rinna/qwen2.5-bakeneko-32b-instruct
Full fine-tune vs Qwen/Qwen2.5-32B. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 1/1, Norms 128/129, MLP 192/192, Attention 448/448, lm_head 1/1
6 derivatives checked
- mradermacher/qwen2.5-bakeneko-32b-instruct-i1-GGUF: Quantization
- mmnga/qwen2.5-bakeneko-32b-instruct-gguf: Quantization
- rinna/qwen2.5-bakeneko-32b-instruct-gguf: Quantization
- featherless-ai-quants/rinna-qwen2.5-bakeneko-32b-instruct-GGUF: Quantization
- mradermacher/qwen2.5-bakeneko-32b-instruct-GGUF: Quantization
- tensorblock/qwen2.5-bakeneko-32b-instruct-GGUF: Quantization