Update README.md

README.md

@@ -1,21 +1,19 @@
----
-base_model: NovatasticRoScript/Atomight-V2.5-1.7B-C1
-tags:
-- text-generation-inference
-- transformers
-- unsloth
-- qwen3
-license: apache-2.0
-language:
-- en
----
+Other details for this model soon. Wait for further information and details. 
 
-# Uploaded finetuned  model
+## Self-reported benchmark results
 
-- **Developed by:** NovatasticRoScript
-- **License:** apache-2.0
-- **Finetuned from model :** NovatasticRoScript/Atomight-V2.5-1.7B-C1
+These results are self-reported for `NovatasticRoScript/Atomight-V2.5-1.7B`.
 
-This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+| Benchmark | Metric | Score |
+|---|---:|---:|
+| ARC-Challenge | Accuracy (normalized) | 43.00 |
+| HellaSwag | Accuracy (normalized) | 60.43 |
+| WinoGrande | Accuracy | 61.09 |
+| TruthfulQA MC2 | Accuracy | 45.89 |
+| HumanEval | Pass@1 | 40.24 |
+| MBPP | Pass@1 | 42.80 |
+| MMLU | Accuracy | 55.68 |
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+### Notes
+- GSM8K is tracked separately in Hugging Face evaluation results.
+- The other scores are listed here as self-reported model card results.