruct model. It provides an efficient way to use the model with reduced memory requirements.

✨ Features

• Powerful Language Generation: Meta developed and released the Meta Llama 3 family of large language models (LLMs), which are a collection of pretrained and instruction - tuned generative text models. The instruction - tuned models are optimized for assistant - like chat, while pretrained models can be adapted for various natural language generation tasks.
• Multiple Sizes: Llama 3 comes in two sizes, 8B and 70B parameters, with both pre - trained and instruction - tuned variants.
• Improved Inference: Both the 8B and 70B versions use Grouped - Query Attention (GQA) for improved inference scalability.

📦 Installation

This repository contains two versions of Meta - Llama - 3 - 8B - Instruct, for use with transformers and with the original llama3 codebase.

Use with transformers

import transformers
import torch

model_id = "meta-llama/Meta-Llama-3-8B-Instruct"

pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.bfloat16},
    device="auto",
)

messages = [
    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
    {"role": "user", "content": "Who are you?"},
]

prompt = pipeline.tokenizer.apply_chat_template(
        messages, 
        tokenize=False, 
        add_generation_prompt=True
)

terminators = [
    pipeline.tokenizer.eos_token_id,
    pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

outputs = pipeline(
    prompt,
    max_new_tokens=256,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.6,
    top_p=0.9,
)
print(outputs[0]["generated_text"][len(prompt):])

Use with llama3

Please follow the instructions in the [repository](https://github.com/meta - llama/llama3). To download Original checkpoints, see the example command below leveraging huggingface - cli:

huggingface-cli download meta-llama/Meta-Llama-3-8B-Instruct --include "original/*" --local-dir Meta-Llama-3-8B-Instruct

💻 Usage Examples

Basic Usage

The following example shows how to use the model with the transformers library for text generation:

import transformers
import torch

model_id = "meta-llama/Meta-Llama-3-8B-Instruct"

pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.bfloat16},
    device="auto",
)

messages = [
    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
    {"role": "user", "content": "Who are you?"},
]

prompt = pipeline.tokenizer.apply_chat_template(
        messages, 
        tokenize=False, 
        add_generation_prompt=True
)

terminators = [
    pipeline.tokenizer.eos_token_id,
    pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

outputs = pipeline(
    prompt,
    max_new_tokens=256,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.6,
    top_p=0.9,
)
print(outputs[0]["generated_text"][len(prompt):])

📚 Documentation

Model Details

Intended Use

Intended Use Cases Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant - like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.

Out - of - scope Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English.

⚠️ Important Note

Developers may fine - tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.

Hardware and Software

Training Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine - tuning, annotation, and evaluation were also performed on third - party cloud compute.

CO2 emissions during pre - training: Time refers to the total GPU time required for training each model. Power Consumption is the peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.

Training Data

Overview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine - tuning data includes publicly available instruction datasets, as well as over 10M human - annotated examples. Neither the pretraining nor the fine - tuning datasets include Meta user data.

Data Freshness The pretraining data has a cutoff of March 2023 for the 8B and December 2023 for the 70B models respectively.

Benchmarks

In this section, we report the results for Llama 3 models on standard automatic benchmarks.

License

A custom commercial license is available at: https://llama.meta.com/llama3/license

The full license agreement can be found in the LICENSE file. The license agreement also includes the Meta Llama 3 Community License Agreement and the Meta Llama 3 Acceptable Use Policy.

Where to send questions or comments about the model: Instructions on how to provide feedback or comments on the model can be found in the model [README](https://github.com/meta - llama/llama3). For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go [here](https://github.com/meta - llama/llama - recipes).