Krystalan/DRT-14B
Full fine-tune vs Qwen/Qwen2.5-14B-Instruct. Fine-tune: 95% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 0/1, Norms 95/97, MLP 144/144, Attention 336/336, lm_head 1/1
11 derivatives checked
- bartowski/DRT-o1-14B-GGUF: Same weights, converted
- mradermacher/DRT-14B-i1-GGUF: Quantization
- mradermacher/DRT-o1-14B-i1-GGUF: Quantization
- mradermacher/DRT-o1-14B-GGUF: Quantization
- mradermacher/DRT-14B-GGUF: Quantization
- sometimesanotion/Lamarck-14B-v0.6: Full fine-tune
- djuna/TEST2-Q2.5-Lenned-14B: Full fine-tune
- djuna/TEST3-Q2.5-Lenned-14B: Full fine-tune
- RDson/WomboCombo-R1-14B-Preview: Full fine-tune
- RDson/CoderO1-14B-Preview: Full fine-tune
- RDson/CoderO1-14B-Preview-v2: Full fine-tune