Highly advanced based model for training:

Sequence Length: 131072
Parm 2 ultra: trained for on OpenO1 chats, sonnet 3.5, qwq messages.

Downloads last month: 58

Safetensors

Model size

3.09B params

Tensor type

FP16

·

Inference Providers NEW

Text Generation

This model is not currently available via any of the supported Inference Providers.

Model tree for Pinkstack/PARM-v2-ULTRA-o1-3B-vLLM

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-3B-Instruct

Finetuned

Pinkstack/PARM-V1.5-base-QwQ-Qwen-2.5-o1-3B

Finetuned

(1)

this model

Collection including Pinkstack/PARM-v2-ULTRA-o1-3B-vLLM

Experimental models

Models which we made as an experiment. Usually more advanced chat models. • 5 items • Updated 13 days ago • 2