Instructions to use Locutusque/gpt2-large-conversational with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Locutusque/gpt2-large-conversational with Transformers:

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

pipe = pipeline("text-generation", model="Locutusque/gpt2-large-conversational")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Locutusque/gpt2-large-conversational")
model = AutoModelForCausalLM.from_pretrained("Locutusque/gpt2-large-conversational")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Locutusque/gpt2-large-conversational with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Locutusque/gpt2-large-conversational"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Locutusque/gpt2-large-conversational",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Locutusque/gpt2-large-conversational

SGLang

How to use Locutusque/gpt2-large-conversational 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 "Locutusque/gpt2-large-conversational" \
    --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": "Locutusque/gpt2-large-conversational",
		"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 "Locutusque/gpt2-large-conversational" \
        --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": "Locutusque/gpt2-large-conversational",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Locutusque/gpt2-large-conversational with Docker Model Runner:
```
docker model run hf.co/Locutusque/gpt2-large-conversational
```

gpt2-large-conversational / run_model.py

Locutusque

Upload 11 files

af9da65 almost 3 years ago

raw

history blame contribute delete

1.89 kB

	import torch
	from transformers import GPT2Tokenizer, AutoModelForCausalLM
	start_token = "<\|ASSISTANT\|>"
	end_token = "<\|"
	tokenizer = GPT2Tokenizer.from_pretrained('gpt2-large')
	model = AutoModelForCausalLM.from_pretrained('gpt2-large', torch_dtype=torch.bfloat16)
	tokenizer.pad_token = "[PAD]"
	tokenizer.eos_token = "<\|endoftext\|>"
	tokenizer.add_special_tokens({"additional_special_tokens": ["<\|ASSISTANT\|>", "<\|USER\|>", "<\|SYSTEM\|>"]})
	model.resize_token_embeddings(len(tokenizer))
	model.load_state_dict(torch.load("/media/locutusque/T7/Projects/results/pytorch_model.bin"))
	model.cuda()
	device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
	def generate_text(model, tokenizer, prompt, max_length=1024):
	prompt = f'<\|USER\|> {prompt} <\|ASSISTANT\|> '
	input_ids = tokenizer.encode(prompt, add_special_tokens=True, return_tensors="pt").to(device)
	attention_mask = torch.ones_like(input_ids).to(device)
	output = model.generate(input_ids,
	max_length=max_length,
	do_sample=True,
	top_k=0,
	top_p=0.1,
	temperature=0.75,
	repetition_penalty=1.176,
	pad_token_id=tokenizer.pad_token_id,
	eos_token_id=tokenizer.eos_token_id,
	attention_mask=attention_mask)
	output_ids = tokenizer.decode(output[0], skip_special_tokens=False)
	return output_ids
	# Loop to interact with the model
	while True:
	prompt = input("Enter a prompt (or 'q' to quit): ")
	if prompt == "q":
	break
	output_text = generate_text(model, tokenizer, prompt)
	text_between_tokens = output_text[output_text.find(start_token) + len(start_token):]
	out = text_between_tokens[:text_between_tokens.find(end_token)]
	print(out)