FastFlowLM
/

Nanbeige4.1-3B-NPU2

Text Generation

Model card Files Files and versions

FastFlowLM commited on 22 days ago

Commit

c56dc44

·

verified ·

1 Parent(s): 61ccd61

Update README.md

Files changed (1) hide show

README.md +2 -4

README.md CHANGED Viewed

@@ -12,8 +12,7 @@ base_model:
 - Nanbeige/Nanbeige4-3B-Base
 ---
 <div align="center">
-<img src="figures/nbg.png" width="220" alt="Nanbeige Logo">
 </div>
@@ -23,8 +22,7 @@ base_model:
 Nanbeige4.1-3B is built upon Nanbeige4-3B-Base and represents an enhanced iteration of our previous reasoning model, Nanbeige4-3B-Thinking-2511, achieved through further post-training optimization with supervised fine-tuning (SFT) and reinforcement learning (RL). As a highly competitive open-source model at a small parameter scale, Nanbeige4.1-3B illustrates that compact models can simultaneously achieve robust **reasoning**, **preference alignment**, and **effective agentic behaviors**.
 <div align="center">
-<img src="figures/model_performance_comparison.png">
 </div>
 Specifically, Nanbeige4.1-3B exhibits the following key strengths:

 - Nanbeige/Nanbeige4-3B-Base
 ---
 <div align="center">
+  <img src="https://huggingface.co/Nanbeige/Nanbeige4.1-3B/resolve/main/figures/nbg.png" width="220" alt="Nanbeige Logo">
 </div>
 Nanbeige4.1-3B is built upon Nanbeige4-3B-Base and represents an enhanced iteration of our previous reasoning model, Nanbeige4-3B-Thinking-2511, achieved through further post-training optimization with supervised fine-tuning (SFT) and reinforcement learning (RL). As a highly competitive open-source model at a small parameter scale, Nanbeige4.1-3B illustrates that compact models can simultaneously achieve robust **reasoning**, **preference alignment**, and **effective agentic behaviors**.
 <div align="center">
+  <img src="https://huggingface.co/Nanbeige/Nanbeige4.1-3B/resolve/main/figures/model_performance_comparison.png" width="800" alt="Model Performance Comparison">
 </div>
 Specifically, Nanbeige4.1-3B exhibits the following key strengths: