Instructions to use Erland/mini-qwen3-1m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Erland/mini-qwen3-1m with Transformers:

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

pipe = pipeline("text-generation", model="Erland/mini-qwen3-1m")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Erland/mini-qwen3-1m")
model = AutoModelForCausalLM.from_pretrained("Erland/mini-qwen3-1m")
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

vLLM

How to use Erland/mini-qwen3-1m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Erland/mini-qwen3-1m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Erland/mini-qwen3-1m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Erland/mini-qwen3-1m

SGLang

How to use Erland/mini-qwen3-1m 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 "Erland/mini-qwen3-1m" \
    --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": "Erland/mini-qwen3-1m",
		"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 "Erland/mini-qwen3-1m" \
        --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": "Erland/mini-qwen3-1m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Erland/mini-qwen3-1m with Docker Model Runner:
```
docker model run hf.co/Erland/mini-qwen3-1m
```

Mini Qwen3 1M

A tiny Qwen3-compatible causal language model for testing and development. It keeps the Hugging Face Qwen3ForCausalLM architecture and the real Qwen3 tokenizer/chat template, but shrinks the model to about 1.2M parameters with randomly initialized weights.

This model is designed for fast Relax/Megatron/SGLang debugging without pulling large Qwen3 checkpoints into every smoke test. It is intentionally not useful for inference or downstream tasks.

Architecture

Parameter	Value
Parameters	1,217,608
Model type	`qwen3`
Hidden size	8
Layers	2
Intermediate size	32
Attention heads	1
KV heads	1
Head dimension	8
Max position embeddings	4,096
Vocab size	151,936
Tensor dtype	`bfloat16`
Tokenizer source	`Qwen/Qwen3-0.6B` local mirror

How this model was created

scripts/tools/create_mock_qwen3.py in the Relax ROCm Megatron workspace:

Loads the tokenizer and config metadata from a local Qwen3-0.6B checkpoint.
Shrinks the Qwen3 config dimensions to the table above.
Initializes Qwen3ForCausalLM with random weights.
Ties word embeddings and saves the model as safetensors.
Writes mock_qwen3_info.json with the exact generation metadata.

The model weights are random. Only tokenizer/chat-template metadata is copied from Qwen3-0.6B.

Reproduction

From the Relax ROCm Megatron repository:

source /vast/users/qirong.ho/miniforge3/etc/profile.d/conda.sh
conda activate relaxrl_rocm
python scripts/tools/create_mock_qwen3.py \
  --tokenizer-source /vast/users/qirong.ho/erland/Python_project/relax_e2e_assets/Qwen3-0.6B \
  --output-dir /vast/users/qirong.ho/erland/Python_project/relax_e2e_assets/Qwen3-Mock-1M

Relax e2e validation

This checkpoint was validated with the Relax AMD ROCm e2e launcher:

NUM_ROLLOUT=2 SAVE_INTERVAL=1 CKPT_FORMAT=torch_dist NO_SAVE_OPTIM=0 \
WANDB_GROUP="qwen3-mock-1m-tmux-20260531_095214" \
./amd_qwen3_mock_2gpu_e2e.sh

Validation evidence:

Ray job: raysubmit_sGx5uTXcKu41nHzL
W&B run: me4ticfh
completed Actor training completed step 0/2
completed Actor training completed step 1/2
saved torch_dist checkpoints at iterations 0 and 1
checkpoint metadata contains optimizer state keys, including optimizer.state.exp_avg and optimizer.state.exp_avg_sq

The e2e validation exercised:

Hugging Face model load
SGLang transformers rollout
Megatron Qwen3Bridge import
distributed weight update
optimizer step
W&B application metrics
optimizer-inclusive torch_dist checkpoint save

Intended use

Fast Relax/Megatron/SGLang startup and integration tests
ROCm smoke tests where Qwen3 code paths matter more than model quality
Checkpointing and resume infrastructure checks
Debugging model-provider, tokenizer, rollout, and weight-sync wiring

Not intended for

Inference quality evaluation
Benchmarking Qwen3 capability
Any downstream task
Reward/loss quality analysis

Because the model is random and extremely small, generated text is expected to be nonsense. During the validation run, rewards were invalid/negative and advantages collapsed to zero; this is expected for this smoke checkpoint.

Downloads last month: 16

Safetensors

Model size

1.22M params

Tensor type

BF16