tsinghua-sigs-robot-lab/VeriLoop-E2
LoRA-style vs Qwen/Qwen3.8-27B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, in_proj_a, in_proj_b, in_proj_qkv, in_proj_z, k_proj, o_proj, out_proj, q_proj, up_proj, v_proj changed, in 64 of 64 layers; norms, biases and embeddings are untouched.
Tensors changed: Norms 0/325, Attention 304/560, MLP 192/307, Embeddings 0/5, lm_head 0/1, other 0/1
6 derivatives checked
- tahaalam2009/VeriLoop-E2-GSQ-RCO-GGUF: Quantization
- NikiKrutan/VeriLoop-E2-MTP-GGUF: Quantization
- tsinghua-sigs-robot-lab/VeriLoop-E2-GGUF: Same weights, converted
- rodrigoramosrs/veriloop-coder-e2-nvfp4: Quantization
- rodrigoramosrs/veriloop-coder-e2-gguf: Same weights, converted
- xiaoqiao64/VeriLoop-E2-Q8_0_ROCMFPX_AGENT-GGUF: Quantization