Instructions to use stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored with Transformers:

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

pipe = pipeline("text-generation", model="stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored")
model = AutoModelForMultimodalLM.from_pretrained("stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored")
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]:]))

llama-cpp-python

How to use stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored",
	filename="unsloth.F16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored: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 stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored: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 stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored:Q4_K_M

Use Docker

docker model run hf.co/stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored:Q4_K_M

LM Studio
Jan

vLLM

How to use stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored:Q4_K_M

SGLang

How to use stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored 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 "stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored" \
    --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": "stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored",
		"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 "stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored" \
        --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": "stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored with Ollama:
```
ollama run hf.co/stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored:Q4_K_M
```

Unsloth Studio

How to use stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored 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 stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored 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 stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored to start chatting

Atomic Chat new
Docker Model Runner
How to use stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored with Docker Model Runner:
```
docker model run hf.co/stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored:Q4_K_M
```

Lemonade

How to use stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored:Q4_K_M

Run and chat with the model

lemonade run user.Mistral-7B-v0.3-Chinese-Chat-uncensored-Q4_K_M

List all available models

lemonade list

Model Details

Model Description

Using shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat as base model, and finetune the dataset as mentioned via unsloth. Makes the model uncensored.

Training Code

Training Procedure Raw Files

ALL the procedure are training on Vast.ai
Hardware in Vast.ai:
- GPU: 1x A100 SXM4 80GB
- CPU: AMD EPYC 7513 32-Core Processor
- RAM: 129 GB
- Disk Space To Allocate：>150GB
- Docker Image: pytorch/pytorch:2.2.0-cuda12.1-cudnn8-devel
- Download the ipynb file.

Training Data

Base Model
- shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat
Dataset

Usage

from transformers import pipeline

qa_model = pipeline("question-answering", model='stephenlzc/Mistral-7B-v0.3-Chinese-Chat-uncensored')
question = "How to make girlfreind laugh? please answer in Chinese."
qa_model(question = question)