SteelStorage/L3.1-MS-Hytroblated-70B

Full fine-tune vs abacusai/Dracarys2-Llama-3.1-70B-Instruct. Fine-tune: 99% of the weights changed, across 80 of 80 layers.

Tensors changed: Embeddings 0/1, Norms 61/161, MLP 240/240, Attention 320/320, lm_head 1/1

2 derivatives checked

• mradermacher/L3.1-MS-Hytroblated-70B-i1-GGUF: Quantization
• mradermacher/L3.1-MS-Hytroblated-70B-GGUF: Quantization

On the Hub · Downloads on Model Pulse