Autotrain compatible Dataset:euirim/goodwiki En Endpoints compatible Generated from trainer Gpt neox Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/pszemraj/pythia-31m-goodwiki-deduped-2048-scratch
Pythia 31M Goodwiki Deduped 2048 Scratch Benchmarks
ARC: 23.12 vs 96.7 (so35)-76.1%
HellaSwag: 25.66 vs 95.3 (gpt4)-73.1%
MMLU: 23.11 vs 88.3 (so35)-73.8%
TruthfulQA: 51.32 vs 59 (gpt4)-13%
WinoGrande: 49.88 vs 87.5 (gpt4)-43%
LLME Score: 0.19916
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)
Pythia 31M Goodwiki Deduped 2048 Scratch Parameters and Internals
| LLM Name | Pythia 31M Goodwiki Deduped 2048 Scratch |
| Repository 🤗 | https://huggingface.co/pszemraj/pythia-31m-goodwiki-deduped-2048-scratch |
| Model Size | 31m |
| Required VRAM | 0.1 GB |
| Updated | 2025-02-22 |
| Maintainer | pszemraj |
| Model Type | gpt_neox |
| Model Files | |
| Supported Languages | en |
| Model Architecture | GPTNeoXForCausalLM |
| License | apache-2.0 |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.33.1 |
| Tokenizer Class | GPTNeoXTokenizer |
| Vocabulary Size | 50304 |
| Torch Data Type | float32 |
Best Alternatives to Pythia 31M Goodwiki Deduped 2048 Scratch
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Pythia 31M Chat V1 | 2K / 0.1 GB | 1886 | 6 |
| ...ia 31M Simplewiki Scratch Bf16 | 2K / 0.1 GB | 2009 | 0 |
| ...implepile Lite 2048 Scratch 2e | 2K / 0.1 GB | 2010 | 0 |
| Pythia 31M Simplewiki 2048 | 2K / 0.1 GB | 2018 | 1 |
| Pythia 31M KI V1 2048 Scratch | 2K / 0.1 GB | 2007 | 0 |
| Pythia 31M | 2K / 0.1 GB | 100 | 0 |
| Pythia 31M | 2K / 0.1 GB | 18710 | 5 |
| ...31M SimpleRW Lite 2048 Scratch | 2K / 0.1 GB | 64 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than pszemraj/pythia-31m-goodwiki-deduped-2048-scratch .
Rank the Pythia 31M Goodwiki Deduped 2048 Scratch 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? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227