Qwen/Qwen2.5-Coder-0.5B-Instruct
Full fine-tune vs Qwen/Qwen2.5-Coder-0.5B. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Embeddings 1/1, Norms 49/49, MLP 72/72, Attention 168/168
52 derivatives checked
- Qwen/Qwen2.5-Coder-0.5B-Instruct-GGUF: Same weights, converted
- unsloth/Qwen2.5-Coder-0.5B-Instruct: Identical copy
- unsloth/Qwen2.5-Coder-0.5B-Instruct-bnb-4bit: Quantization
- bartowski/Qwen2.5-Coder-0.5B-Instruct-GGUF: Same weights, converted
- lmstudio-community/Qwen2.5-Coder-0.5B-Instruct-GGUF: Quantization
- mlx-community/Qwen2.5-Coder-0.5B-Instruct-4bit: Quantization
- lmstudio-community/Qwen2.5-Coder-0.5B-Instruct-MLX-4bit: Quantization
- unsloth/Qwen2.5-Coder-0.5B-Instruct-128K-GGUF: Same weights, converted
- unsloth/Qwen2.5-Coder-0.5B-Instruct-GGUF: Same weights, converted
- mradermacher/Qwen2.5-Coder-0.5B-Instruct-i1-GGUF: Quantization
- minsore/quill-1-preview: LoRA-style
- lmstudio-community/Qwen2.5-Coder-0.5B-Instruct-MLX-8bit: Quantization
- second-state/Qwen2.5-Coder-0.5B-Instruct-GGUF: Same weights, converted
- mradermacher/Qwen2.5-Coder-0.5B-Instruct-GGUF: Same weights, converted
- MadeAgents/Hammer2.1-0.5b: LoRA-style
- codefuse-ai/C2LLM-0.5B: LoRA-style
- gaianet/Qwen2.5-Coder-0.5B-Instruct-GGUF: Same weights, converted
- sahellx/kitty-bash-llm: LoRA-style
- driaforall/Tiny-Agent-a-0.5B: Full fine-tune
- salakash/Minimalism: Different architecture
- albinab/Qwen-0.5B-Coder-El-Terminalo: Full fine-tune
- MidlightDDK/pocketsql-0.5b: LoRA-style
- Alcoft/Qwen2.5-Coder-0.5B-Instruct-GGUF: Quantization
- CooperBench/Qwen2.5-Coder-0.5B-Merge-Resolver: Adapter
- ThuraAung1601/Qwen2.5-Coder-0.5B-Instruct_reform-dafny-loop-inv-gen-aug_GRPO: LoRA-style
- temper-ai/Temper-1-0.5B: Full fine-tune
- Qwen/Qwen2.5-Coder-0.5B-Instruct-AWQ: Quantization
- tensorblock/Qwen2.5-Coder-0.5B-Instruct-GGUF: Quantization
- burhan2753y/qwen2.5-coder-0.5b-nl2bash-gguf: Full fine-tune
- Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int4: Quantization
10 other repos hold byte-for-byte identical weight files.