Salesforce

52 indexed models

52 matching models

BLIP-2, OPT-2.7b

vertexAI/publishers/salesforce/models/blip2-opt-2.7-b@blip2-opt-2.7b

Capabilities
multimodal, visionInput

Benchmarks

  • MTEB: 41.066%

BLIP VQA

vertexAI/publishers/salesforce/models/blip-vqa-base@blip-vqa-base

Salesforce/bart-large-xsum-samsum

azureFoundry/HuggingFace/salesforce-bart-large-xsum-samsum@5

`Salesforce/bart-large-xsum-samsum` is a pre-trained language model available on the Hugging Face Hub. It's specifically designed for the `text2text-generation` task in the `transformers` library. If you want to learn more about the model's architecture, hyperparameters, limitati

Input modalities
text
Output modalities
text

Salesforce-BLIP-2-opt-2-7b-image-to-text · azureml v3

azureFoundry/azureml/Salesforce-BLIP-2-opt-2-7b-image-to-text@3

The `BLIP-2` model, utilizing OPT-2.7b (a large language model with 2.7 billion parameters), is presented in the <a href='https://arxiv.org/abs/2201.12086' target='_blank'>paper</a> titled "BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large La

Input modalities
image
Output modalities
text
Capabilities
visionInput

Salesforce-BLIP-2-opt-2-7b-image-to-text · azureml v5

azureFoundry/azureml/Salesforce-BLIP-2-opt-2-7b-image-to-text@5

The `BLIP-2` model, utilizing OPT-2.7b (a large language model with 2.7 billion parameters), is presented in the <a href='https://arxiv.org/abs/2201.12086' target='_blank'>paper</a> titled "BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large La

Input modalities
image
Output modalities
text
Capabilities
visionInput

Salesforce-BLIP-2-opt-2-7b-image-to-text · azureml v6

azureFoundry/azureml/Salesforce-BLIP-2-opt-2-7b-image-to-text@6

The `BLIP-2` model, utilizing OPT-2.7b (a large language model with 2.7 billion parameters), is presented in the <a href='https://arxiv.org/abs/2201.12086' target='_blank'>paper</a> titled "BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large La

Input modalities
image
Output modalities
text
Capabilities
visionInput

Salesforce-BLIP-2-opt-2-7b-image-to-text · azureml v8

azureFoundry/azureml/Salesforce-BLIP-2-opt-2-7b-image-to-text@8

The `BLIP-2` model, utilizing OPT-2.7b (a large language model with 2.7 billion parameters), is presented in the <a href='https://arxiv.org/abs/2201.12086' target='_blank'>paper</a> titled "BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large La

Input modalities
image
Output modalities
text
Capabilities
visionInput

Salesforce-BLIP-2-opt-2-7b-vqa · azureml v3

azureFoundry/azureml/Salesforce-BLIP-2-opt-2-7b-vqa@3

The `BLIP-2` model, utilizing OPT-2.7b (a large language model with 2.7 billion parameters), is presented in the <a href='https://arxiv.org/abs/2201.12086' target='_blank'>paper</a> titled "BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Lan

Salesforce-BLIP-2-opt-2-7b-vqa · azureml v5

azureFoundry/azureml/Salesforce-BLIP-2-opt-2-7b-vqa@5

The `BLIP-2` model, utilizing OPT-2.7b (a large language model with 2.7 billion parameters), is presented in the <a href='https://arxiv.org/abs/2201.12086' target='_blank'>paper</a> titled "BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Lan

Salesforce-BLIP-2-opt-2-7b-vqa · azureml v7

azureFoundry/azureml/Salesforce-BLIP-2-opt-2-7b-vqa@7

The `BLIP-2` model, utilizing OPT-2.7b (a large language model with 2.7 billion parameters), is presented in the <a href='https://arxiv.org/abs/2201.12086' target='_blank'>paper</a> titled "BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Lan

Salesforce-BLIP-image-captioning-base · azureml v3

azureFoundry/azureml/Salesforce-BLIP-image-captioning-base@3

`BLIP` (Bootstrapping Language-Image Pre-training) designed for unified vision-language understanding and generation is a new VLP framework that expands the scope of downstream tasks compared to existing methods. The framework encompasses two key contributions from both model and

Input modalities
image
Output modalities
text
Capabilities
visionInput

Salesforce-BLIP-image-captioning-base · azureml v5

azureFoundry/azureml/Salesforce-BLIP-image-captioning-base@5

`BLIP` (Bootstrapping Language-Image Pre-training) designed for unified vision-language understanding and generation is a new VLP framework that expands the scope of downstream tasks compared to existing methods. The framework encompasses two key contributions from both model and

Input modalities
image
Output modalities
text
Capabilities
visionInput

Salesforce-BLIP-image-captioning-base · azureml v6

azureFoundry/azureml/Salesforce-BLIP-image-captioning-base@6

`BLIP` (Bootstrapping Language-Image Pre-training) designed for unified vision-language understanding and generation is a new VLP framework that expands the scope of downstream tasks compared to existing methods. The framework encompasses two key contributions from both model and

Input modalities
image
Output modalities
text
Capabilities
visionInput

Salesforce-BLIP-image-captioning-base · azureml v7

azureFoundry/azureml/Salesforce-BLIP-image-captioning-base@7

`BLIP` (Bootstrapping Language-Image Pre-training) designed for unified vision-language understanding and generation is a new VLP framework that expands the scope of downstream tasks compared to existing methods. The framework encompasses two key contributions from both model and

Input modalities
image
Output modalities
text
Capabilities
visionInput

Salesforce-BLIP-vqa-base · azureml v3

azureFoundry/azureml/Salesforce-BLIP-vqa-base@3

`BLIP` (Bootstrapping Language-Image Pre-training) designed for unified vision-language understanding and generation is a new VLP framework that expands the scope of downstream tasks compared to existing methods. The framework encompasses two key contributions from both model and

Salesforce-BLIP-vqa-base · azureml v5

azureFoundry/azureml/Salesforce-BLIP-vqa-base@5

`BLIP` (Bootstrapping Language-Image Pre-training) designed for unified vision-language understanding and generation is a new VLP framework that expands the scope of downstream tasks compared to existing methods. The framework encompasses two key contributions from both model and

Salesforce-BLIP-vqa-base · azureml v6

azureFoundry/azureml/Salesforce-BLIP-vqa-base@6

`BLIP` (Bootstrapping Language-Image Pre-training) designed for unified vision-language understanding and generation is a new VLP framework that expands the scope of downstream tasks compared to existing methods. The framework encompasses two key contributions from both model and

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace