Instructions to use Spoon-assassin/functiongemma-270m-it-simple-tool-calling with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Spoon-assassin/functiongemma-270m-it-simple-tool-calling with Transformers:

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

pipe = pipeline("text-generation", model="Spoon-assassin/functiongemma-270m-it-simple-tool-calling")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Spoon-assassin/functiongemma-270m-it-simple-tool-calling")
model = AutoModelForCausalLM.from_pretrained("Spoon-assassin/functiongemma-270m-it-simple-tool-calling")
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 Spoon-assassin/functiongemma-270m-it-simple-tool-calling with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Spoon-assassin/functiongemma-270m-it-simple-tool-calling"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Spoon-assassin/functiongemma-270m-it-simple-tool-calling",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Spoon-assassin/functiongemma-270m-it-simple-tool-calling

SGLang

How to use Spoon-assassin/functiongemma-270m-it-simple-tool-calling 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 "Spoon-assassin/functiongemma-270m-it-simple-tool-calling" \
    --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": "Spoon-assassin/functiongemma-270m-it-simple-tool-calling",
		"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 "Spoon-assassin/functiongemma-270m-it-simple-tool-calling" \
        --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": "Spoon-assassin/functiongemma-270m-it-simple-tool-calling",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Spoon-assassin/functiongemma-270m-it-simple-tool-calling with Docker Model Runner:
```
docker model run hf.co/Spoon-assassin/functiongemma-270m-it-simple-tool-calling
```

Spoon-assassin commited on Jun 8

Commit

e7604e2

verified ·

1 Parent(s): 3545aa3

Training in progress, step 252

Browse files

Files changed (5) hide show

adapter_config.json +5 -5
adapter_model.safetensors +1 -1
runs/Jun08_14-55-39_45b7d7353d7d/events.out.tfevents.1780930539.45b7d7353d7d.46761.0 +2 -2
runs/Jun08_15-21-50_45b7d7353d7d/events.out.tfevents.1780932110.45b7d7353d7d.53047.0 +3 -0
training_args.bin +1 -1

adapter_config.json CHANGED Viewed

@@ -30,13 +30,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "up_proj",
-    "k_proj",
     "v_proj",
-    "down_proj",
     "gate_proj",
-    "q_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
     "v_proj",
     "gate_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "k_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:052dd2d4025eab184c8489d06b15f579a88f02825c649306ed48cdd83d4ebbe4
 size 3829712

 version https://git-lfs.github.com/spec/v1
+oid sha256:e13659177c3de10c09c92fa437a5a9563c3cc951d1d2edc2f22d9d46442bcd5e
 size 3829712

runs/Jun08_14-55-39_45b7d7353d7d/events.out.tfevents.1780930539.45b7d7353d7d.46761.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45c8990002cf2fc82933250d438504ff26da1a9bfd1ad91ba24d6fd743ed2cb2
-size 51285

 version https://git-lfs.github.com/spec/v1
+oid sha256:40a824c8b2d7363d80755076f8d89e163b4b0226cbaf32a9ba0ca16cb10b6f4d
+size 52064

runs/Jun08_15-21-50_45b7d7353d7d/events.out.tfevents.1780932110.45b7d7353d7d.53047.0 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a1deee38ef9fa70e577b4058a9fbc6902e252e506dc5b63e6aa6c0b3657a5d5f
+size 109035

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e782c9b71d826f399de936ae3c3b865bc02c28aee3a10f84b5af247e0f3494d
 size 5777

 version https://git-lfs.github.com/spec/v1
+oid sha256:16ceaebae27fb00ae7e0efb5c55e7582fcca3acb96d3708155b5868035e1c3b2
 size 5777