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

Libraries

How to use clouditera/secgpt with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("clouditera/secgpt")
model = AutoModelForCausalLM.from_pretrained("clouditera/secgpt")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use clouditera/secgpt with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/clouditera/secgpt

SGLang

How to use clouditera/secgpt 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 "clouditera/secgpt" \
    --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": "clouditera/secgpt",
		"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 "clouditera/secgpt" \
        --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": "clouditera/secgpt",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

secgpt / configuration_baichuan.py

clouditera

first

a055a7a over 2 years ago

raw

history blame

1.49 kB

	# Copyright (c) 2023, Baichuan Intelligent Technology. All rights reserved.

	from transformers.configuration_utils import PretrainedConfig

	class BaichuanConfig(PretrainedConfig):
	model_type = "baichuan"
	keys_to_ignore_at_inference = ["past_key_values"]

	def __init__(
	self,
	vocab_size=64000,
	hidden_size=5120,
	intermediate_size=13696,
	num_hidden_layers=40,
	num_attention_heads=40,
	hidden_act="silu",
	model_max_length=4096,
	initializer_range=0.02,
	rms_norm_eps=1e-6,
	use_cache=True,
	pad_token_id=0,
	bos_token_id=1,
	eos_token_id=2,
	tie_word_embeddings=False,
	gradient_checkpointing=False,
	**kwargs,
	):
	self.vocab_size = vocab_size
	self.model_max_length = model_max_length
	self.hidden_size = hidden_size
	self.intermediate_size = intermediate_size
	self.num_hidden_layers = num_hidden_layers
	self.num_attention_heads = num_attention_heads
	self.hidden_act = hidden_act
	self.initializer_range = initializer_range
	self.rms_norm_eps = rms_norm_eps
	self.use_cache = use_cache
	self.gradient_checkpointing = gradient_checkpointing,
	super().__init__(
	pad_token_id=pad_token_id,
	bos_token_id=bos_token_id,
	eos_token_id=eos_token_id,
	tie_word_embeddings=tie_word_embeddings,
	**kwargs,
	)