CodeLlama-13B-Instruct-GGUF/README.md

language, license, tags, model_name, base_model, inference, model_creator, model_type, pipeline_tag, quantized_by

language	license	tags	model_name	base_model	inference	model_creator	model_type	pipeline_tag	quantized_by
code	llama2	llama-2	CodeLlama 13B Instruct	codellama/CodeLlama-13b-Instruct-hf	false	Meta	llama	text-generation	Second State Inc.

---

CodeLlama-13B-Instruct

Original Model

codellama/CodeLlama-13b-Instruct-hf

Run with LlamaEdge

• LlamaEdge version: v0.2.8 and above

• Prompt template

  • Prompt type: codellama-instruct

  • Prompt string

    <s>[INST] <<SYS>>
    Write code to solve the following coding problem that obeys the constraints and passes the example test cases. Please wrap your code answer using ```: <</SYS>>
    
    {prompt} [/INST]
    

• Context size: 5120

• Run as LlamaEdge command app

  wasmedge --dir .:. --nn-preload default:GGML:AUTO:CodeLlama-13b-Instruct-hf-Q5_K_M.gguf llama-chat.wasm -p codellama-instruct
  

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
CodeLlama-13b-Instruct-hf-Q2_K.gguf	Q2_K	2	5.43 GB	smallest, significant quality loss - not recommended for most purposes
CodeLlama-13b-Instruct-hf-Q3_K_L.gguf	Q3_K_L	3	6.93 GB	small, substantial quality loss
CodeLlama-13b-Instruct-hf-Q3_K_M.gguf	Q3_K_M	3	6.34 GB	very small, high quality loss
CodeLlama-13b-Instruct-hf-Q3_K_S.gguf	Q3_K_S	3	5.66 GB	very small, high quality loss
CodeLlama-13b-Instruct-hf-Q4_0.gguf	Q4_0	4	7.37 GB	legacy; small, very high quality loss - prefer using Q3_K_M
CodeLlama-13b-Instruct-hf-Q4_K_M.gguf	Q4_K_M	4	7.87 GB	medium, balanced quality - recommended
CodeLlama-13b-Instruct-hf-Q4_K_S.gguf	Q4_K_S	4	7.41 GB	small, greater quality loss
CodeLlama-13b-Instruct-hf-Q5_0.gguf	Q5_0	5	8.97 GB	legacy; medium, balanced quality - prefer using Q4_K_M
CodeLlama-13b-Instruct-hf-Q5_K_M.gguf	Q5_K_M	5	9.23 GB	large, very low quality loss - recommended
CodeLlama-13b-Instruct-hf-Q5_K_S.gguf	Q5_K_S	5	8.97 GB	large, low quality loss - recommended
CodeLlama-13b-Instruct-hf-Q6_K.gguf	Q6_K	6	10.7 GB	very large, extremely low quality loss
CodeLlama-13b-Instruct-hf-Q8_0.gguf	Q8_0	8	13.8 GB	very large, extremely low quality loss - not recommended