thinkwee
/

NOVER1-Qwen3-4B

Question Answering

text-generation

general_reasoning

text-generation-inference

Model card Files Files and versions

thinkwee commited on Aug 20

Commit

37b597f

·

verified ·

1 Parent(s): 4c4ab04

Update README.md

Files changed (1) hide show

README.md +3 -1

README.md CHANGED Viewed

@@ -14,6 +14,8 @@ datasets:
 language:
 - en
 pipeline_tag: question-answering
 ---
 <div align="center">
@@ -33,7 +35,7 @@ It is trained on several general reasoning datasets with freeform text answers,
 - **Base Model**: [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507)
 - **Training Method**: NOVER with LoRA finetuning
 - **Dataset**: Modified [NOVEReason_5k_reasoning](https://huggingface.co/datasets/thinkwee/NOVEReason_5k) dataset with custom tags
-- **Finetuning Detail**: [NOVER1-Qwen3-4B config]()
 ## Usage
 ```python

 language:
 - en
 pipeline_tag: question-answering
+metrics:
+- accuracy
 ---
 <div align="center">
 - **Base Model**: [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507)
 - **Training Method**: NOVER with LoRA finetuning
 - **Dataset**: Modified [NOVEReason_5k_reasoning](https://huggingface.co/datasets/thinkwee/NOVEReason_5k) dataset with custom tags
+- **Finetuning Detail**: [NOVER1-Qwen3-4B config](https://github.com/thinkwee/NOVER/blob/main/config/qwen3.yaml)
 ## Usage
 ```python