Instructions to use mlx-community/gemma-2-27b-it-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/gemma-2-27b-it-8bit with Transformers:

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

pipe = pipeline("text-generation", model="mlx-community/gemma-2-27b-it-8bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mlx-community/gemma-2-27b-it-8bit")
model = AutoModelForCausalLM.from_pretrained("mlx-community/gemma-2-27b-it-8bit", 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]:]))

MLX

How to use mlx-community/gemma-2-27b-it-8bit 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/gemma-2-27b-it-8bit")

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/gemma-2-27b-it-8bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mlx-community/gemma-2-27b-it-8bit"
# 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/gemma-2-27b-it-8bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mlx-community/gemma-2-27b-it-8bit

SGLang

How to use mlx-community/gemma-2-27b-it-8bit 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/gemma-2-27b-it-8bit" \
    --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/gemma-2-27b-it-8bit",
		"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/gemma-2-27b-it-8bit" \
        --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/gemma-2-27b-it-8bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

MLX LM

How to use mlx-community/gemma-2-27b-it-8bit 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/gemma-2-27b-it-8bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "mlx-community/gemma-2-27b-it-8bit"
# 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/gemma-2-27b-it-8bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use mlx-community/gemma-2-27b-it-8bit with Docker Model Runner:
```
docker model run hf.co/mlx-community/gemma-2-27b-it-8bit
```

example code doesn't work at all

by cloudyu - opened Jun 28, 2024

Discussion

cloudyu

Jun 28, 2024

•

edited Jun 28, 2024

output is: pad only
Prompt: Write me a poem about Machine Learning.

cloudyu

Jun 28, 2024

mlx 0.15.2
mlx-lm 0.15.0

prince-canuma

MLX Community org Jun 28, 2024

The example code should work fine:

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/gemma-2-27b-it-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)

prince-canuma changed discussion status to closed Jun 28, 2024

ndurner

Jun 29, 2024

Reproducible here:

% mlx_lm.generate --model "mlx-community/gemma-2-27b-it-8bit" --prompt "Hello"
Fetching 11 files: 100%|█████████████████████| 11/11 [00:00<00:00, 31152.83it/s]
==========
Prompt: <bos><start_of_turn>user
Hello<end_of_turn>
<start_of_turn>model

<pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad>
==========
Prompt: 0.538 tokens-per-sec
Generation: 1.840 tokens-per-sec

% python3 prince.py 
Fetching 11 files: 100%|█████████████████████| 11/11 [00:00<00:00, 34820.64it/s]
==========
Prompt: hello
<pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad>
==========
Prompt: 0.124 tokens-per-sec
Generation: 2.043 tokens-per-sec

cloudyu

Jun 29, 2024

yep, very bad exprience.
not work, but someone still tell you works.

The example code should work fine:

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/gemma-2-27b-it-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)

do you really test the code?

very bad exprience.
it not work, but someone still tell you it works.

ndurner

Jun 29, 2024

I have previously noticed differences with mlx-vlm (and PaliGemma) vs. the official demo on HF as well - but didn't have time to pursue this further. Perhaps there is an underlying MLX issue? I am using macOS 14.3 on M3 Max.

By contrast, the 9B-FP16 variant does work:

% mlx_lm.generate --model "mlx-community/gemma-2-9b-it-fp16" --prompt "Hello"
Fetching 9 files: 100%|████████████████████████| 9/9 [00:00<00:00, 17614.90it/s]

Prompt: user
Hello
model

Hello! 👋

How can I help you today? 😊

==========
Prompt: 6.337 tokens-per-sec
Generation: 13.758 tokens-per-sec

prince-canuma

MLX Community org Jun 30, 2024

I'm sorry @cloudyu @ndurner ,

It was an oversight on my part,

There is a tiny bug with the 27B version, and should be fixed soon:
https://github.com/ml-explore/mlx-examples/pull/857

prince-canuma changed discussion status to open Jun 30, 2024

prince-canuma

MLX Community org Jul 4, 2024

Fixed ✅

pip install -U mlx-lm

prince-canuma changed discussion status to closed Jul 4, 2024

kmgk

Dec 17, 2024

This is again an issue. Output is again after version 0.19.1. It works up to 0.19.0 only.

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

example code doesn't work at all

% mlx_lm.generate --model "mlx-community/gemma-2-9b-it-fp16" --prompt "Hello"Fetching 9 files: 100%|████████████████████████| 9/9 [00:00<00:00, 17614.90it/s]

% mlx_lm.generate --model "mlx-community/gemma-2-9b-it-fp16" --prompt "Hello"
Fetching 9 files: 100%|████████████████████████| 9/9 [00:00<00:00, 17614.90it/s]