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

Libraries

How to use tarvico/cummiq 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/cummiq")

Transformers

How to use tarvico/cummiq with Transformers:

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

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

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tarvico/cummiq with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tarvico/cummiq"
# 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/cummiq",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tarvico/cummiq

SGLang

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

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

Model ID

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

It is designed to generate structured responses, assist with knowledge-based tasks, support productivity, and integrate into AI-powered applications and enterprise solutions.

The model provides recommendations and generated content only. Outputs should be reviewed by the consuming application or an authorized human when used in production or decision-making workflows.

Overview

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

Intended Use

This model is intended for integration into AI assistants, business applications, automation platforms, and other systems that require natural language interaction and intelligent response generation.

Depending on the deployment scenario, human review may be appropriate before acting on generated outputs.

Documentation

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

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

Contact

For questions, feature requests, or issue reports, please use the repository's discussion or issue tracker.

Downloads last month: 17