Lambent/Enteles-v0-27B
LoRA-style vs ConicCat/Qwen3.5-27B-Writer. 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, lm_head 0/1, Embeddings 0/5, Attention 253/560, MLP 192/307, other 0/1
2 derivatives checked
- mradermacher/Enteles-v0-27B-i1-GGUF: Quantization
- mradermacher/Enteles-v0-27B-GGUF: Quantization