arcee-ai/Arcee-Blitz
Full fine-tune vs mistralai/Mistral-Small-24B-Instruct-2501. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 18/81, MLP 120/120, Attention 160/160, lm_head 1/1
8 derivatives checked
- arcee-ai/Arcee-Blitz-GGUF: Quantization
- bartowski/arcee-ai_Arcee-Blitz-GGUF: Quantization
- mradermacher/Arcee-Blitz-i1-GGUF: Quantization
- mradermacher/Arcee-Blitz-GGUF: Quantization
- DevQuasar-8/arcee-ai.Arcee-Blitz-GGUF: Same weights, converted
- tensorblock/Arcee-Blitz-GGUF: Quantization
- mergekit-community/Mistral-Small-24B-Merge-V2: Full fine-tune
- trashpanda-org/MS-24B-Bline-v0: Full fine-tune