Qwerky-QwQ-32B

The following is a model converted from Qwen 32B QWQ, to the RWKV based architecture. For existing details of the process from our previous release, find it [here]: https://huggingface.co/recursal/QRWKV6-32B-Instruct-Preview-v0.1

Benchmarks for Qwerky-QwQ-32B and the Qwerky-72B models

Tasks Metric Qwerky-QwQ-32B Qwen/QwQ-32B Qwerky-72B Qwen2.5-72B-Instruct
arc_challenge acc_norm 0.5640 0.5563 0.6382 0.6323
arc_easy acc_norm 0.7837 0.7866 0.8443 0.8329
hellaswag acc_norm 0.8303 0.8407 0.8573 0.8736
lambada_openai acc 0.6621 0.6683 0.7539 0.7506
piqa acc 0.8036 0.7976 0.8248 0.8357
sciq acc 0.9630 0.9630 0.9670 0.9740
winogrande acc 0.7324 0.7048 0.7956 0.7632
mmlu acc 0.7431 0.7985 0.7746 0.8338

All benchmark's besides MMLU are 0 n-shot, and is version 1, MMLU is version 2

Downloads last month
68
Safetensors
Model size
34.9B 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 HF Inference API does not support model that require custom code execution.