Image-Text-to-Text
Transformers
Safetensors
Hebrew
English
lpt6
text-generation
liskcell
deta
endpoints-compatible
conversational
Instructions to use liskcell/lpt-6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use liskcell/lpt-6 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="liskcell/lpt-6") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("liskcell/lpt-6", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use liskcell/lpt-6 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "liskcell/lpt-6" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "liskcell/lpt-6", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/liskcell/lpt-6
- SGLang
How to use liskcell/lpt-6 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 "liskcell/lpt-6" \ --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": "liskcell/lpt-6", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'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 "liskcell/lpt-6" \ --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": "liskcell/lpt-6", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Docker Model Runner
How to use liskcell/lpt-6 with Docker Model Runner:
docker model run hf.co/liskcell/lpt-6
| import gradio as gr | |
| from huggingface_hub import InferenceClient | |
| import os | |
| # --- BRANDING & IDENTITY --- | |
| TITLE = "💎 LPT-6 (Deta) | LiskCell Official Tester" | |
| SUBTITLE = "Experience the next generation of creative AI by LiskCell & xLYR." | |
| DESCRIPTION = """ | |
| Welcome to the testing sandbox for **LPT-6**, the flagship model of the **LiskCell** ecosystem. | |
| Natively powered by **Deta**, this model combines technical precision with an artistic soul. | |
| Founded by **liskasYR** (Yonatan Yosupov), LiskCell pushes the boundaries of AI, art, and music 🎵. | |
| """ | |
| # Theme / CSS for Futuristic Look | |
| custom_css = """ | |
| body { background-color: #0b0f19; color: #e2e8f0; } | |
| .gradio-container { border: 1px solid #1e293b !important; border-radius: 20px !important; background: rgba(15, 23, 42, 0.8) !ax; backdrop-filter: blur(10px); } | |
| #component-0 { background: transparent !important; } | |
| .message.user { background-color: #1e293b !important; border-radius: 15px 15px 0 15px !important; } | |
| .message.bot { background-color: #0f172a !important; border: 1px solid #3b82f6 !important; border-radius: 15px 15px 15px 0 !important; } | |
| footer { display: none !important; } | |
| #title-header { text-align: center; margin-bottom: 20px; } | |
| #title-header h1 { color: #38bdf8; text-shadow: 0 0 10px rgba(56, 189, 248, 0.5); font-family: 'Inter', sans-serif; } | |
| """ | |
| # Initialize Inference Client | |
| # Note: Use an environment variable for the token in Space settings or a default public access if allowed. | |
| # For this tester, we'll try to use the model's inference endpoint. | |
| repo_id = "liskcell-company/lpt-6" | |
| client = InferenceClient(model=repo_id) | |
| def respond(message, history): | |
| messages = [] | |
| # Add System Prompt (Deta Persona) - although it's baked in, we reinforce it here for the UI | |
| # Since the user said it's "Baked in", we'll just send the chat history. | |
| for user_msg, assistant_msg in history: | |
| messages.append({"role": "user", "content": user_msg}) | |
| messages.append({"role": "assistant", "content": assistant_msg}) | |
| messages.append({"role": "user", "content": message}) | |
| response = "" | |
| try: | |
| # Stream the response | |
| for message_chunk in client.chat_completion( | |
| messages, | |
| max_tokens=1024, | |
| stream=True, | |
| temperature=0.7, | |
| top_p=0.9, | |
| ): | |
| token = message_chunk.choices[0].delta.content | |
| if token: | |
| response += token | |
| yield response | |
| except Exception as e: | |
| yield f"⚠️ **Error:** {str(e)}\n\nPlease make sure the Inference Endpoint for {repo_id} is active." | |
| # Create the Gradio Interface | |
| with gr.Blocks(theme=gr.themes.Soft(), css=custom_css) as demo: | |
| with gr.Column(elem_id="title-header"): | |
| gr.Markdown(f"# {TITLE}") | |
| gr.Markdown(f"### {SUBTITLE}") | |
| gr.Markdown(DESCRIPTION) | |
| chatbot = gr.Chatbot( | |
| bubble_full_width=False, | |
| show_label=False, | |
| show_share_button=False, | |
| show_copy_button=True, | |
| layout="panel", | |
| height=600, | |
| ) | |
| with gr.Row(): | |
| msg = gr.Textbox( | |
| placeholder="Talk to Deta... (English or Hebrew)", | |
| show_label=False, | |
| scale=9, | |
| container=False | |
| ) | |
| submit_btn = gr.Button("🚀 Send", scale=1, variant="primary") | |
| msg.submit(respond, [msg, chatbot], [chatbot]) | |
| msg.submit(lambda: "", None, [msg]) | |
| submit_btn.click(respond, [msg, chatbot], [chatbot]) | |
| submit_btn.click(lambda: "", None, [msg]) | |
| gr.Examples( | |
| examples=[ | |
| ["היי Deta, ספרי לי על עצמך ועל LiskCell."], | |
| ["What makes LPT-6 better than previous models?"], | |
| ["Could you help me brainstorm a concept for a futuristic music app?"], | |
| ["כתבי לי שיר קצר על עתיד הטכנולוגיה."] | |
| ], | |
| inputs=msg, | |
| label="Quick Examples" | |
| ) | |
| gr.Markdown("---") | |
| gr.Markdown("Powered by **LiskCell & xLYR** 💎 | Founded by **liskasYR**") | |
| if __name__ == "__main__": | |
| demo.launch() | |