Using Unsloth to train HuggingFaceTB/SmolLM2-360M-Instruct on HuggingFaceH4/MATH-500 for 1k steps. 8k context.
Model tree for JWI2123/SmolLM2-360M-Instruct-MATH
Base model
HuggingFaceTB/SmolLM2-360M-InstructUsing Unsloth to train HuggingFaceTB/SmolLM2-360M-Instruct on HuggingFaceH4/MATH-500 for 1k steps. 8k context.
Base model
HuggingFaceTB/SmolLM2-360M-Instruct