eaddario/Dolphin-Mistral-24B-Venice-Edition-pruned-GGUF
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
20 Commits 1 Branch 0 Tags
664228d4d71a1fec845aeaa4f2089eb1f6bd75f0
Go to file
Clone
Open with VS Code Open with VSCodium Open with Intellij IDEA
Download ZIP Download TAR.GZ Download BUNDLE
Ed Addario 664228d4d7 Generate Perplexity, KLD, ARC, HellaSwag, MMLU, Truthful QA and WinoGrande scores
2025-07-01 08:18:25 +01:00
imatrix
Generate imatrices
2025-06-30 19:02:50 +01:00
logits
Generate base model logits
2025-06-30 18:39:19 +01:00
scores
Generate Perplexity, KLD, ARC, HellaSwag, MMLU, Truthful QA and WinoGrande scores
2025-07-01 08:18:25 +01:00
.gitattributes
Update .gitattributes
2025-06-30 07:30:20 +01:00
.gitignore
Add .gitignore
2025-06-30 07:30:39 +01:00
Dolphin-Mistral-24B-Venice-Edition-F16.gguf
Convert safetensor to GGUF @ F16
2025-06-30 18:13:05 +01:00
Dolphin-Mistral-24B-Venice-Edition-pruned-IQ3_M.gguf
Layer-wise & pruned quantization IQ3_M
2025-07-01 07:38:42 +01:00
Dolphin-Mistral-24B-Venice-Edition-pruned-IQ3_S.gguf
Layer-wise & pruned quantization IQ3_S
2025-07-01 07:31:37 +01:00
Dolphin-Mistral-24B-Venice-Edition-pruned-IQ4_NL.gguf
Layer-wise & pruned quantization IQ4_NL
2025-07-01 06:53:26 +01:00
Dolphin-Mistral-24B-Venice-Edition-pruned-Q3_K_L.gguf
Layer-wise & pruned quantization Q3_K_L
2025-07-01 06:35:54 +01:00
Dolphin-Mistral-24B-Venice-Edition-pruned-Q3_K_M.gguf
Layer-wise & pruned quantization Q3_K_M
2025-06-30 23:02:04 +01:00
Dolphin-Mistral-24B-Venice-Edition-pruned-Q3_K_S.gguf
Layer-wise & pruned quantization Q3_K_S
2025-06-30 22:54:54 +01:00
Dolphin-Mistral-24B-Venice-Edition-pruned-Q4_K_M.gguf
Layer-wise & pruned quantization Q4_K_M
2025-06-30 22:38:06 +01:00
Dolphin-Mistral-24B-Venice-Edition-pruned-Q4_K_S.gguf
Layer-wise & pruned quantization Q4_K_S
2025-06-30 22:05:55 +01:00
Dolphin-Mistral-24B-Venice-Edition-pruned-Q5_K_M.gguf
Layer-wise & pruned quantization Q5_K_M
2025-06-30 21:53:26 +01:00
Dolphin-Mistral-24B-Venice-Edition-pruned-Q5_K_S.gguf
Layer-wise & pruned quantization Q5_K_S
2025-06-30 20:34:15 +01:00
Dolphin-Mistral-24B-Venice-Edition-pruned-Q6_K.gguf
Layer-wise & pruned quantization Q6_K
2025-06-30 19:26:23 +01:00
Dolphin-Mistral-24B-Venice-Edition-pruned-Q8_0.gguf
Layer-wise & pruned quantization Q8_0
2025-06-30 19:03:53 +01:00
README.md
Update README.md
2025-06-30 07:31:19 +01:00

README.md

base_model, datasets, language, license, pipeline_tag, tags
base_model datasets language license pipeline_tag tags
cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition
eaddario/imatrix-calibration
en
apache-2.0
text-generation
gguf
quant
pruned
experimental

Experimental layer-wise + pruned (layers 4 and 5) quantization of cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition

Upload in progress...

Full model card will be available once all files have been uploaded

Description
Model synced from source: eaddario/Dolphin-Mistral-24B-Venice-Edition-pruned-GGUF
Readme 258 KiB
Languages
Arc 100%