README.md

---
license: other
license_name: qwen
license_link: >-
  https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT
language:
- en
- zh
library_name: transformers
pipeline_tag: text-generation
inference: false
tags:
- mistral
- qwen
- qwen1.5
- qwen2
---
This is the Mistral version of [Qwen1.5-7B-Chat](https://huggingface.co/Qwen/Qwen1.5-7B-Chat) model by Alibaba Cloud.
The original codebase can be found at: (https://github.com/hiyouga/LLaMA-Factory/blob/main/tests/llamafy_qwen.py).
I have made modifications to make it compatible with qwen1.5.
This model is converted with https://github.com/Minami-su/character_AI_open/blob/main/mistral_qwen2.py

## special

1.Before using this model, you need to modify modeling_mistral.py in transformers library

2.vim /root/anaconda3/envs/train/lib/python3.9/site-packages/transformers/models/mistral/modeling_mistral.py

3.find MistralAttention,

4.modify q,k,v,o bias=False ----->, bias=config.attention_bias

Before:
![image/png](https://cdn-uploads.huggingface.co/production/uploads/62d7f90b102d144db4b4245b/AKj_fwEoLUKWZ4mViYW-q.png)
After:
![image/png](https://cdn-uploads.huggingface.co/production/uploads/62d7f90b102d144db4b4245b/A2gSwq9l6Zx8X1qegtgvE.png)


## Differences between qwen2 mistral and qwen2 llamafy

Compared to qwen2 llamafy,qwen2 mistral can use sliding window attention,qwen2 mistral is faster than qwen2 llamafy, and the context length is better


Usage:

```python

from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
tokenizer = AutoTokenizer.from_pretrained("Minami-su/Qwen1.5-7B-Chat_mistral")
model = AutoModelForCausalLM.from_pretrained("Minami-su/Qwen1.5-7B-Chat_mistral", torch_dtype="auto", device_map="auto")
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)

messages = [
    {"role": "user", "content": "Who are you?"}
]
inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
inputs = inputs.to("cuda")
generate_ids = model.generate(inputs,max_length=32768, streamer=streamer)

```

## Test
load in 4bit
```
hf-causal (pretrained=Qwen1.5-7B-Chat), limit: None, provide_description: False, num_fewshot: 0, batch_size: 8
|    Task     |Version| Metric |Value |   |Stderr|
|-------------|------:|--------|-----:|---|-----:|
|arc_challenge|      0|acc     |0.4155|±  |0.0144|
|             |       |acc_norm|0.4480|±  |0.0145|
|truthfulqa_mc|      1|mc1     |0.3513|±  |0.0167|
|             |       |mc2     |0.5165|±  |0.0159|
|winogrande   |      0|acc     |0.6330|±  |0.0135|
```
load in 4bit
```
hf-causal (pretrained=Qwen1.5-7B-Chat_mistral), limit: None, provide_description: False, num_fewshot: 0, batch_size: 16
|    Task     |Version| Metric |Value |   |Stderr|
|-------------|------:|--------|-----:|---|-----:|
|arc_challenge|      0|acc     |0.4172|±  |0.0144|
|             |       |acc_norm|0.4480|±  |0.0145|
|truthfulqa_mc|      1|mc1     |0.3488|±  |0.0167|
|             |       |mc2     |0.5161|±  |0.0159|
|winogrande   |      0|acc     |0.6306|±  |0.0136|
```
```