File size: 1,587 Bytes
3822371 0454576 3822371 0454576 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 |
---
tags:
- text-generation-inference
- transformers
- trl
- sft
license: apache-2.0
language:
- en
---
# INFERENCE
```python
import time
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, TextStreamer
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
finetuned_model = AutoModelForCausalLM.from_pretrained("AquilaX-AI/security_assistant")
tokenizer = AutoTokenizer.from_pretrained("AquilaX-AI/security_assistant")
finetuned_model.to(device)
prompt = """<|im_start|>system
You are a helpful AI assistant named Securitron<|im_end|>
<|im_start|>user
cwe_id:CWE-20
cwe_name:Improper Input Validation
affected_line:Pattern Undefined (v3)
partial_code:example: c4d5ea2f-81a2-4a05-bcd3-202126ae21df
name:
type: string
example: Toolbox
serial:
file_name:itemit_openapi.yaml
status:True Positive
reason: There is no pattern property that could lead to insufficient input validation.
remediation_action: Always define a pattern to ensure strict input validation.
How to fix this?<|im_end|>
<|im_start|>assistant
"""
s = time.time()
encodeds = tokenizer(prompt, return_tensors="pt",truncation=True).input_ids.to(device)
text_streamer = TextStreamer(tokenizer, skip_prompt = True)
# Increase max_new_tokens if needed
response = finetuned_model.generate(
input_ids=encodeds,
streamer=text_streamer,
max_new_tokens=512,
use_cache=True,
pad_token_id=151645,
eos_token_id=151645,
num_return_sequences=1
)
e = time.time()
print(f'time taken:{e-s}')
``` |