tencent/Hunyuan-0.5B-Instruct
Full fine-tune vs tencent/Hunyuan-0.5B-Pretrain. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Embeddings 1/1, Norms 97/97, MLP 72/72, Attention 96/96
8 derivatives checked
- bartowski/tencent_Hunyuan-0.5B-Instruct-GGUF: Same weights, converted
- mradermacher/Hunyuan-0.5B-Instruct-i1-GGUF: Quantization
- gabriellarson/Hunyuan-0.5B-Instruct-GGUF: Same weights, converted
- DevQuasar/tencent.Hunyuan-0.5B-Instruct-GGUF: Same weights, converted
- Fu01978/Hunyuan-0.5B-Instruct-GGUF: Same weights, converted
- mradermacher/Hunyuan-0.5B-Instruct-GGUF: Same weights, converted
- 11-47/Hunyuan-Python.GOD-0.5B-GGUF: Full fine-tune
- 11-47/Hunyuan-PythonGOD-0.5B: Full fine-tune