BarraHome/Mistroll-7B-v2.2
Same weights, converted vs yam-peleg/Experiment26-7B. Same weights stored in another dtype (F16 → BF16).
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/128, lm_head 0/1
8 derivatives checked
- mradermacher/Mistroll-7B-v2.2-i1-GGUF: Quantization
- mgonzs13/Mistroll-7B-v2.2-GGUF: Quantization
- mradermacher/Mistroll-7B-v2.2-GGUF: Same weights, converted
- featherless-ai-quants/BarraHome-Mistroll-7B-v2.2-GGUF: Quantization
- ClaudioItaly/Evolutionstory-7B-v2.2: Full fine-tune
- lesserfield/fiona-7B-v0.2: LoRA-style
- Spectre5390/Sidstroll-7B-v1: Full fine-tune
- yweslakarep/huh-1: Full fine-tune