Autotrain compatible Base model:eleutherai/pythia-1... Base model:finetune:eleutherai... Conversational Endpoints compatible Generated from trainer Gpt neox Region:us Safetensors Tensorboard
Model Card on HF 🤗: https://huggingface.co/kashif/ppo
Ppo 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)
Ppo Parameters and Internals
| LLM Name | Ppo |
| Repository 🤗 | https://huggingface.co/kashif/ppo |
| Base Model(s) | |
| Model Size | 160m |
| Required VRAM | 0.3 GB |
| Updated | 2025-06-09 |
| Maintainer | kashif |
| Model Type | gpt_neox |
| Model Files | |
| Model Architecture | GPTNeoXForCausalLM |
| License | apache-2.0 |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.40.1 |
| Tokenizer Class | GPTNeoXTokenizer |
| Padding Token | [PAD] |
| Vocabulary Size | 50304 |
| Torch Data Type | bfloat16 |
Best Alternatives to Ppo
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Pythia 160M C2s | 8K / 0.6 GB | 51 | 6 |
| Pythia 160M Xsum Roya | 2K / 0.6 GB | 66 | 0 |
| Pythia 160M | 2K / 0.4 GB | 143741 | 32 |
| Pythia 160m Sft | 2K / 0 GB | 28 | 0 |
| Sheared Pythia 160M | 2K / 0.7 GB | 16 | 4 |
| Pythia 160M Dolphin Extended | 2K / 0.3 GB | 33 | 0 |
| Pythia 160M Storytelling | 2K / 0.3 GB | 13 | 0 |
| Pythia 160M Deduped | 2K / 0.4 GB | 40252 | 3 |
| Pythia160m Sft Tldr | 2K / 0.6 GB | 20 | 0 |
| Pythia 160m Ft CookingRecipes | 2K / 0.6 GB | 11 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than kashif/ppo .
Rank the Ppo 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? 48046 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124