Add OPT model support - Add OPT architecture support in C++ code - Im… #13799
+261
−5
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
…plement OPT-specific graph builder with separate Q/K/V projections - Add OPT model conversion support in Python - Add OPT tensor mappings and constants in gguf-py - Support some OPT model sizes - Tested with OPT-125M and OPT-13B models
|
hi, I tried to support OPTModel in Llama.cpp too, and I applied your diff on the new version of llamacpp but I found the output of OPT-6.7b is totally bullshitting, have you ever tested OPT-6.7b before? any advice on debugging? thanks!! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.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.
…plement OPT-specific graph builder with separate Q/K/V projections - Add OPT model conversion support in Python - Add OPT tensor mappings and constants in gguf-py - Support some OPT model sizes - Tested with OPT-125M and OPT-13B models
Make sure to read the contributing guidelines before submitting a PR