Qwen/Qwen2.5-Coder-0.5B
Full fine-tune vs Qwen/Qwen2.5-0.5B. 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
33 derivatives checked
- Qwen/Qwen2.5-Coder-0.5B-Instruct: Full fine-tune
- jinaai/jina-code-embeddings-0.5b: Full fine-tune
- saidutta69/Qwen2.5-Coder-0.5B-Instruct-heretic: Full fine-tune
- bartowski/Qwen2.5-Coder-0.5B-GGUF: Same weights, converted
- ThomasBaruzier/Qwen2.5-Coder-0.5B-Instruct-GGUF: Full fine-tune
- unsloth/Qwen2.5-Coder-0.5B-bnb-4bit: Quantization
- 0xgr3y/Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-tall_tame_panther: Full fine-tune
- ggml-org/Qwen2.5-Coder-0.5B-Q8_0-GGUF: Quantization
- featherless-ai-quants/Qwen-Qwen2.5-Coder-0.5B-GGUF: Quantization
- QuantFactory/Qwen2.5-Coder-0.5B-Instruct-GGUF: Full fine-tune
- mradermacher/Qwen2.5-Coder-0.5B-i1-GGUF: Quantization
- Pluto-AI-Labs/Atlas-Coder-0.5B-GGUF: LoRA-style
- mradermacher/Qwen2.5-Coder-0.5B-GGUF: Same weights, converted
- lmstudio-community/Qwen2.5-Coder-0.5B-GGUF: Quantization
- unsloth/Qwen2.5-Coder-0.5B: Identical copy
- Volko76/Qwen2.5-Coder-0.5B-Instruct-GGUF: Full fine-tune
- faisalmumtaz/codecompass-embed: Full fine-tune
- bbidpa/Qwen2.5-Coder-0.5B-Flutter-steps: Full fine-tune
- bbidpa/Qwen2.5-Coder-0.5B-Flutter-direct: Full fine-tune
- Chanithu/Qwen2.5-Coder-0.5B-Instruct: Full fine-tune
- DevQuasar-7/Qwen.Qwen2.5-Coder-0.5B-GGUF: Quantization
- esilva/SlopCoder-Mongo-0.5B: LoRA-style
- alamios/DeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B: Full fine-tune
- vonjack/Qwen2.5-Coder-0.5B-Merged: Full fine-tune
- Strangefrost/CloneOllama-selfplay-coder-0.5B: LoRA-style
- Pluto-AI-Labs/Atlas-Coder-0.5B: LoRA-style
- southfreebird/Qwen2.5-Coder-0.5B-Instruct: Full fine-tune
- arun11karthik/cellsense-fim-0.5b: Full fine-tune
- oieieio/Qwen2.5-Coder-0.5B-Instruct: Full fine-tune
- MoxStone/SmaliLLM-Qwen2.5-Coder-0.5B-Finetuned: Full fine-tune
3 other repos hold byte-for-byte identical weight files.