cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition, UQFF quantization

Run with mistral.rs. Documentation: UQFF docs.

  1. Flexible πŸŒ€: Multiple quantization formats in one file format with one framework to run them all.
  2. Reliable πŸ”’: Compatibility ensured with embedded and checked semantic versioning information from day 1.
  3. Easy πŸ€—: Download UQFF models easily and quickly from Hugging Face, or use a local file.
  4. Customizable πŸ› : Make and publish your own UQFF files in minutes.

Examples

Quantization type(s) Example
Q4_0 ./mistralrs-server -i plain -m sonicrules1234/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-UQFF --from-uqff "Dolphin-Mistral-24B-Venice-Edition-Q4_0-0.uqff;Dolphin-Mistral-24B-Venice-Edition-Q4_0-1.uqff;Dolphin-Mistral-24B-Venice-Edition-Q4_0-2.uqff"
Q4_1 ./mistralrs-server -i plain -m sonicrules1234/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-UQFF --from-uqff "Dolphin-Mistral-24B-Venice-Edition-Q4_1-0.uqff;Dolphin-Mistral-24B-Venice-Edition-Q4_1-1.uqff;Dolphin-Mistral-24B-Venice-Edition-Q4_1-2.uqff"
Q5_0 ./mistralrs-server -i plain -m sonicrules1234/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-UQFF --from-uqff "Dolphin-Mistral-24B-Venice-Edition-Q5_0-0.uqff;Dolphin-Mistral-24B-Venice-Edition-Q5_0-1.uqff;Dolphin-Mistral-24B-Venice-Edition-Q5_0-2.uqff"
Q5_1 ./mistralrs-server -i plain -m sonicrules1234/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-UQFF --from-uqff "Dolphin-Mistral-24B-Venice-Edition-Q5_1-0.uqff;Dolphin-Mistral-24B-Venice-Edition-Q5_1-1.uqff;Dolphin-Mistral-24B-Venice-Edition-Q5_1-2.uqff"
Q8_0 ./mistralrs-server -i plain -m sonicrules1234/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-UQFF --from-uqff "Dolphin-Mistral-24B-Venice-Edition-Q8_0-0.uqff;Dolphin-Mistral-24B-Venice-Edition-Q8_0-1.uqff;Dolphin-Mistral-24B-Venice-Edition-Q8_0-2.uqff;Dolphin-Mistral-24B-Venice-Edition-Q8_0-3.uqff"
Q2K ./mistralrs-server -i plain -m sonicrules1234/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-UQFF --from-uqff Dolphin-Mistral-24B-Venice-Edition-q2k.uqff
Q3K ./mistralrs-server -i plain -m sonicrules1234/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-UQFF --from-uqff Dolphin-Mistral-24B-Venice-Edition-q3k.uqff
Q4K ./mistralrs-server -i plain -m sonicrules1234/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-UQFF --from-uqff "Dolphin-Mistral-24B-Venice-Edition-q4k-0.uqff;Dolphin-Mistral-24B-Venice-Edition-q4k-1.uqff;Dolphin-Mistral-24B-Venice-Edition-q4k-2.uqff"
Q5K ./mistralrs-server -i plain -m sonicrules1234/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-UQFF --from-uqff "Dolphin-Mistral-24B-Venice-Edition-q5k-0.uqff;Dolphin-Mistral-24B-Venice-Edition-q5k-1.uqff;Dolphin-Mistral-24B-Venice-Edition-q5k-2.uqff"
Q6K ./mistralrs-server -i plain -m sonicrules1234/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-UQFF --from-uqff "Dolphin-Mistral-24B-Venice-Edition-q6k-0.uqff;Dolphin-Mistral-24B-Venice-Edition-q6k-1.uqff;Dolphin-Mistral-24B-Venice-Edition-q6k-2.uqff"
HQQ4 ./mistralrs-server -i plain -m sonicrules1234/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-UQFF --from-uqff "Dolphin-Mistral-24B-Venice-Edition-HQQ4-0.uqff;Dolphin-Mistral-24B-Venice-Edition-HQQ4-1.uqff;Dolphin-Mistral-24B-Venice-Edition-HQQ4-2.uqff"
HQQ8 ./mistralrs-server -i plain -m sonicrules1234/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-UQFF --from-uqff "Dolphin-Mistral-24B-Venice-Edition-HQQ8-0.uqff;Dolphin-Mistral-24B-Venice-Edition-HQQ8-1.uqff;Dolphin-Mistral-24B-Venice-Edition-HQQ8-2.uqff;Dolphin-Mistral-24B-Venice-Edition-HQQ8-3.uqff"
FP8 ./mistralrs-server -i plain -m sonicrules1234/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-UQFF --from-uqff "Dolphin-Mistral-24B-Venice-Edition-FP8-0.uqff;Dolphin-Mistral-24B-Venice-Edition-FP8-1.uqff;Dolphin-Mistral-24B-Venice-Edition-FP8-2.uqff;Dolphin-Mistral-24B-Venice-Edition-FP8-3.uqff"
Downloads last month
11
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for sonicrules1234/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-UQFF