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

Opt Flan Iml 6.7B by MayaPH

 »  All LLMs  »  MayaPH  »  Opt Flan Iml 6.7B   URL Share it on

  1249   
  Arxiv:2212.12017   Autotrain compatible   Cot   Dataset:sirneural/flan v2   Instruct   Instruction   Opt   Pytorch   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/MayaPH/opt-flan-iml-6.7b 

Opt Flan Iml 6.7B Benchmarks

ARC: 30.12 vs 96.7 (so35)-68.9%
HellaSwag: 58.82 vs 95.3 (gpt4)-38.3%
MMLU: 25.12 vs 88.3 (so35)-71.6%
TruthfulQA: 36.74 vs 59 (gpt4)-37.7%
WinoGrande: 64.25 vs 87.5 (gpt4)-26.6%
LLME Score: 0.1908
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Opt Flan Iml 6.7B (MayaPH/opt-flan-iml-6.7b)

Opt Flan Iml 6.7B Parameters and Internals

Model Type 
Instruction Meta-Learning, Text Generation
Use Cases 
Areas:
Research, Commercial
Applications:
Text Generation, General AI Tasks
Primary Use Cases:
Instruction Following, Task Automation
Limitations:
Low performance on GSM8K benchmark
Supported Languages 
English (Unknown proficiency)
Training Details 
Data Sources:
FLAN v2
Methodology:
Fine-tuning
Model Architecture:
Patterned after OPT + Instruction Meta-Learning
Input Output 
Input Format:
Text Prompt
Accepted Modalities:
Text
Output Format:
Text
Performance Tips:
Use torch.float16 for faster processing and ensure correct tokenizer.
LLM NameOpt Flan Iml 6.7B
Repository 🤗https://huggingface.co/MayaPH/opt-flan-iml-6.7b 
Model Size6.7b
Required VRAM26.6 GB
Updated2024-12-22
MaintainerMayaPH
Model Typeopt
Instruction-BasedYes
Model Files  10.0 GB: 1-of-3   9.9 GB: 2-of-3   6.7 GB: 3-of-3   10.0 GB: 1-of-3   9.9 GB: 2-of-3   6.7 GB: 3-of-3
Model ArchitectureOPTForCausalLM
Licensecc-by-sa-4.0
Context Length2048
Model Max Length2048
Transformers Version4.32.0.dev0
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 Opt Flan Iml 6.7B

Best Alternatives
Context / RAM
Downloads
Likes
Galactica 6.7B EssayWriter2K / 13.4 GB11563
...lactica 6.7B Evol Instruct 70K2K / 27.4 GB124419
OPI Galactica 6.7B2K / 13.4 GB5614
Ev Glaive Math12K / 27.4 GB110
Ev Glaive Math2K / 27.4 GB100
Open Instruct Opt 6.7B Tulu2K / 26.6 GB252
LongForm OPT 6.7B2K / 13.3 GB214
...PT 6.7B Erebus Instruct Follow2K / 13.8 GB163
Note: green Score (e.g. "73.2") means that the model is better than MayaPH/opt-flan-iml-6.7b.

Rank the Opt Flan Iml 6.7B 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? 40066 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 v20241217
  Support LLM Explorer