mindchain/rlm-arithmetic-training
Upload train_arithmetic_v9_no_lora.py with huggingface_hub
Upload Dockerfile with huggingface_hub
Upload Dockerfile with huggingface_hub
Upload train_arithmetic_v8_simplified_lora.py with huggingface_hub
Upload train_arithmetic_v7_clean.py with huggingface_hub
Upload Dockerfile with huggingface_hub
Upload train_arithmetic_v6_openvino.py with huggingface_hub
Upload train_arithmetic_v6_openvino.py with huggingface_hub
Upload requirements_v6.txt with huggingface_hub
Upload Dockerfile with huggingface_hub
Upload Dockerfile with huggingface_hub
Upload Dockerfile with huggingface_hub
Upload train_arithmetic_v5_ultimate.py with huggingface_hub
Upload Dockerfile with huggingface_hub
Upload Dockerfile_v5 with huggingface_hub
Upload requirements_v5.txt with huggingface_hub
Upload train_arithmetic_v5_ultimate.py with huggingface_hub
Upload train_arithmetic_v3.py with huggingface_hub
Upload Dockerfile with huggingface_hub
Upload train_arithmetic_v3.py with huggingface_hub
Upload train_arithmetic_v2.py with huggingface_hub
Upload Dockerfile with huggingface_hub
Upload train_arithmetic_v2.py with huggingface_hub
Fix hang: remove use_cpu parameter, reduce generations to 2, batch to 2, steps to 20
Fix NoneType.shape error: device handling, CPU optimizer, safe tensor ops
Upload train_arithmetic.py with huggingface_hub
Upload README.md with huggingface_hub
Upload requirements.txt with huggingface_hub
Upload Dockerfile with huggingface_hub
Upload train_arithmetic.py with huggingface_hub
initial commit