Add mascot image and thumbnail back to model card
Browse files
README.md
CHANGED
|
@@ -12,8 +12,13 @@ datasets:
|
|
| 12 |
- KRLabsOrg/tool-output-extraction-swebench
|
| 13 |
base_model: Qwen/Qwen3.5-2B
|
| 14 |
pipeline_tag: text-generation
|
|
|
|
| 15 |
---
|
| 16 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
# Squeez-2B
|
| 18 |
|
| 19 |
**Squeez-2B** is a 2B parameter model fine-tuned from Qwen 3.5 2B for task-conditioned tool-output pruning in coding agents. Given a focused query and one raw tool observation, it extracts the smallest verbatim evidence block the agent should inspect next — removing **92%** of input tokens while retaining **0.86 recall**.
|
|
|
|
| 12 |
- KRLabsOrg/tool-output-extraction-swebench
|
| 13 |
base_model: Qwen/Qwen3.5-2B
|
| 14 |
pipeline_tag: text-generation
|
| 15 |
+
thumbnail: https://raw.githubusercontent.com/KRLabsOrg/squeez/main/assets/squeez_mascot.png
|
| 16 |
---
|
| 17 |
|
| 18 |
+
<p align="center">
|
| 19 |
+
<img src="https://raw.githubusercontent.com/KRLabsOrg/squeez/main/assets/squeez_mascot.png" alt="Squeez mascot" width="180">
|
| 20 |
+
</p>
|
| 21 |
+
|
| 22 |
# Squeez-2B
|
| 23 |
|
| 24 |
**Squeez-2B** is a 2B parameter model fine-tuned from Qwen 3.5 2B for task-conditioned tool-output pruning in coding agents. Given a focused query and one raw tool observation, it extracts the smallest verbatim evidence block the agent should inspect next — removing **92%** of input tokens while retaining **0.86 recall**.
|