maldv/Qwentile2.5-32B-Instruct
Full fine-tune vs AiCloser/Qwen2.5-32B-AGI. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 1/1, Norms 127/129, MLP 192/192, Attention 448/448, lm_head 1/1
4 derivatives checked
- bartowski/Qwentile2.5-32B-Instruct-GGUF: Same weights, converted
- mradermacher/Qwentile2.5-32B-Instruct-i1-GGUF: Quantization
- featherless-ai-quants/maldv-Qwentile2.5-32B-Instruct-GGUF: Quantization
- mradermacher/Qwentile2.5-32B-Instruct-GGUF: Quantization