Merge pull request #733 from allenai/version-0.5.1

Bump to Version 0.5.1 for pip updates

.github/workflows/main.yml

@@ -148,7 +148,6 @@ jobs:
                 constraints:
                   cluster:
                     - ai2/general-cirrascale
-                    - ai2/general-cirrascale-a100-80g-ib
                     - ai2/allennlp-cirrascale
                 envVars:
                   - name: COMMIT_SHA

CHANGELOG.md

@@ -9,8 +9,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 
+## [v0.5.1]
+
+### Added
+
 - Added ability to try loading latest checkpoint from save folder using `--try_load_latest_save`.
 - Added support for flash attention and gradient checkpointing to `hf_olmo`.
+- Added `effective_n_kv_heads` to OLMoConfig for hacky VLLM support.
 
 ## [v0.5.0](https://github.com/allenai/OLMo/releases/tag/v0.5.0) - 2024-08-26
 

olmo/version.py

@@ -2,7 +2,7 @@
 _MINOR = "5"
 # On main and in a nightly release the patch should be one ahead of the last
 # released build.
-_PATCH = "0"
+_PATCH = "1"
 # This is mainly for nightly builds which have the suffix ".dev$DATE". See
 # https://semver.org/#is-v123-a-semantic-version for the semantics.
 _SUFFIX = ""