NovatasticRoScript
/

Atomight-V2.1-0.5B-Inference

Text Generation

reinforcement-learning

text-generation-inference

lm-evaluation-harness

Eval Results (legacy)

Model card Files Files and versions

NovatasticRoScript commited on 20 days ago

Commit

8207ae5

·

verified ·

1 Parent(s): 4d8ec54

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -25,7 +25,7 @@ metrics:
 # Atomight-V2.1-0.5B-Inference
 <p align="center">
-  <img src="official_radar_benchmark.png" alt="Atomight Footprint" width="500" style="max-width: 100%;">
 </p>
 **Atomight-V2.1-0.5B-Inference** is an ultra-compact, reasoning-oriented causal language model developed under the **Atomight Ecosystem**. Built on a Qwen-derived 494M parameter foundation, the model has been refined using **GRPO (Group Relative Policy Optimization)** reinforcement tuning.

 # Atomight-V2.1-0.5B-Inference
 <p align="center">
+  <img src="OfficialAtomight.png" alt="Atomight Logo" width="500" style="max-width: 100%;">
 </p>
 **Atomight-V2.1-0.5B-Inference** is an ultra-compact, reasoning-oriented causal language model developed under the **Atomight Ecosystem**. Built on a Qwen-derived 494M parameter foundation, the model has been refined using **GRPO (Group Relative Policy Optimization)** reinforcement tuning.