Hugging Face Models Support #4
Closed
Conversation
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
…ove the required_inputs attribute and to consolidate the logic to the model-based validation. also, removed the legacy operator type label used by the scheduler, in favor of the graph based scheduler logic which, at an even lower level, groks the fan-in, fan-out, and recurrent structure of operators in the DAG.
…raph representation
- Update vmap.py to use new TransformError class with context - Update pmap.py to use ValidationError, TransformError, and ParallelExecutionError - Replace custom exception classes with unified EmberError hierarchy - Improve error messages with additional context data This is the first step in a systematic rollout of the new exception architecture.
- Update XCS exceptions to inherit from centralized error hierarchy - Maintain backward compatibility with diagnostic_context attribute - Preserve original API surface for smooth transition - Implement proper context handling with new exception base classes This change reduces duplication while ensuring existing code continues to work with the improved exception system.
Updated pmap.py to use the new exception hierarchy consistently: - Changed comment to clarify exception usage - Made code more consistent with the overall architecture principles - Removed references to legacy exception handling This change improves error handling readability and aligns with the project's domain-driven exception architecture.
…debug, passing 4/5
…re vllm being passed in
jaredquincy
force-pushed
the
main
branch
5 times, most recently
from
4e9da19 to
2fb3b1b
Compare
Author
|
@jaredquincy As per Slack, just bumping to re-open this again |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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.
This PR adds support for Hugging Face models in the Ember framework, enabling access to a wide range of models (including open source LLMs) through both the Hugging Face Inference API and local model loading.
Key Features
HuggingFace Provider Implementation: Full provider implementation with proper error handling, retries, and parameter validation
Dual Inference Options: Support for both remote inference via the HF Inference API and local model inference
Added example using Mistral 7B Instruct v0.2
(Testing) Added unit tests for the HuggingFace provider implementation
Notes
Requires HUGGINGFACE_API_KEY environment variable for remote inference
Model from Hugging Face needs to have HF Inference
huggingface_discovery is currently hardcoded to a couple of models. TODO: We need to make a design decision whether it makes sense to implement discovery either per author or not at all due to the sheer size of models available.
Same as [Move over to pyember/ember] Hugging Face Models Support jaredquincy/ember#16. Merged fork of jaredquincy/ember kunalagrawal2/ember:huggingface into fork of pyember/ember, kunalagrawal2/pyember-ember:huggingface (should merge cleanly as most changes were resolved already)