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

Distilgpt2 Nepali Single Qs Generator by Bibek1129

 »  All LLMs  »  Bibek1129  »  Distilgpt2 Nepali Single Qs Generator   URL Share it on

  0   

Distilgpt2 Nepali Single Qs Generator is an open-source language model by Bibek1129. Features: LLM, License: apache-2.0, LLM Explorer Score: 0.12.

  Adapter Base model:adapter:sakonii/dis... Base model:sakonii/distilgpt2-... Dataset:bibek1129/nepali squad...   Finetuned   Lora   Ne   Peft   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/Bibek1129/distilgpt2-nepali-single-qs-generator 

Distilgpt2 Nepali Single Qs Generator Benchmarks

LLME Score: 0.12334
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Distilgpt2 Nepali Single Qs Generator (Bibek1129/distilgpt2-nepali-single-qs-generator)
🌟 Advertise your project 🚀

Distilgpt2 Nepali Single Qs Generator Parameters and Internals

Model Type 
distilgpt2, text generation
Additional Notes 
The model is specifically fine-tuned for generating questions in Nepali based on given context.
Supported Languages 
Nepali (NLP (Natural Language Processing))
Training Details 
Data Sources:
Bibek1129/nepali_SQuAD_single_qsn
Methodology:
The dataset is created by converting SQuAD dataset to nepali using Nepali_nlp and trained with the lora config (rank=32,lora_alpha=64) with 512 tokens per instance, 4 instances per batch, and around 118.1K training steps.
Context Length:
512
LLM NameDistilgpt2 Nepali Single Qs Generator
Repository 🤗https://huggingface.co/Bibek1129/distilgpt2-nepali-single-qs-generator 
Base Model(s)  Distilgpt2 Nepali   Sakonii/distilgpt2-nepali
Required VRAM0 GB
Updated2026-01-20
MaintainerBibek1129
Model Files  0.2 GB   0.0 GB   0.0 GB   0.0 GB
Supported Languagesne
Model ArchitectureAdapter
Licenseapache-2.0
Model Max Length512
Is Biasednone
Tokenizer ClassXLMRobertaTokenizer
Padding Token</s>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Moduleslm_head|c_proj|c_fc|c_attn
LoRA Alpha64
LoRA Dropout0.05
R Param32

Best Alternatives to Distilgpt2 Nepali Single Qs Generator

Best Alternatives
Context / RAM
Downloads
Likes
Phi 3 Mini 4K Instruct Sa V0.10K / 0 GB50
Nemo Kimi Lora0K / 1.8 GB90
Nemo Books Lora 40K / 1.8 GB110
Nemo Books Lora0K / 1.8 GB100
Francois KTO Lora0K / 0 GB110
Francois KTO Lora0K / 0 GB60
Reflection Model0K / 0.2 GB01
Rei V2 Kto0K / 0 GB130
...caaaf043da230d9a30d8e0ddcbe8790K / 0.4 GB110
...357cade9cc1096cecc35c34dba89920K / 1.3 GB100
Note: green Score (e.g. "73.2") means that the model is better than Bibek1129/distilgpt2-nepali-single-qs-generator.

Rank the Distilgpt2 Nepali Single Qs Generator 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? 52721 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