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

Dlite V1 124M by aisquared

 »  All LLMs  »  aisquared  »  Dlite V1 124M   URL Share it on

  1981   
  Autotrain compatible   Dataset:tatsu-lab/alpaca   En   Endpoints compatible   Gpt2   Pytorch   Region:us
Model Card on HF 🤗: https://huggingface.co/aisquared/dlite-v1-124m 

Dlite V1 124M Benchmarks

ARC: 24.32 vs 96.7 (so35)-74.9%
HellaSwag: 31.16 vs 95.3 (gpt4)-67.3%
MMLU: 25.08 vs 88.3 (so35)-71.6%
TruthfulQA: 36.38 vs 59 (gpt4)-38.3%
WinoGrande: 50.2 vs 87.5 (gpt4)-42.6%
LLME Score: 0.15978
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Dlite V1 124M (aisquared/dlite-v1-124m)

Dlite V1 124M Parameters and Internals

Model Type 
Large Language Model
Use Cases 
Limitations:
Not a state-of-the-art model, Experimental model, Can exhibit undesired behaviors: factual inaccuracies, biases, offensive responses, toxicity, and hallucinations
Considerations:
Exercise good judgment when applying this technology.
Additional Notes 
Model not suitable for environments other than research purposes.
Supported Languages 
EN (English)
Training Details 
Data Sources:
tatsu-lab/alpaca
Data Volume:
50k records
Methodology:
Fine-tuning on GPT-2
Hardware Used:
Single T4 GPU
Model Architecture:
Derived from GPT-2
Input Output 
Performance Tips:
Including `torch_dtype=torch.bfloat16` is generally recommended to reduce memory usage.
LLM NameDlite V1 124M
Repository 🤗https://huggingface.co/aisquared/dlite-v1-124m 
Model Size124m
Required VRAM0.5 GB
Updated2025-02-22
Maintaineraisquared
Model Typegpt2
Model Files  0.5 GB   0.0 GB
Supported Languagesen
Model ArchitectureGPT2LMHeadModel
Licenseapache-2.0
Model Max Length1024
Transformers Version4.25.1
Tokenizer ClassGPT2Tokenizer
Vocabulary Size50257
Torch Data Typefloat32
Activation Functiongelu_new

Best Alternatives to Dlite V1 124M

Best Alternatives
Context / RAM
Downloads
Likes
GPT2 124M Poetry RL0K / 0.5 GB130
Gpt2 Final0K / 0.5 GB1680
Filiberto 124M0K / 0.5 GB1250
GPT2 Nepali 124M0K / 0.5 GB123
LaMini GPT 124M0K / 0.5 GB324322
Dlite V2 124M0K / 0.3 GB24436
Note: green Score (e.g. "73.2") means that the model is better than aisquared/dlite-v1-124m.

Rank the Dlite V1 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? 43470 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