Uploaded model

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

Safetensors

Model size

0.1B params

Tensor type

BF16

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Qurtana/SmolLM-135M-Instruct-Reasoning-v0.1

Base model

Quantized

Quantized

(91)

this model