ryanmarten/OpenThinker-32B-Unverified

Full fine-tune vs Qwen/Qwen2.5-32B-Instruct. Fine-tune: 98% of the weights changed, across 64 of 64 layers.

Tensors changed: Embeddings 0/1, Norms 127/129, MLP 192/192, Attention 448/448, lm_head 1/1

3 derivatives checked

• mradermacher/OpenThinker-32B-Unverified-i1-GGUF: Quantization
• DevQuasar-8/open-thoughts.OpenThinker-32B-Unverified-GGUF: Same weights, converted
• mradermacher/OpenThinker-32B-Unverified-GGUF: Quantization

On the Hub · Downloads on Model Pulse