CoolFace
Modelpublic

latam-gpt/Wayra-Perplexity-Estimator-55M

sourceHugging Faceapache-2.0updated 4mo agoView on Hugging Face
21likes1.7kdownloads
root
file.gitattributes2 KBdownload
filearchitecture.png88 KBdownload
filebenchmarks.png133 KBdownload
fileconfig.json880 Bdownload
filemodel.safetensors211.2 MBdownload
fileREADME.md7 KBdownload
filespecial_tokens_map.json301 Bdownload
filetensorrt_config.json449 Bdownload
filetensorrt_inference.py5 KBdownload
filetensorrt_optimization.png103 KBdownload
filetensorrt_requirements.txt633 Bdownload
filetokenizer_config.json49 KBdownload
filetokenizer.json16.4 MBdownload
filewayra-f16.gguf105.6 MBdownload
filewayra-f32.gguf211.2 MBdownload
filewayra-q4_0.gguf29.8 MBdownload
filewayra-q4_k_m.gguf36.1 MBdownload
filewayra-q4_k_s.gguf36.1 MBdownload
filewayra-q5_0.gguf36.4 MBdownload
filewayra-q5_k_m.gguf39.5 MBdownload
filewayra-q5_k_s.gguf39.5 MBdownload
filewayra-q6_k.gguf55.7 MBdownload
filewayra-q8_0.gguf56.1 MBdownload
filewayrappl_fp16_bs2048.engine106.7 MBdownload

latam-gpt/Wayra-Perplexity-Estimator-55M · main · files are served by the source, never re-hosted here