Instructions to use javirandor/passgpt-10characters with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use javirandor/passgpt-10characters with Transformers:

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

pipe = pipeline("text-generation", model="javirandor/passgpt-10characters")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("javirandor/passgpt-10characters")
model = AutoModelForCausalLM.from_pretrained("javirandor/passgpt-10characters", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use javirandor/passgpt-10characters with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "javirandor/passgpt-10characters"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "javirandor/passgpt-10characters",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/javirandor/passgpt-10characters

SGLang

How to use javirandor/passgpt-10characters 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 "javirandor/passgpt-10characters" \
    --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": "javirandor/passgpt-10characters",
		"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 "javirandor/passgpt-10characters" \
        --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": "javirandor/passgpt-10characters",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use javirandor/passgpt-10characters with Docker Model Runner:
```
docker model run hf.co/javirandor/passgpt-10characters
```

javirandor commited on Jul 6, 2023

Commit

0dd2273

1 Parent(s): 541b81a

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -3

README.md CHANGED Viewed

@@ -34,14 +34,13 @@ The model inherits the [GPT2LMHeadModel](https://huggingface.co/docs/transformer
 ### Password Generation
-Passwords can be sampled from the model using the [built-in generation methods](https://huggingface.co/docs/transformers/v4.30.0/en/main_classes/text_generation#transformers.GenerationMixin.generate) provided by HuggingFace and using the "start of password token" as seed (i.e. `<s>`). This code can be used to generate one password with PassGPT. Note you may need to generate an [access token](https://huggingface.co/docs/hub/security-tokens) to authenticate your download.
 ```
 from transformers import GPT2LMHeadModel
 from transformers import RobertaTokenizerFast
 tokenizer = RobertaTokenizerFast.from_pretrained("javirandor/passgpt-10characters",
-                                                  use_auth_token="YOUR_ACCESS_TOKEN",
                                                   max_len=12,
                                                   padding="max_length",
                                                   truncation=True,
@@ -52,7 +51,7 @@ tokenizer = RobertaTokenizerFast.from_pretrained("javirandor/passgpt-10character
                                                   pad_token="<pad>",
                                                   truncation_side="right")
-model = GPT2LMHeadModel.from_pretrained("javirandor/passgpt-10characters", use_auth_token="YOUR_ACCESS_TOKEN").eval()
 NUM_GENERATIONS = 1

 ### Password Generation
+Passwords can be sampled from the model using the [built-in generation methods](https://huggingface.co/docs/transformers/v4.30.0/en/main_classes/text_generation#transformers.GenerationMixin.generate) provided by HuggingFace and using the "start of password token" as seed (i.e. `<s>`). This code can be used to generate one password with PassGPT.
 ```
 from transformers import GPT2LMHeadModel
 from transformers import RobertaTokenizerFast
 tokenizer = RobertaTokenizerFast.from_pretrained("javirandor/passgpt-10characters",
                                                   max_len=12,
                                                   padding="max_length",
                                                   truncation=True,
                                                   pad_token="<pad>",
                                                   truncation_side="right")
+model = GPT2LMHeadModel.from_pretrained("javirandor/passgpt-10characters").eval()
 NUM_GENERATIONS = 1