LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Fbopt 350M 8bit by yec019

 »  All LLMs  »  yec019  »  Fbopt 350M 8bit   URL Share it on

  4153   
  8-bit   8bit   Autotrain compatible   Bitsandbytes   Endpoints compatible   Opt   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/yec019/fbopt-350m-8bit 

Fbopt 350M 8bit Benchmarks

ARC: 23.55 vs 96.7 (so35)-75.6%
HellaSwag: 36.6 vs 95.3 (gpt4)-61.6%
MMLU: 26.22 vs 88.3 (so35)-70.3%
TruthfulQA: 40.97 vs 59 (gpt4)-30.6%
WinoGrande: 52.64 vs 87.5 (gpt4)-39.8%
GSM8K: 1.29 vs 96.4 (so35)-98.7%
LLME Score: 0.22298
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Fbopt 350M 8bit (yec019/fbopt-350m-8bit)

Fbopt 350M 8bit Parameters and Internals

Additional Notes 
This model is for testing the effect of quantization, specifically with 8-bit quantization by bitsandbytes. Part of the UCSD 23Fall 240D course project.
LLM NameFbopt 350M 8bit
Repository 🤗https://huggingface.co/yec019/fbopt-350m-8bit 
Model Size350m
Required VRAM0.4 GB
Updated2025-03-15
Maintaineryec019
Model Typeopt
Model Files  0.4 GB
Quantization Type8bit
Model ArchitectureOPTForCausalLM
Licenseunknown
Context Length2048
Model Max Length2048
Transformers Version4.36.0.dev0
Tokenizer ClassGPT2Tokenizer
Padding Token<pad>
Vocabulary Size50272
Torch Data Typefloat16
Activation Functionrelu
Errorsreplace

Best Alternatives to Fbopt 350M 8bit

Best Alternatives
Context / RAM
Downloads
Likes
Ov Opt 350M 8bit Kv Cache2K / 0.4 GB181
Opt Mini Dataset 02K / 0.7 GB590
Facebook Opt 350M SFT Korz142K / 0.7 GB440
Temp Model Sft2K / 1.3 GB260
Gpt350 Chat S V0 12K / 0.7 GB710
Gpt350 Chat S V02K / 0.7 GB680
Dadjokes Tuned Opt2K / 1.3 GB802
Opt 350M2K / 0.7 GB497507139
Sunday2K / 1.3 GB1560
Remedycure2K / 1.3 GB1550

Rank the Fbopt 350M 8bit 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! 🌟

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? 45097 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227
  Support LLM Explorer