Commit
•
aa0ac4c
1
Parent(s):
42c45e1
Update README.md
Browse files
README.md
CHANGED
|
@@ -7,6 +7,8 @@ Experimental quantization.
|
|
| 7 |
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):
|
| 8 |
|
| 9 |
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
|
|
|
|
|
|
|
| 10 |
|
| 11 |
tokenizer = AutoTokenizer.from_pretrained(quantized_model_dir, use_fast=True)
|
| 12 |
|
|
|
|
| 7 |
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):
|
| 8 |
|
| 9 |
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
|
| 10 |
+
from transformers import AutoTokenizer, TextGenerationPipeline
|
| 11 |
+
|
| 12 |
|
| 13 |
tokenizer = AutoTokenizer.from_pretrained(quantized_model_dir, use_fast=True)
|
| 14 |
|