theprint/h4xx0r-v1-2B
LoRA-style (fewer layers) vs unsloth/Qwen3.5-2B. theprint/h4xx0r-v1-2B matches part of unsloth/Qwen3.5-2B (335 of its 632 tensors; the rest of unsloth/Qwen3.5-2B has no counterpart). On the shared part: Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of k_proj, o_proj, q_proj, v_proj changed, in 6 of 24 layers; norms, biases and embeddings are untouched.
Tensors changed: Attention 24/172, Norms 0/85, Embeddings 0/2, MLP 0/75, other 0/1
2 derivatives checked
- mradermacher/h4xx0r-v1-2B-i1-GGUF: Quantization
- mradermacher/h4xx0r-v1-2B-GGUF: Same weights, converted