Instructions to use dheeyantra/dhee-pravega with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dheeyantra/dhee-pravega with Transformers:

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

pipe = pipeline("text-generation", model="dheeyantra/dhee-pravega")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("dheeyantra/dhee-pravega")
model = AutoModelForMultimodalLM.from_pretrained("dheeyantra/dhee-pravega", device_map="auto")
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?"}
        ]
    },
]
inputs = processor.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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use dheeyantra/dhee-pravega with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/dheeyantra/dhee-pravega

SGLang

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

Docker Model Runner
How to use dheeyantra/dhee-pravega with Docker Model Runner:
```
docker model run hf.co/dheeyantra/dhee-pravega
```

dhee-pravega / LICENSE

sree108

Add Dhee Research-Only Licence v1.0

e74e9b7 verified about 2 months ago

Raw History Blame Contribute Delete

4.66 kB

	Dhee Research-Only Licence v1.0
	Dhee-Pravega and other models released by Dheeyantra Research Labs
	Effective: 2026-09-01

	READ FIRST — THIS MODEL CARRIES TWO SETS OF TERMS

	Dhee-Pravega is a fine-tune of Google's Gemma. Google's Gemma Terms of Use
	continue to apply to it and to anything you derive from it, IN ADDITION to this
	Licence. Nothing here grants you rights Google has not granted, and where this
	Licence is narrower than Gemma's terms, this Licence controls for Dheeyantra's
	contribution. You must comply with BOTH:

	- Gemma Terms of Use ......... https://ai.google.dev/gemma/terms
	- Gemma Prohibited Use Policy https://ai.google.dev/gemma/prohibited_use_policy
	- This Licence

	1. DEFINITIONS

	"Model" means the weights, parameters, configuration and tokenizer files
	published in this repository, and any derivative of them including merges,
	quantisations, adapters, distillations and further fine-tunes.

	"Output" means content generated by the Model.

	"Research Use" means use for academic research, scientific publication,
	evaluation, benchmarking, red-teaming, safety analysis, reproduction of
	published results, teaching, and personal experimentation — carried out
	without commercial purpose.

	"Commercial Use" means any use intended for or directed toward commercial
	advantage or monetary compensation. This includes, without limitation: use
	in or by a product or service offered to third parties whether paid or free;
	internal use in the operations of a for-profit entity; use to provide
	services to customers; and use of Outputs to train, fine-tune or improve any
	model deployed commercially.

	2. GRANT

	Subject to your compliance with this Licence and the Gemma terms above,
	Dheeyantra Research Labs grants you a worldwide, non-exclusive,
	royalty-free, non-transferable, revocable licence to use, reproduce and
	modify the Model, and to distribute the Model and its derivatives, FOR
	RESEARCH USE ONLY.

	3. RESTRICTIONS

	3.1 No Commercial Use. Commercial Use is not licensed here. To obtain
	commercial terms, contact Dheeyantra Research Labs. Commercial licences
	are available and are not unreasonably withheld.

	3.2 Pass-through. If you distribute the Model or any derivative, you must
	include this Licence and the Gemma Terms of Use with it, and you may not
	offer terms that grant recipients more than you received.

	3.3 Attribution. Publications and public artefacts that use the Model should
	identify it by name and version (for example, "Dhee-Pravega v3").

	3.4 No misrepresentation. Do not present Outputs as human-authored where
	that would mislead, and do not present the Model as endorsed by
	Dheeyantra or Google.

	3.5 Prohibited uses. The Gemma Prohibited Use Policy applies in full and is
	incorporated by reference.

	4. OUTPUTS

	Dheeyantra claims no ownership of Outputs you generate. Your use of Outputs
	remains subject to Section 3.1: Outputs produced under this Licence may not
	be used for Commercial Use, including as training data for a commercially
	deployed model.

	5. NO WARRANTY

	THE MODEL IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
	IMPLIED, INCLUDING BUT NOT LIMITED TO WARRANTIES OF MERCHANTABILITY, FITNESS
	FOR A PARTICULAR PURPOSE, ACCURACY AND NON-INFRINGEMENT. The Model is a
	statistical system: it can be wrong, and it can be confidently wrong. It has
	not been validated for any regulated, safety-critical or high-stakes
	application, and its tool-calling behaviour has known measured gaps that are
	documented on the model card. You are responsible for evaluating it for your
	purpose.

	6. LIMITATION OF LIABILITY

	TO THE MAXIMUM EXTENT PERMITTED BY LAW, DHEEYANTRA SHALL NOT BE LIABLE FOR
	ANY INDIRECT, INCIDENTAL, SPECIAL, CONSEQUENTIAL OR EXEMPLARY DAMAGES, OR
	FOR LOST PROFITS, REVENUE OR DATA, ARISING FROM OR RELATING TO THE MODEL,
	WHETHER IN CONTRACT, TORT OR OTHERWISE, EVEN IF ADVISED OF THE POSSIBILITY.

	7. TERMINATION

	This Licence terminates automatically if you breach it. On termination you
	must cease use and destroy your copies of the Model. Sections 4 through 8
	survive.

	8. GENERAL

	This Licence is governed by the laws of India, with exclusive jurisdiction
	in the courts of Bengaluru, Karnataka. If any provision is held
	unenforceable, the rest remains in effect. Dheeyantra may issue future
	versions of this Licence; material already distributed under this version
	stays under this version.

	CONTACT — commercial licensing and questions: Dheeyantra Research Labs.