saishf/Extended-Mega-Mash-262K-8B-L3

Full fine-tune vs saishf/Long-Neural-SOVLish-Devil-8B-L3-262K. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

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

2 derivatives checked

• mradermacher/Extended-Mega-Mash-262K-8B-L3-i1-GGUF: Quantization
• mradermacher/Extended-Mega-Mash-262K-8B-L3-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse