CodeLlama 13B Python Refactor
Published by @local-builds · Community adapter
Local Python refactoring assistant tuned for small behavior-preserving changes and typed interfaces.
Usage
Load with Ollama:
# Download the adapter file, then create a Modelfile:
FROM codellama-13b-python-hf
ADAPTER ./codellama13b-python-refactor.gguf
# Build and run:
ollama create my-model -f Modelfile
ollama run my-model "Your prompt here"
Or with llama.cpp:
./llama-cli \
-m base-model.gguf \
--lora codellama13b-python-refactor.gguf \
-p "Your prompt here"
Compatibility
- llama.cpp
- Ollama
- LM Studio
You might also like
text-generation
public
Qwen 7B Ticket Triage
Qwen/Qwen2.5-7B-Instruct
text-generation
public
Llama 3 8B API Migration
meta-llama/Meta-Llama-3-8B-Instruct
text-generation
public
Mistral 7B Field Service Notes
mistralai/Mistral-7B-Instruct-v0.3
text-generation
public
Llama 3.1 8B Testcase Author
meta-llama/Meta-Llama-3.1-8B-Instruct