fix: trl 0.9.6 + bitsandbytes 0.43.1 cu118

Dockerfile

@@ -10,20 +10,24 @@ RUN apt-get update && apt-get install -y git build-essential && rm -rf /var/lib/
 
 WORKDIR /app
 
+RUN pip install --no-cache-dir torch==2.1.2 --index-url https://download.pytorch.org/whl/cu118
+
 RUN pip install --no-cache-dir numpy==1.26.4
 
-RUN pip install --no-cache-dir torch==2.1.2 --index-url https://download.pytorch.org/whl/cu118
+RUN pip install --no-cache-dir trl==0.9.6
 
 RUN pip install --no-cache-dir \
     transformers==4.40.0 \
     accelerate==0.30.0 \
     peft==0.10.0 \
-    trl==0.8.6 \
-    bitsandbytes==0.43.0 \
+    bitsandbytes==0.43.1 \
     wandb datasets huggingface_hub matplotlib Pillow
 
-RUN pip install --no-cache-dir git+https://github.com/Jayant-kernel/DECEIT-the-ai-truth-environment-.git && \
-    python -c "import deceit_env; print('deceit_env found')"
+RUN pip install --no-cache-dir \
+    git+https://github.com/Jayant-kernel/DECEIT-the-ai-truth-environment-.git
+
+RUN python -c "from trl import GRPOConfig, GRPOTrainer; print('TRL OK')"
+RUN python -c "import bitsandbytes; print('BNB OK')"
 
 RUN mkdir -p /usr/local/lib/python3.10/site-packages/deceit_env/data/ && \
     mkdir -p /usr/local/lib/python3.10/site-packages/deceit_env/server/ && \