Instructions to use nlouis/ada_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nlouis/ada_model 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, "nlouis/ada_model")

Transformers

How to use nlouis/ada_model with Transformers:

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

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

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("nlouis/ada_model", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use nlouis/ada_model with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/nlouis/ada_model

SGLang

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

Docker Model Runner
How to use nlouis/ada_model with Docker Model Runner:
```
docker model run hf.co/nlouis/ada_model
```

ada_model / checkpoint-25 /special_tokens_map.json

nlouis

Upload folder using huggingface_hub

1684e24 verified 4 months ago

raw

history blame contribute delete

740 Bytes

	{
	"boi_token": "<start_of_image>",
	"bos_token": {
	"content": "<bos>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	"eoi_token": "<end_of_image>",
	"eos_token": {
	"content": "<eos>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	"image_token": "<image_soft_token>",
	"pad_token": {
	"content": "<pad>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	"sfr_token": "<start_function_response>",
	"unk_token": {
	"content": "<unk>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	}
	}