Nitral-Archive/Hathor_UMF-v0.420-L3-8B

Full fine-tune vs ChaoticNeutrals/Hathor_Aleph-L3-8B-v0.72. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 60/65, MLP 93/96, Attention 124/128

2 derivatives checked

• mradermacher/Hathor_Ultra-Mix-Final-0.420-L3-8B-i1-GGUF: Quantization
• mradermacher/Hathor_Ultra-Mix-Final-0.420-L3-8B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse