Qwen/Qwen2.5-14B-Instruct-1M
Full fine-tune vs Qwen/Qwen2.5-14B. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 97/97, MLP 144/144, Attention 336/336, lm_head 1/1
23 derivatives checked
- bartowski/Qwen2.5-14B-Instruct-1M-GGUF: Same weights, converted
- lmstudio-community/Qwen2.5-14B-Instruct-1M-GGUF: Quantization
- krmonline/Softnix-Qwen2.5-14B-Instruct-1M-ThaiFood-Cooking-8bit: Full fine-tune
- mkurman/Qwen2.5-14B-DeepSeek-R1-1M: Full fine-tune
- pbhappliedsystems/qwen-2.5-14B-instruct-1m-gguf-Q4-K-M: Quantization
- featherless-ai-quants/Qwen-Qwen2.5-14B-Instruct-1M-GGUF: Quantization
- mradermacher/Qwen2.5-14B-Instruct-1M-i1-GGUF: Quantization
- mradermacher/Qwen2.5-14B-Instruct-1M-GGUF: Quantization
- mlx-community/Qwen2.5-14B-Instruct-1M-4bit: Quantization
- pbhappliedsystems/qwen-2.5-14B-instruct-1m-gguf-F16: Same weights, converted
- DevQuasar-7/Qwen.Qwen2.5-14B-Instruct-1M-GGUF: Same weights, converted
- krmonline/Softnix-Qwen2.5-14B-Instruct-1M-LegalThaiCCL-8bit: Full fine-tune
- mlx-community/Qwen2.5-14B-Instruct-1M-8bit: Quantization
- SicariusSicariiStuff/Impish_QWEN_14B-1M: LoRA-style
- JungZoona/T3Q-qwen2.5-14b-v1.0-e3: LoRA-style
- tensorblock/Qwen2.5-14B-Instruct-1M-GGUF: Quantization
- unsloth/Qwen2.5-14B-Instruct-1M: Same weights, repacked
- ToastyPigeon/Qwen2.5-14B-Instruct-1M-Unalign: LoRA-style
- prithivMLmods/Sombrero-Opus-14B-Sm4: Full fine-tune
- prithivMLmods/Calcium-Opus-14B-Elite-1M: LoRA-style
- prithivMLmods/Rapeto-ReDistill-14B-GOP: Full fine-tune
- JungZoona/T3Q-qwen2.5-14b-v1.2-e2: LoRA-style
- prithivMLmods/Diophantus-14B-R1-Instruct: Full fine-tune
1 other repos hold byte-for-byte identical weight files.