qwen 2.5 1.5b instruct trained to give 6-letter codes representing text, original data generated by qwen 2.5 7b based on the first 20k items in the first shard of the raw deduplicated pile

check out the gguf in the repo at distilled_labeler_f16.gguf

Downloads last month
31
Safetensors
Model size
1.54B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for boopysaur/qwen-2.5-1.5b-instruct-distilled-vibe-labeler

Base model

Qwen/Qwen2.5-1.5B
Quantized
(68)
this model

Datasets used to train boopysaur/qwen-2.5-1.5b-instruct-distilled-vibe-labeler