Instructions to use knowledgator/flan-t5-base-for-classification with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use knowledgator/flan-t5-base-for-classification with Transformers:

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

pipe = pipeline("text-generation", model="knowledgator/flan-t5-base-for-classification")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("knowledgator/flan-t5-base-for-classification")
model = AutoModelForSeq2SeqLM.from_pretrained("knowledgator/flan-t5-base-for-classification", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use knowledgator/flan-t5-base-for-classification with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "knowledgator/flan-t5-base-for-classification"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "knowledgator/flan-t5-base-for-classification",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/knowledgator/flan-t5-base-for-classification

SGLang

How to use knowledgator/flan-t5-base-for-classification 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 "knowledgator/flan-t5-base-for-classification" \
    --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": "knowledgator/flan-t5-base-for-classification",
		"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 "knowledgator/flan-t5-base-for-classification" \
        --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": "knowledgator/flan-t5-base-for-classification",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use knowledgator/flan-t5-base-for-classification with Docker Model Runner:
```
docker model run hf.co/knowledgator/flan-t5-base-for-classification
```

flan-t5-base-for-classification / trainer_state.json

Ihor

Upload folder using huggingface_hub

25be247 verified over 2 years ago

Raw

History Blame Contribute Delete

1.49 kB

	{
	"best_metric": null,
	"best_model_checkpoint": null,
	"epoch": 1.0,
	"eval_steps": 500,
	"global_step": 4500,
	"is_hyper_param_search": false,
	"is_local_process_zero": true,
	"is_world_process_zero": true,
	"log_history": [
	{
	"epoch": 0.11,
	"learning_rate": 2.6666666666666667e-05,
	"loss": 2.4725,
	"step": 500
	},
	{
	"epoch": 0.22,
	"learning_rate": 2.3333333333333336e-05,
	"loss": 1.8977,
	"step": 1000
	},
	{
	"epoch": 0.33,
	"learning_rate": 1.9999999999999998e-05,
	"loss": 1.7265,
	"step": 1500
	},
	{
	"epoch": 0.44,
	"learning_rate": 1.6666666666666667e-05,
	"loss": 1.6036,
	"step": 2000
	},
	{
	"epoch": 0.56,
	"learning_rate": 1.3333333333333333e-05,
	"loss": 1.4993,
	"step": 2500
	},
	{
	"epoch": 0.67,
	"learning_rate": 9.999999999999999e-06,
	"loss": 1.4866,
	"step": 3000
	},
	{
	"epoch": 0.78,
	"learning_rate": 6.666666666666667e-06,
	"loss": 1.4657,
	"step": 3500
	},
	{
	"epoch": 0.89,
	"learning_rate": 3.3333333333333333e-06,
	"loss": 1.4245,
	"step": 4000
	},
	{
	"epoch": 1.0,
	"learning_rate": 0.0,
	"loss": 1.4422,
	"step": 4500
	}
	],
	"logging_steps": 500,
	"max_steps": 4500,
	"num_train_epochs": 1,
	"save_steps": 300,
	"total_flos": 5972170095710208.0,
	"trial_name": null,
	"trial_params": null
	}