SteelStorage/L3.1-MS-Astoria-70b-v2
Full fine-tune vs ArliAI/Llama-3.1-70B-ArliAI-RPMax-v1.2. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 1/1, Norms 161/161, MLP 240/240, Attention 320/320, lm_head 1/1
5 derivatives checked
- bartowski/L3.1-MS-Astoria-70b-v2-GGUF: Quantization
- mradermacher/L3.1-MS-Astoria-70b-v2-i1-GGUF: Quantization
- featherless-ai-quants/Steelskull-L3.1-MS-Astoria-70b-v2-GGUF: Quantization
- featherless-ai-quants/SteelStorage-L3.1-MS-Astoria-70b-v2-GGUF: Quantization
- mradermacher/L3.1-MS-Astoria-70b-v2-GGUF: Quantization