Thox-ai/ThoxEdge-0.8B
LoRA-style (fewer layers) vs Qwen/Qwen3.5-0.8B. Thox-ai/ThoxEdge-0.8B matches part of Qwen/Qwen3.5-0.8B (320 of its 488 tensors; the rest of Qwen/Qwen3.5-0.8B 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 24 of 24 layers; norms, biases and embeddings are untouched.
Tensors changed: Attention 24/168, Norms 0/79, Embeddings 0/1, MLP 72/72
1 derivatives checked
- mradermacher/ThoxEdge-0.8B-GGUF: Same weights, converted