README.md

metadata

license: other
license_name: llama3
base_model: haqishen/Llama-3-8B-Japanese-Instruct
inference: false
model_creator: haqishen
model_type: llama
pipeline_tag: text-generation
quantized_by: Second State Inc.
language:
  - en
  - ja

---

Llama3-8B-Japanese-Chat-GGUF

Original Model

haqishen/Llama-3-8B-Japanese-Instruct

Run with LlamaEdge

• LlamaEdge version: v0.10.1 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: 4096

• Run as LlamaEdge service

  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3-8B-Japanese-Instruct-Q5_K_M.gguf \
    llama-api-server.wasm \
    --prompt-template llama-3-chat \
    --ctx-size 4096 \
    --model-name Llama-3-8B-Japanese-Instruct \
  

• Run as LlamaEdge command app

  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3-8B-Japanese-Instruct-Q5_K_M.gguf \
    llama-chat.wasm \
    --prompt-template llama-3-chat \
    --ctx-size 4096
  

Quantized with llama.cpp b2824.