Qwen/Qwen2.5-7B-Instruct-1M
Full fine-tune vs Qwen/Qwen2.5-7B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 196/196, lm_head 1/1
36 derivatives checked
- lmstudio-community/Qwen2.5-7B-Instruct-1M-GGUF: Quantization
- bartowski/Qwen2.5-7B-Instruct-1M-GGUF: Same weights, converted
- graelo/Qwen2.5-7B-Instruct-1M-AWQ: Quantization
- saidutta69/Qwen2.5-7B-Instruct-1M-heretic: Abliterated
- mradermacher/Qwen2.5-7B-Instruct-1M-i1-GGUF: Quantization
- featherless-ai-quants/Qwen-Qwen2.5-7B-Instruct-1M-GGUF: Quantization
- BabaK07/Qwen2.5-7B-Instruct-1M-GGUF: Same weights, converted
- DevQuasar-8/Qwen.Qwen2.5-7B-Instruct-1M-GGUF: Same weights, converted
- mlx-community/Qwen2.5-7B-Instruct-1M-4bit: Quantization
- mradermacher/Qwen2.5-7B-Instruct-1M-GGUF: Same weights, converted
- yasserrmd/Qwen2.5-7B-Instruct-1M-gguf: LoRA-style
- ngxson/Qwen2.5-7B-Instruct-1M-Q4_K_M-GGUF: Quantization
- Rewnozom/Rewnozom: Partial fine-tune
- tensorblock/Qwen2.5-7B-Instruct-1M-GGUF: Quantization
- SicariusSicariiStuff/Impish_QWEN_7B-1M: Partial fine-tune
- mlx-community/Qwen2.5-7B-Instruct-1M-8bit: Quantization
- unsloth/Qwen2.5-7B-Instruct-1M-bnb-4bit: Quantization
- EasierAI/Qwen-2.5-7B: Quantization
- DavidAU/Qwen2.5-7B-Instruct-1M-Thinking-Claude-Gemini-GPT5.2-DISTILL: LoRA-style
- agurung/Qwen2.5-7B-1M-SFT-LongStory: Full fine-tune
- prithivMLmods/COCO-7B-Instruct-1M: LoRA-style
- ZeroXClem/Qwen2.5-7B-CelestialHarmony-1M: Partial fine-tune
- bunnycore/Qwen2.5-7B-RRP-1M: Full fine-tune
- yasserrmd/DeepSeek-7B-1M: Full fine-tune
- diabolic6045/Sanskrit-qwen-7B-Translate-Legacy: LoRA-style
- marcuscedricridia/Hush-Qwen2.5-7B-RP-v1.4-1M: Full fine-tune
- dumbequation/Qwen2.5-7B-GRPO-1M-Context-Medical-Reasoning-f16-v2: LoRA-style
- marcuscedricridia/Hush-Qwen2.5-7B-RP-v1.1-1M: Full fine-tune
- dumbequation/Qwen2.5-7B-GRPO-1M-Context-Medical-Reasoning-f16: LoRA-style
- Sakalti/deneb-v1-7b: Partial fine-tune
4 other repos hold byte-for-byte identical weight files.