--- title: llama-3-chinese-8b-gguf canonical_url: "https://www.modelscope.cn/models/ChineseAlpacaGroup/llama-3-chinese-8b-gguf" md_url: "https://www.modelscope.cn/models/ChineseAlpacaGroup/llama-3-chinese-8b-gguf.md" repository: ChineseAlpacaGroup/llama-3-chinese-8b-gguf last_updated: 2024-04-30 license: "Apache License 2.0" pipeline_tag: fill-mask tasks: - fill-mask model_type: - llama library_name: - gguf - other frameworks: - other language: - zh - en downloads: 1466 stars: 7 tags: - gguf --- # llama-3-chinese-8b-gguf > llama-3-chinese-8b-gguf - ChineseAlpacaGroup 在 ModelScope 开源的模型。Llama-3-Chinese-8B-GGUF ChineseAlpacaGroup/llama-3-chinese-8b-gguf 是 ModelScope 魔搭社区上的fill-mask模型，采用 Apache License 2.0 许可。 - **Repository**: ChineseAlpacaGroup/llama-3-chinese-8b-gguf - **License**: Apache License 2.0 - **Tasks**: fill-mask - **Tags**: gguf - **Downloads**: 1466 - **Stars**: 7 - **Last updated**: 2024-04-30 Source: https://www.modelscope.cn/models/ChineseAlpacaGroup/llama-3-chinese-8b-gguf --- # Llama-3-Chinese-8B-GGUF ## 提醒: GGUF文件已重新生成，由于llama.cpp仍然有可能对其作出修改，因此建议保留HF版模型。

这个仓库包含了**Llama-3-Chinese-8B-GGUF**（兼容llama.cpp/ollama等），是[Llama-3-Chinese-8B](https://modelscope.cn/models/ChineseAlpacaGroup/llama-3-chinese-8b)模型的量化版本。 **注意：这是一个基座模型，不适用于对话、问答等任务。** 更多细节（性能、使用方法等）请参考GitHub项目页面：https://github.com/ymcui/Chinese-LLaMA-Alpaca-3 ## 量化性能 评测指标：PPL，**越低越好** | Quant | Size | PPL (old model) | 👍🏻 PPL (new model) | | :---: | -------: | ------------------: | ------------------: | | Q2_K | 2.96 GB | 17.7212 +/- 0.59814 | 11.8595 +/- 0.20061 | | Q3_K | 3.74 GB | 8.6303 +/- 0.28481 | 5.7559 +/- 0.09152 | | Q4_0 | 4.34 GB | 8.2513 +/- 0.27102 | 5.5495 +/- 0.08832 | | Q4_K | 4.58 GB | 7.8897 +/- 0.25830 | 5.3126 +/- 0.08500 | | Q5_0 | 5.21 GB | 7.7975 +/- 0.25639 | 5.2222 +/- 0.08317 | | Q5_K | 5.34 GB | 7.7062 +/- 0.25218 | 5.1813 +/- 0.08264 | | Q6_K | 6.14 GB | 7.6600 +/- 0.25043 | 5.1481 +/- 0.08205 | | Q8_0 | 7.95 GB | 7.6512 +/- 0.25064 | 5.1350 +/- 0.08190 | | F16 | 14.97 GB | 7.6389 +/- 0.25001 | 5.1302 +/- 0.08184 | ## 其他 - 完整模型：https://modelscope.cn/models/ChineseAlpacaGroup/llama-3-chinese-8b - LoRA模型：https://modelscope.cn/models/ChineseAlpacaGroup/llama-3-chinese-8b-lora - 关于本模型的提问，请通过 https://github.com/ymcui/Chinese-LLaMA-Alpaca-3 提交issue ---- This repository contains **Llama-3-Chinese-8B-GGUF** (llama.cpp/ollama/tgw, etc. compatible), which is the quantized version of [Llama-3-Chinese-8B](https://modelscope.cn/models/ChineseAlpacaGroup/llama-3-chinese-8b). **Note: this is a foundation model, which is not suitable for conversation, QA, etc.** Further details (performance, usage, etc.) should refer to GitHub project page: https://github.com/ymcui/Chinese-LLaMA-Alpaca-3 ## Performance Metric: PPL, **lower is better** The model name with `-im` suffix is generated with important matrix, which has generally better performance. | Quant | Size | PPL (old model) | 👍🏻 PPL (new model) | | :---: | -------: | ------------------: | ------------------: | | Q2_K | 2.96 GB | 17.7212 +/- 0.59814 | 11.8595 +/- 0.20061 | | Q3_K | 3.74 GB | 8.6303 +/- 0.28481 | 5.7559 +/- 0.09152 | | Q4_0 | 4.34 GB | 8.2513 +/- 0.27102 | 5.5495 +/- 0.08832 | | Q4_K | 4.58 GB | 7.8897 +/- 0.25830 | 5.3126 +/- 0.08500 | | Q5_0 | 5.21 GB | 7.7975 +/- 0.25639 | 5.2222 +/- 0.08317 | | Q5_K | 5.34 GB | 7.7062 +/- 0.25218 | 5.1813 +/- 0.08264 | | Q6_K | 6.14 GB | 7.6600 +/- 0.25043 | 5.1481 +/- 0.08205 | | Q8_0 | 7.95 GB | 7.6512 +/- 0.25064 | 5.1350 +/- 0.08190 | | F16 | 14.97 GB | 7.6389 +/- 0.25001 | 5.1302 +/- 0.08184 | ## Others - For full model, please see: https://modelscope.cn/models/ChineseAlpacaGroup/llama-3-chinese-8b - For LoRA-only model, please see: https://modelscope.cn/models/ChineseAlpacaGroup/llama-3-chinese-8b-lora - If you have questions/issues regarding this model, please submit an issue through https://github.com/ymcui/Chinese-LLaMA-Alpaca-3