Wonderlab-Testing-Grounds/Interferon-gamma-RP-9B-Preview-2608
LoRA-style (fewer layers) vs Qwen/Qwen3.5-9B. Wonderlab-Testing-Grounds/Interferon-gamma-RP-9B-Preview-2608 matches part of Qwen/Qwen3.5-9B (442 of its 775 tensors; the rest of Qwen/Qwen3.5-9B has no counterpart). On the shared part: 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 31 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/2, MLP 96/99, Attention 32/228, other 0/1, Norms 0/111
2 derivatives checked
- mradermacher/Interferon-gamma-RP-9B-Preview-2608-i1-GGUF: Quantization
- mradermacher/Interferon-gamma-RP-9B-Preview-2608-GGUF: Same weights, converted