Pythia 6.9B Deduped Synthetic Instruct by lambdalabs

 ยป  All LLMs  ยป  lambdalabs  ยป  Pythia 6.9B Deduped Synthetic Instruct   URL Share it on

  Autotrain compatible Dataset:dahoas/synthetic-instr...   En   Endpoints compatible   Gpt neox   Instruct   Pythia   Pytorch   Region:us   Sharded

Pythia 6.9B Deduped Synthetic Instruct Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Pythia 6.9B Deduped Synthetic Instruct (lambdalabs/pythia-6.9b-deduped-synthetic-instruct)

Pythia 6.9B Deduped Synthetic Instruct Parameters and Internals

Model Type 
Transformer-based Language Model
Use Cases 
Areas:
Research, Commercial Applications
Primary Use Cases:
Text generation
Additional Notes 
Model specifically finetuned on synthetic instruction-following dataset.
Supported Languages 
English (Fluent)
Training Details 
Data Sources:
Dahoas/synthetic-instruct-gptj-pairwise
Methodology:
Finetuning
Training Time:
6 hours
Hardware Used:
8x A100 80GB GPUs
Model Architecture:
Transformer
Input Output 
Accepted Modalities:
text
Output Format:
text
LLM NamePythia 6.9B Deduped Synthetic Instruct
Repository ๐Ÿค—https://huggingface.co/lambdalabs/pythia-6.9b-deduped-synthetic-instruct 
Model Size6.9b
Required VRAM27.5 GB
Updated2025-02-23
Maintainerlambdalabs
Model Typegpt_neox
Instruction-BasedYes
Model Files  9.9 GB: 1-of-3   9.8 GB: 2-of-3   7.8 GB: 3-of-3
Supported Languagesen
Model ArchitectureGPTNeoXForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.25.1
Tokenizer ClassGPTNeoXTokenizer
Vocabulary Size50278
Torch Data Typefloat32

Best Alternatives to Pythia 6.9B Deduped Synthetic Instruct

Best Alternatives
Context / RAM
Downloads
Likes
Open Instruct Pythia 6.9B Tulu2K / 27.6 GB21935
Note: green Score (e.g. "73.2") means that the model is better than lambdalabs/pythia-6.9b-deduped-synthetic-instruct.

Rank the Pythia 6.9B Deduped Synthetic Instruct 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? 43508 in total.

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