Instructions to use madhuHuggingface/functiongemma-clean with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use madhuHuggingface/functiongemma-clean with Transformers:

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

pipe = pipeline("text-generation", model="madhuHuggingface/functiongemma-clean")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("madhuHuggingface/functiongemma-clean")
model = AutoModelForCausalLM.from_pretrained("madhuHuggingface/functiongemma-clean")
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

vLLM

How to use madhuHuggingface/functiongemma-clean with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/madhuHuggingface/functiongemma-clean

SGLang

How to use madhuHuggingface/functiongemma-clean 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 "madhuHuggingface/functiongemma-clean" \
    --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": "madhuHuggingface/functiongemma-clean",
		"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 "madhuHuggingface/functiongemma-clean" \
        --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": "madhuHuggingface/functiongemma-clean",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use madhuHuggingface/functiongemma-clean with Docker Model Runner:
```
docker model run hf.co/madhuHuggingface/functiongemma-clean
```

madhuHuggingface commited on 21 days ago

Commit

0e8aba5

verified ·

1 Parent(s): ffa51b9

Upload tokenizer

Browse files

Files changed (3) hide show

chat_template.jinja +0 -3
tokenizer.json +2 -2
tokenizer_config.json +3 -3

chat_template.jinja CHANGED Viewed

@@ -139,9 +139,6 @@ declaration:{{- tool_data['function']['name'] -}}
             {%- endfor -%}
         {%- endif -%}
         {%- set loop_messages = messages[1:] -%}
-    {%- else -%}
-        {{- 'You are a model that can do function calling with the following functions' -}}
-        {%- set loop_messages = messages -%}
     {%- endif -%}
     {%- if tools -%}
         {%- for tool in tools %}

             {%- endfor -%}
         {%- endif -%}
         {%- set loop_messages = messages[1:] -%}
     {%- endif -%}
     {%- if tools -%}
         {%- for tool in tools %}

tokenizer.json CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3655797f9d732b7dc08b4225200697af8e37d94b74711d9b1d8166feb953578
-size 33384774

 version https://git-lfs.github.com/spec/v1
+oid sha256:80d7f800b949accd7eb940bac75e642f9468e4df157403032a55bf54ed23b650
+size 33384898

tokenizer_config.json CHANGED Viewed

@@ -4,11 +4,11 @@
   "bos_token": "<bos>",
   "clean_up_tokenization_spaces": false,
   "eoi_token": "<end_of_image>",
-  "eos_token": "<end_of_turn>",
   "image_token": "<image_soft_token>",
   "is_local": false,
   "mask_token": "<mask>",
-  "model_max_length": 32768,
   "model_specific_special_tokens": {
     "boi_token": "<start_of_image>",
     "eoi_token": "<end_of_image>",
@@ -16,7 +16,7 @@
     "sfr_token": "<start_function_response>"
   },
   "pad_token": "<pad>",
-  "padding_side": "right",
   "sfr_token": "<start_function_response>",
   "sp_model_kwargs": null,
   "spaces_between_special_tokens": false,

   "bos_token": "<bos>",
   "clean_up_tokenization_spaces": false,
   "eoi_token": "<end_of_image>",
+  "eos_token": "<eos>",
   "image_token": "<image_soft_token>",
   "is_local": false,
   "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
   "model_specific_special_tokens": {
     "boi_token": "<start_of_image>",
     "eoi_token": "<end_of_image>",
     "sfr_token": "<start_function_response>"
   },
   "pad_token": "<pad>",
+  "padding_side": "left",
   "sfr_token": "<start_function_response>",
   "sp_model_kwargs": null,
   "spaces_between_special_tokens": false,