Model Card on HF 🤗: https://huggingface.co/bradmin/ppo_model
Ppo Model 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 Model Parameters and Internals
| LLM Name | Ppo Model |
| Repository 🤗 | https://huggingface.co/bradmin/ppo_model |
| Required VRAM | 2.7 GB |
| Updated | 2025-06-09 |
| Maintainer | bradmin |
| Model Type | gpt_neox |
| Model Files | |
| Model Architecture | GPTNeoXForCausalLM |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.32.0 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 30080 |
| Torch Data Type | bfloat16 |
Best Alternatives to Ppo Model
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Catlm | 8K / 7.8 GB | 24 | 4 |
| ...Prover 14final Checkpoint 5830 | 4K / 14.9 GB | 24 | 0 |
| Neox Musenet Untrained | 4K / 7.3 GB | 14 | 0 |
| Stabillm Instruct De | 4K / 31.8 GB | 14 | 0 |
| Open Calm Large | 2K / 1.8 GB | 1657 | 11 |
| MonoCoder OMP | 2K / 3.6 GB | 466 | 0 |
| KULLM RLHF | 2K / 25.8 GB | 1571 | 3 |
| Open Calm Small | 2K / 0.4 GB | 3298 | 19 |
| Step3 Mk7 | 2K / 25.8 GB | 25 | 0 |
| Llm Rlhf | 2K / 25.8 GB | 19 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than bradmin/ppo_model .
Rank the Ppo Model 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