mirror of
https://github.com/garrytan/gstack.git
synced 2026-09-21 04:10:47 +02:00
chore: add braintrust + autoevals as dev dependencies
Backing the model benchmark with Braintrust's local eval runner and its autoevals scorer library instead of an in-house scoring engine. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Opus 4.8
parent
a84a6e233d
commit
313e8719f7
+3
-1
@@ -97,6 +97,8 @@
|
||||
],
|
||||
"devDependencies": {
|
||||
"@anthropic-ai/claude-agent-sdk": "0.2.117",
|
||||
"@huggingface/transformers": "^4.1.0"
|
||||
"@huggingface/transformers": "^4.1.0",
|
||||
"autoevals": "^0.3.0",
|
||||
"braintrust": "^3.24.0"
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user