OpenHermes-2.5-Mistral-7B-GGUF/README.md

base_model, inference, language, license, model-index, model_creator, model_name, model_type, tags, quantized_by

base_model	inference	language	license	model-index	model_creator	model_name	model_type	tags	quantized_by
teknium/OpenHermes-2.5-Mistral-7B	false	en	apache-2.0	name results OpenHermes-2-Mistral-7B	Teknium	Openhermes 2.5 Mistral 7B	mistral	mistral instruct finetune chatml gpt4 synthetic data distillation	Second State Inc.

---

OpenHermes-2.5-Mistral-7B-GGUF

Original Model

teknium/OpenHermes-2.5-Mistral-7B

Run with LlamaEdge

• LlamaEdge version: v0.2.8 and above

• Prompt template

  • Prompt type: chatml

  • Prompt string

    <|im_start|>system
    {system_message}<|im_end|>
    <|im_start|>user
    {prompt}<|im_end|>
    <|im_start|>assistant
    

  • Reverse prompt: <|im_end|>

• Run as LlamaEdge service

  wasmedge --dir .:. --nn-preload default:GGML:AUTO:OpenHermes-2.5-Mistral-7B-Q5_K_M.gguf llama-api-server.wasm -p chatml -r '<|im_end|>'
  

• Context size: 4096

• Run as LlamaEdge command app

  wasmedge --dir .:. --nn-preload default:GGML:AUTO:OpenHermes-2.5-Mistral-7B-Q5_K_M.gguf llama-chat.wasm -p chatml -r '<|im_end|>'
  

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
OpenHermes-2.5-Mistral-7B-Q2_K.gguf	Q2_K	2	3.08 GB	smallest, significant quality loss - not recommended for most purposes
OpenHermes-2.5-Mistral-7B-Q3_K_L.gguf	Q3_K_L	3	3.82 GB	small, substantial quality loss
OpenHermes-2.5-Mistral-7B-Q3_K_M.gguf	Q3_K_M	3	3.52 GB	very small, high quality loss
OpenHermes-2.5-Mistral-7B-Q3_K_S.gguf	Q3_K_S	3	3.16 GB	very small, high quality loss
OpenHermes-2.5-Mistral-7B-Q4_0.gguf	Q4_0	4	4.11 GB	legacy; small, very high quality loss - prefer using Q3_K_M
OpenHermes-2.5-Mistral-7B-Q4_K_M.gguf	Q4_K_M	4	4.37 GB	medium, balanced quality - recommended
OpenHermes-2.5-Mistral-7B-Q4_K_S.gguf	Q4_K_S	4	4.14 GB	small, greater quality loss
OpenHermes-2.5-Mistral-7B-Q5_0.gguf	Q5_0	5	5 GB	legacy; medium, balanced quality - prefer using Q4_K_M
OpenHermes-2.5-Mistral-7B-Q5_K_M.gguf	Q5_K_M	5	5.13 GB	large, very low quality loss - recommended
OpenHermes-2.5-Mistral-7B-Q5_K_S.gguf	Q5_K_S	5	5 GB	large, low quality loss - recommended
OpenHermes-2.5-Mistral-7B-Q6_K.gguf	Q6_K	6	5.94 GB	very large, extremely low quality loss
OpenHermes-2.5-Mistral-7B-Q8_0.gguf	Q8_0	8	7.7 GB	very large, extremely low quality loss - not recommended