Qwen/Qwen2.5-0.5B-Instruct
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
301 derivatives checked
- livekit/turn-detector: Different architecture
- Qwen/Qwen2.5-0.5B-Instruct-GGUF: Same weights, converted
- bartowski/Qwen2.5-0.5B-Instruct-GGUF: Same weights, converted
- unsloth/Qwen2.5-0.5B-Instruct-unsloth-bnb-4bit: Quantization
- OPEA/Qwen2.5-0.5B-Instruct-int4-sym-inc: Quantization
- unsloth/Qwen2.5-0.5B-Instruct: Identical copy
- manycore-research/SpatialLM1.1-Qwen-0.5B: Full fine-tune (fewer layers)
- unsloth/Qwen2.5-0.5B-Instruct-bnb-4bit: Quantization
- lmstudio-community/Qwen2.5-0.5B-Instruct-GGUF: Quantization
- Qwen/Qwen2.5-0.5B-Instruct-AWQ: Quantization
- lmstudio-community/Qwen2.5-0.5B-Instruct-MLX-4bit: Quantization
- sallani/EUAIAct-Qwen2.5-0.5B-Edge: LoRA-style
- saidutta69/Qwen2.5-0.5B-Instruct-heretic: Abliterated
- legraphista/Qwen2.5-0.5B-Instruct-IMat-GGUF: Same weights, converted
- mradermacher/Qwen2.5-0.5B-Instruct-GGUF: Same weights, converted
- reaperdoesntknow/DeepReasoning_1R: Full fine-tune
- sbussiso/Qwen2.5-0.5B-abliterated: Partial fine-tune
- sallani/ISO27001-Qwen2.5-0.5B-Edge: LoRA-style
- mradermacher/Qwen2.5-0.5B-Instruct-i1-GGUF: Quantization
- dwidlee/systemone-lite-0.5b: Partial fine-tune
- MaziyarPanahi/Qwen2.5-0.5B-Instruct-GGUF: Same weights, converted
- Caglana/qwen0.5b-tinylora-ds-assistant: LoRA-style
- second-state/Qwen2.5-0.5B-Instruct-GGUF: Same weights, converted
- singhmandavi/math-slm-qwen2.5-0.5b-v4: LoRA-style
- tensorblock/Qwen2.5-0.5B-Instruct-GGUF: Quantization
- Vikhrmodels/Vikhr-Qwen-2.5-0.5b-Instruct: LoRA-style
- Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int4: Quantization
- huihui-ai/Qwen2.5-0.5B-Instruct-abliterated-v3: Abliterated
- QuantFactory/Qwen2.5-0.5b-RBase-GGUF: Full fine-tune
- PollardWeights/HumanBrain-Pollard-H01: Quantization
412 other repos hold byte-for-byte identical weight files.