A collection's of Salesforce's Finance-specific model
			
	
	AI & ML interests
None defined yet.
Recent Activity
				Papers
		
MMPersuade: A Dataset and Evaluation Framework for Multimodal Persuasion

Enterprise Deep Research: Steerable Multi-Agent Deep Research for Enterprise Analytics
CoDA is Salesforce AI Research's open, lightweight and diffusion-based language model.
			
	
	SweRank is a framework for software issue localization, combining an embedding-based retriever (SweRankEmbed) with an LLM-based reranker (SweRankLLM).
			
	
	xLAM: A Family of Large Action Models to Empower AI Agent Systems: https://github.com/SalesforceAIResearch/xLAM
			
	
	A collection of all XGen-MM (Foundation LMM) models!
			
	
	- 
	
	
	  Salesforce/xgen-mm-phi3-mini-instruct-interleave-r-v1.5Image-Text-to-Text • 4B • Updated • 1.13k • 56
- 
	
	
	Salesforce/blip3-kaleViewer • Updated • 235M • 8.36k • 42
- 
	
	
	  Salesforce/xgen-mm-vid-phi3-mini-r-v1.5-128tokens-8framesImage-Text-to-Text • 4B • Updated • 166 • 11
- 
	
	
	  Salesforce/xgen-mm-phi3-mini-instruct-r-v1Image-Text-to-Text • 5B • Updated • 492 • 186
This collection contains all versions of the CoTA (Chain-of-Thought-and-Action) datasets.
			
	
	A collection of contextual QA datasets dedicated to evaluate the contextual faithfulness of LLMs
			
	
	A collection of all BLIP2 models!
			
	
	- 
	
	
	  Salesforce/blip2-opt-2.7bImage-Text-to-Text • 4B • Updated • 420k • 419
- 
	
	
	  Salesforce/blip2-flan-t5-xxlImage-Text-to-Text • 12B • Updated • 5.5k • 93
- 
	
	
	  Salesforce/blip2-opt-6.7b-cocoImage-Text-to-Text • 8B • Updated • 23.6k • 34
- 
	
	
	  Salesforce/blip2-opt-6.7bImage-Text-to-Text • 8B • Updated • 11.2k • 80
- 
	
	
	  Salesforce/moirai-1.1-R-smallTime Series Forecasting • Updated • 60.1k • 7
- 
	
	
	  Salesforce/moirai-1.1-R-baseTime Series Forecasting • Updated • 43.7k • 7
- 
	
	
	  Salesforce/moirai-1.1-R-largeTime Series Forecasting • Updated • 62.1k • 29
- 
	
	
	  Salesforce/moirai-1.0-R-smallTime Series Forecasting • Updated • 9.73k • 29
FARE are Salesforce AI Research's open multi-task evaluator models.
			
	
	A collection of GUI grounding models trained with GRPO.
			
	
	A family of Large Action Model for multi-turn conversation and tool-use
			
	
	- 
	
	
	  Salesforce/Llama-xLAM-2-70b-fc-rText Generation • 71B • Updated • 247 • 47
- 
	
	
	  Salesforce/Llama-xLAM-2-8b-fc-rText Generation • 8B • Updated • 6.36k • • 54
- 
	
	
	  Salesforce/Llama-xLAM-2-8b-fc-r-ggufText Generation • 8B • Updated • 8.12k • 14
- 
	
	
	  Salesforce/xLAM-2-1b-fc-rText Generation • 2B • Updated • 748 • • 10
This collection contains the best-performing TACO models based on LLaMA-3/Qwen2 and SigLIP/CLIP.
			
	
	A collection of all BLIP models 
			
	
	- 
	
	
	  Salesforce/blip-image-captioning-largeImage-to-Text • 0.5B • Updated • 1.18M • 1.43k
- 
	
	
	  Salesforce/blip-image-captioning-baseImage-to-Text • Updated • 2.18M • 802
- 
	
	
	  Salesforce/blip-vqa-baseVisual Question Answering • 0.4B • Updated • 263k • 180
- 
	
	
	  Salesforce/blip-vqa-capfilt-largeVisual Question Answering • Updated • 28.3k • 53
A collection that contains all InstructBLIP models!
			
	
	- 
	
	
	  Salesforce/instructblip-vicuna-7bImage-Text-to-Text • 8B • Updated • 92.4k • 96
- 
	
	
	  Salesforce/instructblip-vicuna-13bImage-Text-to-Text • 14B • Updated • 480 • 43
- 
	
	
	  Salesforce/instructblip-flan-t5-xxlImage-Text-to-Text • 12B • Updated • 404 • 22
- 
	
	
	  Salesforce/instructblip-flan-t5-xlImage-Text-to-Text • 4B • Updated • 11.7k • 30
A collection of embedding models
			
	
	- 
	
	
	  Salesforce/SFR-Embedding-2_RFeature Extraction • 7B • Updated • 17.3k • 93
- 
	
	
	  Salesforce/SFR-Embedding-MistralFeature Extraction • 7B • Updated • 39.7k • 293
- 
	
	
	  Salesforce/SFR-Embedding-Code-2B_RFeature Extraction • 3B • Updated • 3.24k • 46
- 
	
	
	  Salesforce/SFR-Embedding-Code-400M_RFeature Extraction • 0.4B • Updated • 12.6k • 32
A collection's of Salesforce's Finance-specific model
			
	
	FARE are Salesforce AI Research's open multi-task evaluator models.
			
