Pythia 1B Helpful Sft by lomahony

 ยป  All LLMs  ยป  lomahony  ยป  Pythia 1B Helpful Sft   URL Share it on

  Arxiv:2101.00027   Autotrain compatible   Dataset:anthropic/hh-rlhf   En   Endpoints compatible   Gpt neox   Pythia   Pytorch   Region:us   Safetensors

Pythia 1B Helpful Sft Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Pythia 1B Helpful Sft (lomahony/pythia-1b-helpful-sft)

Pythia 1B Helpful Sft Parameters and Internals

Model Type 
causal-lm
Use Cases 
Areas:
Research, Natural Language Processing
Training Details 
Data Sources:
Anthropic/hh-rlhf
Methodology:
Supervised finetuning using TRLx library for 1 epoch
LLM NamePythia 1B Helpful Sft
Repository ๐Ÿค—https://huggingface.co/lomahony/pythia-1b-helpful-sft 
Model Size1b
Required VRAM2 GB
Updated2025-03-25
Maintainerlomahony
Model Typegpt_neox
Model Files  2.0 GB   2.0 GB
Supported Languagesen
Model ArchitectureGPTNeoXForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.34.1
Tokenizer ClassGPTNeoXTokenizer
Padding Token<|padding|>
Vocabulary Size50304
Torch Data Typebfloat16

Best Alternatives to Pythia 1B Helpful Sft

Best Alternatives
Context / RAM
Downloads
Likes
Pythia 2.8B Deduped Rp 710M 4K4K / 11.7 GB111
Pythia 1.4B Deduped Rp 420M 4K4K / 6.1 GB121
Pythia 1.4B Deduped Rp 280M 4K4K / 6.1 GB101
...rAI Pythia 1B Deduped Sft Tldr2K / 4 GB72500
...eduped Tldr Preference Sft Trl2K / 2 GB140
Pythia 1B Deduped Tldr Sft2K / 2 GB2770
Pythia 1B Kto Iter02K / 2 GB340
Pythia 1B Self Kto Iter02K / 2 GB370
Rloo Trial22K / 2 GB80
TinyLM 1B Test22K / 2.7 GB270
Note: green Score (e.g. "73.2") means that the model is better than lomahony/pythia-1b-helpful-sft.

Rank the Pythia 1B Helpful Sft 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? 45595 in total.

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