Arxiv:2305.18290 Autotrain compatible Base model:finetune:jayhyeon/q... Base model:jayhyeon/qwen2.5-0.... Conversational Dataset:trl-lib/ultrafeedback ... Dpo Endpoints compatible Generated from trainer Qwen2 Region:us Safetensors Trl
Model Card on HF 🤗: https://huggingface.co/JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep-DPO_1e-7-3ep_0alp_0lam
Qwen2.5 0.5B SFT 2e 5 2ep DPO 1e 7 3ep 0alp 0lam Benchmarks
MMLU Pro: 6.48
GPQA: 1.79
MUSR: 1.43
BBH: 6.39
IFEval: 25.78 vs 88 (so35)-70.7%
MATH Lvl 5: 3.55
LLME Score: 0.21583
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 SFT 2e 5 2ep DPO 1e 7 3ep 0alp 0lam Parameters and Internals
| LLM Name | Qwen2.5 0.5B SFT 2e 5 2ep DPO 1e 7 3ep 0alp 0lam |
| Repository 🤗 | https://huggingface.co/JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep-DPO_1e-7-3ep_0alp_0lam |
| Model Name | Qwen2.5-0.5B-SFT-2e-5-2ep-DPO_1e-7-3ep_0alp_0lam |
| Base Model(s) | |
| Model Size | 0.5b |
| Required VRAM | 1.3 GB |
| Updated | 2025-09-23 |
| Maintainer | JayHyeon |
| Model Type | qwen2 |
| Model Files | |
| Model Architecture | Qwen2ForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.47.0.dev0 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Qwen2.5 0.5B SFT 2e 5 2ep DPO 1e 7 3ep 0alp 0lam
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Reader Lm 0.5B | 250K / 1 GB | 1190 | 145 |
| Qwen2 0.5B | 128K / 1 GB | 549084 | 157 |
| Qwen2 0.5B Stf Imdb | 128K / 1 GB | 6 | 0 |
| ...0.5B FT EnhancedMUSREnsembleV3 | 128K / 1 GB | 32 | 1 |
| ...PRYMMAL 0.5B FT V4 MUSR Mathis | 128K / 1 GB | 62 | 1 |
| ....5B FT V4 MUSR ENSEMBLE Mathis | 128K / 2 GB | 30 | 1 |
| ...0.5B FT MUSR ENSEMBLE V2Mathis | 128K / 1 GB | 25 | 0 |
| ECE PRYMMAL 0.5B FT V3 MUSR | 128K / 2 GB | 9 | 0 |
| ...44 45ee 44f3 934d Ddc8b6e082f1 | 128K / 1 GB | 8 | 0 |
| ...wen199f16 Merged FinetunedByAG | 128K / 1 GB | 6 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep-DPO_1e-7-3ep_0alp_0lam .
Rank the Qwen2.5 0.5B SFT 2e 5 2ep DPO 1e 7 3ep 0alp 0lam 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? 51545 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124