Sakalti/Qwen2.5-1B-Instruct
Same weights, repacked (fewer layers) vs Sakalti/SJT-0.5B. Sakalti/SJT-0.5B matches part of Sakalti/Qwen2.5-1B-Instruct (291 of its 579 tensors; the rest of Sakalti/Qwen2.5-1B-Instruct has no counterpart). On the shared part: Same weights in different files (re-saved, re-sharded or new metadata), plus 288 new tensors.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 0/168
1 derivatives checked
- nulledinstance/Qwen2.5-1B-Instruct-Q8_0-GGUF: Quantization