Arxiv:1910.09700 Endpoints compatible Feature-extraction Instruct Qwen2 Region:us Safetensors Text-embeddings-inference
Model Card on HF 🤗: https://huggingface.co/JayHyeon/Qwen2.5-0.5B-Instruct-SFT-IRPO-1epoch_v1
Qwen2.5 0.5B Instruct SFT IRPO 1epoch V1 Benchmarks
MMLU Pro: 6.95
GPQA: 4.03
MUSR: 1.27
BBH: 6.62
IFEval: 26.06 vs 88 (so35)-70.4%
MATH Lvl 5: 4.98
LLME Score: 0.21944
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Qwen2.5 0.5B Instruct SFT IRPO 1epoch V1 Parameters and Internals
| LLM Name | Qwen2.5 0.5B Instruct SFT IRPO 1epoch V1 |
| Repository 🤗 | https://huggingface.co/JayHyeon/Qwen2.5-0.5B-Instruct-SFT-IRPO-1epoch_v1 |
| Model Size | 0.5b |
| Required VRAM | 2 GB |
| Updated | 2025-09-23 |
| Maintainer | JayHyeon |
| Model Type | qwen2 |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | Qwen2Model |
| License | mit |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.47.0.dev0 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|im_end|> |
| Vocabulary Size | 151936 |
| Torch Data Type | float32 |
| Errors | replace |
Best Alternatives to Qwen2.5 0.5B Instruct SFT IRPO 1epoch V1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ....5B Instruct SFT DPO 1epoch V1 | 32K / 2 GB | 5 | 0 |
| ...5B Instruct SFT MDPO 1epoch V1 | 32K / 2 GB | 6 | 0 |
Rank the Qwen2.5 0.5B Instruct SFT IRPO 1epoch V1 Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 51544 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124