Instructions to use ltg/normistral-7b-warm-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ltg/normistral-7b-warm-instruct with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ltg/normistral-7b-warm-instruct") 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("ltg/normistral-7b-warm-instruct") model = AutoModelForCausalLM.from_pretrained("ltg/normistral-7b-warm-instruct", 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]:])) - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use ltg/normistral-7b-warm-instruct with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf ltg/normistral-7b-warm-instruct:Q4_K_M # Run inference directly in the terminal: llama cli -hf ltg/normistral-7b-warm-instruct:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf ltg/normistral-7b-warm-instruct:Q4_K_M # Run inference directly in the terminal: llama cli -hf ltg/normistral-7b-warm-instruct:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf ltg/normistral-7b-warm-instruct:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf ltg/normistral-7b-warm-instruct:Q4_K_M
Use Docker
docker model run hf.co/ltg/normistral-7b-warm-instruct:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use ltg/normistral-7b-warm-instruct with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ltg/normistral-7b-warm-instruct" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ltg/normistral-7b-warm-instruct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/ltg/normistral-7b-warm-instruct:Q4_K_M
- SGLang
How to use ltg/normistral-7b-warm-instruct 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 "ltg/normistral-7b-warm-instruct" \ --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": "ltg/normistral-7b-warm-instruct", "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 "ltg/normistral-7b-warm-instruct" \ --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": "ltg/normistral-7b-warm-instruct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Ollama
How to use ltg/normistral-7b-warm-instruct with Ollama:
ollama run hf.co/ltg/normistral-7b-warm-instruct:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use ltg/normistral-7b-warm-instruct with Docker Model Runner:
docker model run hf.co/ltg/normistral-7b-warm-instruct:Q4_K_M
- Lemonade
How to use ltg/normistral-7b-warm-instruct with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull ltg/normistral-7b-warm-instruct:Q4_K_M
Run and chat with the model
lemonade run user.normistral-7b-warm-instruct-Q4_K_M
List all available models
lemonade list
- Atomic Chat
GGUF 8bit model not recommended.
Hi! Thanks a lot for making these models accessible and fully open source!
I was looking at the different quantized models, and from the table, you say that the
8-bit variant is : " very large, extremely low quality loss - not recommended"
First of all, where can i find the results showing that the model has extremely low loss of quality? Could the use of "extremely here be an exaggeration?"
Second, why is it that this variant is not recommended?
Given you have the compute wouldn't you prefer this over the smaller model?
I understand that the smaller models could be more optimal for some, but I don't get why it is just not recommended without any explanation.
If the described magnitude of model size and loss of compression is relative to the other models in the table, then perhaps just call it "largest" and "least loss of quality"?
We have not tested the quantized models yet, and the use cases are from llama.cpp, these are there recommendations for the llama, and mistral 7b models.
I deleted the "recommendations", they depend on how much VRAM you have available and seem quite misleading. Thanks!