Arxiv:2101.00027 Autotrain compatible Dataset:anthropic/hh-rlhf En Endpoints compatible Gpt neox Pythia Pytorch Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/lomahony/pythia-70m-helpful-sft
Pythia 70M Helpful Sft Benchmarks
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 70M Helpful Sft Parameters and Internals
| Model Type |
| ||||||
| Training Details |
|
| LLM Name | Pythia 70M Helpful Sft |
| Repository 🤗 | https://huggingface.co/lomahony/pythia-70m-helpful-sft |
| Model Size | 70m |
| Required VRAM | 0.1 GB |
| Updated | 2025-06-01 |
| Maintainer | lomahony |
| 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 | 4.34.1 |
| Tokenizer Class | GPTNeoXTokenizer |
| Padding Token | <|padding|> |
| Vocabulary Size | 50304 |
| Torch Data Type | bfloat16 |
Best Alternatives to Pythia 70M Helpful Sft
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Pythia 70m Sft Hh | 2K / 0.1 GB | 9 | 0 |
| Pythia 70M Deduped | 2K / 0.2 GB | 845961 | 25 |
| Pythia 70M Multi | 2K / 0.3 GB | 5 | 0 |
| Pythia Chinese 70M UDN | 2K / 0.2 GB | 18 | 0 |
| Pythia 70m Sft | 2K / 0.3 GB | 5 | 0 |
| ...ythia 70M Wikipedia Paragraphs | 2K / 0.3 GB | 31 | 3 |
| Pythia 70M | 2K / 0.2 GB | 156202 | 70 |
| Chessdevilai | 2K / 0.3 GB | 11 | 0 |
| Polish Wikipedia Model | 2K / 0.3 GB | 16 | 0 |
| My Awesome Eli5 Clm Model | 2K / 0.3 GB | 15 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than lomahony/pythia-70m-helpful-sft .
Rank the Pythia 70M Helpful Sft 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? 47770 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227