Skip to content

Add CCLRouter: causal representation routing with RouterBench pretrai… #153

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
kiotori wants to merge 4 commits into
base: main
Choose a base branch
from
Open

Add CCLRouter: causal representation routing with RouterBench pretrai… #153

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
0f586bb
Add CCLRouter: causal representation routing with RouterBench pretrai…
Jun 21, 2026
639d317
fix: add prompt field to prediction files
Jun 22, 2026
1a43308
fix: exact prompts from sweep, 8400 entries, validated model names
Jun 22, 2026
5ec8392
fix: add generated_result placeholders for format validation
Jun 22, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
34 changes: 34 additions & 0 deletions router_inference/config/cclrouter.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,34 @@
{
"pipeline_params": {
"router_name": "cclrouter",
"router_cls_name": "CCLRouter",
"models": [
"Qwen/Qwen3-Coder-Next",
"alibaba/qwen3-235b-a22b-instruct-2507",
"alibaba/qwen3-30b-a3b-instruct-2507",
"anthropic/claude-haiku-4-5-20251001",
"anthropic/claude-sonnet-4",
"anthropic/claude-sonnet-4-5",
"deepseek/deepseek-chat",
"deepseek/deepseek-reasoner",
"deepseek/deepseek-v3.2",
"deepseek/deepseek-v4-flash",
"gemini-2.5-flash",
"google/gemini-2.5-flash",
"google/gemini-2.5-flash-lite",
"google/gemini-3.1-flash-lite",
"gpt-4o-mini",
"gpt-5-nano",
"gpt-5.4-mini",
"grok-4-1-fast-reasoning",
"openai/gpt-4o-mini",
"openai/gpt-5-mini",
"qwen/qwen3-235b-a22b-2507",
"qwen/qwen3-30b-a3b-instruct-2507",
"qwen/qwen3.5-9b"
],
"description": "CCLRouter: Causal representation (c=128d) pretrained on RouterBench (36K queries, 11 models, 80 domains). Lightweight LogisticRegression head (128->23) fine-tuned on RouterArena sub_10 (809 queries). Routes by argmax P(correct|c). Motivation: domain-invariant task representation enables efficient few-shot routing.",
"c_dim": 128,
"pretrain_data": "RouterBench (withmartian/routerbench)"
}
}
Loading
Loading