dphn/dolphin-2.8-mistral-7b-v02
Full fine-tune vs mistral-community/Mistral-7B-v0.2. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 14/65, MLP 96/96, Attention 128/128
10 derivatives checked
- QuantFactory/dolphin-2.8-mistral-7b-v02-GGUF: Quantization
- mradermacher/dolphin-2.8-mistral-7b-v02-i1-GGUF: Quantization
- nasiruddin15/Mistral-dolphin-2.8-grok-instract-2-7B-slerp: Full fine-tune
- mradermacher/dolphin-2.8-mistral-7b-v02-GGUF: Same weights, converted
- Samzzzed/dolphin-mistral-7b: Quantization
- ichigoberry/pandafish-2-7b-32k: Full fine-tune
- saucam/Nereus-7B: Full fine-tune
- WesPro/OpenDolphin-7B-slerp: Full fine-tune
- Fizzarolli/LayliticDolphinOpus: Full fine-tune
- vtboyarc/Adamus-7B-slerp: Full fine-tune