FreedomIntelligence/HuatuoGPT-o1-8B
Full fine-tune vs meta-llama/Llama-3.1-8B-Instruct. Fine-tune: 93% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 14/65, MLP 96/96, Attention 128/128, lm_head 1/1
8 derivatives checked
- mradermacher/HuatuoGPT-o1-8B-i1-GGUF: Quantization
- bartowski/HuatuoGPT-o1-8B-GGUF: Same weights, converted
- mradermacher/HuatuoGPT-o1-8B-GGUF: Same weights, converted
- DevQuasar-6/FreedomIntelligence.HuatuoGPT-o1-8B-GGUF: Same weights, converted
- grimjim/HuatuoSkywork-o1-Llama-3.1-8B: Full fine-tune
- T145/ZEUS-8B-V27: Full fine-tune
- T145/ZEUS-8B-V23: Full fine-tune
- T145/ZEUS-8B-V26: Full fine-tune