open-thoughts/OpenThinker2-32B
Full fine-tune vs Qwen/Qwen2.5-32B-Instruct. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 1/1, Norms 129/129, MLP 192/192, Attention 448/448, lm_head 1/1
6 derivatives checked
- bartowski/open-thoughts_OpenThinker2-32B-GGUF: Same weights, converted
- mradermacher/OpenThinker2-32B-i1-GGUF: Quantization
- mradermacher/OpenThinker2-32B-GGUF: Quantization
- DevQuasar-12/open-thoughts.OpenThinker2-32B-GGUF: Same weights, converted
- lmstudio-community/OpenThinker2-32B-GGUF: Quantization
- nicoboss/OpenThinker2-32B-Uncensored: LoRA-style