Krystalan/DRT-7B
Full fine-tune vs Qwen/Qwen2.5-7B-Instruct. Fine-tune: 93% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 0/1, Norms 55/57, MLP 84/84, Attention 196/196, lm_head 1/1
7 derivatives checked
- bartowski/DRT-o1-7B-GGUF: Same weights, converted
- mradermacher/DRT-7B-i1-GGUF: Quantization
- mradermacher/DRT-o1-7B-i1-GGUF: Quantization
- mradermacher/DRT-7B-GGUF: Same weights, converted
- mradermacher/DRT-o1-7B-GGUF: Same weights, converted
- tensorblock/DRT-o1-7B-GGUF: Quantization
- bunnycore/Blabbertron-1.2: Full fine-tune