Hugging Face's logo

second-state
/
Mistral-Large-Instruct-2407-GGUF

Text Generation
Transformers
GGUF
mistral
Inference Endpoints
conversational
Model card Files Community
Mistral-Large-Instruct-2407-GGUF / README.md
apepkuss79's picture
apepkuss79
Update README.md
298a2b1 verified
preview code
|
raw
history blame contribute delete
13 kB
metadata
license: other
license_name: mrl
license_link: https://mistral.ai/licenses/MRL-0.1.md
model_name: Mistral-Large-Instruct-2407
base_model: mistralai/Mistral-Large-Instruct-2407
model_creator: mistralai
quantized_by: Second State Inc.
language:
  - en
  - fr
  - de
  - es
  - it
  - pt
  - zh
  - ja
  - ru
  - ko

Mistral-Large-Instruct-2407-GGUF

Original Model

mistralai/Mistral-Large-Instruct-2407

Run with LlamaEdge

  • LlamaEdge version: v0.13.0

  • Prompt template

    • Prompt type: mistral-instruct

    • Prompt string

      <s>[INST] {user_message_1} [/INST]{assistant_message_1}</s>[INST] {user_message_2} [/INST]{assistant_message_2}</s>

  • Context size: 128000

  • Run as LlamaEdge service

    wasmedge --dir .:. --nn-preload default:GGML:AUTO:Mistral-Large-Instruct-2407-Q5_K_M.gguf \
    llama-api-server.wasm \
    --prompt-template mistral-instruct \
    --ctx-size 128000 \
    --model-name Mistral-Large-Instruct-2407

  • Run as LlamaEdge command app

    wasmedge --dir .:. --nn-preload default:GGML:AUTO:Mistral-Large-Instruct-2407-Q5_K_M.gguf \
  llama-chat.wasm \
  --prompt-template mistral-instruct \
  --ctx-size 32000

