FreedomIntelligence/HuatuoGPT-o1-72B

Full fine-tune vs Qwen/Qwen2.5-72B-Instruct. Fine-tune: 98% of the weights changed, across 80 of 80 layers.

Tensors changed: Embeddings 0/1, Norms 122/161, MLP 240/240, Attention 560/560, lm_head 1/1

4 derivatives checked

• bartowski/HuatuoGPT-o1-72B-v0.1-GGUF: Quantization
• bartowski/HuatuoGPT-o1-72B-GGUF: Full fine-tune
• DevQuasar-6/FreedomIntelligence.HuatuoGPT-o1-72B-GGUF: Full fine-tune
• tensorblock/HuatuoGPT-o1-72B-GGUF: Full fine-tune

On the Hub · Downloads on Model Pulse