Instructions to use mlx-community/quantized-gemma-2b-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/quantized-gemma-2b-it with Transformers:

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

pipe = pipeline("text-generation", model="mlx-community/quantized-gemma-2b-it")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mlx-community/quantized-gemma-2b-it")
model = AutoModelForCausalLM.from_pretrained("mlx-community/quantized-gemma-2b-it")
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]:]))

MLX

How to use mlx-community/quantized-gemma-2b-it with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/quantized-gemma-2b-it")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

vLLM

How to use mlx-community/quantized-gemma-2b-it with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mlx-community/quantized-gemma-2b-it"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlx-community/quantized-gemma-2b-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mlx-community/quantized-gemma-2b-it

SGLang

How to use mlx-community/quantized-gemma-2b-it 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 "mlx-community/quantized-gemma-2b-it" \
    --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": "mlx-community/quantized-gemma-2b-it",
		"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 "mlx-community/quantized-gemma-2b-it" \
        --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": "mlx-community/quantized-gemma-2b-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

MLX LM

How to use mlx-community/quantized-gemma-2b-it with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "mlx-community/quantized-gemma-2b-it"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "mlx-community/quantized-gemma-2b-it"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "mlx-community/quantized-gemma-2b-it",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use mlx-community/quantized-gemma-2b-it with Docker Model Runner:
```
docker model run hf.co/mlx-community/quantized-gemma-2b-it
```

error while using the model with transformers library

by SadokBarbouche - opened Apr 19, 2024

Discussion

SadokBarbouche

Apr 19, 2024

Sorry I am still discovering mlx but I tried to run the quantized version of gemma 2b-it :
model_id = "mlx-community/quantized-gemma-2b-it"
model = AutoModelForCausalLM.from_pretrained(model_id)
tokenizer = AutoTokenizer.from_pretrained(model_id)

and got this error :
running this code causes this issue with the transformers library causes this issue :

AttributeError Traceback (most recent call last)
Cell In[20], line 8
5 model_id = "mlx-community/quantized-gemma-2b-it"
6 # model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config, device_map={"":0})
7 # okenizer = AutoTokenizer.from_pretrained(model_id, add_eos_token=True)
----> 8 model = AutoModelForCausalLM.from_pretrained(model_id)
9 tokenizer = AutoTokenizer.from_pretrained(model_id)

File /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:561, in _BaseAutoModelClass.from_pretrained(cls, pretrained_model_name_or_path, *model_args, **kwargs)
559 elif type(config) in cls._model_mapping.keys():
560 model_class = _get_model_class(config, cls._model_mapping)
--> 561 return model_class.from_pretrained(
562 pretrained_model_name_or_path, *model_args, config=config, **hub_kwargs, **kwargs
563 )
564 raise ValueError(
565 f"Unrecognized configuration class {config.class} for this kind of AutoModel: {cls.name}.\n"
566 f"Model type should be one of {', '.join(c.name for c in cls._model_mapping.keys())}."
567 )

File /opt/conda/lib/python3.10/site-packages/transformers/modeling_utils.py:3287, in PreTrainedModel.from_pretrained(cls, pretrained_model_name_or_path, config, cache_dir, ignore_mismatched_sizes, force_download, local_files_only, token, revision, use_safetensors, *model_args, **kwargs)
3284 with safe_open(resolved_archive_file, framework="pt") as f:
3285 metadata = f.metadata()
-> 3287 if metadata.get("format") == "pt":
3288 pass
3289 elif metadata.get("format") == "tf":

AttributeError: 'NoneType' object has no attribute 'get'

How to solve it please ?

SadokBarbouche changed discussion status to closed Apr 24, 2024

valedenicola

Feb 6, 2025

Hello, how do you solved this?

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

error while using the model with transformers library

and got this error :running this code causes this issue with the transformers library causes this issue :

and got this error :
running this code causes this issue with the transformers library causes this issue :