Instructions to use CodeferSystem/GPT2-Hacker-password-generator-Medium with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CodeferSystem/GPT2-Hacker-password-generator-Medium with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="CodeferSystem/GPT2-Hacker-password-generator-Medium")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CodeferSystem/GPT2-Hacker-password-generator-Medium")
model = AutoModelForCausalLM.from_pretrained("CodeferSystem/GPT2-Hacker-password-generator-Medium")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use CodeferSystem/GPT2-Hacker-password-generator-Medium with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CodeferSystem/GPT2-Hacker-password-generator-Medium"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CodeferSystem/GPT2-Hacker-password-generator-Medium",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/CodeferSystem/GPT2-Hacker-password-generator-Medium

SGLang

How to use CodeferSystem/GPT2-Hacker-password-generator-Medium with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "CodeferSystem/GPT2-Hacker-password-generator-Medium" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CodeferSystem/GPT2-Hacker-password-generator-Medium",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "CodeferSystem/GPT2-Hacker-password-generator-Medium" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CodeferSystem/GPT2-Hacker-password-generator-Medium",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use CodeferSystem/GPT2-Hacker-password-generator-Medium with Docker Model Runner:
```
docker model run hf.co/CodeferSystem/GPT2-Hacker-password-generator-Medium
```

CodeferSystem commited on Apr 6

Commit

ea709ec

verified ·

1 Parent(s): 9b43f0d

Update README.md

Browse files

Refining the description.

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -8,6 +8,7 @@ pipeline_tag: text-generation
 tags:
 - cybersecurity
 - passwords
 ---
 # GPT-2 Hacker password generator (medium)
@@ -45,7 +46,7 @@ output = model.generate(
     **inputs,
     max_length=60,
     do_sample=True,
-    temperature=0.9,
     top_p=0.95,
     no_repeat_ngram_size=2
 )
@@ -75,5 +76,5 @@ Assistant: t~5^>6hVhxQ$yY
 [GPT2-Hacker-password-generator Small model](https://huggingface.co/CodeferSystem/GPT2-Hacker-password-generator)
-# Fine-tune data
 The dataset on which the model was trained will be published later.

 tags:
 - cybersecurity
 - passwords
+library_name: transformers
 ---
 # GPT-2 Hacker password generator (medium)
     **inputs,
     max_length=60,
     do_sample=True,
+    temperature=0.9, # Change for creativity
     top_p=0.95,
     no_repeat_ngram_size=2
 )
 [GPT2-Hacker-password-generator Small model](https://huggingface.co/CodeferSystem/GPT2-Hacker-password-generator)
+# Dataset of this model
 The dataset on which the model was trained will be published later.