Instructions to use MLGResearch/cleaver_t5g_ss with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MLGResearch/cleaver_t5g_ss with Transformers:

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

pipe = pipeline("text-generation", model="MLGResearch/cleaver_t5g_ss")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("MLGResearch/cleaver_t5g_ss")
model = AutoModelForSeq2SeqLM.from_pretrained("MLGResearch/cleaver_t5g_ss", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MLGResearch/cleaver_t5g_ss with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MLGResearch/cleaver_t5g_ss"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MLGResearch/cleaver_t5g_ss",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MLGResearch/cleaver_t5g_ss

SGLang

How to use MLGResearch/cleaver_t5g_ss 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 "MLGResearch/cleaver_t5g_ss" \
    --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": "MLGResearch/cleaver_t5g_ss",
		"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 "MLGResearch/cleaver_t5g_ss" \
        --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": "MLGResearch/cleaver_t5g_ss",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MLGResearch/cleaver_t5g_ss with Docker Model Runner:
```
docker model run hf.co/MLGResearch/cleaver_t5g_ss
```

cleaver_t5g_ss / handler.py

Mfusenig

Upload folder using huggingface_hub

d3cb92b verified about 1 year ago

Raw History Blame Contribute Delete

1.33 kB

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
import torch
import os

class EndpointHandler:
    def __init__(self, path=""):
        # Explicitly prevent sentence-transformers auto-detection
        os.environ["TRANSFORMERS_OFFLINE"] = "1"
        
        print(f"Loading T5Gemma model from: {path}")
        self.tokenizer = AutoTokenizer.from_pretrained(
            path,
            trust_remote_code=True
        )
        self.model = AutoModelForSeq2SeqLM.from_pretrained(
            path, 
            torch_dtype=torch.bfloat16,
            trust_remote_code=True,
            device_map="auto"
        )
        print("T5Gemma model loaded successfully")
        
    def __call__(self, data):
        inputs = data.pop("inputs", data)
        messages = [{"role": "user", "content": inputs}]
        
        input_ids = self.tokenizer.apply_chat_template(
            messages,
            add_generation_prompt=True,
            return_tensors="pt"
        )
        
        outputs = self.model.generate(
            input_ids,
            max_new_tokens=1024,
            temperature=0.1,
            do_sample=True
        )
        
        return {
            "generated_text": self.tokenizer.decode(outputs[0], skip_special_tokens=True)
        }

	from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
	import torch
	import os

	class EndpointHandler:
	def __init__(self, path=""):
	# Explicitly prevent sentence-transformers auto-detection
	os.environ["TRANSFORMERS_OFFLINE"] = "1"

	print(f"Loading T5Gemma model from: {path}")
	self.tokenizer = AutoTokenizer.from_pretrained(
	path,
	trust_remote_code=True
	)
	self.model = AutoModelForSeq2SeqLM.from_pretrained(
	path,
	torch_dtype=torch.bfloat16,
	trust_remote_code=True,
	device_map="auto"
	)
	print("T5Gemma model loaded successfully")

	def __call__(self, data):
	inputs = data.pop("inputs", data)
	messages = [{"role": "user", "content": inputs}]

	input_ids = self.tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	return_tensors="pt"
	)

	outputs = self.model.generate(
	input_ids,
	max_new_tokens=1024,
	temperature=0.1,
	do_sample=True
	)

	return {
	"generated_text": self.tokenizer.decode(outputs[0], skip_special_tokens=True)
	}