Yuma42/KangalKhan-RawEmerald-7B

Full fine-tune vs argilla/CapybaraHermes-2.5-Mistral-7B. Fine-tune: 96% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 1/65, MLP 96/96, Attention 128/128, lm_head 0/1

2 derivatives checked

• mradermacher/KangalKhan-RawEmerald-7B-GGUF: Same weights, converted
• Yuma42/KangalKhan-RawRuby-7B: LoRA-style

On the Hub · Downloads on Model Pulse