You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: articles/ai-studio/how-to/deploy-models-phi-3-5-vision.md
+4-4Lines changed: 4 additions & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -27,7 +27,7 @@ The Phi-3.5 small language models (SLMs) are a collection of instruction-tuned g
27
27
28
28
## Phi-3.5 chat model with vision
29
29
30
-
Phi-3.5 Vision is a lightweight, state-of-the-art, open multimodal model. The model was built upon datasets that include synthetic data and filtered, publicly-available websites - with a focus on high-quality, reasoning-dense data, both on text and vision. The model belongs to the Phi-3 model family, and the multimodal version comes with 128K context length (in tokens) that it can support. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning and direct preference optimization, to ensure precise instruction adherence and robust safety measures.
30
+
Phi-3.5 Vision is a lightweight, state-of-the-art, open multimodal model. The model was built upon datasets that include synthetic data and filtered, publiclyavailable websites - with a focus on high-quality, reasoning-dense data, both on text and vision. The model belongs to the Phi-3 model family, and the multimodal version comes with 128K context length (in tokens) that it can support. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning and direct preference optimization, to ensure precise instruction adherence and robust safety measures.
31
31
32
32
33
33
You can learn more about the models in their respective model card:
@@ -347,7 +347,7 @@ Usage:
347
347
348
348
## Phi-3.5 chat model with vision
349
349
350
-
Phi-3.5 Vision is a lightweight, state-of-the-art, open multimodal model. The model was built upon datasets that include synthetic data and filtered, publicly-available websites - with a focus on high-quality, reasoning-dense data, both on text and vision. The model belongs to the Phi-3 model family, and the multimodal version comes with 128K context length (in tokens) that it can support. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning and direct preference optimization, to ensure precise instruction adherence and robust safety measures.
350
+
Phi-3.5 Vision is a lightweight, state-of-the-art, open multimodal model. The model was built upon datasets that include synthetic data and filtered, publiclyavailable websites - with a focus on high-quality, reasoning-dense data, both on text and vision. The model belongs to the Phi-3 model family, and the multimodal version comes with 128K context length (in tokens) that it can support. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning and direct preference optimization, to ensure precise instruction adherence and robust safety measures.
351
351
352
352
353
353
You can learn more about the models in their respective model card:
@@ -690,7 +690,7 @@ Usage:
690
690
691
691
## Phi-3.5 chat model with vision
692
692
693
-
Phi-3.5 Vision is a lightweight, state-of-the-art, open multimodal model. The model was built upon datasets that include synthetic data and filtered, publicly-available websites - with a focus on high-quality, reasoning-dense data, both on text and vision. The model belongs to the Phi-3 model family, and the multimodal version comes with 128K context length (in tokens) that it can support. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning and direct preference optimization, to ensure precise instruction adherence and robust safety measures.
693
+
Phi-3.5 Vision is a lightweight, state-of-the-art, open multimodal model. The model was built upon datasets that include synthetic data and filtered, publiclyavailable websites - with a focus on high-quality, reasoning-dense data, both on text and vision. The model belongs to the Phi-3 model family, and the multimodal version comes with 128K context length (in tokens) that it can support. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning and direct preference optimization, to ensure precise instruction adherence and robust safety measures.
694
694
695
695
696
696
You can learn more about the models in their respective model card:
@@ -1030,7 +1030,7 @@ Usage:
1030
1030
1031
1031
## Phi-3.5 chat model with vision
1032
1032
1033
-
Phi-3.5 Vision is a lightweight, state-of-the-art, open multimodal model. The model was built upon datasets that include synthetic data and filtered, publicly-available websites -with a focus on high-quality, reasoning-dense data, both on text and vision. The model belongs to the Phi-3 model family, and the multimodal version comes with128K context length (in tokens) that it can support. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning and direct preference optimization, to ensure precise instruction adherence and robust safety measures.
1033
+
Phi-3.5 Vision is a lightweight, state-of-the-art, open multimodal model. The model was built upon datasets that include synthetic data and filtered, publiclyavailable websites -with a focus on high-quality, reasoning-dense data, both on text and vision. The model belongs to the Phi-3 model family, and the multimodal version comes with128K context length (in tokens) that it can support. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning and direct preference optimization, to ensure precise instruction adherence and robust safety measures.
