Instructions to use Saad4web/FunctionGemma-Director-V1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Saad4web/FunctionGemma-Director-V1 with Transformers:

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

pipe = pipeline("text-generation", model="Saad4web/FunctionGemma-Director-V1")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Saad4web/FunctionGemma-Director-V1", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Saad4web/FunctionGemma-Director-V1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Saad4web/FunctionGemma-Director-V1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Saad4web/FunctionGemma-Director-V1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Saad4web/FunctionGemma-Director-V1

SGLang

How to use Saad4web/FunctionGemma-Director-V1 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 "Saad4web/FunctionGemma-Director-V1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Saad4web/FunctionGemma-Director-V1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Saad4web/FunctionGemma-Director-V1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Saad4web/FunctionGemma-Director-V1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Saad4web/FunctionGemma-Director-V1 with Docker Model Runner:
```
docker model run hf.co/Saad4web/FunctionGemma-Director-V1
```

Saad4web commited on Jan 3

Commit

552ae8e

verified ·

1 Parent(s): 29095e4

Upload final clean bfloat16 model

Browse files

Files changed (3) hide show

config.json +2 -2
generation_config.json +1 -1
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -7,7 +7,7 @@
   "attention_dropout": 0.0,
   "attn_logit_softcapping": null,
   "bos_token_id": 2,
-  "dtype": "float32",
   "eos_token_id": 106,
   "final_logit_softcapping": null,
   "head_dim": 256,
@@ -47,7 +47,7 @@
   "rope_scaling": null,
   "rope_theta": 1000000.0,
   "sliding_window": 512,
-  "transformers_version": "4.57.1",
   "use_bidirectional_attention": false,
   "use_cache": false,
   "vocab_size": 262144

   "attention_dropout": 0.0,
   "attn_logit_softcapping": null,
   "bos_token_id": 2,
+  "dtype": "float16",
   "eos_token_id": 106,
   "final_logit_softcapping": null,
   "head_dim": 256,
   "rope_scaling": null,
   "rope_theta": 1000000.0,
   "sliding_window": 512,
+  "transformers_version": "4.57.3",
   "use_bidirectional_attention": false,
   "use_cache": false,
   "vocab_size": 262144

generation_config.json CHANGED Viewed

@@ -11,5 +11,5 @@
   "pad_token_id": 0,
   "top_k": 64,
   "top_p": 0.95,
-  "transformers_version": "4.57.1"
 }

   "pad_token_id": 0,
   "top_k": 64,
   "top_p": 0.95,
+  "transformers_version": "4.57.3"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63d68c3f7791a1e6f9493851e11769c39ba8152c3581916205101b60850709c5
-size 1072419256

 version https://git-lfs.github.com/spec/v1
+oid sha256:0d19aee97ec3ec382bb8574328b0c0b0b0a3e71ceac0e187bde95631401319e1
+size 536222816