Clarifications on the "llama" labeling for Velvet on Ollama
#11
by
Kar0nte
- opened
Hi,
I noticed that the Velvet-2B/14B model by Almawave, described as developed from scratch and not derived from Llama or Mistral, is listed on Ollama with the label "model: llama." This seems to contradict the official documentation, which states that Velvet is an independent base model.
My question is:
Is this a labeling error on Ollama?
Or could it be related to technical compatibility with frameworks like llama.cpp?
Thank you in advance for any clarification!
Hi, we used llmapa.cpp to make our model compatible with the Ollama framework. The 'llama' label you mentioned is not related to the Velvet neural architecture itself, but rather depends on how Ollama represents our model.
Thank you for you interest in Velvet