AI4Bharat / IndicLLMSuite
A blueprint for creating Pretraining and Fine-Tuning datasets for Indic languages
☆106Updated 7 months ago
Alternatives and similar repositories for IndicLLMSuite
Users that are interested in IndicLLMSuite are comparing it to the libraries listed below
Sorting:
- Code repository for "Introducing Airavata: Hindi Instruction-tuned LLM"☆59Updated 6 months ago
- Pretraining, fine-tuning and evaluation scripts for IndicBERT-v2 and IndicXTREME☆94Updated last month
- Repository for fine-tuning gemma models using unsloth for indic languages☆92Updated last year
- Translation models for 22 scheduled languages of India☆312Updated last week
- A simple, consistent and extendable toolkit for IndicTrans2☆26Updated last week
- This repository contains the code for dataset curation and finetuning of instruct variant of the Bilingual OpenHathi model. The resultin…☆23Updated last year
- ☆30Updated last year
- A lightweight evaluation suite tailored specifically for assessing Indic LLMs across a diverse range of tasks☆35Updated 11 months ago
- Chitralekha - A video transcreation platform for Indic languages, supporting transcription, translation and voice-over☆101Updated 4 months ago
- lancedb-myntra-fashion-search☆27Updated last year
- Shoonya - Platform to Annotate and label data at scale.☆54Updated 8 months ago
- Official repo for the paper PHUDGE: Phi-3 as Scalable Judge. Evaluate your LLMs with or without custom rubric, reference answer, absolute…☆49Updated 10 months ago
- indicTranslate v1 - Machine Translation for 11 Indic languages. For latest v2, check: https://github.com/AI4Bharat/IndicTrans2☆127Updated last year
- A pipeline for transliteration, spell correction, POS tagging and word sense disambiguation of Hinglish code mixed data to Hindi Devanaga…☆36Updated last year
- ☆27Updated last year
- Transliteration models for 21 Indic languages☆89Updated last year
- A open-source framework designed to adapt pre-trained Language Models (LLMs), such as Llama, Mistral, and Mixtral, to a wide array of dom…☆14Updated 11 months ago
- Generate large textual corpora for almost any language by crawling the web☆12Updated last year
- Low latency, High Accuracy, Custom Query routers for Humans and Agents. Built by Prithivi Da☆103Updated last month
- Mistral + Haystack: build RAG pipelines that rock 🤘☆103Updated last year
- IndicGenBench is a high-quality, multilingual, multi-way parallel benchmark for evaluating Large Language Models (LLMs) on 4 user-facing …☆47Updated 8 months ago
- This playlab encompasses a multitude of projects crafted through the utilization of Large Language Models, showcasing the versatility and…☆118Updated 3 weeks ago
- agent-from-scratch is a Python-based repository designed for developers and researchers interested in understanding the inner workings of…☆82Updated 5 months ago
- Setu is a comprehensive pipeline designed to clean, filter, and deduplicate diverse data sources including Web, PDF, and Speech data. Bui…☆16Updated 11 months ago
- Fine-Tuning Falcon-7B, LLAMA 2 with QLoRA to create an advanced AI model with a profound understanding of the Indian legal context.☆79Updated last year
- MILU (Multi-task Indic Language Understanding Benchmark) is a comprehensive evaluation dataset designed to assess the performance of LLMs…☆18Updated 3 months ago
- meta_llama_2finetuned_text_generation_summarization☆21Updated last year
- Text-to-Speech for languages of India☆237Updated 6 months ago
- A tool that facilitates easy, efficient and high-quality fine-tuning of Cohere's models☆73Updated last month
- Complete implementation of Llama2 with/without KV cache & inference 🚀☆46Updated 11 months ago