Quantization made by Richard Erkhov.
Llama-3.1-security - bnb 8bits
Original model description:
library_name: transformers
license: apache-2.0
Model Card for Model ID
Model Details
This Model fine-tuned by Security dataset.
I will fine-tune continuous...
Model Description
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by: [More Information Needed]
- Funded by [optional]: [More Information Needed]
- Shared by [optional]: [More Information Needed]
- Model type: [More Information Needed]
- Language(s) (NLP): [More Information Needed]
- License: [More Information Needed]
- Finetuned from model [optional]: [More Information Needed]
Model Sources [optional]
- Repository: [More Information Needed]
- Paper [optional]: [More Information Needed]
- Demo [optional]: [More Information Needed]
Uses
1import os
2import torch
3from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
4from peft import PeftModel
5
6model_id = 'model_result'
7
8bnb_config = BitsAndBytesConfig(
9 load_in_4bit=True,
10 bnb_4bit_quant_type="nf4",
11 bnb_4bit_compute_dtype=torch.bfloat16,
12 bnb_4bit_use_double_quant=True,
13)
14
15tokenizer = AutoTokenizer.from_pretrained(model_id)
16tokenizer.pad_token = tokenizer.eos_token
17
18model = AutoModelForCausalLM.from_pretrained(
19 model_id,
20 #torch_dtype=torch.bfloat16,
21 quantization_config=bnb_config, # 4-bit quantization (4비트 양자화)
22 device_map="auto",
23)
24
25model.eval()
26
27from transformers import TextStreamer
28
29def inference(input: str):
30 streamer = TextStreamer(tokenizer=tokenizer, skip_prompt=True, skip_special_tokens=True)
31
32 messages = [
33 {"role": "system", "content": "You are an information security AI assistant. Information security questions must be answered accurately."},
34 {"role": "user", "content": f"Please provide concise, non-repetitive answers to the following questions:\n {input}"}
35 # {"role": "user", "content": f"{input}"}
36 ]
37
38 input_ids = tokenizer.apply_chat_template(
39 messages,
40 tokenize=True,
41 add_generation_prompt=True,
42 return_tensors="pt",
43 ).to(model.device)
44
45 outputs = model.generate(
46 input_ids,
47 streamer=streamer,
48 max_new_tokens=8192,
49 num_beams=1,
50 do_sample=True,
51 temperature=0.1,
52 top_p=0.95,
53 top_k=10
54 )
55
56inference("해킹 당하지 않으려면 어떻게 해야하는지 알려줘.")
57
58해킹 당하지 않으려면 다음과 같은 것들을 고려해 보세요:
59
601. **패스워드 관리**: 강력한 패스워드를 사용하고, 패스워드의 복잡성과 변환 주기를 잘 유지하세요.
612. **시스템 업데이트**: 최신 소프트웨어와 보안 패치를 설치하고, 지속적으로 시스템을 업데이트하세요.
623. **스캔 및 검사**: 시스템과 네트워크를 자주 스캔하고, 보안 취약점을 검사해 보세요.
634. **안전한 브라우징**: 안전한 브라우저와 확장 기능을 사용하고, 악성 소프트웨어 설치를 방지하세요.
645. **데이터 백업**: 중요한 데이터를 백업하고, 이를 안전한 저장소에 보관하세요.
656. **네트워크 보안**: 네트워크 보안 장비를 사용하고, 침입자에 대한 통제와 감시를 유지하세요.
667. **사용자 교육**: 사용자들이 안전한 사용 방법을 이해하고, 정보 보안에 대한 중요성을 인지하세요.
678. **계약자 관리**: 계약자와 파트너와의 계약을 잘 확인하고, 정보 보안에 대한 합의를 유지하세요.
68
Direct Use
[More Information Needed]
Downstream Use [optional]
[More Information Needed]
Out-of-Scope Use
[More Information Needed]
Bias, Risks, and Limitations
[More Information Needed]
Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
Training Details
Training Data
[More Information Needed]
Training Procedure
Preprocessing [optional]
[More Information Needed]
Training Hyperparameters
- Training regime: [More Information Needed]
Speeds, Sizes, Times [optional]
[More Information Needed]
Evaluation
Testing Data, Factors & Metrics
Testing Data
[More Information Needed]
Factors
[More Information Needed]
Metrics
[More Information Needed]
Results
[More Information Needed]
Summary
Model Examination [optional]
[More Information Needed]
Environmental Impact
Carbon emissions can be estimated using the
Machine Learning Impact calculator presented in
Lacoste et al. (2019).
- Hardware Type: [More Information Needed]
- Hours used: [More Information Needed]
- Cloud Provider: [More Information Needed]
- Compute Region: [More Information Needed]
- Carbon Emitted: [More Information Needed]
Technical Specifications [optional]
Model Architecture and Objective
[More Information Needed]
Compute Infrastructure
[More Information Needed]
Hardware
[More Information Needed]
Software
[More Information Needed]
Citation [optional]
BibTeX:
[More Information Needed]
APA:
[More Information Needed]
Glossary [optional]
[More Information Needed]
More Information [optional]
[More Information Needed]
Model Card Authors [optional]
[More Information Needed]
Model Card Contact
[More Information Needed]
