nanzhang

/

QuantLRM-Olmo-3-7B-Think-DPO-3-bit

like 0

Hi! I'm Niels from the Hugging Face community science team. This PR aims to enhance the discoverability and clarity of this model by:

• Adding the pipeline_tag: text-generation to reflect its primary function.
• Including library_name: transformers as the model uses Olmo3ForCausalLM architecture and mentions transformers compatibility.
• Specifying base_model: allenai/Olmo-3-7B-Think-DPO to clearly link to its original foundation.
• Adding the reasoning tag for better categorization.
• Updating the paper link to the official Hugging Face Papers URL.
• Hyperlinking the base model in the "Uses" section for convenience.

These updates align with best practices for model cards on the Hugging Face Hub, making the model easier to find and understand.