Qwen/Qwen2.5-Coder-7B
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
63 derivatives checked
- Qwen/Qwen2.5-Coder-7B-Instruct: Full fine-tune
- mlx-community/Qwen2.5-Coder-7B-Instruct-4bit: Quantization
- unsloth/Qwen2.5-Coder-7B-bnb-4bit: Quantization
- DeepHat/DeepHat-V1-7B: Full fine-tune
- itlwas/Qwen2.5-Coder-7B-Q4_K_M-GGUF: Quantization
- ggml-org/Qwen2.5-Coder-7B-Q8_0-GGUF: Quantization
- QuantFactory/Qwen2.5-Coder-7B-Instruct-GGUF: Full fine-tune
- WhiteRabbitNeo/WhiteRabbitNeo-2.5-Qwen-2.5-Coder-7B: Full fine-tune
- ThomasBaruzier/Qwen2.5-Coder-7B-Instruct-GGUF: Full fine-tune
- mradermacher/Qwen2.5-Coder-7B-i1-GGUF: Quantization
- QuantFactory/WhiteRabbitNeo-2.5-Qwen-2.5-Coder-7B-GGUF: Full fine-tune
- featherless-ai-quants/Qwen-Qwen2.5-Coder-7B-GGUF: Quantization
- mlx-community/Qwen2.5-Coder-7B-Instruct-8bit: Quantization
- QuantFactory/CursorCore-QW2.5-7B-GGUF: Full fine-tune
- unsloth/Qwen2.5-Coder-7B: Identical copy
- Mungert/instinct-GGUF: Full fine-tune
- QuantFactory/instinct-GGUF: Full fine-tune
- QuantFactory/Qwen2.5-Coder-7B-Chat-Instruct-TIES-v1.2-GGUF: Full fine-tune
- mradermacher/Qwen2.5-Coder-7B-GGUF: Same weights, converted
- bigxho15/Qwen2.5-Coder-7B-Instruct: Full fine-tune
- mlx-community/Qwen2.5-Coder-7B-Instruct-bf16: Full fine-tune
- DevQuasar-8/Qwen.Qwen2.5-Coder-7B-GGUF: Same weights, converted
- apple/DiffuCoder-7B-Base: Full fine-tune
- nvidia/CUDA-Autocomplete: Full fine-tune
- AdvancedDataIntelligence/adi-qwen2.5-coder-7b-kimi2.7-code-GGUF: Quantization
- prithivMLmods/Qwen2.5-Coder-7B-GGUF: LoRA-style
- sweepai/sweep-next-edit-v2-7B: Full fine-tune
- mendrika261/DeepHat-V1-7B-GGUF: Full fine-tune
- NovaVest/VN-Noxa-v1-7b-Beta-Pro: Full fine-tune
- m1ndgames/Qwen2.5-Coder-7B-Instruct-heretic: Full fine-tune
7 other repos hold byte-for-byte identical weight files.