A simple unalignment fine-tune on ~900k tokens aiming to make the model more compliant and willing to handle user requests.

This is the same unalignment training seen in concedo/Beepo-22B, so big thanks to concedo for the dataset.

Chat template is same as the original, ChatML.

Safetensors

Model size

14.8B params

Tensor type

BF16

Inference Providers NEW

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

The model cannot be deployed to the HF Inference API: The model has no library tag.

Model tree for ToastyPigeon/Qwen2.5-14B-Instruct-1M-Unalign

Base model

Qwen/Qwen2.5-14B

Finetuned

Finetuned

(12)

this model

Finetunes

Merges

Quantizations

Collection including ToastyPigeon/Qwen2.5-14B-Instruct-1M-Unalign