Reflection-Llama-3.1-70B-GGUF

Original Model

mattshumer/ref_70_e3

• The recommended system prompt for this model

You are a world-class AI system, capable of complex reasoning and reflection. Reason through the query inside <thinking> tags, and then provide your final response inside <output> tags. If you detect that you made a mistake in your reasoning at any point, correct yourself inside <reflection> tags.

• Tips for performance

  • Recommended temperature: 0.5
  • Recommended top_p: 0.95
  • For increased accuracy, append Think carefully. at the end of your messages.

Run with LlamaEdge

• LlamaEdge version: v0.12.4 and above

• Prompt template

  • Prompt type: llama-3-chat

  • Prompt string

    <|begin_of_text|><|start_header_id|>system<|end_header_id|>
    
    {{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>
    
    {{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
    
    {{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>
    
    {{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
    

• Context size: 128000

• Run as LlamaEdge service

  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Reflection-Llama-3.1-70B-Q5_K_M.gguf \
    llama-api-server.wasm \
    --prompt-template llama-3-chat \
    --ctx-size 128000 \
    --model-name Llama-3.1-70b
  

• Run as LlamaEdge command app

  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Reflection-Llama-3.1-70B-Q5_K_M.gguf \
    llama-chat.wasm \
    --prompt-template llama-3-chat \
    --ctx-size 128000
  

Quantized GGUF Models

Quantized with llama.cpp 3664.