Instructions to use webspaceai/webspaceai-one-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use webspaceai/webspaceai-one-preview with Transformers:

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

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

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("webspaceai/webspaceai-one-preview", dtype="auto")

PEFT
How to use webspaceai/webspaceai-one-preview with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use webspaceai/webspaceai-one-preview with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/webspaceai/webspaceai-one-preview

SGLang

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

Docker Model Runner
How to use webspaceai/webspaceai-one-preview with Docker Model Runner:
```
docker model run hf.co/webspaceai/webspaceai-one-preview
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Model Trained Using WEBSPACEAI_TRANIER AGENT

WEBSPACEAI Trainer Agent is a powerful tool designed to streamline the training of large language models (LLMs) using PyTorch and TensorFlow. It offers efficient data management, enabling users to curate and organize datasets for optimal model performance. The platform supports comprehensive training strategies, allowing for iterative adjustments to enhance accuracy. With collaboration features and a user-friendly interface, the Trainer Agent makes AI training accessible to both technical and non-technical users, empowering organizations to develop sophisticated AI solutions tailored to their needs.

Usage


from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = "webspaceai/webspaceai-one-preview"

tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
    model_path,
    device_map="auto",
    torch_dtype='auto'
).eval()

# Prompt content: "hi"
messages = [
    {"role": "user", "content": "hi"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
output_ids = model.generate(input_ids.to('cuda'))
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)

# Model response: "Hello! How can I assist you today?"
print(response)

Downloads last month: -; Downloads are not tracked for this model. How to track