v.1.0
family
BLOOMZ
No description provided.
BigScience Workshop
Multitask Fine-tuned Language Model
All cards
Filter by model family
No date provided.
No version provided.
dataset
COYO-700M
COYO-700M is a large-scale dataset consisting of 747 million image-text pairs. It was developed by Kakao Brain.
No publisher provided
No model type provided
v.1.0
dataset
P3
No description provided.
BigScience Workshop
No model type provided
v.1.0
dataset
The BigScience ROOTS Corpus
No description provided.
BigScience Workshop
No model type provided
v.1.0.0
model
mt5-base
No description provided.
Text-to-text Transformer-based Language Model
v.1.0.0
model
bloom-7b1
No description provided.
BigScience Workshop
Transformer-based Language Model
v.1.0.0
model
bloomz-3b
No description provided.
BigScience Workshop
Multitask Fine-tuned Language Model
No date provided.
No version provided.
family
No description provided.
No publisher provided
No model type provided
v.1.0
family
Llama 2
Meta developed and released the Llama 2 family of large language models (LLMs), a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama-2-Chat, are optimized for dialogue use cases. Llama-2-Chat models outperform open-source chat models on most benchmarks we tested, and in our human evaluations for helpfulness and safety, are on par with some popular closed-source models like ChatGPT and PaLM.
Meta
Large Language Model
No date provided.
No version provided.
dataset
LAION 5B
No description provided.
No publisher provided
No model type provided
v.1.0.0
model
mt0-large
No description provided.
BigScience Workshop
Transformer-based Language Model
v.1.0.0
model
mt5-small
No description provided.
Text-to-text Transformer-based Language Model
v.1.0.0
model
LLaVA-1.6 Vicuna 13B
Science QA is a dataset designed for evaluating and training models in the task of answering science-related questions.
LMSYS Org
Chatbot
No date provided.
No version provided.
model
Test Model - 1.2.0
No description provided.
No publisher provided
No model type provided
No date provided.
No version provided.
dataset
Common Crawl
Over 250 billion pages spanning 17 years. Free and open corpus since 2007.
No publisher provided
No model type provided
No date provided.
No version provided.
model
PLIP
No description provided.
No publisher provided
Contrastive Model
No date provided.
No version provided.
family
LAION
Large-scale Artificial Intelligence Open Network (LAION) organization
No publisher provided
No model type provided
No date provided.
v.1.0.0
dataset
LLaVa MM-Instruct
LLaVA utilized GPT-4 to generate multimodal instruction-following data, resulting in 158,000 unique samples. This dataset includes 58,000 conversational samples, 23,000 detailed descriptions, and 77,000 complex reasoning samples.
OpenAI
Multi-Modal LLM
v.1.0.0
family
Vicuna
No description provided.
LMSYS ORG
Language Model
v.2
model
PaLM 2
No description provided.
Large Language Model
No date provided.
No version provided.
dataset
Web Image Text
400 million image-text pairs collected from various sources on the internet used to train CLIP.
No publisher provided
No model type provided
v.1.0.0
model
Llama 2 70B
This is the 70B variant.
Meta
Large Language Model
v.1.0.0
model
bloomz-1b7
No description provided.
BigScience Workshop
Multitask Fine-tuned Language Model
No date provided.
No version provided.
model
CLIP
No description provided.
No publisher provided
Contrastive Model
v.1.0.0
model
mt0-small
No description provided.
BigScience Workshop
Transformer-based Language Model
v.1.0
dataset
xP3mt
No description provided.
BigScience Workshop
No model type provided
v.1.0.0
model
mt0-xl
No description provided.
BigScience Workshop
Transformer-based Language Model
v.1.0
dataset
xP3x
No description provided.
BigScience Workshop
No model type provided
v.1.0.0
model
bloomz-1b1
No description provided.
BigScience Workshop
Multitask Fine-tuned Language Model
v.1.0
family
mt0
No description provided.
BigScience Workshop
Transformer-based Language Model
No date provided.
No version provided.
dataset
CC3M
CC3M, short for Conceptual Captions 3 Million, is a large-scale image-caption dataset designed for training and evaluating image captioning models.
No publisher provided
No model type provided
v.1.0
dataset
mC4
No description provided.
No model type provided
v.1.0.0
model
mt5-xl
No description provided.
Text-to-text Transformer-based Language Model
No date provided.
