Instructions to use mlx-community/Mistral-7B-v0.1-LoRA-Text2SQL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/Mistral-7B-v0.1-LoRA-Text2SQL with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="mlx-community/Mistral-7B-v0.1-LoRA-Text2SQL")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mlx-community/Mistral-7B-v0.1-LoRA-Text2SQL")
model = AutoModelForCausalLM.from_pretrained("mlx-community/Mistral-7B-v0.1-LoRA-Text2SQL")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use mlx-community/Mistral-7B-v0.1-LoRA-Text2SQL with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mlx-community/Mistral-7B-v0.1-LoRA-Text2SQL"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlx-community/Mistral-7B-v0.1-LoRA-Text2SQL",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mlx-community/Mistral-7B-v0.1-LoRA-Text2SQL

SGLang

How to use mlx-community/Mistral-7B-v0.1-LoRA-Text2SQL with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "mlx-community/Mistral-7B-v0.1-LoRA-Text2SQL" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlx-community/Mistral-7B-v0.1-LoRA-Text2SQL",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "mlx-community/Mistral-7B-v0.1-LoRA-Text2SQL" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlx-community/Mistral-7B-v0.1-LoRA-Text2SQL",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mlx-community/Mistral-7B-v0.1-LoRA-Text2SQL with Docker Model Runner:
```
docker model run hf.co/mlx-community/Mistral-7B-v0.1-LoRA-Text2SQL
```

军舰 commited on Jan 25, 2024

Commit

aa9de2b

1 Parent(s): e3678d1

Update upload model to huggingface hub.

Browse files

Files changed (1) hide show

README.md +66 -10

README.md CHANGED Viewed

@@ -4,15 +4,15 @@ license: mit
 ## [mlx-community/Mistral-7B-v0.1-LoRA-Text2SQL](https://huggingface.co/mlx-community/Mistral-7B-v0.1-LoRA-Text2SQL)
-本次微调的模型我已经上传到了 HuggingFace Hub 上，大家可以直接使用。
-### 安装
 ```bash
 pip install mlx-lm
 ```
-### 生成
 ```
 python -m mlx_lm.generate --model mlx-community/Mistral-7B-v0.1-LoRA-Text2SQL \
                           --max-tokens 50 \
@@ -61,7 +61,7 @@ if __name__ == "__main__":
 ### 样本示例
-```json
 table: 1-10753917-1
 columns: Season, Driver, Team, Engine, Poles, Wins, Podiums, Points, Margin of defeat
 Q: Which podiums did the alfa romeo team have?
@@ -129,7 +129,7 @@ python fuse.py --model mistralai/Mistral-7B-v0.1 \
 ```
-## 生成
 ### 王军建的姓名是什么？
@@ -244,13 +244,69 @@ SELECT COUNT Name FROM students WHERE Grade = 9
 附加的提示信息可以轻松添加，不用太在意放置的位置。
-## 上传模型
 ```bash
-python -m mlx_lm.convert \
-    --mlx-path lora_fused_model/ \
-    --quantize \
-    --upload-repo mlx-community/Mistral-7B-v0.1-LoRA-Text2SQL
 ```

 ## [mlx-community/Mistral-7B-v0.1-LoRA-Text2SQL](https://huggingface.co/mlx-community/Mistral-7B-v0.1-LoRA-Text2SQL)
+本次微调的模型我已经上传到了 HuggingFace Hub 上，大家可以进行尝试。
+### 安装 mlx-lm
 ```bash
 pip install mlx-lm
 ```
+### 生成 SQL
 ```
 python -m mlx_lm.generate --model mlx-community/Mistral-7B-v0.1-LoRA-Text2SQL \
                           --max-tokens 50 \
 ### 样本示例
+```
 table: 1-10753917-1
 columns: Season, Driver, Team, Engine, Poles, Wins, Podiums, Points, Margin of defeat
 Q: Which podiums did the alfa romeo team have?
 ```
+## 生成 SQL
 ### 王军建的姓名是什么？
 附加的提示信息可以轻松添加，不用太在意放置的位置。
+## 上传模型到 HuggingFace Hub
+1. 加入 [MLX Community](https://huggingface.co/mlx-community) 组织
+2. 在 MLX Community 组织中创建一个新的模型 [mlx-community/Mistral-7B-v0.1-LoRA-Text2SQL](https://huggingface.co/mlx-community/Mistral-7B-v0.1-LoRA-Text2SQL)
+3. 克隆仓库 [mlx-community/Mistral-7B-v0.1-LoRA-Text2SQL](https://huggingface.co/mlx-community/Mistral-7B-v0.1-LoRA-Text2SQL)
+```bash
+git clone https://huggingface.co/mlx-community/Mistral-7B-v0.1-LoRA-Text2SQL
+```
+4. 将生成的模型文件（`lora_fused_model` 目录下的所有文件）复制到仓库目录下
+5. 上传模型到 HuggingFace Hub
+```bash
+git add .
+git commit -m "Fine tuning Text2SQL based on Mistral-7B using LoRA on MLX"
+git push
+```
+### git push 错误
+1. 不能 push
+错误信息：
+```
+Uploading LFS objects:   0% (0/2), 0 B | 0 B/s, done.
+batch response: Authorization error.
+error: failed to push some refs to 'https://huggingface.co/mlx-community/Mistral-7B-v0.1-LoRA-Text2SQL'
+```
+解决方法：
+```bash
+vim .git/config
+```
+```conf
+[remote "origin"]
+    url = https://wangjunjian:write_token@huggingface.co/mlx-community/Mistral-7B-v0.1-LoRA-Text2SQL
+    fetch = +refs/heads/*:refs/remotes/origin/*
+```
+2. 不能上传大于 5GB 的文件
+错误信息：
+```
+warning: current Git remote contains credentials
+batch response:
+You need to configure your repository to enable upload of files > 5GB.
+Run "huggingface-cli lfs-enable-largefiles ./path/to/your/repo" and try again.
+```
+解决方法：
 ```bash
+huggingface-cli longin
+huggingface-cli lfs-enable-largefiles /Users/junjian/HuggingFace/mlx-community/Mistral-7B-v0.1-LoRA-Text2SQL
 ```