vh/heretic
1
0
Fork 0
mirror of https://github.com/p-e-w/heretic.git synced 2026-09-29 07:21:27 -07:00
Code Issues Packages Projects Releases Wiki Activity

feat: support dataset specifications containing multiple individual datasets

Browse Source
This commit is contained in:
Philipp Emanuel Weidmann
2026-09-25 16:43:11 +05:30
parent dc6703788c
commit ffa66af2d4
13 changed files with 235 additions and 52 deletions
Download Patch File Download Diff File Expand all files Collapse all files
config.default.toml
+17
View File
@@ -102,6 +102,23 @@ max_shard_size = "5GB"
# System prompt to use when prompting the model.
system_prompt = "You are a helpful assistant."
# Dataset of prompts to use for automatically determining the optimal batch size.
[batch_size_test_prompts]
dataset = "mlabonne/harmless_alpaca"
split = "train[:256]"
column = "text"
# Dataset of prompts to use for automatically determining the response prefix.
[[response_prefix_test_prompts]]
dataset = "mlabonne/harmless_alpaca"
split = "train[:100]"
column = "text"
[[response_prefix_test_prompts]]
dataset = "mlabonne/harmful_behaviors"
split = "train[:100]"
column = "text"
# Plugin-specific settings live in top-level TOML tables.
#
# For scorer plugins, use: `[scorer.<ClassName>]` (and optionally `[scorer.<ClassName>_<instance_name>]` for instance-related config).