Autotrain compatible Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-0.5b-i... Conversational Dataset:huggingfaceh4/ultrafee... Endpoints compatible Generated from trainer Instruct Qwen2 Region:us Safetensors Sft Trl
Model Card on HF 🤗: https://huggingface.co/JayHyeon/Qwen2.5-0.5B-Instruct-SFT
Qwen2.5 0.5B Instruct SFT Benchmarks
MMLU Pro: 5.78
GPQA: 4.36
MUSR: 1.27
BBH: 5.93
IFEval: 27.68 vs 88 (so35)-68.5%
MATH Lvl 5: 3.93
LLME Score: 0.24563
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 Parameters and Internals
| LLM Name | Qwen2.5 0.5B Instruct SFT |
| Repository 🤗 | https://huggingface.co/JayHyeon/Qwen2.5-0.5B-Instruct-SFT |
| Model Name | Qwen2.5-0.5B-Instruct-SFT |
| Base Model(s) | |
| Model Size | 0.5b |
| Required VRAM | 1.3 GB |
| Updated | 2025-04-29 |
| Maintainer | JayHyeon |
| Model Type | qwen2 |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | Qwen2ForCausalLM |
| 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 | bfloat16 |
| Errors | replace |
Best Alternatives to Qwen2.5 0.5B Instruct SFT
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen2 0.5B Abyme Merge3 | 128K / 1.3 GB | 17 | 1 |
| Qwen2 0.5B Abyme Merge2 | 128K / 0.3 GB | 6 | 0 |
| Qwen2.5 0.5B Instruct | 32K / 1 GB | 2589190 | 5 |
| Qwen2.5 0.5B Instruct | 32K / 1 GB | 1153808 | 315 |
| Qwen2.5 Coder 0.5B Instruct | 32K / 1 GB | 127688 | 44 |
| ...nsyn Swarm Fierce Placid Whale | 32K / 2 GB | 3088 | 2 |
| Qwen2 0.5B Instruct | 32K / 1 GB | 226049 | 186 |
| ... Swarm Singing Timid Cassowary | 32K / 2 GB | 800 | 1 |
| Lb Reranker 0.5B V1.0 | 32K / 1 GB | 761 | 67 |
| TESS QwenRe Fact 0.5B | 32K / 2 GB | 22 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than JayHyeon/Qwen2.5-0.5B-Instruct-SFT .
Rank the Qwen2.5 0.5B Instruct SFT 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? 46792 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227