Instructions to use OpenMEDLab/PULSE-7bv5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenMEDLab/PULSE-7bv5 with Transformers:

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

pipe = pipeline("text-generation", model="OpenMEDLab/PULSE-7bv5")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OpenMEDLab/PULSE-7bv5")
model = AutoModelForCausalLM.from_pretrained("OpenMEDLab/PULSE-7bv5", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OpenMEDLab/PULSE-7bv5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenMEDLab/PULSE-7bv5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenMEDLab/PULSE-7bv5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OpenMEDLab/PULSE-7bv5

SGLang

How to use OpenMEDLab/PULSE-7bv5 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 "OpenMEDLab/PULSE-7bv5" \
    --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": "OpenMEDLab/PULSE-7bv5",
		"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 "OpenMEDLab/PULSE-7bv5" \
        --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": "OpenMEDLab/PULSE-7bv5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OpenMEDLab/PULSE-7bv5 with Docker Model Runner:
```
docker model run hf.co/OpenMEDLab/PULSE-7bv5
```

genggui001 commited on Jun 27, 2023

Commit

353f9a8

1 Parent(s): de4e5fb

First model version

Browse files

Files changed (1) hide show

README.md +11 -11

README.md CHANGED Viewed

@@ -35,17 +35,17 @@
 由于模型参数量较小和自回归生成范式，尽管模型提供了有关疾病诊断和治疗的推理结果，但这些结果不能代替线下职业医生的建议和治疗方案。所有回答仅供参考，不应作为诊断或治疗的依据。我们强烈建议用户在需要诊断或治疗疾病时，寻求专业医生的帮助和建议。
 ### Elo评测
-| model_name   | model_size   |   MedQA_Mainland |   PromptCBLUE |   med_detailed_answer |   webMedQA |     ALL |
-|:-------------|:-------------|-----------------:|--------------:|----------------------:|-----------:|--------:|
-| GPT4         | 220B*8(?)    |          1118.20 |       1166.39 |               1122.20 |    1132.74 | 1243.79 |
-| ChatGPT      | 175B(?)      |          1083.05 |       1102.31 |               1098.38 |    1097.88 | 1149.38 |
-| PULSE_14bv5  | 14B          |          1003.55 |       1055.56 |               1074.79 |    1074.28 | 1114.23 |
-| PULSE_7bv5   | 7B           |          1047.35 |       1047.27 |               1029.37 |    1069.40 | 1084.18 |
-| QiZhenGPT    | 13B          |           952.66 |        929.56 |               1076.41 |    1006.85 |  979.94 |
-| BianQue      | 6B           |           927.86 |        922.65 |               1050.22 |    1042.64 |  959.35 |
-| Med-ChatGLM  | 6B           |           989.59 |        928.77 |                882.08 |     856.66 |  869.54 |
-| BenTsao      | 7B           |           954.20 |        933.39 |                815.51 |     856.20 |  809.13 |
-| DoctorGLM    | 6B           |           923.54 |        914.10 |                851.04 |     863.35 |  790.47 |
 ## 推理

 由于模型参数量较小和自回归生成范式，尽管模型提供了有关疾病诊断和治疗的推理结果，但这些结果不能代替线下职业医生的建议和治疗方案。所有回答仅供参考，不应作为诊断或治疗的依据。我们强烈建议用户在需要诊断或治疗疾病时，寻求专业医生的帮助和建议。
 ### Elo评测
+| model_name   | model_size   |     ALL |   MedQA_Mainland |   PromptCBLUE |   detailedMedQA |   webMedQA |
+|:-------------|:-------------|--------:|-----------------:|--------------:|----------------------:|-----------:|
+| GPT4         | 220B*8(?)    | 1243.79 |          1118.20 |       1166.39 |               1122.20 |    1132.74 |
+| ChatGPT      | 175B(?)      | 1149.38 |          1083.05 |       1102.31 |               1098.38 |    1097.88 |
+| PULSE_14b  | 14B          | 1114.23 |          1003.55 |       1055.56 |               1074.79 |    1074.28 |
+| PULSE_7b   | 7B           | 1084.18 |          1047.35 |       1047.27 |               1029.37 |    1069.40 |
+| QiZhenGPT    | 13B          |  979.94 |           952.66 |        929.56 |               1076.41 |    1006.85 |
+| BianQue      | 6B           |  959.35 |           927.86 |        922.65 |               1050.22 |    1042.64 |
+| Med-ChatGLM  | 6B           |  869.54 |           989.59 |        928.77 |                882.08 |     856.66 |
+| BenTsao      | 7B           |  809.13 |           954.20 |        933.39 |                815.51 |     856.20 |
+| DoctorGLM    | 6B           |  790.47 |           923.54 |        914.10 |                851.04 |     863.35 |
 ## 推理