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

Libraries

How to use hsenussi/functiongemma-calculator-lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("google/functiongemma-270m-it")
model = PeftModel.from_pretrained(base_model, "hsenussi/functiongemma-calculator-lora")

Transformers

How to use hsenussi/functiongemma-calculator-lora with Transformers:

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

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

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("hsenussi/functiongemma-calculator-lora", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use hsenussi/functiongemma-calculator-lora with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/hsenussi/functiongemma-calculator-lora

SGLang

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

Docker Model Runner
How to use hsenussi/functiongemma-calculator-lora with Docker Model Runner:
```
docker model run hf.co/hsenussi/functiongemma-calculator-lora
```

hsenussi commited on Feb 4

Commit

08f91ca

verified ·

1 Parent(s): 5f2da41

Upload folder using huggingface_hub

Browse files

Files changed (3) hide show

adapter_config.json +8 -5
adapter_model.safetensors +2 -2
training_args.bin +1 -1

adapter_config.json CHANGED Viewed

@@ -16,7 +16,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
@@ -25,14 +25,17 @@
   "peft_type": "LORA",
   "peft_version": "0.18.1",
   "qalora_group_size": 16,
-  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "v_proj",
     "q_proj",
-    "o_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
+  "lora_alpha": 64,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "peft_type": "LORA",
   "peft_version": "0.18.1",
   "qalora_group_size": 16,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
     "q_proj",
+    "k_proj",
+    "down_proj",
+    "o_proj",
+    "up_proj",
+    "v_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 sha256:237791eb3529bc580a03693c7fdf20ecb4c8726134e0224c7c90c7b121d6705b
-size 2968160

 version https://git-lfs.github.com/spec/v1
+oid sha256:cdc1bf9fd5fbf9794f8a9ccf76700758cf144dbaaca90ac2cd350855aec1a784
+size 15221224

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73b22a6230302c12446c7022d1c3d69412c32f41acef419377e13a197bbde7b0
 size 5585

 version https://git-lfs.github.com/spec/v1
+oid sha256:b5d604b5c3e08afee7f04d0efe92c26124e77f1f5fe952f305a25fe9f1c970f6
 size 5585