tanliboy/lambda-qwen2.5-32b-dpo-test
Full fine-tune vs Qwen/Qwen2.5-32B-Instruct. Fine-tune: 98% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 0/1, Norms 123/129, MLP 192/192, Attention 447/448, lm_head 1/1
2 derivatives checked
- mradermacher/lambda-qwen2.5-32b-dpo-test-i1-GGUF: Quantization
- mradermacher/lambda-qwen2.5-32b-dpo-test-GGUF: Quantization