Chen-01AI's picture
Update README.md with license information
fe0f0a6 verified
|
raw
history blame
4.32 kB
metadata
base_model: OrionStarAI/OrionStar-Yi-34B-Chat-Llama
inference: false
model_creator: OrionStarAI
model_name: OrionStar Yi 34B Chat Llama
model_type: yi
pipeline_tag: text-generation
quantized_by: Second State Inc.
license: apache-2.0

OrionStar-Yi-34B-Chat-Llama-GGUF

Original Model

OrionStarAI/OrionStar-Yi-34B-Chat-Llama

Run with LlamaEdge

  • LlamaEdge version: v0.2.9 and above

  • Prompt template

    • Prompt type: human-assistant

    • Prompt string

      Human: {input_1}\n\nAssistant:{output_1}Human: {input_2}\n\nAssistant:
      
  • Context size: 7168

  • Run as LlamaEdge service

    wasmedge --dir .:. --nn-preload default:GGML:AUTO:OrionStar-Yi-34B-Chat-Llama-Q5_K_M.gguf llama-api-server.wasm -p human-assistant
    
  • Run as LlamaEdge command app

    wasmedge --dir .:. --nn-preload default:GGML:AUTO:OrionStar-Yi-34B-Chat-Llama-Q5_K_M.gguf llama-chat.wasm -p human-assistant
    

Quantized GGUF Models

Name Quant method Bits Size Use case
OrionStar-Yi-34B-Chat-Llama-Q2_K.gguf Q2_K 2 12.8 GB smallest, significant quality loss - not recommended for most purposes
OrionStar-Yi-34B-Chat-Llama-Q3_K_L.gguf Q3_K_L 3 18.1 GB small, substantial quality loss
OrionStar-Yi-34B-Chat-Llama-Q3_K_M.gguf Q3_K_M 3 16.7 GB very small, high quality loss
OrionStar-Yi-34B-Chat-Llama-Q3_K_S.gguf Q3_K_S 3 15.0 GB very small, high quality loss
OrionStar-Yi-34B-Chat-Llama-Q4_0.gguf Q4_0 4 19.5 GB legacy; small, very high quality loss - prefer using Q3_K_M
OrionStar-Yi-34B-Chat-Llama-Q4_K_M.gguf Q4_K_M 4 20.7 GB medium, balanced quality - recommended
OrionStar-Yi-34B-Chat-Llama-Q4_K_S.gguf Q4_K_S 4 19.6 GB small, greater quality loss
OrionStar-Yi-34B-Chat-Llama-Q5_0.gguf Q5_0 5 23.7 GB legacy; medium, balanced quality - prefer using Q4_K_M
OrionStar-Yi-34B-Chat-Llama-Q5_K_M.gguf Q5_K_M 5 24.3 GB large, very low quality loss - recommended
OrionStar-Yi-34B-Chat-Llama-Q5_K_S.gguf Q5_K_S 5 23.7 GB large, low quality loss - recommended
OrionStar-Yi-34B-Chat-Llama-Q6_K.gguf Q6_K 6 28.2 GB very large, extremely low quality loss
OrionStar-Yi-34B-Chat-Llama-Q8_0.gguf Q8_0 8 36.5 GB very large, extremely low quality loss - not recommended