Add Llama/Llama2 support in Question-Answering#745
Conversation
|
Fixed issue reported GS-23: missing LlamaForQuestionAnswering class issue reported is fixed by applying huggingface/transformers 28777. Fixed run_qa.py script to support Llama tokenizer. |
|
|
6f1f112 to
61a701f
Compare
|
Verified with updated transformer v4.38.2 #788, work fine. |
61a701f to
fe4ea04
Compare
regisss
left a comment
There was a problem hiding this comment.
Can you update the main branch of your fork and rebase this PR on it please?
fe4ea04 to
6ad6b74
Compare
|
rebased |
regisss
left a comment
There was a problem hiding this comment.
LGTM!
I pushed two additional commits to refine a bit the README and run make style.
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
Added Llama/Llama2 support in Question-Answering