Instructions to use mohommed/Testing with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mohommed/Testing with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("EleutherAI/gpt-neo-1.3B")
model = PeftModel.from_pretrained(base_model, "mohommed/Testing")

Transformers

How to use mohommed/Testing with Transformers:

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

pipe = pipeline("text-generation", model="mohommed/Testing")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mohommed/Testing", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mohommed/Testing with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/mohommed/Testing

SGLang

How to use mohommed/Testing 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 "mohommed/Testing" \
    --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": "mohommed/Testing",
		"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 "mohommed/Testing" \
        --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": "mohommed/Testing",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mohommed/Testing with Docker Model Runner:
```
docker model run hf.co/mohommed/Testing
```

Testing / Main.py

mohommed

Create Main.py

930e89e verified over 1 year ago

Raw History Blame Contribute Delete

1.31 kB

# Install dependencies
!pip install transformers accelerate peft

# Import libraries
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel, PeftConfig
import torch

# Load base model and PEFT adapter
base_model_name = "EleutherAI/gpt-neo-1.3B"
peft_model_name = "mohommed/Testing"

# Load tokenizer and base model
tokenizer = AutoTokenizer.from_pretrained(base_model_name)
base_model = AutoModelForCausalLM.from_pretrained(base_model_name, device_map="auto", torch_dtype=torch.float16)

# Apply the PEFT adapter
model = PeftModel.from_pretrained(base_model, peft_model_name)
model.eval()

# Define generation function
def generate_article(prompt, max_new_tokens=700):
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    with torch.no_grad():
        outputs = model.generate(
            **inputs,
            max_new_tokens=max_new_tokens,
            temperature=0.8,
            top_p=0.95,
            do_sample=True,
            eos_token_id=tokenizer.eos_token_id,
        )
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

# Example prompt
prompt = "Write a 600-word Medium article about how to stay motivated as a writer. Use a personal tone and clear structure."

# Generate article
output = generate_article(prompt)
print(output)

	# Install dependencies
	!pip install transformers accelerate peft

	# Import libraries
	from transformers import AutoTokenizer, AutoModelForCausalLM
	from peft import PeftModel, PeftConfig
	import torch

	# Load base model and PEFT adapter
	base_model_name = "EleutherAI/gpt-neo-1.3B"
	peft_model_name = "mohommed/Testing"

	# Load tokenizer and base model
	tokenizer = AutoTokenizer.from_pretrained(base_model_name)
	base_model = AutoModelForCausalLM.from_pretrained(base_model_name, device_map="auto", torch_dtype=torch.float16)

	# Apply the PEFT adapter
	model = PeftModel.from_pretrained(base_model, peft_model_name)
	model.eval()

	# Define generation function
	def generate_article(prompt, max_new_tokens=700):
	inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
	with torch.no_grad():
	outputs = model.generate(
	**inputs,
	max_new_tokens=max_new_tokens,
	temperature=0.8,
	top_p=0.95,
	do_sample=True,
	eos_token_id=tokenizer.eos_token_id,
	)
	return tokenizer.decode(outputs[0], skip_special_tokens=True)

	# Example prompt
	prompt = "Write a 600-word Medium article about how to stay motivated as a writer. Use a personal tone and clear structure."

	# Generate article
	output = generate_article(prompt)
	print(output)