CombinHorizon/YiSM-blossom5.1-34B-SLERP

Full fine-tune vs Azure99/blossom-v5.1-34b. Fine-tune: 98% of the weights changed, across 60 of 60 layers.

Tensors changed: Embeddings 1/1, Norms 121/121, MLP 177/180, Attention 236/240, lm_head 1/1

2 derivatives checked

• mradermacher/YiSM-blossom5.1-34B-SLERP-GGUF: Quantization
• mradermacher/YiSM-blossom5.1-34B-SLERP-i1-GGUF: Quantization

On the Hub · Downloads on Model Pulse