Ppo Tldr by vwxyzjn

 ยป  All LLMs  ยป  vwxyzjn  ยป  Ppo Tldr   URL Share it on

  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 ๐Ÿค—: 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").
Ppo Tldr (vwxyzjn/ppo_tldr)

Ppo Tldr Parameters and Internals

Training Details 
Hardware Used:
multi-GPU
LLM NamePpo Tldr
Repository ๐Ÿค—https://huggingface.co/vwxyzjn/ppo_tldr 
Base Model(s)  ...rAI Pythia 1B Deduped Sft Tldr   cleanrl/EleutherAI_pythia-1b-deduped__sft__tldr
Model Size1b
Required VRAM2 GB
Updated2025-02-22
Maintainervwxyzjn
Model Typegpt_neox
Model Files  2.0 GB   0.0 GB
Model ArchitectureGPTNeoXForCausalLM
Context Length2048
Model Max Length2048
Transformers Version4.40.1
Tokenizer ClassGPTNeoXTokenizer
Padding Token[PAD]
Vocabulary Size50304
Torch Data Typebfloat16

Best Alternatives to Ppo Tldr

Best Alternatives
Context / RAM
Downloads
Likes
Pythia 2.8B Deduped Rp 710M 4K4K / 11.7 GB21
Pythia 1.4B Deduped Rp 420M 4K4K / 6.1 GB71
Pythia 1.4B Deduped Rp 280M 4K4K / 6.1 GB71
...eduped Tldr Preference Sft Trl2K / 2 GB140
...rAI Pythia 1B Deduped Sft Tldr2K / 4 GB43950
Pythia 1B Kto Iter02K / 2 GB1540
Pythia 1B Deduped Tldr Sft2K / 2 GB3600
Pythia 1B Self Kto Iter02K / 2 GB1510
Rloo Trial22K / 2 GB80
TinyLM 1B Test22K / 2.7 GB610
Note: green Score (e.g. "73.2") means that the model is better than vwxyzjn/ppo_tldr.

Rank the Ppo Tldr Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 43470 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227