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

OpenHathi 7B Hi V0.1 Base by sarvamai

 »  All LLMs  »  sarvamai  »  OpenHathi 7B Hi V0.1 Base   URL Share it on

  3100   
  Autotrain compatible   Endpoints compatible   Gguf   Hi   Llama   Q4   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/sarvamai/OpenHathi-7B-Hi-v0.1-Base 

OpenHathi 7B Hi V0.1 Base Benchmarks

MMLU Pro: 6.04
GPQA: 0.45
MUSR: 5.03
BBH: 7.65
IFEval: 18.04 vs 88 (so35)-79.5%
ARC: 49.49 vs 96.7 (so35)-48.8%
HellaSwag: 74.34 vs 95.3 (gpt4)-22%
MMLU: 41.38 vs 88.3 (so35)-53.1%
TruthfulQA: 37.46 vs 59 (gpt4)-36.5%
WinoGrande: 71.27 vs 87.5 (gpt4)-18.5%
GSM8K: 5.91 vs 96.4 (so35)-93.9%
MATH Lvl 5: 0.83
LLME Score: 0.20784
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
OpenHathi 7B Hi V0.1 Base (sarvamai/OpenHathi-7B-Hi-v0.1-Base)
🌟 Advertise your project 🚀

OpenHathi 7B Hi V0.1 Base Parameters and Internals

Model Type 
Causal Language Model
Use Cases 
Areas:
Research, Commercial Applications
Limitations:
This is a base model and not meant to be used as is
Considerations:
Recommended to finetune on specific tasks.
Supported Languages 
Hindi (proficient), English (proficient), Hinglish (proficient)
Training Details 
Data Sources:
Hindi, English, and Hinglish texts
Methodology:
Based on Llama2
Input Output 
Accepted Modalities:
text
Output Format:
text
LLM NameOpenHathi 7B Hi V0.1 Base
Repository 🤗https://huggingface.co/sarvamai/OpenHathi-7B-Hi-v0.1-Base 
Base Model(s)  shuvom/OpenHathi-7B-FT-v0.1_SI   shuvom/OpenHathi-7B-FT-v0.1_SI
Model Size7b
Required VRAM13.8 GB
Updated2025-08-20
Maintainersarvamai
Model Typellama
Model Files  3.9 GB   4.3 GB   5.0 GB: 1-of-3   5.0 GB: 2-of-3   3.8 GB: 3-of-3
Supported Languageshi
GGUF QuantizationYes
Quantization Typeq4|gguf
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.35.0
Tokenizer ClassLlamaTokenizer
Padding Token[PAD]
Vocabulary Size48064
Torch Data Typebfloat16

Best Alternatives to OpenHathi 7B Hi V0.1 Base

Best Alternatives
Context / RAM
Downloads
Likes
Lucie 7B Instruct31K / 13.4 GB411520
Lucie 7B Instruct Human Data31K / 13.4 GB1646
Lucie 7B Instruct Gguf31K / 4.1 GB15684
Sqlcoder 7B 216K / 13.5 GB34629378
Llm Compiler 7B Ftd GGUF16K / 2.5 GB9080
Llm Compiler 7B GGUF16K / 2.5 GB521
Llm Compiler 7B Ftd GGUF16K / 2.5 GB230
Llm Compiler 7B GGUF16K / 2.5 GB90
Bachinstruct Codellama7b16K / 13.5 GB191
Musicllm16K / 13.5 GB120
Note: green Score (e.g. "73.2") means that the model is better than sarvamai/OpenHathi-7B-Hi-v0.1-Base.

Rank the OpenHathi 7B Hi V0.1 Base 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? 50767 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