frameworks, license, model-type, language, tools
frameworks license model-type language tools
other
Apache License 2.0
llama
zh
en
llamacpp

license: apache-2.0 language:

  • zh
  • en

📣📣📣 v3版指令模型已发布欢迎使用 👉 [HF版] [GGUF版]

Llama-3-Chinese-8B-Instruct-v2-GGUF

这个仓库包含了Llama-3-Chinese-8B-Instruct-v2-GGUF兼容llama.cpp/ollama等Llama-3-Chinese-8B-Instruct-v2模型的量化版本。

注意:这是一个指令模型,可以直接适用于对话、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
Q2_K 2.96 GB 13.2488 +/- 0.17217
Q3_K 3.74 GB 6.9618 +/- 0.08420
Q4_0 4.34 GB 6.8925 +/- 0.08437
Q4_K 4.58 GB 6.4851 +/- 0.07892
Q5_0 5.21 GB 6.4608 +/- 0.07862
Q5_K 5.34 GB 6.3742 +/- 0.07740
Q6_K 6.14 GB 6.3494 +/- 0.07703
Q8_0 7.95 GB 6.3110 +/- 0.07673
F16 14.97 GB 6.3005 +/- 0.07658

其他


This repository contains Llama-3-Chinese-8B-Instruct-v2-GGUF (llama.cpp/ollama/tgw, etc. compatible), which is the quantized version of Llama-3-Chinese-8B-Instruct-v2.

Note: this is an instruction (chat) model, which can be used 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

Quant Size PPL
Q2_K 2.96 GB 13.2488 +/- 0.17217
Q3_K 3.74 GB 6.9618 +/- 0.08420
Q4_0 4.34 GB 6.8925 +/- 0.08437
Q4_K 4.58 GB 6.4851 +/- 0.07892
Q5_0 5.21 GB 6.4608 +/- 0.07862
Q5_K 5.34 GB 6.3742 +/- 0.07740
Q6_K 6.14 GB 6.3494 +/- 0.07703
Q8_0 7.95 GB 6.3110 +/- 0.07673
F16 14.97 GB 6.3005 +/- 0.07658

Others

Description
Model synced from source: ChineseAlpacaGroup/llama-3-chinese-8b-instruct-v2-gguf
Readme 26 KiB