Commit Graph

2 Commits

Author SHA1 Message Date
c753f72c85 Support for attention bias in gemma + refactor things a bit. (#1744)
* Support for attention bias in gemma + refactor things a bit.

* Fix the cuda tests.
2024-02-22 09:35:28 +01:00
0dee8ea19b Add the ChatGLM model. (#1237)
* Add the ChatGLM model.

* Rotary embeddings.

* Add to the forward pass.

* Add to the forward pass.

* Add the rotary embeddings.

* Add the KV cache.

* Add the chatglm example.

* Bugfix.

* More glm fixes.

* Fix some shape issues.

* Get the inference to work.
2024-02-09 11:51:38 +01:00