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

Dlite V2 124M by aisquared

 »  All LLMs  »  aisquared  »  Dlite V2 124M   URL Share it on

  1400   
  Autotrain compatible Dataset:aisquared/databricks-d...   En   Endpoints compatible   Gpt2   Pytorch   Region:us
Model Card on HF 🤗: https://huggingface.co/aisquared/dlite-v2-124m 

Dlite V2 124M Benchmarks

ARC: 23.98 vs 96.7 (so35)-75.2%
HellaSwag: 31.1 vs 95.3 (gpt4)-67.4%
MMLU: 25.29 vs 88.3 (so35)-71.4%
TruthfulQA: 38.98 vs 59 (gpt4)-33.9%
WinoGrande: 50.43 vs 87.5 (gpt4)-42.4%
LLME Score: 0.14567
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Dlite V2 124M (aisquared/dlite-v2-124m)
🌟 Advertise your project 🚀

Dlite V2 124M Parameters and Internals

Model Type 
Large Language Model
Use Cases 
Limitations:
Factual inaccuracies, Biases, Offensive responses, Toxicity, Hallucinations
Considerations:
Exercise good judgment when applying this technology.
Additional Notes 
DLite is an experimental technology and is not designed for use in any environment without significant testing and safety consideration.
Supported Languages 
EN (NLP)
Training Details 
Data Sources:
Databricks' 'Dolly 15k' Dataset
Data Volume:
15k records
Methodology:
Fine-tuned on a single GPU
Hardware Used:
Single GPU
Input Output 
Performance Tips:
Including torch_dtype=torch.bfloat16 is generally recommended.
LLM NameDlite V2 124M
Repository 🤗https://huggingface.co/aisquared/dlite-v2-124m 
Model Size124m
Required VRAM0.3 GB
Updated2025-07-29
Maintaineraisquared
Model Typegpt2
Model Files  0.3 GB   0.0 GB
Supported Languagesen
Model ArchitectureGPT2LMHeadModel
Licenseapache-2.0
Model Max Length1024
Transformers Version4.25.1
Tokenizer ClassGPT2Tokenizer
Vocabulary Size50260
Torch Data Typefloat32
Activation Functiongelu_new

Best Alternatives to Dlite V2 124M

Best Alternatives
Context / RAM
Downloads
Likes
BrtGPT 124M Base0K / 0.4 GB7171
GPT2 124M Poetry RL0K / 0.5 GB7461
Gpt2 Final0K / 0.5 GB50
Filiberto 124M0K / 0.5 GB70
GPT2 Nepali 124M0K / 0.5 GB295
GPT2 Nepali 124M0K / 0.5 GB65
LaMini GPT 124M0K / 0.5 GB402322
Dlite V1 124M0K / 0.5 GB12740
Note: green Score (e.g. "73.2") means that the model is better than aisquared/dlite-v2-124m.

Rank the Dlite V2 124M 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? 50230 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 v20241124
  Support LLM Explorer