microsoft/Magma-8B ↗
- source model id
- HuggingFace/microsoft-magma-8b@1
- hosting
- foundry-managed-compute
- platforms
- Microsoft Foundry
- license
- mit
- architecture
- input_modalities
- text
- output_modalities
- text
- capabilities
`microsoft/Magma-8B` powered by Hugging Face Inference Toolkit - [Original Model Card](https://huggingface.co/microsoft/Magma-8B) ### Send Request You can use cURL or any REST Client to send a reques…
azureFoundry/HuggingFace/microsoft-magma-8b@5
microsoft/Magma-8B powered by Hugging Face Inference Toolkit
You can use cURL or any REST Client to send a request to the AzureML endpoint with your AzureML token.
curl <AZUREML_ENDPOINT_URL>/v1/chat/completions \
-X POST \
-d '{"model":"microsoft/Magma-8B","messages":[{"role":"system","content":"You are agent that can see, talk and act."},{"role":"user","content":[{"type":"text","text":"What is in this image?"},{"type":"image_url","image_url":{"url":"https://assets-c4akfrf5b4d3f4b7.z01.azurefd.net/assets/2024/04/BMDataViz_661fb89f3845e.png"}}]}],"temperature":1.0,"stream":true}' \
-H "Authorization: Bearer <AZUREML_TOKEN>" \
-H "Content-Type: application/json"
For more information on the supported parameters refer the OpenAI documentation for chat completions.
The following input payload:
1–8 / 8
1–11 / 11
Hugging Face · microsoft/Magma-8B ↗
Microsoft Foundry · Model page ↗
Microsoft Foundry · Model page ↗
Microsoft Foundry · Model page ↗
Microsoft Foundry · Model page ↗
Microsoft Foundry · Model page ↗
Microsoft Foundry · Model page ↗
Microsoft Foundry · Model page ↗
Microsoft Foundry · Model page ↗
1–1 / 1
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.