Model Card on HF 🤗: https://huggingface.co/doas/test5
Test5 Benchmarks
ARC: 28.41 vs 96.7 (so35)-70.6%
HellaSwag: 26.63 vs 95.3 (gpt4)-72.1%
MMLU: 25.36 vs 88.3 (so35)-71.3%
TruthfulQA: 47.34 vs 59 (gpt4)-19.8%
WinoGrande: 52.64 vs 87.5 (gpt4)-39.8%
LLME Score: 0.15098
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)
Test5 Parameters and Internals
| LLM Name | Test5 |
| Repository 🤗 | https://huggingface.co/doas/test5 |
| Model Size | 13b |
| Required VRAM | 51.4 GB |
| Updated | 2025-10-17 |
| Maintainer | doas |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaModel |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.31.0 |
| Tokenizer Class | LlamaTokenizer |
| Beginning of Sentence Token | <s> |
| End of Sentence Token | </s> |
| Unk Token | <unk> |
| Vocabulary Size | 32001 |
| Torch Data Type | float32 |
Best Alternatives to Test5
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama2 13B Platypus Ckpt 1000 | 4K / 51.4 GB | 5 | 0 |
| Llama 2 13B Public | 4K / 51.4 GB | 7 | 0 |
| Llama 2 13B 12 153950 | 4K / 51.4 GB | 7 | 0 |
| Llama 2 13B Sf | 4K / 51.4 GB | 7 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than doas/test5 .
Rank the Test5 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