Hugging Face's logo

codefuse-ai
/
CodeFuse-CodeLlama-34B-4bits

Text Generation
Transformers
PyTorch
llama
text-generation-inference
Inference Endpoints
Model card Files Community
3
chencyudel goforce5500 commited on
Commit
14c11c4
•
1 Parent(s): 444fe8f

Update README.md (#2)

Browse files

- Update README.md (29eb44e14fd8c2a09799930dc8703896340394fc)


Co-authored-by: GoForce5500 <[email protected]>

Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -135,7 +135,7 @@ def load_model_tokenizer(model_name_or_local_path):
135
  tokenizer = AutoTokenizer.from_pretrained(model_name_or_local_path,
136
  trust_remote_code=True,
137
  use_fast=False,
138
- lagecy=False)
139
  tokenizer.padding_side = "left"
140
 
141
  model = AutoGPTQForCausalLM.from_quantized(model_name_or_local_path,
@@ -338,7 +338,7 @@ def load_model_tokenizer(model_name_or_local_path):
338
  tokenizer = AutoTokenizer.from_pretrained(model_name_or_local_path,
339
  trust_remote_code=True,
340
  use_fast=False,
341
- lagecy=False)
342
  tokenizer.padding_side = "left"
343
 
344
  model = AutoGPTQForCausalLM.from_quantized(model_name_or_local_path,
 
135
  tokenizer = AutoTokenizer.from_pretrained(model_name_or_local_path,
136
  trust_remote_code=True,
137
  use_fast=False,
138
+ legacy=False)
139
  tokenizer.padding_side = "left"
140
 
141
  model = AutoGPTQForCausalLM.from_quantized(model_name_or_local_path,
 
338
  tokenizer = AutoTokenizer.from_pretrained(model_name_or_local_path,
339
  trust_remote_code=True,
340
  use_fast=False,
341
+ legacy=False)
342
  tokenizer.padding_side = "left"
343
 
344
  model = AutoGPTQForCausalLM.from_quantized(model_name_or_local_path,