win10/Qwen2.5-Coder-12.3b-Instruct
Partial fine-tune (fewer layers) vs Qwen/Qwen2.5-Coder-7B-Instruct. Qwen/Qwen2.5-Coder-7B-Instruct matches part of win10/Qwen2.5-Coder-12.3b-Instruct (339 of its 579 tensors; the rest of win10/Qwen2.5-Coder-12.3b-Instruct has no counterpart). On the shared part: Partial change: 61% of the weights changed (attention, mlp, norms), in 20 of 28 layers.
Tensors changed: Embeddings 0/1, Norms 40/57, MLP 60/84, Attention 140/196, lm_head 0/1
2 derivatives checked
- mradermacher/Qwen2.5-Coder-12.3b-Instruct-i1-GGUF: Quantization
- mradermacher/Qwen2.5-Coder-12.3b-Instruct-GGUF: Quantization