---
title: Llama-3-8b-sft-mixture
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/Llama-3-8b-sft-mixture"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/Llama-3-8b-sft-mixture.md"
repository: AI-ModelScope/Llama-3-8b-sft-mixture
last_updated: 2025-02-14
model_type:
  - llama
architectures:
  - LlamaForCausalLM
parameters: 8.0B
tensor_type:
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 965
stars: 0
---

# Llama-3-8b-sft-mixture

> Llama-3-8b-sft-mixture - AI-ModelScope 在 ModelScope 开源的模型。Copy from https://huggingface.co/RLHFlow/LLaMA3-SFT We fixed the generationconfig.json.

AI-ModelScope/Llama-3-8b-sft-mixture 是 ModelScope 魔搭社区上的 8.0B 参数机器学习模型，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: AI-ModelScope/Llama-3-8b-sft-mixture
- **Parameters**: 8.0B
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Downloads**: 965
- **Stars**: 0
- **Last updated**: 2025-02-14

Source: https://www.modelscope.cn/models/AI-ModelScope/Llama-3-8b-sft-mixture

---

>Copy from https://huggingface.co/RLHFlow/LLaMA3-SFT
>
>We fixed the `generation_config.json`.

This is the SFT checkpoint used for the project [Online-RLHF](https://github.com/RLHFlow/Online-RLHF). Also, check the [technical report here](https://arxiv.org/pdf/2405.07863). 

The model is trained from [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on a mixture of diverse open-source high-quality data for 1 epoch with detailed parameters in the report. It has not been trained by RLHF and can serve as a good starting point for the RLHF research.

The datasets included: ShareGPT, Evol-Instruct, SlimOrca, MathInstruct, Magicoder-Evol-Instruct, GPT4-LLM, OrcaMath, GPTeacher, UltraInteract.