You should try our new, experimental version with better performance: Pinkstack/Superthoughts-lite-1.8B-experimental-o1

this model uses the ChatML format

  • trained on 9.5K HTML,CSS codes (although performance there is still lacking)
  • 181K QwQ chats (cleaned)
  • 140K Sonnet 3.5 (cleaned)

Uploaded model

  • Developed by: Pinkstack
  • License: apache-2.0
  • Finetuned from model : Pinkstack/PARM-2-Smollm2-1.7B-Lcot-PyTorch

made with unsloth

Downloads last month
183
Safetensors
Model size
1.71B params
Tensor type
FP16
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for Pinkstack/PARM-2-TINY-1.7B-QwQ-o1

Collection including Pinkstack/PARM-2-TINY-1.7B-QwQ-o1