List of Embedding Models in DKubeX LLM Catalog¶
The following list contains the embedding models which are currently registered with the DKubeX LLM Catalog on the current version of DKubeX (DKubeX v0.8.5.4.1).
Embedding Model Name |
Accelerator |
Trust Remote Code |
Max Total Tokens |
Number of GPUs needed |
---|---|---|---|---|
|
t4 |
true |
512 |
1 |
|
t4 |
true |
512 |
1 |
These embedding models can be deployed on the DKubeX platform without using any config files provided the resource and permission requirements are met. You can deploy these embedding models on DKubeX using local resources or using cloud resources using SkyPilot.
Note
For more information regarding deploying embedding models on DKubeX, refer to Deploying Embedding Models on DKubeX.
To deploy an embedding model using local resources, you can use the command given below. Replace the following fields in the command with the appropriate values:
<name of the deployment>
: Unique name for the embedding model deployment<emb Name>
: Name of the embedding model provided in the list above
Note
Use the --publish
flag if you want to make the deployment available for any user on the same setup to access and use.
d3x emb deploy --name <name of the deployment> --model <emb Name> --publish
d3x emb deploy -n bge-large --model BAAI--bge-large-en-v1-5 --publish
To deploy an embedding model using cloud resources via SkyPilot, you can use the command given below. Replace the following fields in the command with the appropriate values:
<name of the deployment>
: Unique name for the embedding model deployment<emb Name>
: Name of the embedding model provided in the list above
Note
Use the --publish
flag if you want to make the deployment available for any user on the same setup to access and use.
d3x emb deploy --name <name of the deployment> --model <emb Name> -sky --publish
d3x emb deploy -n bge-large --model BAAI--bge-large-en-v1-5 -sky --publish