PowerInfer
/

SmallThinker-3B-Preview

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

yixinsong commited on 16 days ago

Commit

f0ad825

·

1 Parent(s): 46c2512

minor

Files changed (2) hide show

.gitattributes +0 -1
README.md +1 -1

.gitattributes CHANGED Viewed

@@ -45,5 +45,4 @@ rng_state_7.pth filter=lfs diff=lfs merge=lfs -text
 rng_state_0.pth filter=lfs diff=lfs merge=lfs -text
 rng_state_4.pth filter=lfs diff=lfs merge=lfs -text
 latest filter=lfs diff=lfs merge=lfs -text
-LICENSE filter=lfs diff=lfs merge=lfs -text
 rng_state_2.pth filter=lfs diff=lfs merge=lfs -text

 rng_state_0.pth filter=lfs diff=lfs merge=lfs -text
 rng_state_4.pth filter=lfs diff=lfs merge=lfs -text
 latest filter=lfs diff=lfs merge=lfs -text
 rng_state_2.pth filter=lfs diff=lfs merge=lfs -text

README.md CHANGED Viewed

@@ -20,7 +20,7 @@ We introduce **SmallThinker-3B-alpha**, a new model fine-tuned from the [Qwen2.5
 SmallThinker is designed for the following use cases:
 1.  **Edge Deployment:** Its small size makes it ideal for deployment on resource-constrained devices.
-2.  **Draft Model for QwQ-32B-Preview:** QwQ can serve as a fast and efficient draft model for the larger QwQ-32B-Preview model.
 ## Limitations & Disclaimer

 SmallThinker is designed for the following use cases:
 1.  **Edge Deployment:** Its small size makes it ideal for deployment on resource-constrained devices.
+2.  **Draft Model for QwQ-32B-Preview:** SmallThinker can serve as a fast and efficient draft model for the larger QwQ-32B-Preview model.
 ## Limitations & Disclaimer