Open nickpotafiy opened 2 weeks ago
This PR adds the ability to grab the last hidden state from a job.
job = ExLlamaV2DynamicJob( input_ids=input_ids, max_new_tokens=0, gen_settings=gen_settings, return_last_state=True, )
This is a minimalist implementation I'm using for my own project. I haven't ran any extensive tests, but would be nice to see a feature like this added for things like generating embeddings for contextual search.
This PR adds the ability to grab the last hidden state from a job.
This is a minimalist implementation I'm using for my own project. I haven't ran any extensive tests, but would be nice to see a feature like this added for things like generating embeddings for contextual search.