Model Card on HF 🤗: https://huggingface.co/PRIME-RL/EurusPRM-Stage1
EurusPRM Stage1 Benchmarks
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)
EurusPRM Stage1 Parameters and Internals
| LLM Name | EurusPRM Stage1 |
| Repository 🤗 | https://huggingface.co/PRIME-RL/EurusPRM-Stage1 |
| Model Size | 7b |
| Required VRAM | 15.2 GB |
| Updated | 2025-02-05 |
| Maintainer | PRIME-RL |
| Model Type | qwen2 |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | Qwen2ForCausalLM |
| License | apache-2.0 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.45.2 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 152064 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to EurusPRM Stage1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen2.5 7B Instruct 1M | 986K / 15.4 GB | 25044 | 175 |
| Qwen2.5 7B RRP 1M | 986K / 15.2 GB | 97 | 4 |
| COCO 7B Instruct 1M | 986K / 15.2 GB | 73 | 8 |
| Q2.5 Instruct 1M Harmony | 986K / 15.2 GB | 35 | 0 |
| Impish QWEN 7B 1M | 986K / 15.2 GB | 39 | 1 |
| Qwen2.5 7B DeepSeek R1 1M | 986K / 15.2 GB | 50 | 8 |
| MwM 7B CoT Merge1 | 986K / 15.2 GB | 22 | 2 |
| Mergekit Della Linear Vmeykci | 986K / 16.2 GB | 11 | 0 |
| SJT 7B 1M | 986K / 15.2 GB | 13 | 1 |
| ....5 7B DeepSeek BunnyHarmony 1M | 986K / 14.8 GB | 0 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than PRIME-RL/EurusPRM-Stage1 .
Rank the EurusPRM Stage1 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? 42577 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227