unsloth/Qwen2.5-7B-Instruct
Same weights, repacked vs Qwen/Qwen2.5-7B-Instruct. Same weights in different files (re-saved, re-sharded or new metadata).
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196, lm_head 0/1
14 derivatives checked
- Glowstorm/qwen_no_prefill_35steps_50samples_multiturn: LoRA-style
- Benjaminpwh/qwen2.5-7b-instruct-poly-adaLORA-6: Adapter
- gokhanarkan/sommo-7b-v1: Quantization
- unlogic-ai/UnPuzzler-sft-qwen-7b-answer: LoRA-style
- JosephNguyen/Qwen2.5-7B-Instruct-finetuned: LoRA-style
- nhyha/N3N_Qwen2.5-7B-Instruct_20241023_0314: Full fine-tune
- JosephNguyen/Qwen2.5-7B-Instruct-reasoning-finetuned: LoRA-style
- 2point5p/krx-qwen2.5-7b-it-prompt-v2: LoRA-style
- yusikyang/Qwen2.5-7B-Instruct-YS-V2: Full fine-tune
- muverqqw/Noir-Ultra: LoRA-style
- 2point5p/krx-qwen2.5-7b-it-prompt: LoRA-style
- Q-PING/krx_Qwen2.5-7B-It_1104: Full fine-tune
- DuoNeural/ml-ai-engineer-7b: LoRA-style
- Sumanth2377/winning-wedding-planner-7b: LoRA-style
83 other repos hold byte-for-byte identical weight files.