Instructions to use mohith-das/jetson-assistant-0.5b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mohith-das/jetson-assistant-0.5b with Transformers:

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

pipe = pipeline("text-generation", model="mohith-das/jetson-assistant-0.5b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mohith-das/jetson-assistant-0.5b")
model = AutoModelForCausalLM.from_pretrained("mohith-das/jetson-assistant-0.5b", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mohith-das/jetson-assistant-0.5b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mohith-das/jetson-assistant-0.5b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mohith-das/jetson-assistant-0.5b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mohith-das/jetson-assistant-0.5b

SGLang

How to use mohith-das/jetson-assistant-0.5b 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 "mohith-das/jetson-assistant-0.5b" \
    --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": "mohith-das/jetson-assistant-0.5b",
		"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 "mohith-das/jetson-assistant-0.5b" \
        --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": "mohith-das/jetson-assistant-0.5b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mohith-das/jetson-assistant-0.5b with Docker Model Runner:
```
docker model run hf.co/mohith-das/jetson-assistant-0.5b
```

jetson-assistant-0.5b

Final deployable checkpoint from Phase 1 of the llm_distillery project — a personal AI assistant distilled and aligned entirely on a Jetson Orin Nano Super (8GB unified memory), start to finish.

Plain FP16 Qwen2ForCausalLM checkpoint — no PEFT/adapter machinery needed at inference, loads directly with AutoModelForCausalLM.from_pretrained("mohith-das/jetson-assistant-0.5b"). Built by merging two LoRA adapters sequentially into the Qwen2.5-0.5B base:

Stage 1 — cognitive distillation (jetson-assistant-stage1-adapter): reasoning, code, and conversational-structure imitation from teacher datasets (AM-DeepSeek-R1, OpenCodeInstruct, FineVision).
Stage 2 — personal alignment (jetson-assistant-stage2-adapter): trained on top of the Stage 1 merge, on a small handwritten dataset of assistant behaviors (message drafting, scheduling, contact lookup, summarizing).

Order matters: Stage 2 was trained on already-merged Stage 1 weights, so this checkpoint reproduces that exact order (base -> +stage1 -> +stage2), not an independent combination of both adapters.

This is also the base model for Phase 2 of the project — see jetson-hybrid-flat-cache-0.5b for a follow-on attention-architecture experiment (alternating sliding-window / gated-linear attention) built on top of this checkpoint.

Downloads last month: 36

Safetensors

Model size

0.5B params

Tensor type

F16

Model tree for mohith-das/jetson-assistant-0.5b

Base model

Qwen/Qwen2.5-0.5B

Adapter

(432)

this model

Adapters

1 model