Hugging Face's logo

mpasila
/
gpt-7b-nordic-prerelease-exl2-4bpw

Text Generation
Transformers
llama
Inference Endpoints
4-bit precision
exl2
Model card Files Community

This is an ExLlamaV2 quantized model in 4bpw of HPLT/gpt-7b-nordic-prerelease using the default calibration dataset.

Original Model card:

This is a pre-release checkpoint for a Nordic generative language model currently in training. This preliminary release is provided for HPLT (https://hplt-project.org/) deliverable 4.1 (“First language models trained”)(https://hplt-project.org/deliverables). Consult the HPLT website for further details. More documentation will be provided soon.

Downloads last month
21
Inference Providers NEW
Text Generation
This model is not currently available via any of the supported Inference Providers.

Model tree for mpasila/gpt-7b-nordic-prerelease-exl2-4bpw

Base model

HPLT/gpt-7b-nordic-prerelease
Quantized
(1)
this model

Collection including mpasila/gpt-7b-nordic-prerelease-exl2-4bpw