-
Barcelona Supercomputing Center
- Madrid
- http://luisgasco.es/
- @luisgasco
Highlights
- Pro
HRproject
Dataset used in the paper "VacancySBERT: the method for representation of titles and skills for semantic similarity search in the recruitment domain"
Dataset used to evaluate Skill Extraction systems based on the ESCO skills taxonomy.
The dataset used to evaluate JobBERT on the task of job title normalization.
A (smart) rule based NLP module to extract job skills from text
Automated Resume Screening System using Machine Learning (With Dataset)
A program to select Resumes for Interviews
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
A collection of libraries to optimise AI model performances
Toolkit for creating, sharing and using natural language prompts.
Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform
Instruction Tuning with GPT-4
Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
Powerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled corpus and yields massive improvement: "GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptatio…
SKILLSPAN: Competences as Spans for Skill Extraction from Job Postings
A code for the paper Learning Representations for Soft Skill Matching
This is a repository to post issues, announcements, feature requests and other information related to CCARS Job Postings datasets