Instructions to use google/gemma-2-9b-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use google/gemma-2-9b-it with Transformers:

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

pipe = pipeline("text-generation", model="google/gemma-2-9b-it")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-9b-it")
model = AutoModelForCausalLM.from_pretrained("google/gemma-2-9b-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-2-9b-it with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "google/gemma-2-9b-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-2-9b-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/google/gemma-2-9b-it

SGLang

How to use google/gemma-2-9b-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-2-9b-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-2-9b-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-2-9b-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-2-9b-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use google/gemma-2-9b-it with Docker Model Runner:
```
docker model run hf.co/google/gemma-2-9b-it
```

Ran into an issues while I was trying to sample more than one sentence

#27

by joeysss - opened Jul 12, 2024

Discussion

joeysss

Jul 12, 2024

RuntimeError: shape mismatch: value tensor of shape [5, 8, 192, 256] cannot be broadcast to indexing result of shape [1, 8, 192, 256]

I know this was caused by sampling because I tried to change "num_return_sequences" to 1 and the error disappeared.
Is it a bug or just my bugs?

Full traceback:

Traceback (most recent call last):
File "/data/home/xxx/anaconda3/envs/train/lib/python3.10/site-packages/torch/multiprocessing/spawn.py", line 75, in _wrap
fn(i, *args)
File "/data/home/xxx/paper_code/eval_scripts/open_source_coder_inference_mp.py", line 211, in inference_proc
raise e
File "/data/home/xxx/paper_code/eval_scripts/open_source_coder_inference_mp.py", line 186, in inference_proc
output = model.generate(
File "/data/home/xxx/anaconda3/envs/train/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/data/home/xxx/anaconda3/envs/train/lib/python3.10/site-packages/transformers/generation/utils.py", line 1914, in generate
result = self._sample(
File "/data/home/xxx/anaconda3/envs/train/lib/python3.10/site-packages/transformers/generation/utils.py", line 2651, in _sample
outputs = self(
File "/data/home/xxx/anaconda3/envs/train/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/data/home/xxx/anaconda3/envs/train/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "/data/home/xxx/anaconda3/envs/train/lib/python3.10/site-packages/transformers/models/gemma2/modeling_gemma2.py", line 1068, in forward
outputs = self.model(
File "/data/home/xxx/anaconda3/envs/train/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/data/home/xxx/anaconda3/envs/train/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "/data/home/xxx/anaconda3/envs/train/lib/python3.10/site-packages/transformers/models/gemma2/modeling_gemma2.py", line 908, in forward
layer_outputs = decoder_layer(
File "/data/home/xxx/anaconda3/envs/train/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/data/home/xxx/anaconda3/envs/train/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "/data/home/xxx/anaconda3/envs/train/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 "/data/home/xxx/anaconda3/envs/train/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/data/home/xxx/anaconda3/envs/train/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "/data/home/xxx/anaconda3/envs/train/lib/python3.10/site-packages/transformers/models/gemma2/modeling_gemma2.py", line 341, in forward
key_states, value_states = past_key_value.update(key_states, value_states, self.layer_idx, cache_kwargs)
File "/data/home/xxx/anaconda3/envs/train/lib/python3.10/site-packages/transformers/cache_utils.py", line 1071, in update
return update_fn(
File "/data/home/xxx/anaconda3/envs/train/lib/python3.10/site-packages/transformers/cache_utils.py", line 1046, in _static_update
k_out[:, :, cache_position] = key_states

RaccoonOnion

Aug 28, 2024

Your issue seems similar to mine here: https://huggingface.co/google/gemma-2-9b-it/discussions/40#66bd81baac86b9411ec14281
Have you found a way around?

joeysss

Aug 29, 2024

@RaccoonOnion Not yet I`ve simply given up using this one since it was just one of my baseline candidates.

Renu11

Google org Oct 15, 2024

Hi @joeysss , Could you please try again by updating the transformers version to the latest one using !pip install -U transformers as mentioned by @RaccoonOnion on provided link or can share the reproducible code to replicate the error if the issue still persists. Thank you.

joeysss

Oct 30, 2024

Hi @Renu11 , the issue no longer persist; it works fine now.

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