README.md

metadata

license: llama3.1
model_name: Llama-3.1-Nemotron-70B-Reward-HF
base_model: nvidia/Llama-3.1-Nemotron-70B-Reward-HF
inference: false
pipeline_tag: text-generation
library_name: transformers
model_creator: nvidia
quantized_by: Second State Inc.
tags:
  - nvidia
  - llama3.1
  - reward model

---

Llama-3.1-Nemotron-70B-Reward-HF-GGUF

Original Model

nvidia/Llama-3.1-Nemotron-70B-Reward-HF

Run with LlamaEdge

• LlamaEdge version: coming soon

• 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:Llama-3.1-Nemotron-70B-Reward-HF-Q5_K_M.gguf \
    llama-api-server.wasm \
    --prompt-template llama-3-chat \
    --ctx-size 128000 \
    --model-name Llama-3.1-Nemotron-70b
  

• Run as LlamaEdge command app

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

Quantized with llama.cpp 3932.