deep-analysis-research/D2IL-Japanese-Qwen2.5-32B-Instruct-v0.1

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

2 derivatives checked

• mradermacher/D2IL-Japanese-Qwen2.5-32B-Instruct-v0.1-i1-GGUF: Quantization
• mradermacher/D2IL-Japanese-Qwen2.5-32B-Instruct-v0.1-GGUF: Quantization

On the Hub · Downloads on Model Pulse