open-thoughts/OpenThinker-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 54/57, MLP 84/84, Attention 196/196, lm_head 1/1
6 derivatives checked
- DGurgurov/OpenThinker3-7B-SFT-GRPO-DE: Full fine-tune
- bartowski/OpenThinker-7B-GGUF: Same weights, converted
- mradermacher/OpenThinker-7B-i1-GGUF: Quantization
- DevQuasar-8/open-thoughts.OpenThinker-7B-GGUF: Same weights, converted
- mradermacher/OpenThinker-7B-GGUF: Same weights, converted
- nkpz/OpenThinker-7B-Uncensored-DeLMAT: LoRA-style
7 other repos hold byte-for-byte identical weight files.