Edit model card

GeM2-Llamion-14B

We have released Llamion as GeM 2.0, the second series of generative models developed by VAIV Company to address the our principal business needs.

Llamion (Llamafied Orion) is derived from transforming the Orion model into the standard LLaMA architecture through parameter mapping and offline knowledge transfer. Further technical specifications and study results will be detailed in our upcoming paper, available on this page.

vaiv_png

Notably, the LongChat model supports an extensive text range of 200K tokens. The following figure shows the perplexity of models on English Wikipedia corpus and Korean Wikipedia corpus, respectively.

ppl_wiki_enko

Contributors

Downloads last month
2,878
Safetensors
Model size
14.5B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for vaiv/GeM2-Llamion-14B-LongChat

Adapters
2 models
Quantizations
5 models