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
Local Apps Settings

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
```

Fails to generate with `inputs_embeds`

#18

by JaronTHU - opened Jul 1, 2024

Discussion

JaronTHU

Jul 1, 2024

I can run the following code successfully with transformers==4.42.3

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-9b-it")
model = AutoModelForCausalLM.from_pretrained(
    "google/gemma-2-9b-it",
    device_map="auto",
    torch_dtype=torch.bfloat16
)

input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))

However, when I try to replace input_ids with inputs_embeds:

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-9b-it")
model = AutoModelForCausalLM.from_pretrained(
    "google/gemma-2-9b-it",
    device_map="auto",
    torch_dtype=torch.bfloat16
)

input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

+  input_ids['inputs_embeds'] = model.get_input_embeddings()(input_ids.pop('input_ids'))

outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))

I get the following error

Traceback (most recent call last):
  File "/workspace/tmp1.py", line 22, in <module>
    outputs = model.generate(**input_ids)
  File "/data/miniconda3/envs/env-3.10.6/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "/usr/local/app/.local/lib/python3.10/site-packages/transformers/generation/utils.py", line 1914, in generate
    result = self._sample(
  File "/usr/local/app/.local/lib/python3.10/site-packages/transformers/generation/utils.py", line 2651, in _sample
    outputs = self(
  File "/data/miniconda3/envs/env-3.10.6/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/data/miniconda3/envs/env-3.10.6/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/usr/local/app/.local/lib/python3.10/site-packages/transformers/models/gemma2/modeling_gemma2.py", line 1068, in forward
    outputs = self.model(
  File "/data/miniconda3/envs/env-3.10.6/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/data/miniconda3/envs/env-3.10.6/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/usr/local/app/.local/lib/python3.10/site-packages/transformers/models/gemma2/modeling_gemma2.py", line 908, in forward
    layer_outputs = decoder_layer(
  File "/data/miniconda3/envs/env-3.10.6/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/data/miniconda3/envs/env-3.10.6/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/usr/local/app/.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 "/data/miniconda3/envs/env-3.10.6/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/data/miniconda3/envs/env-3.10.6/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/usr/local/app/.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 "/usr/local/app/.local/lib/python3.10/site-packages/transformers/cache_utils.py", line 1071, in update
    return update_fn(
  File "/usr/local/app/.local/lib/python3.10/site-packages/transformers/cache_utils.py", line 1046, in _static_update
    k_out[:, :, cache_position] = key_states
IndexError: index 11 is out of bounds for dimension 0 with size 11

This error does not happen if I replace google/gemma-2-9b-it with other LLMs, e.g., mistralai/Mistral-7B-Instruct-v0.3. How to fix it?

Renu11

Google org Jul 26, 2024

•

edited Jul 26, 2024

Hi @JaronTHU , Could you please try again by upgrading with the latest transformers version(4.43.2) along with setting the max_length as I am able to run the model code successfully. Please have a look at the below screenshot.

JaronTHU

Jul 26, 2024

Thank you! After upgrading transformers, this problem has been solved.

JaronTHU changed discussion status to closed Jul 26, 2024

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