Instructions to use lunahr/SystemGemma2-2b-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lunahr/SystemGemma2-2b-it with Transformers:

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

pipe = pipeline("text-generation", model="lunahr/SystemGemma2-2b-it")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lunahr/SystemGemma2-2b-it")
model = AutoModelForCausalLM.from_pretrained("lunahr/SystemGemma2-2b-it", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lunahr/SystemGemma2-2b-it with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lunahr/SystemGemma2-2b-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": "lunahr/SystemGemma2-2b-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lunahr/SystemGemma2-2b-it

SGLang

How to use lunahr/SystemGemma2-2b-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 "lunahr/SystemGemma2-2b-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": "lunahr/SystemGemma2-2b-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 "lunahr/SystemGemma2-2b-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": "lunahr/SystemGemma2-2b-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use lunahr/SystemGemma2-2b-it with Docker Model Runner:
```
docker model run hf.co/lunahr/SystemGemma2-2b-it
```

Piotr Zalewski commited on Aug 8, 2024

Commit

7c13e43

verified ·

1 Parent(s): 6f6e06d

copied READMEs be like

Browse files

Files changed (1) hide show

README.md +13 -13

README.md CHANGED Viewed

@@ -62,7 +62,7 @@ from transformers import pipeline
 pipe = pipeline(
     "text-generation",
-    model="google/gemma-2-9b-it",
     model_kwargs={"torch_dtype": torch.bfloat16},
     device="cuda",  # replace with "mps" to run on a Mac device
 )
@@ -84,9 +84,9 @@ print(assistant_response)
 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,
 )
@@ -122,9 +122,9 @@ You can also use `float32` if you skip the dtype, but no precision increase will
 # pip install accelerate
 from transformers import AutoTokenizer, AutoModelForCausalLM
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-9b-it")
 model = AutoModelForCausalLM.from_pretrained(
-    "google/gemma-2-9b-it",
     device_map="auto",
 )
@@ -142,7 +142,7 @@ for running Gemma 2 through a command line interface, or CLI. Follow the [instal
 for getting started, then launch the CLI through the following command:
 ```shell
-local-gemma --model 9b --preset speed
 ```
 #### Quantized Versions through `bitsandbytes`
@@ -158,9 +158,9 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
 quantization_config = BitsAndBytesConfig(load_in_8bit=True)
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-9b-it")
 model = AutoModelForCausalLM.from_pretrained(
-    "google/gemma-2-9b-it",
     quantization_config=quantization_config,
 )
@@ -183,9 +183,9 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
 quantization_config = BitsAndBytesConfig(load_in_4bit=True)
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-9b-it")
 model = AutoModelForCausalLM.from_pretrained(
-    "google/gemma-2-9b-it",
     quantization_config=quantization_config,
 )
@@ -220,8 +220,8 @@ import torch
 torch.set_float32_matmul_precision("high")
 # load the model + tokenizer
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-9b-it")
-model = Gemma2ForCausalLM.from_pretrained("google/gemma-2-9b-it", torch_dtype=torch.bfloat16)
 model.to("cuda")
 # apply the torch compile transformation
@@ -271,7 +271,7 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
 import transformers
 import torch
-model_id = "google/gemma-2-9b-it"
 dtype = torch.bfloat16
 tokenizer = AutoTokenizer.from_pretrained(model_id)

 pipe = pipeline(
     "text-generation",
+    model="google/gemma-2-2b-it",
     model_kwargs={"torch_dtype": torch.bfloat16},
     device="cuda",  # replace with "mps" to run on a Mac device
 )
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
+tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-2b-it")
 model = AutoModelForCausalLM.from_pretrained(
+    "google/gemma-2-2b-it",
     device_map="auto",
     torch_dtype=torch.bfloat16,
 )
 # pip install accelerate
 from transformers import AutoTokenizer, AutoModelForCausalLM
+tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-2b-it")
 model = AutoModelForCausalLM.from_pretrained(
+    "google/gemma-2-2b-it",
     device_map="auto",
 )
 for getting started, then launch the CLI through the following command:
 ```shell
+local-gemma --model 2b --preset speed
 ```
 #### Quantized Versions through `bitsandbytes`
 quantization_config = BitsAndBytesConfig(load_in_8bit=True)
+tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-2b-it")
 model = AutoModelForCausalLM.from_pretrained(
+    "google/gemma-2-2b-it",
     quantization_config=quantization_config,
 )
 quantization_config = BitsAndBytesConfig(load_in_4bit=True)
+tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-2b-it")
 model = AutoModelForCausalLM.from_pretrained(
+    "google/gemma-2-2b-it",
     quantization_config=quantization_config,
 )
 torch.set_float32_matmul_precision("high")
 # load the model + tokenizer
+tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-2b-it")
+model = Gemma2ForCausalLM.from_pretrained("google/gemma-2-2b-it", torch_dtype=torch.bfloat16)
 model.to("cuda")
 # apply the torch compile transformation
 import transformers
 import torch
+model_id = "google/gemma-2-2b-it"
 dtype = torch.bfloat16
 tokenizer = AutoTokenizer.from_pretrained(model_id)