Meta Llama 3.1 Models

**Overview**

The Llama_v3_1 models are large language models (LLMs) developed by Meta AI. The models provided in this listing are

- [meta_llama_v3_1_405b](https://huggingface.co/meta-llama/Meta-Llama-3.1-405B)
- [meta_llama_v3_1_70b](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B)
- [meta_llama_v3_1_8b](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B)
- [meta_llama_v3_1_405b_instruct_fp8](https://huggingface.co/meta-llama/Meta-Llama-3.1-405B-Instruct-FP8)
- [meta_llama_v3_1_70b_instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct)
- [meta_llama_v3_1_8b_instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct)

The models are packaged using MLflow’s transformers flavor.
- [meta_llama_v3_1_405b_instruct_fp8](https://huggingface.co/meta-llama/Meta-Llama-3.1-405B-Instruct-FP8), [meta_llama_v3_1_70b_instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct), [meta_llama_v3_1_8b_instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct): fine-tuned for dialogue-based use cases.
- [meta_llama_v3_1_405b](https://huggingface.co/meta-llama/Meta-Llama-3.1-405B), [meta_llama_v3_1_70b](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B), [meta_llama_v3_1_8b](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B): pretrained generative text model that can be used for further fine-tuning on specific applications.

Llama_v3_1 models are licensed under the [Meta Llama 3.1 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE). By installing this listing, you acknowledge and agree to the license.

**Use cases**

[meta_llama_v3_1_405b_instruct_fp8](https://huggingface.co/meta-llama/Meta-Llama-3.1-405B-Instruct-FP8), [meta_llama_v3_1_70b_instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct), [meta_llama_v3_1_8b_instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct):
- Generating responses to text-based instructions
- Chatbots and conversational AI systems

[meta_llama_v3_1_405b](https://huggingface.co/meta-llama/Meta-Llama-3.1-405B), [meta_llama_v3_1_70b](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B), [meta_llama_v3_1_8b](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B):
- Fine-tuning on specific applications.

**Product details**

The pre-trained model can be used for further fine-tuning on specific applications. The fine-tuned model in this listing can be deployed directly to Databricks Model Serving for immediate use, or loaded for fine-tuning or batch inference use cases. For more details, install the listing and view the provided model cards for each model.

搜集汇总

背景与挑战

背景概述

该数据集包含Meta AI开发的大型语言模型Llama_v3_1系列，提供不同规模的预训练模型（405b、70b、8b）和针对对话场景优化的指令微调版本。模型采用MLflow格式封装，遵循Meta Llama 3.1社区许可协议。