tepirale/Ornith-Agents-A1-3.7-35B-A3B-dare_ties_v4
Full fine-tune (fewer layers) vs InternScience/Agents-A1. tepirale/Ornith-Agents-A1-3.7-35B-A3B-dare_ties_v4 matches part of InternScience/Agents-A1 (946 of its 31666 tensors; the rest of InternScience/Agents-A1 has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 4/4, lm_head 1/1, Norms 238/241, Attention 371/388, MLP 309/312
2 derivatives checked
- tepirale/Ornith-Agents-A1-3.7-35B-A3B-dare_ties_v4-MTP-GGUF: Same weights, converted
- felkf/Ornith-Agents-A1-3.7-35B-A3B-dare_ties_v4-oQ6-fp16: Quantization