|
--- |
|
license: cc-by-4.0 |
|
--- |
|
|
|
Experimental quantization. |
|
|
|
Working inference code (regular inference with autogptq does not work without return_token_type_ids=False, didn't get it to work with textgen-webui): |
|
|
|
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig |
|
|
|
from transformers import AutoTokenizer, TextGenerationPipeline |
|
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained(quantized_model_dir, use_fast=True) |
|
|
|
model = AutoGPTQForCausalLM.from_quantized(quantized_model_dir, device="cuda:0", use_triton=False) |
|
|
|
input_ids = tokenizer("Question: What is the purpose of life?\n\nAnswer:", return_tensors="pt").input_ids.to("cuda:0") |
|
|
|
out = model.generate(input_ids=input_ids,max_length=300) |
|
|
|
print(tokenizer.decode(out[0])) |
|
|
|
or |
|
|
|
print(tokenizer.decode(model.generate(**tokenizer("test is", return_tensors="pt", return_token_type_ids=False).to("cuda:0"))[0])) |
