microsoft/UserLM-8b
Full fine-tune vs meta-llama/Llama-3.1-8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 65/65, MLP 96/96, Attention 128/128
5 derivatives checked
- bartowski/microsoft_UserLM-8b-GGUF: Same weights, converted
- mradermacher/UserLM-8b-i1-GGUF: Quantization
- mradermacher/UserLM-8b-GGUF: Same weights, converted
- DevQuasar/microsoft.UserLM-8b-GGUF: Same weights, converted
- liodon-ai/UserLM-8b-imatrix-GGUF: Quantization