olaverse/MIST-1-70B
Full fine-tune vs NousResearch/Hermes-3-Llama-3.1-70B. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 1/1, Norms 161/161, MLP 240/240, Attention 320/320, lm_head 1/1
3 derivatives checked
- mradermacher/MIST-1-70B-i1-GGUF: Quantization
- mradermacher/MIST-1-70B-GGUF: Quantization
- olaverse/MIST-1-140B: Partial fine-tune (fewer layers)