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 Qcqa Ub 6 Best For Q Loss by xformAI

 »  All LLMs  »  xformAI  »  Facebook Opt 125M Qcqa Ub 6 Best For Q Loss   URL Share it on

  24   
  Autotrain compatible   En   Endpoints compatible   Opt   Pytorch   Region:us
Model Card on HF 🤗: https://huggingface.co/xformAI/facebook-opt-125m-qcqa-ub-6-best-for-q-loss 

Facebook Opt 125M Qcqa Ub 6 Best For Q Loss Benchmarks

ARC: 23.29 vs 96.7 (so35)-75.9%
HellaSwag: 25.57 vs 95.3 (gpt4)-73.2%
MMLU: 23.15 vs 88.3 (so35)-73.8%
TruthfulQA: 49.03 vs 59 (gpt4)-16.9%
WinoGrande: 49.17 vs 87.5 (gpt4)-43.8%
LLME Score: 0.19975
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 Qcqa Ub 6 Best For Q Loss (xformAI/facebook-opt-125m-qcqa-ub-6-best-for-q-loss)

Facebook Opt 125M Qcqa Ub 6 Best For Q Loss Parameters and Internals

Model Type 
transformers, quality-concerned query-aware question answering (QCQA)
Additional Notes 
The model is a QCQA version maintaining the original MHA architecture with modified K/V heads for efficiency.
Supported Languages 
en (proficient)
LLM NameFacebook Opt 125M Qcqa Ub 6 Best For Q Loss
Repository 🤗https://huggingface.co/xformAI/facebook-opt-125m-qcqa-ub-6-best-for-q-loss 
Model Size125m
Required VRAM0.5 GB
Updated2025-04-30
MaintainerxformAI
Model Typeopt
Model Files  0.5 GB
Supported Languagesen
Model ArchitectureOPTForCausalLM
Licensemit
Context Length2048
Model Max Length2048
Transformers Version4.26.1
Tokenizer ClassGPT2Tokenizer
Beginning of Sentence Token</s>
End of Sentence Token</s>
Unk Token</s>
Vocabulary Size50272
Torch Data Typefloat32
Activation Functionrelu
Errorsreplace

Best Alternatives to Facebook Opt 125M Qcqa Ub 6 Best For Q Loss

Best Alternatives
Context / RAM
Downloads
Likes
...5M Qcqa Ub 6 Best For KV Cache2K / 0.5 GB380
...25M Gqa Ub 6 Best For KV Cache2K / 0.5 GB300
Opt 125M2K / 0.3 GB6448507198
Galactica 125M Cot2K / 0.5 GB60
Galactica Ref2K / 0.5 GB130
Galactica 125M DPO Pos2K / 0.5 GB130
Galactica 125M DPO2K / 0.5 GB120
BertQA2K / 0.5 GB60
BertQA2K / 0.5 GB50
Opt 125M Quantized Brevitas2K /  GB50
Note: green Score (e.g. "73.2") means that the model is better than xformAI/facebook-opt-125m-qcqa-ub-6-best-for-q-loss.

Rank the Facebook Opt 125M Qcqa Ub 6 Best For Q Loss 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? 46860 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