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

Flan T5 Xl Ct2 Int8 by jncraton

 »  All LLMs  »  jncraton  »  Flan T5 Xl Ct2 Int8   URL Share it on

  1   

Flan T5 Xl Ct2 Int8 is an open-source language model by jncraton. Features: LLM, VRAM: 2.9GB, License: apache-2.0, LLM Explorer Score: 0.08.

  Arxiv:1910.09700   Arxiv:2210.11416   Dataset:aqua rat   Dataset:deepmind/code contests   Dataset:djaym7/wiki dialog   Dataset:esnli   Dataset:gsm8k   Dataset:lambada   Dataset:qed   Dataset:quasc   Dataset:svakulenk0/qrecc   Dataset:taskmaster2   De   En   Endpoints compatible   Fr   Multilingual   Region:us   Ro
Model Card on HF 🤗: https://huggingface.co/jncraton/flan-t5-xl-ct2-int8 

Flan T5 Xl Ct2 Int8 Benchmarks

LLME Score: 0.08106
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Flan T5 Xl Ct2 Int8 (jncraton/flan-t5-xl-ct2-int8)
🌟 Advertise your project 🚀

Flan T5 Xl Ct2 Int8 Parameters and Internals

Model Type 
text2text-generation
Use Cases 
Areas:
Research
Applications:
Zero-shot NLP tasks, Few-shot learning NLP tasks
Limitations:
Model has not been tested in real world applications.
Additional Notes 
The model is fine-tuned with a focus on instruction-based tasks.
Supported Languages 
languages_supported (multilingual), specific_languages (English, Spanish, Japanese, Persian, Hindi, French, Chinese, Bengali, Gujarati, German, Telugu, Italian, Arabic, Polish, Tamil, Marathi, Malayalam, Oriya, Panjabi, Portuguese, Urdu, Galician, Hebrew, Korean, Catalan, Thai, Dutch, Indonesian, Vietnamese, Bulgarian, Filipino, Central Khmer, Lao, Turkish, Russian, Croatian, Swedish, Yoruba, Kurdish, Burmese, Malay, Czech, Finnish, Somali, Tagalog, Swahili, Sinhala, Kannada, Zhuang, Igbo, Xhosa, Romanian, Haitian, Estonian, Slovak, Lithuanian, Greek, Nepali, Assamese, Norwegian)
Training Details 
Data Sources:
Mixture of 1836 tasks
Data Volume:
Unknown
Methodology:
Fine-tuned with instructions for zero-shot and few-shot learning
Training Time:
Unknown
Hardware Used:
TPU v3 or TPU v4 pods
Model Architecture:
Based on pretrained T5
Safety Evaluation 
Ethical Considerations:
Flan-T5 is potentially vulnerable to generating inappropriate content or replicating biases in the underlying data.
Responsible Ai Considerations 
Fairness:
Biases in the training data may affect fairness.
Accountability:
Developers are accountable for the model's outputs.
Mitigation Strategies:
The model should not be used without assessing safety and fairness concerns.
Input Output 
Input Format:
Text input (e.g., 'translate English to German: How old are you?')
Accepted Modalities:
text
Output Format:
Text output (e.g., translation result)
LLM NameFlan T5 Xl Ct2 Int8
Repository 🤗https://huggingface.co/jncraton/flan-t5-xl-ct2-int8 
Required VRAM2.9 GB
Updated2026-03-24
Maintainerjncraton
Model Files  2.9 GB
Supported Languagesen fr ro de
Model ArchitectureAutoModel
Licenseapache-2.0
Model Max Length512
Tokenizer ClassT5Tokenizer
Padding Token<pad>

Best Alternatives to Flan T5 Xl Ct2 Int8

Best Alternatives
Context / RAM
Downloads
Likes
Distil Longformer Base 40964K / 0.4 GB360
Daedalus 11K /  GB91
Tiny Random Detr1K / 0.2 GB210
Opengpt2 Pytorch Backward1K / 6 GB41
Opengpt2 Pytorch Forward1K / 6 GB41
Finsent Transformer0.5K / 0.4 GB01
Simbert Chinese Base0.5K / 0.4 GB60
Bert Chinese L 12 H 768 A 120.5K / 0.4 GB11
Simbert Chinese Tiny0.5K / 0 GB50
Bert Tiny0.5K / 0 GB784113139
Note: green Score (e.g. "73.2") means that the model is better than jncraton/flan-t5-xl-ct2-int8.

Rank the Flan T5 Xl Ct2 Int8 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? 52473 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer