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

Libraries

How to use google/gemma-2-27b-it with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-27b-it")
model = AutoModelForCausalLM.from_pretrained("google/gemma-2-27b-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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use google/gemma-2-27b-it with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/google/gemma-2-27b-it

SGLang

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

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

Setting num_return_sequences results in shape mismatch error.

#28

by Watarungurunnn - opened Jul 8, 2024

Discussion

Watarungurunnn

Jul 8, 2024

•

edited Jul 8, 2024

hf_args:
do_sample: true
temperature: 0.8
top_k: 50
top_p: 0.95
num_return_sequences: 30

model = AutoModelForCausalLM.from_pretrained(
            model_path,
            trust_remote_code=True,
            torch_dtype="auto",
            device_map="auto",
            **model_args,
        )
generated_tokens = model.generate(
                    inputs=input_ids,
                    pad_token_id=tokenizer.pad_token_id,
                    **hf_args,
                )

Error:

  File "/home/user_2942/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
    return forward_call(*args, **kwargs)
  File "/home/user_2942/.local/lib/python3.10/site-packages/transformers/models/gemma2/modeling_gemma2.py", line 1068, in forward
    outputs = self.model(
  File "/home/user_2942/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/home/user_2942/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
    return forward_call(*args, **kwargs)
  File "/home/user_2942/.local/lib/python3.10/site-packages/transformers/models/gemma2/modeling_gemma2.py", line 908, in forward
    layer_outputs = decoder_layer(
  File "/home/user_2942/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/home/user_2942/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
    return forward_call(*args, **kwargs)
  File "/home/user_2942/.local/lib/python3.10/site-packages/transformers/models/gemma2/modeling_gemma2.py", line 650, in forward
    hidden_states, self_attn_weights, present_key_value = self.self_attn(
  File "/home/user_2942/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/home/user_2942/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
    return forward_call(*args, **kwargs)
  File "/home/user_2942/.local/lib/python3.10/site-packages/transformers/models/gemma2/modeling_gemma2.py", line 252, in forward
    key_states, value_states = past_key_value.update(key_states, value_states, self.layer_idx, cache_kwargs)
  File "/home/user_2942/.local/lib/python3.10/site-packages/transformers/cache_utils.py", line 1227, in update
    return update_fn(
  File "/home/user_2942/.local/lib/python3.10/site-packages/transformers/cache_utils.py", line 1202, in _static_update
    k_out[:, :, cache_position] = key_states
RuntimeError: shape mismatch: value tensor of shape [30, 16, 942, 128] cannot be broadcast to indexing result of shape [1, 16, 942, 128]
time="2024-07-09T04:45:52 UTC" level=info msg="sub-process exited" argo=true error="<nil>"
Error: exit status 1

OSalem99

Jul 17, 2024

Hi,
Changing line 1767 in generation/utils.py to getattr(generation_config, "num_beams", 1) * getattr(generation_config, "num_return_sequences", 1) * batch_size , fixed the problem for me. Hope you find that helpful :)

pvalois

Aug 13, 2024

Any update on this issue? I cannot use a fork of transformers on my project.

OSalem99

Aug 13, 2024

It was fixed and released already, just make sure to update transformers 😄

lkv

Google org Dec 19, 2024

Hi @Watarungurunnn , Could you please confirm if you are facing still issue after updated the transformers, let us know will assist you or else we can close this issue.

Thank you.

Watarungurunnn

Dec 20, 2024

Seems fixed! Thank you

Watarungurunnn changed discussion status to closed Dec 20, 2024

ZhaoyangLi

May 3, 2025

same problem in gemma3
when I use transformers==4.50.0或者4.51.0

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