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, AutoModelForMultimodalLM

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

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
```

Xenova HF Staff commited on Jul 28, 2024

Commit

17a0165

verified ·

1 Parent(s): 980ca64

Update EOS token ids (#1)

Browse files

- Update EOS token ids (a6354b7c157bc3e9d89b909dc6e66435ca793e61)
- Update generation_config.json (bbe764c5039982ea559fb1687b0863614b3aba59)

Files changed (2) hide show

config.json +4 -1
generation_config.json +4 -1

config.json CHANGED Viewed

@@ -7,7 +7,10 @@
   "attn_logit_softcapping": 50.0,
   "bos_token_id": 2,
   "cache_implementation": "hybrid",
-  "eos_token_id": 1,
   "final_logit_softcapping": 30.0,
   "head_dim": 256,
   "hidden_act": "gelu_pytorch_tanh",

   "attn_logit_softcapping": 50.0,
   "bos_token_id": 2,
   "cache_implementation": "hybrid",
+  "eos_token_id": [
+    1,
+    107
+  ],
   "final_logit_softcapping": 30.0,
   "head_dim": 256,
   "hidden_act": "gelu_pytorch_tanh",

generation_config.json CHANGED Viewed

@@ -2,7 +2,10 @@
   "_from_model_config": true,
   "bos_token_id": 2,
   "cache_implementation": "hybrid",
-  "eos_token_id": 1,
   "pad_token_id": 0,
   "transformers_version": "4.42.4"
 }

   "_from_model_config": true,
   "bos_token_id": 2,
   "cache_implementation": "hybrid",
+  "eos_token_id": [
+    1,
+    107
+  ],
   "pad_token_id": 0,
   "transformers_version": "4.42.4"
 }