README.md

metadata

license: apache-2.0
tags:
  - code
  - llama-cpp
  - gguf-my-repo
base_model: deepseek-ai/deepseek-coder-6.7b-base
datasets:
  - JetBrains/KExercises
results:
  - task:
      type: text-generation
    dataset:
      name: MultiPL-HumanEval (Kotlin)
      type: openai_humaneval
    metrics:
      - name: pass@1
        type: pass@1
        value: 55.28

YorkieOH10/deepseek-coder-6.7B-kexer-Q8_0-GGUF

This model was converted to GGUF format from JetBrains/deepseek-coder-6.7B-kexer using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

Use with llama.cpp

Install llama.cpp through brew.

brew install ggerganov/ggerganov/llama.cpp

Invoke the llama.cpp server or the CLI. CLI:

llama-cli --hf-repo YorkieOH10/deepseek-coder-6.7B-kexer-Q8_0-GGUF --model deepseek-coder-6.7b-kexer-q8_0.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo YorkieOH10/deepseek-coder-6.7B-kexer-Q8_0-GGUF --model deepseek-coder-6.7b-kexer-q8_0.gguf -c 2048

Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.

git clone https://github.com/ggerganov/llama.cpp && \
cd llama.cpp && \
make && \
./main -m deepseek-coder-6.7b-kexer-q8_0.gguf -n 128