Instructions to use Ashok75/base2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ashok75/base2 with Transformers:

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

pipe = pipeline("text-generation", model="Ashok75/base2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ashok75/base2")
model = AutoModelForCausalLM.from_pretrained("Ashok75/base2", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Ashok75/base2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ashok75/base2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ashok75/base2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ashok75/base2

SGLang

How to use Ashok75/base2 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 "Ashok75/base2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ashok75/base2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Ashok75/base2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ashok75/base2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Ashok75/base2 with Docker Model Runner:
```
docker model run hf.co/Ashok75/base2
```

base2 / load_model.py

Ashok75

Upload 28 files

428ef01 verified 7 months ago

Raw

History Blame Contribute Delete

1.36 kB

	# load_model.py
	import torch
	import os
	from transformers import AutoModelForCausalLM, AutoTokenizer

	_model = None
	_tokenizer = None

	def init_model(model_dir: str = "."):
	"""Call this ONCE at startup to load model into memory"""
	global _model, _tokenizer

	if _model is not None:
	print("✅ Model already loaded!")
	return _model, _tokenizer

	device = "cuda" if torch.cuda.is_available() else "cpu"
	if device == "cpu":
	torch.set_num_threads(os.cpu_count())

	print("\n" + "=" * 70)
	print(f"Loading model from local files on {device.upper()}...")
	print("=" * 70)

	_model = AutoModelForCausalLM.from_pretrained(
	model_dir,
	device_map=device,
	torch_dtype="auto",
	trust_remote_code=True,
	local_files_only=True,
	)

	_tokenizer = AutoTokenizer.from_pretrained(
	model_dir,
	local_files_only=True,
	)

	print(f"✅ Model loaded! ({sum(p.numel() for p in _model.parameters()) / 1e9:.1f}B params)")
	print("=" * 70 + "\n")

	return _model, _tokenizer

	def get_model():
	"""Get the already-loaded model (fast)"""
	global _model, _tokenizer
	if _model is None:
	raise RuntimeError("Model not initialized! Call init_model() first.")
	return _model, _tokenizer