117 lines
4.2 KiB
Markdown
117 lines
4.2 KiB
Markdown
---
|
||
frameworks:
|
||
- other
|
||
license: Apache License 2.0
|
||
model-type:
|
||
- llama
|
||
language:
|
||
- zh
|
||
- en
|
||
tools:
|
||
- llamacpp
|
||
|
||
#model-type:
|
||
##如 gpt、phi、llama、chatglm、baichuan 等
|
||
#- gpt
|
||
|
||
#domain:
|
||
##如 nlp、cv、audio、multi-modal
|
||
#- nlp
|
||
|
||
#language:
|
||
##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
|
||
#- cn
|
||
|
||
#metrics:
|
||
##如 CIDEr、Blue、ROUGE 等
|
||
#- CIDEr
|
||
|
||
#tags:
|
||
##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
|
||
#- pretrained
|
||
|
||
#tools:
|
||
##如 vllm、fastchat、llamacpp、AdaSeq 等
|
||
#- vllm
|
||
---
|
||
|
||
---
|
||
license: apache-2.0
|
||
language:
|
||
- zh
|
||
- en
|
||
---
|
||
## **📣📣📣 v3版指令模型已发布，欢迎使用 👉 [[HF版]](https://modelscope.cn/models/ChineseAlpacaGroup/llama-3-chinese-8b-instruct-v3) [[GGUF版]](https://modelscope.cn/models/ChineseAlpacaGroup/llama-3-chinese-8b-instruct-v3-gguf)**
|
||
|
||
# Llama-3-Chinese-8B-Instruct-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。
|
||
|
||
<p align="center">
|
||
<a href="https://github.com/ymcui/Chinese-LLaMA-Alpaca-3"><img src="https://ymcui.com/images/chinese-llama-alpaca-3-banner.png" width="600"/></a>
|
||
</p>
|
||
|
||
这个仓库包含了**Llama-3-Chinese-8B-Instruct-GGUF**（兼容llama.cpp/ollama等），是[Llama-3-Chinese-8B-Instruct](https://modelscope.cn/models/ChineseAlpacaGroup/llama-3-chinese-8b-instruct)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 (old model) | 👍🏻 PPL (new model) |
|
||
| :---: | -------: | -----------------: | ------------------: |
|
||
| Q2_K | 2.96 GB | 10.3918 +/- 0.13288 | 9.1168 +/- 0.10711 |
|
||
| Q3_K | 3.74 GB | 6.3018 +/- 0.07849 | 5.4082 +/- 0.05955 |
|
||
| Q4_0 | 4.34 GB | 6.0628 +/- 0.07501 | 5.2048 +/- 0.05725 |
|
||
| Q4_K | 4.58 GB | 5.9066 +/- 0.07419 | 5.0189 +/- 0.05520 |
|
||
| Q5_0 | 5.21 GB | 5.8562 +/- 0.07355 | 4.9803 +/- 0.05493 |
|
||
| Q5_K | 5.34 GB | 5.8062 +/- 0.07331 | 4.9195 +/- 0.05436 |
|
||
| Q6_K | 6.14 GB | 5.7757 +/- 0.07298 | 4.8966 +/- 0.05413 |
|
||
| Q8_0 | 7.95 GB | 5.7626 +/- 0.07272 | 4.8822 +/- 0.05396 |
|
||
| F16 | 14.97 GB | 5.7628 +/- 0.07275 | 4.8802 +/- 0.05392 |
|
||
|
||
|
||
## 其他
|
||
|
||
- 完整模型：https://modelscope.cn/models/ChineseAlpacaGroup/llama-3-chinese-8b-instruct
|
||
|
||
- LoRA模型：https://modelscope.cn/models/ChineseAlpacaGroup/llama-3-chinese-8b-instruct-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-Instruct-GGUF** (llama.cpp/ollama/tgw, etc. compatible), which is the quantized version of [Llama-3-Chinese-8B-Instruct](https://huggingface.co/hfl/llama-3-chinese-8b-instruct).
|
||
|
||
**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 (old model) | 👍🏻 PPL (new model) |
|
||
| :---: | -------: | -----------------: | ------------------: |
|
||
| Q2_K | 2.96 GB | 10.3918 +/- 0.13288 | 9.1168 +/- 0.10711 |
|
||
| Q3_K | 3.74 GB | 6.3018 +/- 0.07849 | 5.4082 +/- 0.05955 |
|
||
| Q4_0 | 4.34 GB | 6.0628 +/- 0.07501 | 5.2048 +/- 0.05725 |
|
||
| Q4_K | 4.58 GB | 5.9066 +/- 0.07419 | 5.0189 +/- 0.05520 |
|
||
| Q5_0 | 5.21 GB | 5.8562 +/- 0.07355 | 4.9803 +/- 0.05493 |
|
||
| Q5_K | 5.34 GB | 5.8062 +/- 0.07331 | 4.9195 +/- 0.05436 |
|
||
| Q6_K | 6.14 GB | 5.7757 +/- 0.07298 | 4.8966 +/- 0.05413 |
|
||
| Q8_0 | 7.95 GB | 5.7626 +/- 0.07272 | 4.8822 +/- 0.05396 |
|
||
| F16 | 14.97 GB | 5.7628 +/- 0.07275 | 4.8802 +/- 0.05392 |
|
||
|
||
|
||
## Others
|
||
|
||
- For full model, please see: https://huggingface.co/hfl/llama-3-chinese-8b-instruct
|
||
|
||
- For LoRA-only model, please see: https://huggingface.co/hfl/llama-3-chinese-8b-instruct-lora
|
||
|
||
- If you have questions/issues regarding this model, please submit an issue through https://github.com/ymcui/Chinese-LLaMA-Alpaca-3 |