JaniRaviRash-523 commited on
Commit
86e9eab
·
verified ·
1 Parent(s): 3944e9c

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +9 -5
README.md CHANGED
@@ -2,7 +2,15 @@
2
 
3
  ## Team
4
  - **Team name:** SinBotics
5
- - **Members / corresponding member:** <NAME(S), AFFILIATION, E-MAIL>
 
 
 
 
 
 
 
 
6
 
7
  ## System summary
8
  - **Base model:** [`Qwen/Qwen3.5-4B`](https://huggingface.co/Qwen/Qwen3.5-4B), revision `851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a` (released 2026-02-27, Apache-2.0, open weights).
@@ -40,10 +48,6 @@ python inference.py
40
  | Training validation (2,745 held-out questions from the two training sources, digit prompt) | 44.4% → 54.8% after fine-tuning |
41
  | Final run | answers stated in the reasoning for 56.0% of questions; the rest hit the 4,096-token limit and are read off after the cue |
42
 
43
- ## Disclosure
44
- <!-- TEAM: check and complete this section before uploading -->
45
- - We chose the final configuration (base model Qwen3.5-4B, the combined-data adapter, and thinking mode) by comparing candidate systems on a 300-question subset of the shared-task test questions (100 per level), scored with answers we had for that subset. No test question or answer was used for training.
46
-
47
  ## Files
48
  - `inference.py` – the exact system that produced our final Codabench submission (self-contained; see above)
49
  - `predictions.jsonl` – the exact file we submitted to the final leaderboard
 
2
 
3
  ## Team
4
  - **Team name:** SinBotics
5
+
6
+ **Members:**
7
+
8
+ | Name | Affiliation | E-mail |
9
+ |---|---|---|
10
+ | Sachintha Weththasinghe | SLIIT | akalankasachintha125@gmail.com |
11
+ | Hasitha Hirushan | SLIIT | hasithahja@gmail.com |
12
+ | Hasaan Saadhiq | SLIIT | hsaadhiq@gmail.com |
13
+ | Janith Ramanayake | UoM | janithramanayake523@gmail.com |
14
 
15
  ## System summary
16
  - **Base model:** [`Qwen/Qwen3.5-4B`](https://huggingface.co/Qwen/Qwen3.5-4B), revision `851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a` (released 2026-02-27, Apache-2.0, open weights).
 
48
  | Training validation (2,745 held-out questions from the two training sources, digit prompt) | 44.4% → 54.8% after fine-tuning |
49
  | Final run | answers stated in the reasoning for 56.0% of questions; the rest hit the 4,096-token limit and are read off after the cue |
50
 
 
 
 
 
51
  ## Files
52
  - `inference.py` – the exact system that produced our final Codabench submission (self-contained; see above)
53
  - `predictions.jsonl` – the exact file we submitted to the final leaderboard