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

Libraries

How to use tarvico/CaptionIQ with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0")
model = PeftModel.from_pretrained(base_model, "tarvico/CaptionIQ")

Transformers

How to use tarvico/CaptionIQ with Transformers:

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

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

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tarvico/CaptionIQ", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tarvico/CaptionIQ with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/tarvico/CaptionIQ

SGLang

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

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

Model ID

Model ID is an AI-powered language model developed to support intelligent conversations, task assistance, and workflow automation within its intended application domain.

It provides structured responses, recommendations, and natural language understanding to improve productivity and user experience across supported use cases.

The model generates recommendations only and should not replace human judgment or decision-making where accuracy, compliance, or professional oversight is required.

Overview

Conversational AI
Task assistance
Intelligent reasoning
Workflow automation
Knowledge support
Natural language understanding

Intended Use

This model is intended for integration into AI-powered applications, assistants, and enterprise workflows where natural language interaction and decision support are required.

Outputs should always be validated by the consuming application or an authorized human reviewer when used in production environments.

Documentation

This public repository intentionally excludes implementation details, training methodology, underlying model information, evaluation procedures, and deployment architecture.

Private technical documentation—including model training notes, architecture decisions, evaluation reports, datasets, and deployment configurations—is maintained separately within internal documentation.

Contact

For questions regarding this repository, please use the repository discussion or issue tracker.

Downloads last month: 8