apepkuss79's picture
Update README.md
58f7ae0 verified
metadata
base_model: Intel/neural-chat-7b-v3-3
inference: false
license: apache-2.0
model_creator: Intel
model_name: Neural Chat 7B V3-3
model_type: mistral
pipeline_tag: text-generation
quantized_by: Second State Inc.

Neural-Chat-7B-v3-3-GGUF

Original Model

Intel/neural-chat-7b-v3-3

Run with LlamaEdge

  • LlamaEdge version: v0.2.8 and above

  • Prompt template

    • Prompt type: intel-neural

    • Prompt string

      \### System:
      {system}
      \### User:
      {usr}
      \### Assistant:
      

      Note that the \ character is used to escape the ### in the prompt string. Remove it in the practical use.

  • Context size: 4096

  • Run as LlamaEdge service

    wasmedge --dir .:. --nn-preload default:GGML:AUTO:neural-chat-7b-v3-3-Q5_K_M.gguf llama-api-server.wasm -p intel-neural
    
  • Run as LlamaEdge command app

    wasmedge --dir .:. --nn-preload default:GGML:AUTO:neural-chat-7b-v3-3-Q5_K_M.gguf llama-chat.wasm -p intel-neural
    

Quantized GGUF Models

Name Quant method Bits Size Use case
neural-chat-7b-v3-3-Q2_K.gguf Q2_K 2 3.08 GB smallest, significant quality loss - not recommended for most purposes
neural-chat-7b-v3-3-Q3_K_L.gguf Q3_K_L 3 3.82 GB small, substantial quality loss
neural-chat-7b-v3-3-Q3_K_M.gguf Q3_K_M 3 3.52 GB very small, high quality loss
neural-chat-7b-v3-3-Q3_K_S.gguf Q3_K_S 3 3.16 GB very small, high quality loss
neural-chat-7b-v3-3-Q4_0.gguf Q4_0 4 4.11 GB legacy; small, very high quality loss - prefer using Q3_K_M
neural-chat-7b-v3-3-Q4_K_M.gguf Q4_K_M 4 4.37 GB medium, balanced quality - recommended
neural-chat-7b-v3-3-Q4_K_S.gguf Q4_K_S 4 4.14 GB small, greater quality loss
neural-chat-7b-v3-3-Q5_0.gguf Q5_0 5 5.00 GB legacy; medium, balanced quality - prefer using Q4_K_M
neural-chat-7b-v3-3-Q5_K_M.gguf Q5_K_M 5 5.13 GB large, very low quality loss - recommended
neural-chat-7b-v3-3-Q5_K_S.gguf Q5_K_S 5 5.00 GB large, low quality loss - recommended
neural-chat-7b-v3-3-Q6_K.gguf Q6_K 6 5.94 GB very large, extremely low quality loss
neural-chat-7b-v3-3-Q8_0.gguf Q8_0 8 7.70 GB very large, extremely low quality loss - not recommended