Instructions to use mohitkrconnect/heed-tasks-only-qwen3-0.6b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mohitkrconnect/heed-tasks-only-qwen3-0.6b with Transformers:

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

pipe = pipeline("text-generation", model="mohitkrconnect/heed-tasks-only-qwen3-0.6b")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mohitkrconnect/heed-tasks-only-qwen3-0.6b")
model = AutoModelForCausalLM.from_pretrained("mohitkrconnect/heed-tasks-only-qwen3-0.6b", device_map="auto")

LiteRT-LM

How to use mohitkrconnect/heed-tasks-only-qwen3-0.6b with LiteRT-LM:

# LiteRT-LM runs on various platforms (Android, iOS, Windows, Linux, macOS, IoT, Web/WASM)
# and supports many APIs (C++, Python, Kotlin, Swift, JavaScript, Flutter).
# For platform-specific integration guides, please refer to the official developer website:
# https://ai.google.dev/edge/litert-lm

# To try LiteRT-LM, the easiest way is to use our CLI tool.
# 1. Install the LiteRT-LM CLI tool:
pip install -U litert-lm

# 2. Download and run this model locally:
# See: https://ai.google.dev/edge/litert-lm/cli
# A single .litertlm file in the repo is picked automatically; otherwise the CLI asks which one to run
# (or pass its name right after the repo id).
litert-lm run \
  --from-huggingface-repo=mohitkrconnect/heed-tasks-only-qwen3-0.6b \
  --prompt="Write me a poem"

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mohitkrconnect/heed-tasks-only-qwen3-0.6b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mohitkrconnect/heed-tasks-only-qwen3-0.6b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mohitkrconnect/heed-tasks-only-qwen3-0.6b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mohitkrconnect/heed-tasks-only-qwen3-0.6b

SGLang

How to use mohitkrconnect/heed-tasks-only-qwen3-0.6b 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 "mohitkrconnect/heed-tasks-only-qwen3-0.6b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mohitkrconnect/heed-tasks-only-qwen3-0.6b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "mohitkrconnect/heed-tasks-only-qwen3-0.6b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mohitkrconnect/heed-tasks-only-qwen3-0.6b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mohitkrconnect/heed-tasks-only-qwen3-0.6b with Docker Model Runner:
```
docker model run hf.co/mohitkrconnect/heed-tasks-only-qwen3-0.6b
```

Heed tasks-only, Qwen3-0.6B (EXP-038): the first model on the phone

This is the first Heed model to run inside the app on a real phone. It is a research checkpoint:

it writes task text only (no buckets);
it was trained on an older label set;
it has no judged score.

All later models build on it. The current model is heed-tasks-qwen3-0.6b.

Why this model exists

Its Qwen3.5-0.8B twin, heed-tasks-only-qwen3.5-0.8b, scored slightly higher, but Google's official LiteRT-LM converter could not convert its hybrid attention (decision D103). Qwen3-0.6B can be converted.

EXP-038 tested whether the 0.6B gives up little enough quality to be worth the switch. It was trained on exactly the same data with the same settings:

word-overlap F1 on the yardstick: 91.2 against 91.6;
on real notes: 77.9 against 81.5.

Format

Note: <the note text>
Tasks:

The answer is {"tasks":["…","…"]}, then EOS. Use greedy decoding and no chat template.

Files

model.safetensors: bf16 weights for transformers.
heed-tasks-only-qwen3-0.6b-int8.litertlm: the int8 file that ran in the app (614,458,976 bytes, sha256 d17fa2d8d2779f8c88cd0b838a0dfa78e37a12af6d5bdd896d5b96957d2b3ab3).
- Made with litert-torch export_hf … --cache_length=1024, which uses int8 weights and fp32 activations.
- Checked on a Mac on 30 notes before going on the phone.
- Batched and one-at-a-time answers were identical on 45 of 48 notes.

Training

Setting	Value
Base	`Qwen/Qwen3-0.6B-Base`, full fine-tune, 596,049,920 trainable parameters
Data	The same 4,221 notes as the 0.8B twin, one row each. HeedSet (synthetic, Claude Opus), simulated user-style notes, notes I planned generated with ChatGPT, Claude brain dumps, 140 real notes from me and five friends and 10 typed by me
Labels	Older mixed labels: Sonnet-relabelled plus Sonnet-labelled HeedSet. They keep hedges like "Maybe…"
Recipe	lr 1e-5, AdamW, 5% warm-up + cosine, batch 8 × 2 = 16, 3 epochs (792 steps), max length 1,024, loss on answer tokens only, bf16 autocast, seed 0
Hardware / time / cost	1 × RTX 4090, 7.1 minutes, peak 13.9 GB; about $0.45 of GPU (estimate)

Results (word-overlap F1 only; no judged score)

Validation has 371 notes; the yardstick is 199 of them (59 real plus 140 HeedSet).

Yardstick F1 91.2 (recall 91.2, precision 91.2), with exact lists on 72.4% of notes.
Real notes F1 77.9, with exact lists on 47.5%.
HeedSet slice 95.2.
Valid JSON on 199 of 199 notes.

On the phone (EXP-041: OnePlus CPH2717, Dimensity 8300, 40 test notes):

Metric	Value
Time per note	2.2 to 3.7 s
Prefill / decode	about 240 to 300 / 19 to 25 tokens per second (about 14 tokens per second with the screen locked)
Memory	PSS about 1.1 GB (616 MB of memory-mapped weights)
Heat	36 to 40 °C over several minutes, using about 3.5 CPU cores
Background	It kept working with the screen locked and in the background

What it taught the study

The labels taught it to hedge. On the phone it wrote tasks like "Maybe call the bank", because about 1 in 5 hedged tasks in its training labels kept the hedge. That led to one consistent relabelling of every note with a single Sonnet prompt (EXP-046).
It had no long notes. Adding 2,697 long synthetic notes later raised long-note quality by +9.4 (EXP-048/049).
It had no buckets. The next models write a bucket for every task.

Data: the synthetic part of the training, validation and test notes, with all five systems' answers and the judge's verdicts on the public test notes, is in mohitkrconnect/heed-voice-notes-to-tasks. My real notes and my friends' are not published.

License

Apache-2.0, the same as the base model. The training labels and most training notes were produced with Claude, Gemini and GPT models. Check those providers' terms before using this model to build a competing general-purpose model.