Instructions to use praneeth-narisetty/Mako with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use praneeth-narisetty/Mako with Transformers:

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

pipe = pipeline("text-generation", model="praneeth-narisetty/Mako")
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("praneeth-narisetty/Mako")
model = AutoModelForMultimodalLM.from_pretrained("praneeth-narisetty/Mako", 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 praneeth-narisetty/Mako with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/praneeth-narisetty/Mako

SGLang

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

Docker Model Runner
How to use praneeth-narisetty/Mako with Docker Model Runner:
```
docker model run hf.co/praneeth-narisetty/Mako
```

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.

Mako

Mako is a fine-tune of Qwen3.8-27B (a Qwen3-Next / Qwen3_5 hybrid, ~27B parameters, bf16).

Training

Method: LoRA supervised fine-tuning (merged into the base weights here).
LoRA config: rank 64, alpha 128, dropout 0.05; targets all attention, linear-attention (gated delta rule) and MLP projections.
Framework: LLaMA-Factory.
Chat template: qwen3_5 (thinking-capable).

The multi-token-prediction (MTP) head is preserved (model-auxiliary.safetensors).

Usage

```python import torch from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "praneeth-narisetty/Mako" tok = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained( model_id, trust_remote_code=True, dtype=torch.bfloat16, device_map="auto")

msgs = [{"role": "user", "content": "Explain what a buffer overflow is."}] enc = tok.apply_chat_template(msgs, add_generation_prompt=True, tokenize=True, return_tensors="pt", return_dict=True).to(model.device) out = model.generate(**enc, max_new_tokens=256) print(tok.decode(out[0][enc["input_ids"].shape[1]:], skip_special_tokens=True)) ```

Status

Private / in testing. License to be confirmed before any public release.

Downloads last month: -

Safetensors

Model size

27B params

Tensor type

BF16