kushalpatil/jevify-gemma4-26b-a4b-lora
Text Generation • Updated • 33
Kushal Patil
kushalpatil
AI & ML interests
None yet
Recent Activity
updated a model 8 days ago
kushalpatil/jevify-gemma4-26b-a4b-lora published a model 8 days ago
kushalpatil/jevify-gemma4-26b-a4b-lora updated a model 8 days ago
kushalpatil/jevify-gemma4-26b-a4bOrganizations
None yet
updated a
model 8 days ago
published a
model 8 days ago
updated a
model 8 days ago
published a
model 8 days ago
updated a
model 8 days ago
published a
model 8 days ago
updated a
model 8 days ago
published a
model 8 days ago
vLLM prefix caching for phonellm (nemotron_h): bug report + first fix upstream
#1 opened 28 days ago
by kushalpatil
commented on How to Fine-Tune Nemotron 3.5 ASR for Your Language, Domain, or Accent about 2 months ago
Is the finetuning like a LORA adapter, or are all weights of the model changed?
Is it possible to host a base model with a few layers of swappable weights that I can change for each of my use cases?