Qwen/Qwen2.5-1.5B-Instruct
Full fine-tune vs Qwen/Qwen2.5-1.5B. 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
367 derivatives checked
- Qwen/Qwen2.5-1.5B-Instruct-GGUF: Same weights, converted
- MaziyarPanahi/Qwen2.5-1.5B-Instruct-GGUF: Same weights, converted
- Qwen/Qwen2.5-1.5B-Instruct-AWQ: Quantization
- bartowski/Qwen2.5-1.5B-Instruct-GGUF: Same weights, converted
- prismor/prompt-guard-1.5b: LoRA-style
- unsloth/Qwen2.5-1.5B-Instruct-unsloth-bnb-4bit: Quantization
- Sedibaai/SedibaLM: LoRA-style
- JackKozmo29/depguard-jev-style-1.5b: LoRA-style
- JackKozmo29/mailguard-jev-style-1.5b: LoRA-style
- unsloth/Qwen2.5-1.5B-Instruct: Identical copy
- unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit: Quantization
- JackKozmo29/sevclassifier-jev-style-1.5b: LoRA-style
- JackKozmo29/codeguard-jev-style-1.5b: LoRA-style
- katanemo/Arch-Router-1.5B: Partial fine-tune
- SakanaAI/TinySwallow-1.5B-Instruct: Full fine-tune
- lmstudio-community/Qwen2.5-1.5B-Instruct-GGUF: Quantization
- SZLHOLDINGS/SZL-Khipu-1.5B: LoRA-style
- mradermacher/Qwen2.5-1.5B-Instruct-i1-GGUF: Quantization
- Efficient-Large-Model/Fast_dLLM_v2_1.5B: Full fine-tune
- BytedanceDouyinContent/SAIL-VL-1d6-8B: Different architecture
- Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int4: Quantization
- legraphista/Qwen2.5-1.5B-Instruct-IMat-GGUF: Same weights, converted
- mradermacher/Qwen2.5-1.5B-Instruct-GGUF: Same weights, converted
- SakanaAI/TinySwallow-1.5B-Instruct-GGUF: Full fine-tune
- QuantFactory/Qwen2.5-Sex-GGUF: Full fine-tune
- saidutta69/Qwen2.5-1.5B-Instruct-heretic: Abliterated
- yavuz-ai/qwen2.5-1.5b-rm-ultrafeedback: LoRA-style
- katanemo/Arch-Router-1.5B.gguf: Full fine-tune
- eth-nlped/Qwen2.5-1.5B-pedagogical-rewardmodel: Partial fine-tune
- zkkdinx/Qwen2.5-1.5B-Instruct-Q4_K_M-GGUF: Quantization
127 other repos hold byte-for-byte identical weight files.