Skip to content

Commit 4fd130b

Browse files
committed
more acrolinx fixes
1 parent 9a8562e commit 4fd130b

File tree

4 files changed

+16
-16
lines changed

4 files changed

+16
-16
lines changed

articles/ai-studio/how-to/deploy-models-phi-3-5-vision.md

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -27,7 +27,7 @@ The Phi-3.5 small language models (SLMs) are a collection of instruction-tuned g
2727

2828
## Phi-3.5 chat model with vision
2929

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, 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.
3131

3232

3333
You can learn more about the models in their respective model card:
@@ -347,7 +347,7 @@ Usage:
347347

348348
## Phi-3.5 chat model with vision
349349

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, 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.
351351

352352

353353
You can learn more about the models in their respective model card:
@@ -690,7 +690,7 @@ Usage:
690690
691691
## Phi-3.5 chat model with vision
692692
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, 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.
694694
695695
696696
You can learn more about the models in their respective model card:
@@ -1030,7 +1030,7 @@ Usage:
10301030

10311031
## Phi-3.5 chat model with vision
10321032

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 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.
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 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.
10341034

10351035

10361036
You can learn more about the models in their respective model card:

articles/ai-studio/how-to/deploy-models-phi-3-vision.md

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -27,7 +27,7 @@ The Phi-3 family of small language models (SLMs) is a collection of instruction-
2727

2828
## Phi-3 chat model with vision
2929

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, 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.
3131

3232

3333
You can learn more about the models in their respective model card:
@@ -347,7 +347,7 @@ Usage:
347347

348348
## Phi-3 chat model with vision
349349

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, 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.
351351

352352

353353
You can learn more about the models in their respective model card:
@@ -690,7 +690,7 @@ Usage:
690690
691691
## Phi-3 chat model with vision
692692
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, 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.
694694
695695
696696
You can learn more about the models in their respective model card:
@@ -1030,7 +1030,7 @@ Usage:
10301030

10311031
## Phi-3 chat model with vision
10321032

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 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.
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 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.
10341034

10351035

10361036
You can learn more about the models in their respective model card:

articles/machine-learning/how-to-deploy-models-phi-3-5-vision.md

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -26,7 +26,7 @@ The Phi-3.5 small language models (SLMs) are a collection of instruction-tuned g
2626

2727
## Phi-3.5 chat model with vision
2828

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, 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.
3030

3131

3232
You can learn more about the models in their respective model card:
@@ -346,7 +346,7 @@ Usage:
346346

347347
## Phi-3.5 chat model with vision
348348

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, 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.
350350

351351

352352
You can learn more about the models in their respective model card:
@@ -689,7 +689,7 @@ Usage:
689689
690690
## Phi-3.5 chat model with vision
691691
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, 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.
693693
694694
695695
You can learn more about the models in their respective model card:
@@ -1029,7 +1029,7 @@ Usage:
10291029

10301030
## Phi-3.5 chat model with vision
10311031

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 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.
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 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.
10331033

10341034

10351035
You can learn more about the models in their respective model card:

0 commit comments

Comments
 (0)