apepkuss79's picture
Update README.md
4931687 verified
|
raw
history blame
6.63 kB
metadata
license: llama3.1
model_name: Meta-Llama-3.1-70B-Instruct
base_model: meta-llama/Meta-Llama-3.1-70B-Instruct
inference: false
model_creator: Meta Llama3
model_type: llama
pipeline_tag: text-generation
quantized_by: Second State Inc.
language:
  - en
  - de
  - fr
  - it
  - pt
  - hi
  - es
  - th
tags:
  - facebook
  - meta
  - pytorch
  - llama
  - llama-3

Meta-Llama-3.1-70B-Instruct-GGUF

Original Model

meta-llama/Meta-Llama-3.1-70B-Instruct

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:Meta-Llama-3.1-70B-Instruct-Q4_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:Meta-Llama-3.1-70B-Instruct-Q4_K_M.gguf \
      llama-chat.wasm \
      --prompt-template llama-3-chat \
      --ctx-size 128000
    

Quantized with llama.cpp 3445.