mergesloppa123123/Hermyale-stack-90B

Partial fine-tune vs NousResearch/Hermes-3-Llama-3.1-70B. Partial change: 72% of the weights changed (attention, mlp, norms), in 59 of 80 layers.

Tensors changed: Embeddings 0/1, Norms 118/161, MLP 177/240, Attention 236/320, lm_head 0/1

2 derivatives checked

• mradermacher/Hermyale-stack-90B-i1-GGUF: Quantization
• mradermacher/Hermyale-stack-90B-GGUF: Quantization

On the Hub · Downloads on Model Pulse