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

Telugu Gemma 7B Finetuned Sft by Telugu-LLM-Labs

 »  All LLMs  »  Telugu-LLM-Labs  »  Telugu Gemma 7B Finetuned Sft   URL Share it on

  0   
Base model:finetune:google/gem...   Base model:google/gemma-7b Dataset:telugu-llm-labs/telugu... Dataset:telugu-llm-labs/telugu...   En   Endpoints compatible   Finetuned   Instruct   Lora   Region:us   Safetensors   Te
Model Card on HF 🤗: https://huggingface.co/Telugu-LLM-Labs/Telugu-gemma-7b-finetuned-sft 

Telugu Gemma 7B Finetuned Sft Benchmarks

LLME Score: 0.14097
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Telugu Gemma 7B Finetuned Sft (Telugu-LLM-Labs/Telugu-gemma-7b-finetuned-sft)
🌟 Advertise your project 🚀

Telugu Gemma 7B Finetuned Sft Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
text generation
Applications:
instruction-following tasks
Additional Notes 
The model currently supports Telugu text generation with upcoming updates for transliteration. Inference can be done using unsloth or HuggingFace library.
Supported Languages 
en (English), te (Telugu)
Training Details 
Data Sources:
yahma_alpaca_cleaned_telugu_filtered_and_romanized, teknium_GPTeacher_general_instruct_telugu_filtered_and_romanized
Methodology:
LoRA finetuning using unsloth library
Context Length:
2048
Input Output 
Input Format:
### Instruction: {instruction} ### Input: {input} ## Response: {response}
Accepted Modalities:
text
Output Format:
string/text
Performance Tips:
Use specific libraries for faster inference, e.g., unsloth or HuggingFace
LLM NameTelugu Gemma 7B Finetuned Sft
Repository 🤗https://huggingface.co/Telugu-LLM-Labs/Telugu-gemma-7b-finetuned-sft 
Base Model(s)  Gemma 7B   google/gemma-7b
Model Size7b
Required VRAM0.8 GB
Updated2025-09-23
MaintainerTelugu-LLM-Labs
Instruction-BasedYes
Model Files  0.8 GB
Supported Languageste en
Model ArchitectureAutoModel
Licenseother
Model Max Length8192
Is Biasednone
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Moduleso_proj|k_proj|v_proj|gate_proj|down_proj|up_proj|q_proj
LoRA Alpha128
LoRA Dropout0
R Param64

Best Alternatives to Telugu Gemma 7B Finetuned Sft

Best Alternatives
Context / RAM
Downloads
Likes
... 7b 448 Qinstruct Preview V0.12K / 17.3 GB244
Autotrain Z7uyk Cwqtz0K / 0.2 GB70
Qwen 2.5 7B 1M RRP V1 Lora0K / 0.2 GB03
...2.5 7B Instruct Abliterated V30K / 0.2 GB01
Medical Mixtral 7B V2k0K / 0.4 GB80
Mistral 7B Instruct V0.2 ONNX0K /  GB316
...emma 7B Finetuned Sft Navarasa0K / 0.8 GB09
...l 7B Instructv0.2 Finetuned V20K / 0 GB3836
...tral 7B Instruct V0.1 Int8 Ct20K / 7.2 GB52
...tral 7B Instruct V0.1 Ct2 Int80K / 7.2 GB52
Note: green Score (e.g. "73.2") means that the model is better than Telugu-LLM-Labs/Telugu-gemma-7b-finetuned-sft.

Rank the Telugu Gemma 7B Finetuned Sft 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? 51544 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