lewiswatson/Frame2KG-InternVL3.5-1b-JSON
LoRA-style (fewer layers) vs OpenGVLab/InternVL3_5-1B-HF. lewiswatson/Frame2KG-InternVL3.5-1b-JSON matches part of OpenGVLab/InternVL3_5-1B-HF (311 of its 753 tensors; the rest of OpenGVLab/InternVL3_5-1B-HF has no counterpart). On the shared part: lewiswatson/Frame2KG-InternVL3.5-1b-JSON is a GGUF (F16) of different weights. 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: lm_head 0/1, Embeddings 0/1, Norms 0/113, MLP 84/84, Attention 112/112