Skip to content

Support VLM finetuning #183

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
nikita-smetanin merged 1 commit into from
Dec 23, 2025
Merged

Support VLM finetuning #183

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 13 additions & 0 deletions openapi.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1684,6 +1684,8 @@ paths:
oneOf:
- $ref: '#/components/schemas/FullTrainingType'
- $ref: '#/components/schemas/LoRATrainingType'
multimodal_params:
$ref: '#/components/schemas/MultimodalParams'
from_checkpoint:
type: string
description: The checkpoint identifier to continue training from a previous fine-tuning job. Format is `{$JOB_ID}` or `{$OUTPUT_MODEL_NAME}` or `{$JOB_ID}:{$STEP}` or `{$OUTPUT_MODEL_NAME}:{$STEP}`. The step value is optional; without it, the final checkpoint will be used.
Expand Down Expand Up @@ -1823,6 +1825,8 @@ paths:
oneOf:
- $ref: '#/components/schemas/FullTrainingType'
- $ref: '#/components/schemas/LoRATrainingType'
multimodal_params:
$ref: '#/components/schemas/MultimodalParams'
from_checkpoint:
type: string
description: The checkpoint identifier to continue training from a previous fine-tuning job. Format is `{$JOB_ID}` or `{$OUTPUT_MODEL_NAME}` or `{$JOB_ID}:{$STEP}` or `{$OUTPUT_MODEL_NAME}:{$STEP}`. The step value is optional; without it, the final checkpoint will be used.
Expand Down Expand Up @@ -7436,6 +7440,8 @@ components:
oneOf:
- $ref: '#/components/schemas/FullTrainingType'
- $ref: '#/components/schemas/LoRATrainingType'
multimodal_params:
$ref: '#/components/schemas/MultimodalParams'
status:
$ref: '#/components/schemas/FinetuneJobStatus'
job_id:
Expand Down Expand Up @@ -7832,6 +7838,13 @@ components:
required:
- method

MultimodalParams:
type: object
properties:
train_vision:
type: boolean
description: Whether to train the vision encoder of the model. Only available for multimodal models.

LRScheduler:
type: object
properties:
Expand Down