How to use ramonsj11/recipe-llm-gguf with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="ramonsj11/recipe-llm-gguf", filename="tinyllama-recipes-q4.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] )
How to use ramonsj11/recipe-llm-gguf with llama.cpp:
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf ramonsj11/recipe-llm-gguf # Run inference directly in the terminal: llama-cli -hf ramonsj11/recipe-llm-gguf
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf ramonsj11/recipe-llm-gguf # Run inference directly in the terminal: llama-cli -hf ramonsj11/recipe-llm-gguf
# 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 ramonsj11/recipe-llm-gguf # Run inference directly in the terminal: ./llama-cli -hf ramonsj11/recipe-llm-gguf
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 ramonsj11/recipe-llm-gguf # Run inference directly in the terminal: ./build/bin/llama-cli -hf ramonsj11/recipe-llm-gguf
docker model run hf.co/ramonsj11/recipe-llm-gguf
How to use ramonsj11/recipe-llm-gguf with vLLM:
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ramonsj11/recipe-llm-gguf" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ramonsj11/recipe-llm-gguf", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'
How to use ramonsj11/recipe-llm-gguf with Ollama:
ollama run hf.co/ramonsj11/recipe-llm-gguf
How to use ramonsj11/recipe-llm-gguf with Unsloth Studio:
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 ramonsj11/recipe-llm-gguf to start chatting
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 ramonsj11/recipe-llm-gguf to start chatting
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for ramonsj11/recipe-llm-gguf to start chatting
How to use ramonsj11/recipe-llm-gguf with Docker Model Runner:
How to use ramonsj11/recipe-llm-gguf with Lemonade:
# Download Lemonade from https://lemonade-server.ai/ lemonade pull ramonsj11/recipe-llm-gguf
lemonade run user.recipe-llm-gguf-{{QUANT_TAG}}
lemonade list
TinyLlama-1.1B-Chat fine-tuned with LoRA for recipe generation. Quantized to Q4_K_M GGUF for CPU inference with llama-cpp-python.
llama-cpp-python
from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="ramonsj11/recipe-llm-gguf", filename="tinyllama-recipes-q4.gguf", )
Chat template
We're not able to determine the quantization variants.
