Aanaphi2 V0.1 Benchmarks
ARC: 63.91 vs 96.7 (so35)-33.9%
HellaSwag: 77.97 vs 95.3 (gpt4)-18.2%
MMLU: 57.73 vs 88.3 (so35)-34.6%
TruthfulQA: 51.56 vs 59 (gpt4)-12.6%
WinoGrande: 73.64 vs 87.5 (gpt4)-15.8%
GSM8K: 54.89 vs 96.4 (so35)-43.1%
LLME Score: 0.22058
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)
Aanaphi2 V0.1 Parameters and Internals
| LLM Name | Aanaphi2 V0.1 |
| Repository 🤗 | https://huggingface.co/mobiuslabsgmbh/aanaphi2-v0.1 |
| Model Size | 2.8b |
| Required VRAM | 5.6 GB |
| Updated | 2024-09-07 |
| Maintainer | mobiuslabsgmbh |
| Model Type | phi |
| Model Files | |
| Model Architecture | PhiForCausalLM |
| License | mit |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.37.2 |
| Tokenizer Class | CodeGenTokenizer |
| Padding Token | [PAD] |
| Vocabulary Size | 51200 |
| Torch Data Type | float16 |
Best Alternatives to Aanaphi2 V0.1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| MFANN3bv0.19.12 | 32K / 5.6 GB | 453 | 0 |
| MFANN3bv0.19 | 32K / 11.1 GB | 26 | 0 |
| MFANN3bv0.18 | 32K / 11.1 GB | 13 | 0 |
| MFANN3bv0.15 | 32K / 11.1 GB | 24 | 0 |
| MFANN3bv0.19.11 | 32K / 11.1 GB | 7 | 0 |
| MFANN3bv0.18.11 | 32K / 11.1 GB | 8 | 0 |
| MFANN3bv0.11 | 32K / 11.1 GB | 6 | 0 |
| MFANN3bv0.10.10 | 32K / 5.6 GB | 5 | 0 |
| MFANN3bv0.17.11 | 32K / 11.1 GB | 5 | 0 |
| MFANN3bv0.17 | 32K / 11.1 GB | 7 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than mobiuslabsgmbh/aanaphi2-v0.1 .
Rank the Aanaphi2 V0.1 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? 35693 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803