Skip to content

Commit f68e788

Browse files
authored
Release v0.5.13 (#4089)
1 parent 993393b commit f68e788

File tree

3 files changed

+43
-3
lines changed

3 files changed

+43
-3
lines changed

CHANGELOG.md

Lines changed: 41 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -2,6 +2,45 @@
22

33
## [Upcoming]
44

5+
## [v0.5.13] - 2026-02-25
6+
7+
- Previously, in `HuggingFaceClient`, Hugging Face models were loaded with `trust_remote_code=True` by default. This was a security risk as it permitted executing arbitrary code from the model repositories. This will no longer be done. If needed, `trust_remote_code` must be explicitly set in the `args` field in `model_deployments.yaml` for Hugging Face models. (#4054)
8+
- Previously, responses from models on the Mistral AI API were tokenized locally locally. These responses will no longer be tokenized. (#4084)
9+
10+
### Models
11+
12+
- Do not set `trust_remote_code=True` by default in HuggingFaceClient (#4054)
13+
- Add Grok 4 Fast and Grok 4.1 Fast (#4071)
14+
- Add GPT-5.2 (#4075)
15+
- Add Claude Sonnet 4.6 and Opus 4.6 (#4083)
16+
- Add Gemini 3.1 Pro (#4076)
17+
- Explicitly set `pad_token_id` for Hugging Face generations (#4087)
18+
- Support models on HuggingFace Inference Providers (#4086)
19+
20+
### Scenarios
21+
22+
- Add links to the cited papers in the schema for HEIM (#4063, #4074)
23+
24+
### Framework
25+
26+
- Add `--export-path` arg to helm-server for exporting a static website (#4047)
27+
- Use Python standard library for downloading files (#4052)
28+
- Use Python standard library for decompressing archives (#4051)
29+
- Add validation for schema YAML files (#4049)
30+
- Add optional dependencies for summarization metrics (#4067)
31+
32+
### Frontend
33+
34+
- Render whitespace in adapter values in frontend using CSS pre-wrap (#4062)
35+
- Render whitespace in model responses in proxy server frontend using CSS pre-wrap (#4085)
36+
37+
### Contributors
38+
39+
Thank you to the following contributors for your work on this HELM release!
40+
41+
- @HetanshWaghela
42+
- @yifanmai
43+
544
## [v0.5.12] - 2026-01-27
645

746
### Models
@@ -1282,7 +1321,8 @@ Thank you to the following contributors for your contributions to this HELM rele
12821321

12831322
- Initial release
12841323

1285-
[upcoming]: https://github.com/stanford-crfm/helm/compare/v0.5.12...HEAD
1324+
[upcoming]: https://github.com/stanford-crfm/helm/compare/v0.5.13...HEAD
1325+
[v0.5.13]: https://github.com/stanford-crfm/helm/releases/tag/v0.5.13
12861326
[v0.5.12]: https://github.com/stanford-crfm/helm/releases/tag/v0.5.12
12871327
[v0.5.11]: https://github.com/stanford-crfm/helm/releases/tag/v0.5.11
12881328
[v0.5.10]: https://github.com/stanford-crfm/helm/releases/tag/v0.5.10

pyproject.toml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
44

55
[project]
66
name = "crfm-helm"
7-
version = "0.5.12"
7+
version = "0.5.13"
88
authors = [
99
{ name = "Stanford CRFM", email = "contact-crfm@stanford.edu" }
1010
]

uv.lock

Lines changed: 1 addition & 1 deletion
Some generated files are not rendered by default. Learn more about customizing how changed files appear on GitHub.

0 commit comments

Comments
 (0)