Sparkles
Dialogue model
Develops multimodal instruction-following models for open-ended dialogues across multiple images
Sparkles: Unlocking Chats Across Multiple Images for Multimodal Instruction-Following Models
41 stars
1 watching
1 forks
Language: Python
last commit: 5 months ago Related projects:
| Repository | Description | Stars |
|---|---|---|
 h2oai/sparkling-water | Integrates H2O's machine learning capabilities with Apache Spark for big data processing and analytics | 968 |
 tubular/sparkly | A set of Python libraries and tools to simplify interactions with various data sources using Apache Spark. | 60 |
 sparklingpandas/sparklingpandas | Enables distributed data analysis using PySpark and Pandas APIs | 361 |
 hpreston/myhero_spark | An interactive chat service for a voting system using a Cisco Spark Bot | 1 |
 iwannabelikemike/plugin.video.sparkle | An Kodi plugin that aggregates Acestream links from the web. | 43 |
 gorillalabs/sparkling | A Clojure API for interacting with Apache Spark | 448 |
 sparklyr/sparklyr | An R interface to Apache Spark for distributed data analysis and machine learning | 957 |
 lensacom/sparkit-learn | A Python library that integrates PySpark and scikit-learn for distributed machine learning | 1,154 |
 yfzhang114/slime | Develops large multimodal models for high-resolution understanding and analysis of text, images, and other data types. | 137 |
 platisd/phonix | Generates captions for videos using OpenAI's Whisper API | 37 |
 lightyear-turing/turingmm-34b-chat | An English-Chinese chat model developed from a large language model for conversational AI | 9 |
 pku-yuangroup/languagebind | Extending pretraining models to handle multiple modalities by aligning language and video representations | 723 |
 wuhaozhe/style_avatar | Generates stylized talking faces and videos using deep learning models | 278 |
 holy-shine/prefixspan-py | An efficient data mining algorithm to discover sequential patterns in large datasets. | 20 |
 orionstarai/orionstar-yi-34b-chat | A high-quality chat model trained on 15W+ high-quality data to provide excellent conversational experiences. | 259 |