Instructions to use lxcxjxhx/MSN_demo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use lxcxjxhx/MSN_demo with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="lxcxjxhx/MSN_demo", filename="DSR1-Q7-4S.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use lxcxjxhx/MSN_demo with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf lxcxjxhx/MSN_demo # Run inference directly in the terminal: llama-cli -hf lxcxjxhx/MSN_demo
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf lxcxjxhx/MSN_demo # Run inference directly in the terminal: llama-cli -hf lxcxjxhx/MSN_demo
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 lxcxjxhx/MSN_demo # Run inference directly in the terminal: ./llama-cli -hf lxcxjxhx/MSN_demo
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 lxcxjxhx/MSN_demo # Run inference directly in the terminal: ./build/bin/llama-cli -hf lxcxjxhx/MSN_demo
Use Docker
docker model run hf.co/lxcxjxhx/MSN_demo
- LM Studio
- Jan
- Ollama
How to use lxcxjxhx/MSN_demo with Ollama:
ollama run hf.co/lxcxjxhx/MSN_demo
- Unsloth Studio new
How to use lxcxjxhx/MSN_demo 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 lxcxjxhx/MSN_demo 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 lxcxjxhx/MSN_demo to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for lxcxjxhx/MSN_demo to start chatting
- Docker Model Runner
How to use lxcxjxhx/MSN_demo with Docker Model Runner:
docker model run hf.co/lxcxjxhx/MSN_demo
- Lemonade
How to use lxcxjxhx/MSN_demo with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull lxcxjxhx/MSN_demo
Run and chat with the model
lemonade run user.MSN_demo-{{QUANT_TAG}}List all available models
lemonade list
llm.create_chat_completion(
messages = "No input example has been defined for this model task."
)YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
---license: apache-2.0
Model Description
This model is a fine-tuning model based on Deepseek ai/Deepseek R1 and is currently in its early stages.
This model is committed to minimizing the model size as much as possible and providing models for a single professional field.
(This model is only used for learning purposes)
Model Details
DEMO 1:Attempt to reduce the size of the local model
DEMO 2:Reupload the usable quantized gguf model and attach a Llama.cpp compiled based on mysys2 for calling during model migration.
1.0:For the first fine-tuning and training, we attempted to use a smaller model and added a dataset from
huzaifa525 Medical_Sntelligence-Dataset_40k-Rows_of-Disease_info_Treatments_and_Sedical_QA based on the Lora training method
- Downloads last month
- 6
We're not able to determine the quantization variants.
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="lxcxjxhx/MSN_demo", filename="DSR1-Q7-4S.gguf", )