Mistral-related models for QnA (#34045)

* mistral qna start

* mixtral qna

* oops

* qwen2 qna

* qwen2moe qna

* add missing input embed methods

* add copied to all methods, can't directly from llama due to the prefix

* make top level copied from
This commit is contained in:
Anton Vlasjuk
2024-10-14 08:53:32 +02:00
committed by GitHub
parent 37ea04013b
commit 7434c0ed21
19 changed files with 507 additions and 4 deletions

View File

@@ -209,3 +209,7 @@ A list of official Hugging Face and community (indicated by 🌎) resources to h
[[autodoc]] MixtralForTokenClassification
- forward
## MixtralForQuestionAnswering
[[autodoc]] MixtralForQuestionAnswering
- forward