	
	CoDA is Salesforce AI Research's open, lightweight and diffusion-based language model.
			
	
	A collection of GUI grounding models trained with GRPO.
			
	
	SweRank is a framework for software issue localization, combining an embedding-based retriever (SweRankEmbed) with an LLM-based reranker (SweRankLLM).
			
	
	xLAM: A Family of Large Action Models to Empower AI Agent Systems: https://github.com/SalesforceAIResearch/xLAM
			
	
	A family of Large Action Model for multi-turn conversation and tool-use
			
	
	- 
	
	
	  Salesforce/Llama-xLAM-2-70b-fc-rText Generation • 71B • Updated • 247 • 47
- 
	
	
	  Salesforce/Llama-xLAM-2-8b-fc-rText Generation • 8B • Updated • 6.36k • • 54
- 
	
	
	  Salesforce/Llama-xLAM-2-8b-fc-r-ggufText Generation • 8B • Updated • 8.12k • 14
- 
	
	
	  Salesforce/xLAM-2-1b-fc-rText Generation • 2B • Updated • 748 • • 10
A collection of all XGen-MM (Foundation LMM) models!
			
	
	- 
	
	
	  Salesforce/xgen-mm-phi3-mini-instruct-interleave-r-v1.5Image-Text-to-Text • 4B • Updated • 1.13k • 56
- 
	
	
	Salesforce/blip3-kaleViewer • Updated • 235M • 8.36k • 42
- 
	
	
	  Salesforce/xgen-mm-vid-phi3-mini-r-v1.5-128tokens-8framesImage-Text-to-Text • 4B • Updated • 166 • 11
- 
	
	
	  Salesforce/xgen-mm-phi3-mini-instruct-r-v1Image-Text-to-Text • 5B • Updated • 492 • 186
This collection contains all versions of the CoTA (Chain-of-Thought-and-Action) datasets.
			
	
	This collection contains the best-performing TACO models based on LLaMA-3/Qwen2 and SigLIP/CLIP.
			
	
	A collection of contextual QA datasets dedicated to evaluate the contextual faithfulness of LLMs
			
	
	A collection of all BLIP models 
			
	
	- 
	
	
	  Salesforce/blip-image-captioning-largeImage-to-Text • 0.5B • Updated • 1.18M • 1.43k
- 
	
	
	  Salesforce/blip-image-captioning-baseImage-to-Text • Updated • 2.18M • 802
- 
	
	
	  Salesforce/blip-vqa-baseVisual Question Answering • 0.4B • Updated • 263k • 180
- 
	
	
	  Salesforce/blip-vqa-capfilt-largeVisual Question Answering • Updated • 28.3k • 53
A collection of all BLIP2 models!
			
	
	- 
	
	
	  Salesforce/blip2-opt-2.7bImage-Text-to-Text • 4B • Updated • 420k • 419
- 
	
	
	  Salesforce/blip2-flan-t5-xxlImage-Text-to-Text • 12B • Updated • 5.5k • 93
- 
	
	
	  Salesforce/blip2-opt-6.7b-cocoImage-Text-to-Text • 8B • Updated • 23.6k • 34
- 
	
	
	  Salesforce/blip2-opt-6.7bImage-Text-to-Text • 8B • Updated • 11.2k • 80
A collection that contains all InstructBLIP models!
			
	
	- 
	
	
	  Salesforce/instructblip-vicuna-7bImage-Text-to-Text • 8B • Updated • 92.4k • 96
- 
	
	
	  Salesforce/instructblip-vicuna-13bImage-Text-to-Text • 14B • Updated • 480 • 43
- 
	
	
	  Salesforce/instructblip-flan-t5-xxlImage-Text-to-Text • 12B • Updated • 404 • 22
- 
	
	
	  Salesforce/instructblip-flan-t5-xlImage-Text-to-Text • 4B • Updated • 11.7k • 30
- 
	
	
	  Salesforce/moirai-1.1-R-smallTime Series Forecasting • Updated • 60.1k • 7
- 
	
	
	  Salesforce/moirai-1.1-R-baseTime Series Forecasting • Updated • 43.7k • 7
- 
	
	
	  Salesforce/moirai-1.1-R-largeTime Series Forecasting • Updated • 62.1k • 29
- 
	
	
	  Salesforce/moirai-1.0-R-smallTime Series Forecasting • Updated • 9.73k • 29
A collection of embedding models
			
	
	- 
	
	
	  Salesforce/SFR-Embedding-2_RFeature Extraction • 7B • Updated • 17.3k • 93
- 
	
	
	  Salesforce/SFR-Embedding-MistralFeature Extraction • 7B • Updated • 39.7k • 293
- 
	
	
	  Salesforce/SFR-Embedding-Code-2B_RFeature Extraction • 3B • Updated • 3.24k • 46
- 
	
	
	  Salesforce/SFR-Embedding-Code-400M_RFeature Extraction • 0.4B • Updated • 12.6k • 32