Text Generation
Transformers
GGUF
English
mixtral
text-generation-inference
apepkuss79's picture
Update README.md
7a4b09f verified
metadata
base_model: cognitivecomputations/dolphin-2.7-mixtral-8x7b
datasets:
  - ehartford/dolphin
  - jondurbin/airoboros-2.2.1
  - ehartford/dolphin-coder
  - teknium/openhermes
  - ise-uiuc/Magicoder-OSS-Instruct-75K
  - ise-uiuc/Magicoder-Evol-Instruct-110K
  - LDJnr/Capybara
inference: false
language:
  - en
license: apache-2.0
model_creator: Cognitive Computations
model_name: Dolphin 2.7 Mixtral 8X7B
model_type: mixtral
quantized_by: Second State Inc.

Dolphin-2.7-mixtral-8x7b-GGUF

Original Model

cognitivecomputations/dolphin-2.7-mixtral-8x7b

Run with LlamaEdge

  • LlamaEdge version: v0.2.8 and above

  • Prompt template

    • Prompt type: chatml

    • Prompt string

      <|im_start|>system
      {system_message}<|im_end|>
      <|im_start|>user
      {prompt}<|im_end|>
      <|im_start|>assistant
      
  • Context size: 4096

  • Run as LlamaEdge service

    wasmedge --dir .:. --nn-preload default:GGML:AUTO:dolphin-2.7-mixtral-8x7b-Q5_K_M.gguf llama-api-server.wasm -p chatml
    
  • Run as LlamaEdge command app

    wasmedge --dir .:. --nn-preload default:GGML:AUTO:dolphin-2.7-mixtral-8x7b-Q5_K_M.gguf llama-chat.wasm -p chatml
    

Quantized GGUF Models

Name Quant method Bits Size Use case
dolphin-2.7-mixtral-8x7b-Q2_K.gguf Q2_K 2 15.6 GB smallest, significant quality loss - not recommended for most purposes
dolphin-2.7-mixtral-8x7b-Q3_K_L.gguf Q3_K_L 3 20.4 GB small, substantial quality loss
dolphin-2.7-mixtral-8x7b-Q3_K_M.gguf Q3_K_M 3 20.4 GB very small, high quality loss
dolphin-2.7-mixtral-8x7b-Q3_K_S.gguf Q3_K_S 3 20.3 GB very small, high quality loss
dolphin-2.7-mixtral-8x7b-Q4_0.gguf Q4_0 4 26.4 GB legacy; small, very high quality loss - prefer using Q3_K_M
dolphin-2.7-mixtral-8x7b-Q4_K_M.gguf Q4_K_M 4 26.4 GB medium, balanced quality - recommended
dolphin-2.7-mixtral-8x7b-Q4_K_S.gguf Q4_K_S 4 26.4 GB small, greater quality loss
dolphin-2.7-mixtral-8x7b-Q5_0.gguf Q5_0 5 32.2 GB legacy; medium, balanced quality - prefer using Q4_K_M
dolphin-2.7-mixtral-8x7b-Q5_K_M.gguf Q5_K_M 5 32.2 GB large, very low quality loss - recommended
dolphin-2.7-mixtral-8x7b-Q5_K_S.gguf Q5_K_S 5 32.2 GB large, low quality loss - recommended
dolphin-2.7-mixtral-8x7b-Q6_K.gguf Q6_K 6 38.4 GB very large, extremely low quality loss
dolphin-2.7-mixtral-8x7b-Q8_0.gguf Q8_0 8 49.6 GB very large, extremely low quality loss - not recommended