techwithsergiu/Qwen3.5-text-4B
Same weights, repacked (fewer layers) vs Qwen/Qwen3.5-4B. techwithsergiu/Qwen3.5-text-4B matches part of Qwen/Qwen3.5-4B (441 of its 738 tensors; the rest of Qwen/Qwen3.5-4B has no counterpart). On the shared part: Same weights in different files (re-saved, re-sharded or new metadata).
Tensors changed: Embeddings 0/2, MLP 0/99, Attention 0/228, Norms 0/111, other 0/1
2 derivatives checked
- techwithsergiu/Qwen3.5-text-4B-bnb-4bit: Quantization
- techwithsergiu/Qwen3.5-text-4B-GGUF: Same weights, converted