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

Facebook Opt 125M HQQ 1bit Smashed by PrunaAI

 »  All LLMs  »  PrunaAI  »  Facebook Opt 125M HQQ 1bit Smashed   URL Share it on

  5   
  1bit   Autotrain compatible   Endpoints compatible   Opt   Pruna-ai   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/PrunaAI/facebook-opt-125m-HQQ-1bit-smashed 

Facebook Opt 125M HQQ 1bit Smashed Benchmarks

LLME Score: 0.16553
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Facebook Opt 125M HQQ 1bit Smashed (PrunaAI/facebook-opt-125m-HQQ-1bit-smashed)

Facebook Opt 125M HQQ 1bit Smashed Parameters and Internals

Additional Notes 
Metrics include memory_disk, memory_inference, inference_latency, inference_throughput, inference_CO2_emissions, inference_energy_consumption. Calibration data if needed, was WikiText.
Training Details 
Data Sources:
WikiText
Methodology:
hqq compression
Hardware Used:
NVIDIA A100-PCIE-40GB
Input Output 
Performance Tips:
We recommend testing efficiency gains directly in use-cases.
LLM NameFacebook Opt 125M HQQ 1bit Smashed
Repository 🤗https://huggingface.co/PrunaAI/facebook-opt-125m-HQQ-1bit-smashed 
Model Size125m
Required VRAM0.1 GB
Updated2025-05-15
MaintainerPrunaAI
Model Typeopt
Model Files  0.1 GB
Quantization Type1bit
Model ArchitectureOPTForCausalLM
Context Length2048
Model Max Length2048
Transformers Version4.37.1
Vocabulary Size50272
Torch Data Typefloat16
Activation Functionrelu

Best Alternatives to Facebook Opt 125M HQQ 1bit Smashed

Best Alternatives
Context / RAM
Downloads
Likes
...book Opt 125M HQQ 2bit Smashed2K / 0.1 GB121
Opt 125M Bnb 4bit2K / 0.1 GB26842
Opt 125M Gptq2K / 0.1 GB30680
...5M Qcqa Ub 6 Best For KV Cache2K / 0.5 GB220
...125M Qcqa Ub 6 Best For Q Loss2K / 0.5 GB80
...25M Gqa Ub 6 Best For KV Cache2K / 0.5 GB120
Opt 125M2K / 0.3 GB6927948198
Opt 125M Gptq2K / 0.1 GB50
Quantized Opt 125M2K / 0.2 GB160
Galactica 125M Cot2K / 0.5 GB160
Note: green Score (e.g. "73.2") means that the model is better than PrunaAI/facebook-opt-125m-HQQ-1bit-smashed.

Rank the Facebook Opt 125M HQQ 1bit Smashed 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? 47368 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