README.md

metadata

language:
  - en
license: apache-2.0
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - llama
  - trl
  - llama-cpp
  - gguf-my-lora
base_model: vinhnx90/llama-3-8b-bnb-4bit
datasets:
  - yahma/alpaca-cleaned

vinhnx90/llama-3-8b-bnb-4bit-F16-GGUF

This LoRA adapter was converted to GGUF format from vinhnx90/llama-3-8b-bnb-4bit via the ggml.ai's GGUF-my-lora space. Refer to the original adapter repository for more details.

Use with llama.cpp

# with cli
llama-cli -m base_model.gguf --lora llama-3-8b-bnb-4bit-f16.gguf (...other args)

# with server
llama-server -m base_model.gguf --lora llama-3-8b-bnb-4bit-f16.gguf (...other args)

To know more about LoRA usage with llama.cpp server, refer to the llama.cpp server documentation.