abeja/ABEJA-Qwen2.5-32b-Japanese-v0.1
Full fine-tune vs Qwen/Qwen2.5-32B-Instruct. 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
6 derivatives checked
- mmnga/ABEJA-Qwen2.5-32b-Japanese-v0.1-gguf: Quantization
- mradermacher/ABEJA-Qwen2.5-32b-Japanese-v0.1-i1-GGUF: Quantization
- mradermacher/ABEJA-Qwen2.5-32b-Japanese-v0.1-GGUF: Quantization
- smorce/ABEJA-Qwen2.5-32b-Japanese-v0.1-AWQ: Quantization
- nitky/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-Japanese-ABEJA-32B-Preview: Full fine-tune
- TeamDelta/ABEJA-Qwen2.5-32B-base-jp-v0.1: Full fine-tune