XXL GGUF
Collection
Inspired by Unsloth XL quants, I started mastering my own GGUF quants with gool to make them even better then XL ones. • 13 items • Updated
How to use altomek/CodeRosa-70B-AB1-XXL-GGUF with llama.cpp:
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf altomek/CodeRosa-70B-AB1-XXL-GGUF:Q2_K_XXL # Run inference directly in the terminal: llama cli -hf altomek/CodeRosa-70B-AB1-XXL-GGUF:Q2_K_XXL
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf altomek/CodeRosa-70B-AB1-XXL-GGUF:Q2_K_XXL # Run inference directly in the terminal: llama cli -hf altomek/CodeRosa-70B-AB1-XXL-GGUF:Q2_K_XXL
# 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 altomek/CodeRosa-70B-AB1-XXL-GGUF:Q2_K_XXL # Run inference directly in the terminal: ./llama-cli -hf altomek/CodeRosa-70B-AB1-XXL-GGUF:Q2_K_XXL
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 altomek/CodeRosa-70B-AB1-XXL-GGUF:Q2_K_XXL # Run inference directly in the terminal: ./build/bin/llama-cli -hf altomek/CodeRosa-70B-AB1-XXL-GGUF:Q2_K_XXL
docker model run hf.co/altomek/CodeRosa-70B-AB1-XXL-GGUF:Q2_K_XXL
How to use altomek/CodeRosa-70B-AB1-XXL-GGUF with Ollama:
ollama run hf.co/altomek/CodeRosa-70B-AB1-XXL-GGUF:Q2_K_XXL
How to use altomek/CodeRosa-70B-AB1-XXL-GGUF with Docker Model Runner:
docker model run hf.co/altomek/CodeRosa-70B-AB1-XXL-GGUF:Q2_K_XXL
How to use altomek/CodeRosa-70B-AB1-XXL-GGUF with Lemonade:
# Download Lemonade from https://lemonade-server.ai/ lemonade pull altomek/CodeRosa-70B-AB1-XXL-GGUF:Q2_K_XXL
lemonade run user.CodeRosa-70B-AB1-XXL-GGUF-Q2_K_XXL
lemonade list
XXL GGUF quant of https://huggingface.co/altomek/CodeRosa-70B-AB1
I am still experimenting with this quant, mayby update it later, but this one is quite good.
2-bit
Base model
altomek/CodeRosa-70B-AB1