RazhanHameed / kurdish-llamaLinks
This is an attempt to fine-tune the Llama model for Central Kurdish.
☆16Updated 2 years ago
Alternatives and similar repositories for kurdish-llama
Users that are interested in kurdish-llama are comparing it to the libraries listed below
Sorting:
- AsoSoft Text Corpus is the first large scale text corpus for the Kurdish language.☆26Updated 3 years ago
- Tesseract4 finetuned traineddata for Central Kurdish/Sorani☆11Updated 5 years ago
- Tacotron 2 - Persian☆38Updated 3 years ago
- ☆10Updated 3 years ago
- Bert-Based persian spell-checker☆19Updated last year
- A repository for resources in Kurdish Language☆20Updated 5 years ago
- AsoSoft Speech Corpus can be used for spoken language processing tasks in Central Kurdish such as speech recognition, speaker recognition…☆11Updated 3 years ago
- fine-tune Wav2vec2. an ASR model released by Facebook☆38Updated 3 years ago
- A Persian Image Captioning model based on Vision Encoder Decoder Models of the transformers🤗.☆21Updated 3 years ago
- ☆123Updated 2 years ago
- ✍🏼 Neural Spell Checker for Central Kurdish (Sorani)☆21Updated last year
- ☆128Updated last year
- Zabanshenas is a solution for identifying the most likely language of a piece of written text. Demo (👇 )☆18Updated 4 years ago
- ☆21Updated 2 years ago
- PCoQA: Persian Conversational Question Answering Dataset☆21Updated last year
- CLIPfa: Connecting Farsi Text and Images☆84Updated 2 years ago
- Persian Bert For Long-Range Sequences☆63Updated 4 years ago
- Code, datasets, and models designed to generate product catalogs using LLMs.☆35Updated last year
- ☆42Updated 2 years ago
- Repo for the Belebele dataset, a massively multilingual reading comprehension dataset.☆336Updated 11 months ago
- Pretraining, fine-tuning and evaluation scripts for IndicBERT-v2 and IndicXTREME☆105Updated 7 months ago
- ParsBench provides toolkits for benchmarking LLMs based on the Persian language tasks.☆73Updated 6 months ago
- Place where folks can contribute to 🤗 community events☆427Updated last year
- The official implementation of CATT Arabic diacritization models.☆55Updated 4 months ago
- Whisper finetuned on VinBigdata-VLSP2020-100h + KenLM☆38Updated 2 years ago
- Minimal example scripts of the Hugging Face Trainer, focused on staying under 150 lines☆196Updated last year
- Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free☆232Updated last year
- A well-structured summarization dataset for the Persian language!☆50Updated last year
- 🌟 Cache-cool: A fast, flexible LLM caching proxy that reduces latency and API costs by caching repetitive calls to LLM services. 🔄 Su…☆28Updated 3 months ago
- ☆23Updated last year