StellarX 4B V0 Benchmarks
ARC: 36.95 vs 96.7 (so35)-61.8%
HellaSwag: 61.9 vs 95.3 (gpt4)-35%
MMLU: 26.85 vs 88.3 (so35)-69.6%
TruthfulQA: 34.3 vs 59 (gpt4)-41.9%
WinoGrande: 63.85 vs 87.5 (gpt4)-27%
LLME Score: 0.17691
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)
StellarX 4B V0 Parameters and Internals
| LLM Name | StellarX 4B V0 |
| Repository 🤗 | https://huggingface.co/Dampish/StellarX-4B-V0 |
| Model Size | 4b |
| Required VRAM | 8.1 GB |
| Updated | 2024-09-07 |
| Maintainer | Dampish |
| Model Type | gpt_neox |
| Model Files | |
| Model Architecture | GPTNeoXForCausalLM |
| License | cc-by-nc-sa-4.0 |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.29.2 |
| Tokenizer Class | GPTNeoXTokenizer |
| Vocabulary Size | 50432 |
| Torch Data Type | float16 |
Best Alternatives to StellarX 4B V0
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Sft Tldr Pythia 1 4b | 2K / 5.7 GB | 1048 | 0 |
| Bilingual GPT Neox 4B | 2K / 7.7 GB | 1809 | 28 |
| ...al GPT Neox 4B Instruction Sft | 2K / 7.6 GB | 1126 | 18 |
| Tora 4B | 2K / 7.6 GB | 4 | 2 |
| ...x 4B Instruction Sft En Ja 84K | 2K / 7.6 GB | 4 | 1 |
| Bilingual GPT Neox 4B 8K | 2K / 7.7 GB | 600 | 23 |
| ...al GPT Neox 4B Instruction Ppo | 2K / 7.7 GB | 575 | 15 |
| StellarX 4B V0.2 | 2K / 16 GB | 702 | 2 |
| StellarX 4B V0.2 GPTQ | 2K / 1.8 GB | 12 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than Dampish/StellarX-4B-V0 .
Rank the StellarX 4B V0 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