How would you recommend Training a nano LLm model, say the Efficient-Large-Model/VILA1.5-3b for example.
Im thinking something like:
model = NanoLLM.from_pretrained(
model="Efficient-Large-Model/VILA1.5-3b", # Replace with your model
api="hf",
use_cache=False
)
model.train()
model.save()
How would you recommend Training a nano LLm model, say the Efficient-Large-Model/VILA1.5-3b for example.
Im thinking something like:
model = NanoLLM.from_pretrained(
model="Efficient-Large-Model/VILA1.5-3b", # Replace with your model
api="hf",
use_cache=False
)
model.train()
model.save()