Demon Su

Results 2 issues of Demon Su

response = model.chat(tokenizer, messages, streaming=Flase) 。。。=》False

--> 162 v_quant, quant_state = bnb.functional.quantize_nf4(v.cuda(), blocksize=64) ``` ssertionError Traceback (most recent call last) Cell In[1], line 7 3 MAX_LENGTH = 128 4 # could use hugging face model repo...