MergeFuel/Mistral-11B-v0.2
Partial fine-tune (fewer layers) vs mistral-community/Mistral-7B-v0.2. mistral-community/Mistral-7B-v0.2 matches part of MergeFuel/Mistral-11B-v0.2 (291 of its 435 tensors; the rest of MergeFuel/Mistral-11B-v0.2 has no counterpart). On the shared part: Partial change: 24% of the weights changed (attention, mlp, norms), in 8 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 16/65, MLP 24/96, Attention 32/128, lm_head 0/1
1 derivatives checked
- mradermacher/Mistral-11B-v0.2-GGUF: Same weights, converted