Model Card on HF 🤗: https://huggingface.co/klosax/pythia-160m-deduped-step92k-193bt
Pythia 160M Deduped Step92k 193bt Benchmarks
ARC: 24.23 vs 96.7 (so35)-74.9%
HellaSwag: 32.33 vs 95.3 (gpt4)-66.1%
MMLU: 24.54 vs 88.3 (so35)-72.2%
TruthfulQA: 43.49 vs 59 (gpt4)-26.3%
WinoGrande: 50.83 vs 87.5 (gpt4)-41.9%
GSM8K: 0.38 vs 96.4 (so35)-99.6%
LLME Score: 0.16259
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 160M Deduped Step92k 193bt Parameters and Internals
| LLM Name | Pythia 160M Deduped Step92k 193bt |
| Repository 🤗 | https://huggingface.co/klosax/pythia-160m-deduped-step92k-193bt |
| Model Size | 160m |
| Required VRAM | 0.4 GB |
| Updated | 2025-08-20 |
| Maintainer | klosax |
| Model Type | gpt_neox |
| Model Files | |
| Model Architecture | GPTNeoXForCausalLM |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.24.0 |
| Tokenizer Class | GPTNeoXTokenizer |
| Vocabulary Size | 50304 |
| Torch Data Type | float16 |
Best Alternatives to Pythia 160M Deduped Step92k 193bt
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Pythia 160M C2s | 8K / 0.6 GB | 89 | 6 |
| Pythia 160M Xsum Roya | 2K / 0.6 GB | 14 | 0 |
| Pythia 160m Sft | 2K / 0 GB | 8 | 0 |
| Pythia 160M | 2K / 0.4 GB | 118454 | 32 |
| Sheared Pythia 160M | 2K / 0.7 GB | 5 | 4 |
| Pythia 160M Dolphin Extended | 2K / 0.3 GB | 5 | 0 |
| Pythia 160M Storytelling | 2K / 0.3 GB | 7 | 0 |
| Pythia160m Sft Tldr | 2K / 0.6 GB | 5 | 0 |
| Pythia 160M Deduped | 2K / 0.4 GB | 37602 | 3 |
| Pythia 160m Ft CookingRecipes | 2K / 0.6 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than klosax/pythia-160m-deduped-step92k-193bt .
Rank the Pythia 160M Deduped Step92k 193bt 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? 50767 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124