No version provided.
dataset
Pathology twitter
208,214 pathology image-text pairs from pathology Twitter hashtags, from strict data quality filtering used to train PLIP.
No publisher provided
No model type provided
v.1.0
model
BLOOM
No description provided.
BigScience Workshop
Transformer-based Language Model
No date provided.
No version provided.
dataset
LAION 2B
No description provided.
No publisher provided
No model type provided
v.1.0.0
model
mt5-large
No description provided.
Text-to-text Transformer-based Language Model
v.1.0.0
model
Vicuna-13B
70K user-shared ChatGPT conversations were used for fine-tuning. GPT-4 used for preliminary evaluation to benchmark against ChatGPT and Google Bard.
LMSYS Org
Chatbot
v.1.0.0
model
bloom-1b1
No description provided.
BigScience Workshop
Transformer-based Language Model
No date provided.
No version provided.
family
OpenAI GPT
No description provided.
No publisher provided
No model type provided
No date provided.
No version provided.
dataset
Science QA
Science QA is a dataset designed for evaluating and training models in the task of answering science-related questions.
No publisher provided
No model type provided
No date provided.
No version provided.
dataset
COCO
The COCO (Common Objects in Context) dataset is a large-scale object detection, segmentation, and captioning dataset.
No publisher provided
No model type provided
v.1.0.0
model
bloomz-7b1-p3
No description provided.
BigScience Workshop
Multitask Fine-tuned Language Model
v.1.0.0
model
bloom-1b7
No description provided.
BigScience Workshop
Transformer-based Language Model
v.1.0
dataset
xP3megds
No description provided.
BigScience Workshop
No model type provided
v.1.0.0
model
mt0-base
No description provided.
BigScience Workshop
Transformer-based Language Model
v.1.0.0
model
bloom-3b
No description provided.
BigScience Workshop
Transformer-based Language Model
v.1.0.0
model
bloomz-560m
No description provided.
BigScience Workshop
Multitask Fine-tuned Language Model
v.1.0.0
model
bloomz-7b1-mt
No description provided.
BigScience Workshop
Multitask Fine-tuned Language Model
No date provided.
No version provided.
dataset
LAION 400m
The LAION-400M dataset is an open dataset consisting of 400 million image-text pairs. Filtering of NSFW content based on CLIP embeddings.
No publisher provided
No model type provided
No date provided.
v.1.0.0
dataset
Vicuna 70k ChatGPT
70K user-shared ChatGPT conversations were used for fine-tuning. GPT-4 used for preliminary evaluation to benchmark against ChatGPT and Google Bard.
OpenAI
Multi-Modal LLM
v.1.0.0
model
bloomz-7b1
No description provided.
BigScience Workshop
Multitask Fine-tuned Language Model
v.1.0.0
model
mt5-xxl
No description provided.
Text-to-text Transformer-based Language Model
v.1.0.0
model
Llama 2 13B
Meta developed and released the Llama 2 family of large language models (LLMs), a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama-2-Chat, are optimized for dialogue use cases. Llama-2-Chat models outperform open-source chat models on most benchmarks we tested, and in our human evaluations for helpfulness and safety, are on par with some popular closed-source models like ChatGPT and PaLM.
Meta
Large Language Model
v.1.0.0
model
Llama 2 7B
This is the 7B variant.
Meta
Large Language Model
v.1.0
model
mT5
No description provided.
Text-to-text Transformer-based Language Model
No date provided.
v.1.0.0
model
GPT 4
No description provided.
OpenAI
Multi-Modal LLM
v.1.0
dataset
xP3
No description provided.
BigScience Workshop
No model type provided
v.1.0.0
model
bloomz-560m
No description provided.
BigScience Workshop
Transformer-based Language Model
v.1.0
dataset
xP3all
No description provided.
BigScience Workshop
No model type provided
No date provided.
No version provided.
family
LLaVA
No description provided.
No publisher provided
No model type provided
v.1.0.0
model
mt0-xxl
No description provided.
BigScience Workshop
Transformer-based Language Model
No date provided.
v.1.0.0
model
EVA-G
No description provided.
Beijing Academy of Artificial Intelligence (BAAI)
Contrastive Model
No date provided.
No version provided.
model
RRT-MIL
No description provided.
No publisher provided
No model type provided
v.2
model
Claude 2
No description provided.
Anthropic
Large Language Model