SteelStorage/L3.3-MS-Evayale-70B
Partial fine-tune vs EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0. Partial change: 50% of the weights changed (attention, lm_head, mlp), in 77 of 80 layers.
Tensors changed: Embeddings 0/1, Norms 0/161, MLP 120/240, Attention 160/320, lm_head 1/1
3 derivatives checked
- bartowski/L3.3-MS-Evayale-70B-GGUF: Quantization
- mradermacher/L3.3-MS-Evayale-70B-i1-GGUF: Quantization
- mradermacher/L3.3-MS-Evayale-70B-GGUF: Quantization