bespokelabs/Bespoke-Stratos-32B
Full fine-tune vs Qwen/Qwen2.5-32B-Instruct. Fine-tune: 98% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 0/1, Norms 125/129, MLP 192/192, Attention 448/448, lm_head 1/1
5 derivatives checked
- mradermacher/Bespoke-Stratos-32B-i1-GGUF: Quantization
- mradermacher/Bespoke-Stratos-32B-GGUF: Quantization
- second-state/Bespoke-Stratos-32B-GGUF: Same weights, converted
- tensorblock/Bespoke-Stratos-32B-GGUF: Quantization
- gaianet/Bespoke-Stratos-32B-GGUF: Same weights, converted