Vikhrmodels
/

it-5.2-fp16-cp

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

AlexWortega commited on May 24

Commit

2182fb3

•

1 Parent(s): 81d5541

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -21,10 +21,10 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 model = AutoModelForCausalLM.from_pretrained("Vikhrmodels/it-5.2-fp16-cp",
                                              device_map="auto",
-                                             attn_implementation="flash_attention_2",
                                              torch_dtype=torch.bfloat16)
-tokenizer = AutoTokenizer.from_pretrained("Vikhrmodels/Vikhr-7B-instruct_0.4")
 from transformers import  AutoTokenizer, pipeline
 pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
 prompts = [

 import torch
 model = AutoModelForCausalLM.from_pretrained("Vikhrmodels/it-5.2-fp16-cp",
                                              device_map="auto",
+                                             attn_implementation="sdpa",
                                              torch_dtype=torch.bfloat16)
+tokenizer = AutoTokenizer.from_pretrained("Vikhrmodels/it-5.2-fp16-cp")
 from transformers import  AutoTokenizer, pipeline
 pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
 prompts = [