feat: support arbitrary HuggingFace models via custom repo ID#169
Draft
HWiese1980 wants to merge 1 commit into1038lab:mainfrom
Draft
feat: support arbitrary HuggingFace models via custom repo ID#169HWiese1980 wants to merge 1 commit into1038lab:mainfrom
HWiese1980 wants to merge 1 commit into1038lab:mainfrom
Conversation
Add custom_model_repo input to all HF nodes (QwenVL, QwenVL Advanced, PromptEnhancer) allowing users to specify any HuggingFace repo ID (e.g. user/model-name) to override the predefined model dropdown. Add custom_repo_id, custom_model_file, and custom_mmproj_file inputs to all GGUF nodes (QwenVL GGUF, QwenVL GGUF Advanced, GGUF Prompt Enhancer) for downloading and using arbitrary GGUF models from HF. Key changes: - ensure_model() accepts direct HF repo IDs (user/model format) - enforce_memory() gracefully skips VRAM checks for unknown models - GGUF _load_model() bypasses catalog when custom fields are provided - PromptEnhancer _load_text_model() handles direct repo IDs - All changes are backward-compatible (empty fields use dropdown)
HWiese1980
changed the title
HWiese1980
changed the title
Author
|
I'll mark this as draft for now because I want to harmonize it with the already existing |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Add custom_model_repo input to all HF nodes (QwenVL, QwenVL Advanced, PromptEnhancer) allowing users to specify any HuggingFace repo ID (e.g. user/model-name) to override the predefined model dropdown.
Add custom_repo_id, custom_model_file, and custom_mmproj_file inputs to all GGUF nodes (QwenVL GGUF, QwenVL GGUF Advanced, GGUF Prompt Enhancer) for downloading and using arbitrary GGUF models from HF.
Key changes: