Model card for demo-SmolLM2-135M-Instruct
This model was trained using Hugging Face Jobs using trl and the HuggingFaceTB/smol-smoltalk dataset on 3000 steps.
Model card for demo-SmolLM2-135M-Instruct
This model was trained using Hugging Face Jobs using trl and the HuggingFaceTB/smol-smoltalk dataset on 3000 steps.