Quantized GGUF Models

Name Quant method Bits Size Use case
Mistral-Large-Instruct-2407-Q2_K.gguf Q2_K 2 45.2 GB smallest, significant quality loss - not recommended for most purposes
Mistral-Large-Instruct-2407-Q3_K_L-00001-of-00003.gguf Q3_K_L 3 29.9 GB small, substantial quality loss
Mistral-Large-Instruct-2407-Q3_K_L-00002-of-00003.gguf Q3_K_L 3 29.9 GB small, substantial quality loss
Mistral-Large-Instruct-2407-Q3_K_L-00003-of-00003.gguf Q3_K_L 3 4.70 GB small, substantial quality loss
Mistral-Large-Instruct-2407-Q3_K_M-00001-of-00002.gguf Q3_K_M 3 29.9 GB very small, high quality loss
Mistral-Large-Instruct-2407-Q3_K_M-00002-of-00002.gguf Q3_K_M 3 29.2 GB very small, high quality loss
Mistral-Large-Instruct-2407-Q3_K_S-00001-of-00002.gguf Q3_K_S 3 29.9 GB very small, high quality loss
Mistral-Large-Instruct-2407-Q3_K_S-00002-of-00002.gguf Q3_K_S 3 29.2 GB very small, high quality loss
Mistral-Large-Instruct-2407-Q4_0-00001-of-00003.gguf Q4_0 4 30.0 GB legacy; small, very high quality loss - prefer using Q3_K_M
Mistral-Large-Instruct-2407-Q4_0-00002-of-00003.gguf Q4_0 4 30.0 GB legacy; small, very high quality loss - prefer using Q3_K_M
Mistral-Large-Instruct-2407-Q4_0-00003-of-00003.gguf Q4_0 4 9.09 GB legacy; small, very high quality loss - prefer using Q3_K_M
Mistral-Large-Instruct-2407-Q4_K_M-00001-of-00003.gguf Q4_K_M 4 30.0 GB medium, balanced quality - recommended
Mistral-Large-Instruct-2407-Q4_K_M-00002-of-00003.gguf Q4_K_M 4 29.9 GB medium, balanced quality - recommended
Mistral-Large-Instruct-2407-Q4_K_M-00003-of-00003.gguf Q4_K_M 4 13.3 GB medium, balanced quality - recommended
Mistral-Large-Instruct-2407-Q4_K_S-00001-of-00003.gguf Q4_K_S 4 29.9 GB small, greater quality loss
Mistral-Large-Instruct-2407-Q4_K_S-00002-of-00003.gguf Q4_K_S 4 30.0 GB small, greater quality loss
Mistral-Large-Instruct-2407-Q4_K_S-00003-of-00003.gguf Q4_K_S 4 9.67 GB small, greater quality loss
Mistral-Large-Instruct-2407-Q5_0-00001-of-00003.gguf Q5_0 5 30.0 GB legacy; medium, balanced quality - prefer using Q4_K_M
Mistral-Large-Instruct-2407-Q5_0-00002-of-00003.gguf Q5_0 5 30.0 GB legacy; medium, balanced quality - prefer using Q4_K_M
Mistral-Large-Instruct-2407-Q5_0-00003-of-00003.gguf Q5_0 5 24.4 GB legacy; medium, balanced quality - prefer using Q4_K_M
Mistral-Large-Instruct-2407-Q5_K_M-00001-of-00003.gguf Q5_K_M 5 29.9 GB large, very low quality loss - recommended
Mistral-Large-Instruct-2407-Q5_K_M-00002-of-00003.gguf Q5_K_M 5 29.7 GB large, very low quality loss - recommended
Mistral-Large-Instruct-2407-Q5_K_M-00003-of-00003.gguf Q5_K_M 5 26.8 GB large, very low quality loss - recommended
Mistral-Large-Instruct-2407-Q5_K_S-00001-of-00003.gguf Q5_K_S 5 30.0 GB large, low quality loss - recommended
Mistral-Large-Instruct-2407-Q5_K_S-00002-of-00003.gguf Q5_K_S 5 30.0 GB large, low quality loss - recommended
Mistral-Large-Instruct-2407-Q5_K_S-00003-of-00003.gguf Q5_K_S 5 24.4 GB large, low quality loss - recommended
Mistral-Large-Instruct-2407-Q6_K-00001-of-00004.gguf Q6_K 6 29.9 GB very large, extremely low quality loss
Mistral-Large-Instruct-2407-Q6_K-00002-of-00004.gguf Q6_K 6 29.8 GB very large, extremely low quality loss
Mistral-Large-Instruct-2407-Q6_K-00003-of-00004.gguf Q6_K 6 29.8 GB very large, extremely low quality loss
Mistral-Large-Instruct-2407-Q6_K-00004-of-00004.gguf Q6_K 6 11.1 GB very large, extremely low quality loss
Mistral-Large-Instruct-2407-Q8_0-00001-of-00005.gguf Q8_0 8 29.8 GB very large, extremely low quality loss - not recommended
Mistral-Large-Instruct-2407-Q8_0-00002-of-00005.gguf Q8_0 8 29.8 GB very large, extremely low quality loss - not recommended
Mistral-Large-Instruct-2407-Q8_0-00003-of-00005.gguf Q8_0 8 29.8 GB very large, extremely low quality loss - not recommended
Mistral-Large-Instruct-2407-Q8_0-00004-of-00005.gguf Q8_0 8 29.8 GB very large, extremely low quality loss - not recommended
Mistral-Large-Instruct-2407-Q8_0-00005-of-00005.gguf Q8_0 8 11.1 GB very large, extremely low quality loss - not recommended
Mistral-Large-Instruct-2407-f16-00001-of-00009.gguf f16 16 29.8 GB
Mistral-Large-Instruct-2407-f16-00002-of-00009.gguf f16 16 29.8 GB
Mistral-Large-Instruct-2407-f16-00003-of-00009.gguf f16 16 29.7 GB
Mistral-Large-Instruct-2407-f16-00004-of-00009.gguf f16 16 29.8 GB
Mistral-Large-Instruct-2407-f16-00005-of-00009.gguf f16 16 29.7 GB
Mistral-Large-Instruct-2407-f16-00006-of-00009.gguf f16 16 29.8 GB
Mistral-Large-Instruct-2407-f16-00007-of-00009.gguf f16 16 29.7 GB
Mistral-Large-Instruct-2407-f16-00008-of-00009.gguf f16 16 29.7 GB
Mistral-Large-Instruct-2407-f16-00009-of-00009.gguf f16 16 7.05 GB

Quantized with llama.cpp b3499.