Update README.md

README.md

@@ -14,15 +14,15 @@ language:
 If you find this model helpful, please *like* this model and star us on https://github.com/LianjiaTech/BELLE !
 
 ## Model description
-8 bits quantization of [Bloom](https://arxiv.org/pdf/2211.05100.pdf) using [GPTQ](https://arxiv.org/abs/2210.17323)
+8 bits quantization of [BELLE-7B-2M](https://huggingface.co/BelleGroup/BELLE-7B-2M) and [BELLE-7B-0.2M](https://huggingface.co/BelleGroup/BELLE-7B-0.2M) using [GPTQ](https://arxiv.org/abs/2210.17323)
 
 GPTQ is SOTA one-shot weight quantization method.
 
-The code of inference can be found in our Github project repository: https://github.com/LianjiaTech/BELLE/gptq.
+The code of inference can be found in our Github project repository: https://github.com/LianjiaTech/BELLE/tree/main/gptq.
 
 Basically, 8-bit quantization and 128 groupsize are recommended.
 
-**This code is based on [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa)**
+**This code is based on [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa) for [Bloom](https://arxiv.org/pdf/2211.05100.pdf) model**
 
 ## Model list
 
@@ -34,6 +34,17 @@ Basically, 8-bit quantization and 128 groupsize are recommended.
 |           bloom7b-0.2m-8bit-128g.pt                  |          9.7G        |       ~11.4G          |
 |           bloom7b-0.2m-4bit-128g.pt                  |          6.9G        |        ~8.4G          |
 
+## Limitations
+There still exists a few issues in the model trained on current base model and data:
+
+1. The model might generate factual errors when asked to follow instructions related to facts.
+
+2. Occasionally generates harmful responses since the model still struggles to identify potential harmful instructions.
+
+3. Needs improvements on reasoning and coding.
+
+Since the model still has its limitations, we require developers only use the open-sourced code, data, model and any other artifacts generated via this project for research purposes. Commercial use and other potential harmful use cases are not allowed.
+
 ## Citation
 
 Please cite us when using our code, data or model.
@@ -59,15 +70,15 @@ Cite the original BLOOM, Stanford Alpaca and Self-Instruct papers as well!
 如果您觉得此模型对您有帮助，请like此模型并在https://github.com/LianjiaTech/BELLE 项目中star我们！
 
 ## 模型描述
-对[Bloom](https://arxiv.org/pdf/2211.05100.pdf)模型使用[GPTQ](https://arxiv.org/abs/2210.17323)进行8 bit（8位）量化。
+对[BELLE-7B-2M](https://huggingface.co/BelleGroup/BELLE-7B-2M) and [BELLE-7B-0.2M](https://huggingface.co/BelleGroup/BELLE-7B-0.2M)进行8 bit（8位）量化。
 
 GPTQ是目前SOTA的one-shot权重量化方法。
 
-此模型的推理代码请见https://github.com/LianjiaTech/BELLE/gptq .
+此模型的推理代码请见https://github.com/LianjiaTech/BELLE/tree/main/gptq .
 
 一般来说，推荐使用8-bit量化及groupsize = 128.
 
-**推理代码基于[GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa)**
+**[Bloom](https://arxiv.org/pdf/2211.05100.pdf)模型使用[GPTQ](https://arxiv.org/abs/2210.17323)的推理代码基于[GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa)**
 
 ## 模型列表
 
@@ -79,6 +90,17 @@ GPTQ是目前SOTA的one-shot权重量化方法。
 |           bloom7b-0.2m-8bit-128g.pt                  |          9.7G        |       ~11.4G          |
 |           bloom7b-0.2m-4bit-128g.pt                  |          6.9G        |        ~8.4G          |
 
+## 局限性和使用限制
+基于当前数据和基础模型训练得到的SFT模型，在效果上仍存在以下问题：
+
+1. 在涉及事实性的指令上可能会产生违背事实的错误回答。
+
+2. 对于具备危害性的指令无法很好的鉴别，由此会产生危害性言论。
+
+3. 在一些涉及推理、代码等场景下模型的能力仍有待提高。
+
+基于以上模型局限性，我们要求开发者仅将我们开源的代码、数据、模型及后续用此项目生成的衍生物用于研究目的，不得用于商业，以及其他会对社会带来危害的用途。
+
 ## 引用
 如果使用本项目的代码、数据或模型，请引用本项目。
 ```