Arxiv:1910.09700 Autotrain compatible Base model:finetune:islabresea... Base model:islabresearch/opend... Dataset:zhaorui-nb/uniteddaily... Endpoints compatible Gpt neox Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/zhaorui-nb/pythia-chinese-70m-UDN
Pythia Chinese 70M UDN 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 Chinese 70M UDN Parameters and Internals
| LLM Name | Pythia Chinese 70M UDN |
| Repository 🤗 | https://huggingface.co/zhaorui-nb/pythia-chinese-70m-UDN |
| Base Model(s) | |
| Model Size | 70m |
| Required VRAM | 0.2 GB |
| Updated | 2024-11-29 |
| Maintainer | zhaorui-nb |
| Model Type | gpt_neox |
| Model Files | |
| Model Architecture | GPTNeoXForCausalLM |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.45.2 |
| Tokenizer Class | GPTNeoXTokenizer |
| Padding Token | <|pad|> |
| Vocabulary Size | 69586 |
| Torch Data Type | bfloat16 |
Best Alternatives to Pythia Chinese 70M UDN
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Pythia 70M Multi | 2K / 0.3 GB | 8 | 0 |
| Pythia 70m Sft | 2K / 0.3 GB | 19 | 0 |
| ...a 70M Deduped Cleansharegpt En | 2K / 0.3 GB | 2001 | 0 |
| Pythia 70M Deduped | 2K / 0.2 GB | 126337 | 25 |
| ...thia 70M Deduped Cleansharegpt | 2K / 0.3 GB | 2125 | 1 |
| Polish Wikipedia Model | 2K / 0.3 GB | 172 | 0 |
| My Awesome Eli5 Clm Model | 2K / 0.3 GB | 164 | 0 |
| Pythia 70M | 2K / 0.2 GB | 70119 | 63 |
| Chessdevilai | 2K / 0.3 GB | 58 | 0 |
| Pythia 70M Instruct | 2K / 0.3 GB | 66 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than zhaorui-nb/pythia-chinese-70m-UDN .
Rank the Pythia Chinese 70M UDN 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