davidheineman/davids-email-llm
LoRA-style vs Qwen/Qwen3-0.6B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of up_proj changed, in 1 of 28 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/113, MLP 1/84, Attention 0/112
1 derivatives checked
- Flexan/davidheineman-davids-email-llm-GGUF: Same weights, converted