1034
1034
1035
1035
1036
1036
You can learn more about the models in their respective model card:
Copy file name to clipboardExpand all lines: articles/ai-studio/how-to/deploy-models-phi-3-vision.md
+4-4Lines changed: 4 additions & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -27,7 +27,7 @@ The Phi-3 family of small language models (SLMs) is a collection of instruction-
27
27
28
28
## Phi-3 chat model with vision
29
29
30
-
Phi-3 Vision is a lightweight, state-of-the-art, open multimodal model. The model was built upon datasets that include synthetic data and filtered, publicly-available websites - with a focus on high-quality, reasoning-dense data, both on text and vision. The model belongs to the Phi-3 model family, and the multimodal version comes with 128K context length (in tokens) that it can support. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning and direct preference optimization, to ensure precise instruction adherence and robust safety measures.
30
+
Phi-3 Vision is a lightweight, state-of-the-art, open multimodal model. The model was built upon datasets that include synthetic data and filtered, publiclyavailable websites - with a focus on high-quality, reasoning-dense data, both on text and vision. The model belongs to the Phi-3 model family, and the multimodal version comes with 128K context length (in tokens) that it can support. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning and direct preference optimization, to ensure precise instruction adherence and robust safety measures.
31
31
32
32
33
33
You can learn more about the models in their respective model card:
@@ -347,7 +347,7 @@ Usage:
347
347
348
348
## Phi-3 chat model with vision
349
349
350
-
Phi-3 Vision is a lightweight, state-of-the-art, open multimodal model. The model was built upon datasets that include synthetic data and filtered, publicly-available websites - with a focus on high-quality, reasoning-dense data, both on text and vision. The model belongs to the Phi-3 model family, and the multimodal version comes with 128K context length (in tokens) that it can support. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning and direct preference optimization, to ensure precise instruction adherence and robust safety measures.
350
+
Phi-3 Vision is a lightweight, state-of-the-art, open multimodal model. The model was built upon datasets that include synthetic data and filtered, publiclyavailable websites - with a focus on high-quality, reasoning-dense data, both on text and vision. The model belongs to the Phi-3 model family, and the multimodal version comes with 128K context length (in tokens) that it can support. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning and direct preference optimization, to ensure precise instruction adherence and robust safety measures.
351
351
352
352
353
353
You can learn more about the models in their respective model card:
@@ -690,7 +690,7 @@ Usage:
690
690
691
691
## Phi-3 chat model with vision
692
692
693
-
Phi-3 Vision is a lightweight, state-of-the-art, open multimodal model. The model was built upon datasets that include synthetic data and filtered, publicly-available websites - with a focus on high-quality, reasoning-dense data, both on text and vision. The model belongs to the Phi-3 model family, and the multimodal version comes with 128K context length (in tokens) that it can support. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning and direct preference optimization, to ensure precise instruction adherence and robust safety measures.
693
+
Phi-3 Vision is a lightweight, state-of-the-art, open multimodal model. The model was built upon datasets that include synthetic data and filtered, publiclyavailable websites - with a focus on high-quality, reasoning-dense data, both on text and vision. The model belongs to the Phi-3 model family, and the multimodal version comes with 128K context length (in tokens) that it can support. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning and direct preference optimization, to ensure precise instruction adherence and robust safety measures.
694
694
695
695
696
696
You can learn more about the models in their respective model card:
@@ -1030,7 +1030,7 @@ Usage:
1030
1030
1031
1031
## Phi-3 chat model with vision
1032
1032
1033
-
Phi-3 Vision is a lightweight, state-of-the-art, open multimodal model. The model was built upon datasets that include synthetic data and filtered, publicly-available websites -with a focus on high-quality, reasoning-dense data, both on text and vision. The model belongs to the Phi-3 model family, and the multimodal version comes with128K context length (in tokens) that it can support. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning and direct preference optimization, to ensure precise instruction adherence and robust safety measures.
1033
+
Phi-3 Vision is a lightweight, state-of-the-art, open multimodal model. The model was built upon datasets that include synthetic data and filtered, publiclyavailable websites -with a focus on high-quality, reasoning-dense data, both on text and vision. The model belongs to the Phi-3 model family, and the multimodal version comes with128K context length (in tokens) that it can support. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning and direct preference optimization, to ensure precise instruction adherence and robust safety measures.
