FreedomIntelligence/ShizhenGPT-32B-VL
Full fine-tune (fewer layers) vs Qwen/Qwen2.5-32B. Qwen/Qwen2.5-32B matches part of FreedomIntelligence/ShizhenGPT-32B-VL (771 of its 1161 tensors; the rest of FreedomIntelligence/ShizhenGPT-32B-VL has no counterpart). On the shared part: 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
2 derivatives checked
- mradermacher/ShizhenGPT-32B-VL-i1-GGUF: Quantization (fewer layers)
- mradermacher/ShizhenGPT-32B-VL-GGUF: Quantization (fewer layers)
1 other repos hold byte-for-byte identical weight files.