List the Qandy 1.0 27B dataset
Browse files
README.md
CHANGED
|
@@ -49,12 +49,18 @@ QANDY 2.0 27B is our own 27-billion-parameter financial model, and it powers QAN
|
|
| 49 |
|
| 50 |
Head-to-head results for QANDY 2.0 27B against Claude Opus 5.5 and GPT 6.1 Sol will be published on the QandyEval page once all three models have been run on the same frozen item set.
|
| 51 |
|
| 52 |
-
## Models on this page
|
| 53 |
|
| 54 |
| Model | Size | What it is |
|
| 55 |
|---|---|---|
|
| 56 |
| [Qandy 1.0 27B](https://huggingface.co/QandyAI/qandy-1.0-27B) | 27B | Our first 27B model, from Starburst, our trading research line. It is a reasoning model for crypto perpetual-futures entries. This is a recipe and evaluation release; the weights are not included. |
|
| 57 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
## Links
|
| 59 |
|
| 60 |
- Website: [qandy.ai](https://qandy.ai)
|
|
|
|
| 49 |
|
| 50 |
Head-to-head results for QANDY 2.0 27B against Claude Opus 5.5 and GPT 6.1 Sol will be published on the QandyEval page once all three models have been run on the same frozen item set.
|
| 51 |
|
| 52 |
+
## Models and datasets on this page
|
| 53 |
|
| 54 |
| Model | Size | What it is |
|
| 55 |
|---|---|---|
|
| 56 |
| [Qandy 1.0 27B](https://huggingface.co/QandyAI/qandy-1.0-27B) | 27B | Our first 27B model, from Starburst, our trading research line. It is a reasoning model for crypto perpetual-futures entries. This is a recipe and evaluation release; the weights are not included. |
|
| 57 |
|
| 58 |
+
**Datasets**
|
| 59 |
+
|
| 60 |
+
| Dataset | Rows | What it is |
|
| 61 |
+
|---|---|---|
|
| 62 |
+
| [Qandy 1.0 27B data](https://huggingface.co/datasets/QandyAI/qandy-1.0-27B-data) | 12,462 | The SFT and KTO training sets and the two evaluation sets behind Qandy 1.0 27B: crypto perpetual-futures snapshots paired with reasoned LONG, SHORT or NO TRADE decisions and their outcomes. |
|
| 63 |
+
|
| 64 |
## Links
|
| 65 |
|
| 66 |
- Website: [qandy.ai](https://qandy.ai)
|