1034
1034
1035
1035
1036
1036
You can learn more about the models in their respective model card:
Copy file name to clipboardExpand all lines: articles/machine-learning/how-to-deploy-models-phi-3-5-vision.md
+4-4Lines changed: 4 additions & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -26,7 +26,7 @@ The Phi-3.5 small language models (SLMs) are a collection of instruction-tuned g
26
26
27
27
## Phi-3.5 chat model with vision
28
28
29
-
Phi-3.5 Vision is a lightweight, state-of-the-art, open multimodal model. The model was built upon datasets that include synthetic data and filtered, publicly-available websites - with a focus on high-quality, reasoning-dense data, both on text and vision. The model belongs to the Phi-3 model family, and the multimodal version comes with 128K context length (in tokens) that it can support. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning and direct preference optimization, to ensure precise instruction adherence and robust safety measures.
29
+
Phi-3.5 Vision is a lightweight, state-of-the-art, open multimodal model. The model was built upon datasets that include synthetic data and filtered, publiclyavailable websites - with a focus on high-quality, reasoning-dense data, both on text and vision. The model belongs to the Phi-3 model family, and the multimodal version comes with 128K context length (in tokens) that it can support. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning and direct preference optimization, to ensure precise instruction adherence and robust safety measures.
30
30
31
31
32
32
You can learn more about the models in their respective model card:
@@ -346,7 +346,7 @@ Usage:
346
346
347
347
## Phi-3.5 chat model with vision
348
348
349
-
Phi-3.5 Vision is a lightweight, state-of-the-art, open multimodal model. The model was built upon datasets that include synthetic data and filtered, publicly-available websites - with a focus on high-quality, reasoning-dense data, both on text and vision. The model belongs to the Phi-3 model family, and the multimodal version comes with 128K context length (in tokens) that it can support. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning and direct preference optimization, to ensure precise instruction adherence and robust safety measures.
349
+
Phi-3.5 Vision is a lightweight, state-of-the-art, open multimodal model. The model was built upon datasets that include synthetic data and filtered, publiclyavailable websites - with a focus on high-quality, reasoning-dense data, both on text and vision. The model belongs to the Phi-3 model family, and the multimodal version comes with 128K context length (in tokens) that it can support. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning and direct preference optimization, to ensure precise instruction adherence and robust safety measures.
350
350
351
351
352
352
You can learn more about the models in their respective model card:
@@ -689,7 +689,7 @@ Usage:
689
689
690
690
## Phi-3.5 chat model with vision
691
691
692
-
Phi-3.5 Vision is a lightweight, state-of-the-art, open multimodal model. The model was built upon datasets that include synthetic data and filtered, publicly-available websites - with a focus on high-quality, reasoning-dense data, both on text and vision. The model belongs to the Phi-3 model family, and the multimodal version comes with 128K context length (in tokens) that it can support. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning and direct preference optimization, to ensure precise instruction adherence and robust safety measures.
692
+
Phi-3.5 Vision is a lightweight, state-of-the-art, open multimodal model. The model was built upon datasets that include synthetic data and filtered, publiclyavailable websites - with a focus on high-quality, reasoning-dense data, both on text and vision. The model belongs to the Phi-3 model family, and the multimodal version comes with 128K context length (in tokens) that it can support. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning and direct preference optimization, to ensure precise instruction adherence and robust safety measures.
693
693
694
694
695
695
You can learn more about the models in their respective model card:
@@ -1029,7 +1029,7 @@ Usage:
1029
1029
1030
1030
## Phi-3.5 chat model with vision
1031
1031
1032
-
Phi-3.5 Vision is a lightweight, state-of-the-art, open multimodal model. The model was built upon datasets that include synthetic data and filtered, publicly-available websites -with a focus on high-quality, reasoning-dense data, both on text and vision. The model belongs to the Phi-3 model family, and the multimodal version comes with128K context length (in tokens) that it can support. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning and direct preference optimization, to ensure precise instruction adherence and robust safety measures.
1032
+
Phi-3.5 Vision is a lightweight, state-of-the-art, open multimodal model. The model was built upon datasets that include synthetic data and filtered, publiclyavailable websites -with a focus on high-quality, reasoning-dense data, both on text and vision. The model belongs to the Phi-3 model family, and the multimodal version comes with128K context length (in tokens) that it can support. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning and direct preference optimization, to ensure precise instruction adherence and robust safety measures.
1033
1033
1034
1034
1035
1035
You can learn more about the models in their respective model card:
0 commit comments