Update README.md

README.md

@@ -22,20 +22,9 @@ RL-trained Qwen3-8B on SWEsmith tasks (65k context with YaRN rope scaling factor
 ## Training Details
 
 - **Base model**: [laion/r2egym-nl2bash-stack-bugsseq-fixthink-again](https://huggingface.co/laion/r2egym-nl2bash-stack-bugsseq-fixthink-again) (Qwen3-8B SFT)
-- **Training method**: RLOO-N (Reinforcement Learning with Leave-One-Out baselines)
+- **Training method**: RLOO-N 
 - **Training data**: 2,500 SWEsmith tasks (oracle-verified, 120s timeout)
-- **Framework**: BenSkyRL + Harbor (Apptainer Bridge on JUWELS)
+- **Framework**: BenSkyRL + Harbor 
 - **Sandbox**: Apptainer containers with proxychains for internet access
 
-## Eval Results (dev_set_71_tasks, n=3)
 
-See results_20260316.md for full comparison tables.
-
-## Usage
-
-```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
-
-model = AutoModelForCausalLM.from_pretrained("laion/SweSmith-8B-SFT-Rope-step62")
-tokenizer = AutoTokenizer.from_pretrained("laion/SweSmith-8B-SFT-Rope-step62")
-```