Dampfinchen/Ultra-Instruct-12B
Full fine-tune vs IntervitensInc/Mistral-Nemo-Base-2407-chatml. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 42/81, MLP 120/120, Attention 160/160, lm_head 1/1
5 derivatives checked
- mradermacher/Ultra-Instruct-12B-i1-GGUF: Quantization
- bartowski/Ultra-Instruct-12B-GGUF: Same weights, converted
- mradermacher/Ultra-Instruct-12B-GGUF: Quantization
- pot99rta/Ultracore-Instruct-12B: Full fine-tune
- pot99rta/Ultracore-Instruct-12BV2: Full fine-tune