Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
开源社区第一个能下载、能运行的中文 LLaMA2 模型！
| Date | Stars |
|---|---|
| 2026-07-24 | 2205 |
| 2026-07-25 | 2205 |
| 2026-07-28 | 2205 |
| 2026-07-30 | 2205 |
| 2026-08-06 | 2205 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Chinese Llama 2 7B
[](https://github.com/LinkSoul-AI/Chinese-Llama-2-7b) [](https://github.com/LinkSoul-AI/Chinese-Llama-2-7b) [](https://github.com/LinkSoul-AI/Chinese-Llama-2-7b/blob/main/LICENSE) [](https://huggingface.co/spaces/LinkSoul/Chinese-Llama-2-7b) [](https://huggingface.co/datasets/LinkSoul/instruction_merge_set)
全部开源，完全可商用的**中文版 Llama2 模型及中英文 SFT 数据集**，输入格式严格遵循 *llama-2-chat* 格式，兼容适配所有针对原版 *llama-2-chat* 模型的优化。
## 基础演示
## 在线试玩
> Talk is cheap, Show you the Demo.
- [Demo 地址 / HuggingFace Spaces](https://huggingface.co/spaces/LinkSoul/Chinese-Llama-2-7b)
- [Colab (FP16/需要开启高RAM,免费版无法使用)](https://colab.research.google.com/github/LinkSoul-AI/Chinese-Llama-2-7b/blob/main/chinese-llama-2-7b.ipynb)
- [Colab (INT4/需要开启高RAM,免费版无法使用)](https://colab.research.google.com/github/LinkSoul-AI/Chinese-Llama-2-7b/blob/main/chinese-llama-2-7b-4bit.ipynb)
## 最新更新
- 10月26日 提供始智AI链接[Chinese Llama2 Chat Model](https://www.wisemodel.cn/models/LinkSoul/Chinese-Llama-2-7b/intro) 🔥🔥🔥
- 8月24日 新加ModelScope链接[Chinese Llama2 Chat Model](https://www.modelscope.cn/linksoul/Chinese-Llama-2-7b) 🔥🔥🔥
- 7月31号 基于 Chinese-llama2-7b 的中英双语语音-文本 [LLaSM](https://github.com/LinkSoul-AI/LLaSM) 多模态模型开源 🔥🔥🔥
- 7月31号 基于 Chinese-llama2-7b 的中英双语视觉-文本 [Chinese-LLaVA](https://github.com/LinkSoul-AI/Chinese-LLaVA) 多模态模型开源 🔥🔥🔥
- 7月26号 Chinese-llama2-7b-ggml 模型开源🔥🔥
- 7月23日 更新7b模型，添加API，提供4bit量化模型🔥🔥
- 7月22号 SFT训练/推理代码上线 🔥
- 7月21号 docker 一键部署上线 🔥
- 7月21号 demo上线 🔥
- 7月21号 中英双语 SFT 数据开源 🔥🔥
- 7月21号 Chinese-llama2-7b 模型开源 🔥🔥
## 资源下载
- 模型下载
- 始智AI: [Chinese Llama2 Chat Model](https://www.wisemodel.cn/models/LinkSoul/Chinese-Llama-2-7b/intro)
- ModelScope: [Chinese Llama2 Chat Model](https://www.modelscope.cn/linksoul/Chinese-Llama-2-7b)
- HuggingFace: [Chinese Llama2 Chat Model](https://huggingface.co/LinkSoul/Chinese-Llama-2-7b)
- 百度网盘: [1.0 正式版](https://pan.baidu.com/s/1GQ9S0szo7LCJIkGoAHciDg?pwd=zusq)
- 百度网盘: [1.1 加强火力版](https://pan.baidu.com/s/1RFp3rUKsn5oTYE6rignIGA?pwd=qyrh)
- 4bit量化
- HuggingFace：[Chinese Llama2 4bit Chat Model](https://huggingface.co/LinkSoul/Chinese-Llama-2-7b-4bit)
- 百度网盘: [Chinese Llama2 4bit Chat Model](https://pan.baidu.com/s/17Llr3rIGF5AviT_l4DN_YA?pwd=ug13)
- GGML Q4 模型：
- [https://huggingface.co/LinkSoul/Chinese-Llama-2-7b-ggml](https://huggingface.co/LinkSoul/Chinese-Llama-2-7b-ggml)
- [https://huggingface.co/rffx0/Chinese-Llama-2-7b-ggml-model-q4_0](https://huggingface.co/rffx0/Chinese-Llama-2-7b-ggml-model-q4_0)
- [https://huggingface.co/soulteary/Chinese-Llama-2-7b-ggml-q4](https://huggingface.co/soulteary/Chinese-Llama-2-7b-ggml-q4)
- 百度网盘: [Chinese-Llama-2-7b-ggml](https://pan.baidu.com/s/1yfTeBgkqZ4DV00Q-XrLq2Q?pwd=bwvd)
> 我们使用了中英文 SFT 数据集，数据量 1000 万。
- 数据集：[https://huggingface.co/datasets/LinkSoul/instruction_merge_set](https://huggingface.co/datasets/LinkSoul/instruction_merge_set)
## 快速测试
```python
from transformers import AutoTokenizer, AutoModelForCausalLM, TextStreamer
model_path = "LinkSoul/Chinese-Llama-2-7b"
tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(model_path).half().cuda()
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
instruction = """[INST] <<SYS>>\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
If a question does not make any sense, or is not factuallExcerpt of 8,975 characters
Read on GitHub
39
Su Yang · China
18
3
3
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:d0fe389bed8a4b1e, topic:deep-learning, topic:pytorch
matched fp:d0fe389bed8a4b1e, topic:llm