Marathi GPT Gemma 2B by l3cube-pune

 »  All LLMs  »  l3cube-pune  »  Marathi GPT Gemma 2B   URL Share it on

  Arxiv:2205.14728   Autotrain compatible   Endpoints compatible   Gemma   Mr   Region:us   Safetensors   Sharded   Tensorflow

Marathi GPT Gemma 2B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Marathi GPT Gemma 2B Parameters and Internals

Model Type 
Gemma, text generation
Additional Notes 
This is part of the MahaNLP initiative. More details coming soon.
Supported Languages 
Marathi (high)
Training Details 
Data Sources:
translated Marathi datasets
Methodology:
LoRA fine-tuning
Input Output 
Input Format:
\n### Instruction:\nमहाराष्ट्राची राजधानी काय आहे?\n\n### Input:\n\n\n### Response:\n
Accepted Modalities:
text
Output Format:
text
LLM NameMarathi GPT Gemma 2B
Repository 🤗https://huggingface.co/l3cube-pune/marathi-gpt-gemma-2b 
Model Size2b
Required VRAM9 GB
Updated2025-09-23
Maintainerl3cube-pune
Model Typegemma
Model Files  4.9 GB: 1-of-2   4.1 GB: 2-of-2
Supported Languagesmr
Model ArchitectureGemmaForCausalLM
Licensecc-by-4.0
Context Length8192
Model Max Length8192
Transformers Version4.38.2
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typefloat16

Best Alternatives to Marathi GPT Gemma 2B

Best Alternatives
Context / RAM
Downloads
Likes
Gemma 1.1 2B It8K / 5.1 GB250244167
Gita SastraGPT V18K / 5.1 GB271
Codegemma 2B8K / 5.1 GB2353986
Caca Tinny 2B V38K / 5.1 GB41
Pandas Tutor Gemma 2B8K / 5.1 GB91
Gemma Qlora Customer Support8K / 5.1 GB90
Octopus V28K / 5.1 GB1387885
Octopus V28K / 5.1 GB1349889
... 2B Finetuned Sft Navarasa 2.08K / 10 GB125325
Gemma Ko 1.1 2B It8K / 5.1 GB6481
Note: green Score (e.g. "73.2") means that the model is better than l3cube-pune/marathi-gpt-gemma-2b.

Rank the Marathi GPT Gemma 2B 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? 51534 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124