open-thoughts/OpenThinker3-7B
Full fine-tune vs Qwen/Qwen2.5-7B-Instruct. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 196/196, lm_head 1/1
4 derivatives checked
- bartowski/open-thoughts_OpenThinker3-7B-GGUF: Same weights, converted
- DevQuasar/open-thoughts.OpenThinker3-7B-GGUF: Same weights, converted
- lmstudio-community/OpenThinker3-7B-GGUF: Quantization
- prithivMLmods/OpenThinker3-7B-F32-GGUF: LoRA-style
5 other repos hold byte-for-byte identical weight files.