codelion/Qwen3-0.6B-ICM-DPO
LoRA-style vs unsloth/Qwen3-0.6B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 28 of 28 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/113, MLP 81/84, Attention 109/112
1 derivatives checked
- mradermacher/Qwen3-0.6B-ICM-DPO-GGUF: Partial fine-tune