Instructions to use nisten/deepseek-r1-qwen32b-mlx-6bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nisten/deepseek-r1-qwen32b-mlx-6bit with Transformers:

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

pipe = pipeline("text-generation", model="nisten/deepseek-r1-qwen32b-mlx-6bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nisten/deepseek-r1-qwen32b-mlx-6bit")
model = AutoModelForCausalLM.from_pretrained("nisten/deepseek-r1-qwen32b-mlx-6bit", 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 nisten/deepseek-r1-qwen32b-mlx-6bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nisten/deepseek-r1-qwen32b-mlx-6bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nisten/deepseek-r1-qwen32b-mlx-6bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nisten/deepseek-r1-qwen32b-mlx-6bit

SGLang

How to use nisten/deepseek-r1-qwen32b-mlx-6bit 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 "nisten/deepseek-r1-qwen32b-mlx-6bit" \
    --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": "nisten/deepseek-r1-qwen32b-mlx-6bit",
		"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 "nisten/deepseek-r1-qwen32b-mlx-6bit" \
        --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": "nisten/deepseek-r1-qwen32b-mlx-6bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nisten/deepseek-r1-qwen32b-mlx-6bit with Docker Model Runner:
```
docker model run hf.co/nisten/deepseek-r1-qwen32b-mlx-6bit
```

There is some issue with tokenization...

by ckolozsy - opened Jan 21, 2025

Discussion

ckolozsy

Jan 21, 2025

❯ mlx_lm.server --model nisten/deepseek-r1-qwen32b-mlx-6bit --log-level DEBUG
2025-01-20 19:43:30,142 - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
2025-01-20 19:43:30,356 - DEBUG - https://huggingface.co:443 "GET /api/models/nisten/deepseek-r1-qwen32b-mlx-6bit/revision/main HTTP/1.1" 200 4367
Fetching 10 files: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████| 10/10 [00:00<00:00, 47393.27it/s]
Traceback (most recent call last):
File "/opt/anaconda3/envs/mlx/bin/mlx_lm.server", line 8, in
sys.exit(main())
^^^^^^
File "/opt/anaconda3/envs/mlx/lib/python3.12/site-packages/mlx_lm/server.py", line 752, in main
run(args.host, args.port, ModelProvider(args))
^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/mlx/lib/python3.12/site-packages/mlx_lm/server.py", line 134, in init
self.load("default_model")
File "/opt/anaconda3/envs/mlx/lib/python3.12/site-packages/mlx_lm/server.py", line 161, in load
model, tokenizer = load(
^^^^^
File "/opt/anaconda3/envs/mlx/lib/python3.12/site-packages/mlx_lm/utils.py", line 739, in load
tokenizer = load_tokenizer(
^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/mlx/lib/python3.12/site-packages/mlx_lm/tokenizer_utils.py", line 367, in load_tokenizer
AutoTokenizer.from_pretrained(model_path, **tokenizer_config_extra),
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/mlx/lib/python3.12/site-packages/transformers/models/auto/tokenization_auto.py", line 862, in from_pretrained
return tokenizer_class.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/mlx/lib/python3.12/site-packages/transformers/tokenization_utils_base.py", line 2089, in from_pretrained
return cls._from_pretrained(
^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/mlx/lib/python3.12/site-packages/transformers/tokenization_utils_base.py", line 2311, in _from_pretrained
tokenizer = cls(*init_inputs, **init_kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/mlx/lib/python3.12/site-packages/transformers/models/llama/tokenization_llama_fast.py", line 124, in init
super().init(
File "/opt/anaconda3/envs/mlx/lib/python3.12/site-packages/transformers/tokenization_utils_fast.py", line 111, in init
fast_tokenizer = TokenizerFast.from_file(fast_tokenizer_file)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Exception: data did not match any variant of untagged enum ModelWrapper at line 757491 column 3

    ~/Desktop/mlx-model ▓▒░

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment