Autotrain compatible Base model:cleanrl/eleutherai ... Base model:finetune:cleanrl/el... Conversational Endpoints compatible Generated from trainer Gpt neox Region:us Safetensors Tensorboard
Model Card on HF 🤗: https://huggingface.co/vwxyzjn/ppo_tldr
Ppo Tldr 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 Tldr Parameters and Internals
| Training Details |
|
| LLM Name | Ppo Tldr |
| Repository 🤗 | https://huggingface.co/vwxyzjn/ppo_tldr |
| Base Model(s) | |
| Model Size | 1b |
| Required VRAM | 2 GB |
| Updated | 2025-02-22 |
| Maintainer | vwxyzjn |
| Model Type | gpt_neox |
| Model Files | |
| Model Architecture | GPTNeoXForCausalLM |
| 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 Tldr
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Pythia 2.8B Deduped Rp 710M 4K | 4K / 11.7 GB | 2 | 1 |
| Pythia 1.4B Deduped Rp 420M 4K | 4K / 6.1 GB | 7 | 1 |
| Pythia 1.4B Deduped Rp 280M 4K | 4K / 6.1 GB | 7 | 1 |
| ...eduped Tldr Preference Sft Trl | 2K / 2 GB | 14 | 0 |
| ...rAI Pythia 1B Deduped Sft Tldr | 2K / 4 GB | 4395 | 0 |
| Pythia 1B Kto Iter0 | 2K / 2 GB | 154 | 0 |
| Pythia 1B Deduped Tldr Sft | 2K / 2 GB | 360 | 0 |
| Pythia 1B Self Kto Iter0 | 2K / 2 GB | 151 | 0 |
| Rloo Trial2 | 2K / 2 GB | 8 | 0 |
| TinyLM 1B Test2 | 2K / 2.7 GB | 61 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than vwxyzjn/ppo_tldr .
Rank the Ppo Tldr 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