Instructions to use jun10k/Qwen1.5-7B-MeChat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jun10k/Qwen1.5-7B-MeChat with Transformers:

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

pipe = pipeline("text-generation", model="jun10k/Qwen1.5-7B-MeChat")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jun10k/Qwen1.5-7B-MeChat")
model = AutoModelForCausalLM.from_pretrained("jun10k/Qwen1.5-7B-MeChat")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use jun10k/Qwen1.5-7B-MeChat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jun10k/Qwen1.5-7B-MeChat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jun10k/Qwen1.5-7B-MeChat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jun10k/Qwen1.5-7B-MeChat

SGLang

How to use jun10k/Qwen1.5-7B-MeChat 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 "jun10k/Qwen1.5-7B-MeChat" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jun10k/Qwen1.5-7B-MeChat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "jun10k/Qwen1.5-7B-MeChat" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jun10k/Qwen1.5-7B-MeChat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jun10k/Qwen1.5-7B-MeChat with Docker Model Runner:
```
docker model run hf.co/jun10k/Qwen1.5-7B-MeChat
```

jun10k commited on Apr 26, 2024

Commit

af3a8bb

verified ·

1 Parent(s): ba75c6b

Update README.md

Browse files

Files changed (1) hide show

README.md +25 -0

README.md CHANGED Viewed

@@ -1,3 +1,28 @@
 ---
 license: apache-2.0
 ---

 ---
 license: apache-2.0
+language:
+- zh
+tags:
+- medical
 ---
+本项目是用Qwen1.5-7B为基础，使用心理健康对话数据集实现微调。仅用于技术研究用途。
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/645345c9c895e6437dc97110/b_u5oGQHfEoEHT5R1RNSK.png)
+## 引用
+本项目的使用来自中文心理健康支持对话 · 数据集(SmileChat)
+其具体信息如下
+```
+@misc{qiu2023smile,
+      title={SMILE: Single-turn to Multi-turn Inclusive Language Expansion via ChatGPT for Mental Health Support},
+      author={Huachuan Qiu and Hongliang He and Shuai Zhang and Anqi Li and Zhenzhong Lan},
+      year={2023},
+      eprint={2305.00450},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```