Instructions to use QuantFactory/ClinicalGPT-base-zh-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuantFactory/ClinicalGPT-base-zh-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="QuantFactory/ClinicalGPT-base-zh-GGUF",
	filename="ClinicalGPT-base-zh.Q2_K.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use QuantFactory/ClinicalGPT-base-zh-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/ClinicalGPT-base-zh-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/ClinicalGPT-base-zh-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/ClinicalGPT-base-zh-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/ClinicalGPT-base-zh-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf QuantFactory/ClinicalGPT-base-zh-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf QuantFactory/ClinicalGPT-base-zh-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf QuantFactory/ClinicalGPT-base-zh-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf QuantFactory/ClinicalGPT-base-zh-GGUF:Q4_K_M

Use Docker

docker model run hf.co/QuantFactory/ClinicalGPT-base-zh-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use QuantFactory/ClinicalGPT-base-zh-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QuantFactory/ClinicalGPT-base-zh-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QuantFactory/ClinicalGPT-base-zh-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/QuantFactory/ClinicalGPT-base-zh-GGUF:Q4_K_M

Ollama
How to use QuantFactory/ClinicalGPT-base-zh-GGUF with Ollama:
```
ollama run hf.co/QuantFactory/ClinicalGPT-base-zh-GGUF:Q4_K_M
```

Unsloth Studio new

How to use QuantFactory/ClinicalGPT-base-zh-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for QuantFactory/ClinicalGPT-base-zh-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for QuantFactory/ClinicalGPT-base-zh-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for QuantFactory/ClinicalGPT-base-zh-GGUF to start chatting

Docker Model Runner
How to use QuantFactory/ClinicalGPT-base-zh-GGUF with Docker Model Runner:
```
docker model run hf.co/QuantFactory/ClinicalGPT-base-zh-GGUF:Q4_K_M
```

Lemonade

How to use QuantFactory/ClinicalGPT-base-zh-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull QuantFactory/ClinicalGPT-base-zh-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.ClinicalGPT-base-zh-GGUF-Q4_K_M

List all available models

lemonade list

QuantFactory/ClinicalGPT-base-zh-GGUF

This is quantized version of medicalai/ClinicalGPT-base-zh created using llama.cpp

Original Model Card

ClinicalGPT

This model card introduces ClinicalGPT model, a large language model designed and optimized for clinical scenarios. ClinicalGPT is fine-tuned on extensive and diverse medical datasets, including medical records, domain-specific knowledge, and multi-round dialogue consultations. The model is undergoing ongoing and continuous updates.

Model Fine-tuning

We set the learning rate to 5e-5, with a batch size of 128 and a maximum length of 1,024, training across 3 epochs.

How to use the model

Load the model via the transformers library:

from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("medicalai/ClinicalGPT-base-zh")
model = AutoModelForCausalLM.from_pretrained("medicalai/ClinicalGPT-base-zh")

Limitations

The project is intended for research purposes only and restricted from commercial or clinical use. The generated content by the model is subject to factors such as model computations, randomness, misinterpretation, and biases, and this project cannot guarantee its accuracy. This project assumes no legal liability for any content produced by the model. Users are advised to exercise caution and independently verify the generated results.

Downloads last month: 41

GGUF

Model size

8B params

Architecture

bloom

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit