janhq
/

Jan-v1-edge

@@ -3,7 +3,7 @@ license: apache-2.0
 language:
 - en
 base_model:
-- Qwen/Qwen3-1.7B
 pipeline_tag: text-generation
 library_name: transformers
 ---
@@ -26,7 +26,7 @@ Jan-edge was developed through a two-phase post-training process. The first phas
 **Jan-edge** achieves **84.2% accuracy without a system prompt**, and **84.8% with a system prompt**. The small 0.6% gap highlights the model’s stability and reliability across prompting conditions — a critical property for real-world deployments where system prompts may vary.
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/655e3b59d5c0d3db5359ca3c/xMtldxoYpghypsbc19qEr.png)
 ### Chat & Instruction Following

 language:
 - en
 base_model:
+- Menlo/Jan-edge
 pipeline_tag: text-generation
 library_name: transformers
 ---
 **Jan-edge** achieves **84.2% accuracy without a system prompt**, and **84.8% with a system prompt**. The small 0.6% gap highlights the model’s stability and reliability across prompting conditions — a critical property for real-world deployments where system prompts may vary.
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/655e3b59d5c0d3db5359ca3c/o-nO_cC_Fb8n_u-ShQUuc.png)
 ### Chat & Instruction Following