Qwen/Qwen2.5-Coder-1.5B
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
46 derivatives checked
- Qwen/Qwen2.5-Coder-1.5B-Instruct: Full fine-tune
- jinaai/jina-code-embeddings-1.5b: Full fine-tune
- ggml-org/Qwen2.5-Coder-1.5B-Q8_0-GGUF: Quantization
- QuantFactory/Qwen2.5-Coder-1.5B-Instruct-GGUF: Full fine-tune
- mlx-community/Qwen2.5-Coder-1.5B-Instruct-4bit: Quantization
- unsloth/Qwen2.5-Coder-1.5B-bnb-4bit: Quantization
- ThomasBaruzier/Qwen2.5-Coder-1.5B-Instruct-GGUF: Full fine-tune
- QuantFactory/CursorCore-QW2.5-1.5B-SR-GGUF: Full fine-tune
- TobiasLogic/qwen-2.5-coder-Uncensored: Quantization
- mradermacher/Qwen2.5-Coder-1.5B-i1-GGUF: Quantization
- featherless-ai-quants/Qwen-Qwen2.5-Coder-1.5B-GGUF: Quantization
- unsloth/Qwen2.5-Coder-1.5B: Identical copy
- mlx-community/Qwen2.5-Coder-1.5B-Instruct-bf16: Full fine-tune
- RichardErkhov/TechxGenus_-_CursorCore-QW2.5-1.5B-gguf: Full fine-tune
- prithivMLmods/Qwen2.5-Coder-1.5B-GGUF: LoRA-style
- mradermacher/Qwen2.5-Coder-1.5B-GGUF: Same weights, converted
- RichardErkhov/TechxGenus_-_CursorCore-QW2.5-1.5B-SR-gguf: Full fine-tune
- tensorblock/Qwen2.5-Coder-1.5B-GGUF: Quantization
- itlwas/Qwen2.5-Coder-1.5B-Q4_K_M-GGUF: Quantization
- Volko76/Qwen2.5-Coder-1.5B-Instruct-GGUF: Full fine-tune
- ikw/Qwen2.5-Coder-1.5B-GGUF: Quantization
- enver/ayncoding-qwen2.5-coder-1.5b: Full fine-tune
- mlx-community/Qwen2.5-Coder-1.5B-Instruct-8bit: Quantization
- Isaacwienert/isaacbot: LoRA-style
- dannyleehicks9/Qwen2.5-Coder-1.5B-Instruct: Full fine-tune
- DevQuasar-4/Qwen.Qwen2.5-Coder-1.5B-GGUF: Quantization
- Posilovic/Qwen2.5-Coder-1.5B-Q4_K_M-GGUF: Quantization
- ggml-org/Qwen2.5-Coder-1.5B-IQ3_XXS-GGUF: Quantization
- Nayan7r839/EchooaiForge: Adapter
- RachidAR/Qwen2.5-Coder-1.5B-Q5_K_M-GGUF: Quantization
6 other repos hold byte-for-byte identical weight files.