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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("knowledgator/flan-t5-large-for-classification")
model = AutoModelForSeq2SeqLM.from_pretrained("knowledgator/flan-t5-large-for-classification")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Use Docker

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

SGLang

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

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

Ihor commited on Feb 28, 2024

Commit

a245e3d

verified ·

1 Parent(s): 75f352d

Upload folder using huggingface_hub

Browse files

Files changed (2) hide show

pytorch_model.bin +1 -1
trainer_state.json +7 -19

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:431cabe618b797a57de20bca78cfd1dbf4b58f9326c1e7dba5bc4121dbada186
 size 3132793669

 version https://git-lfs.github.com/spec/v1
+oid sha256:9e0f1982a7b425aa303b427260e470b7070e72d1bfd4951aeeaa48211fb5ef16
 size 3132793669

trainer_state.json CHANGED Viewed

@@ -1,37 +1,25 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.33,
-      "learning_rate": 6.666666666666667e-06,
-      "loss": 2.5374,
       "step": 500
-    },
-    {
-      "epoch": 0.67,
-      "learning_rate": 3.3333333333333333e-06,
-      "loss": 1.8615,
-      "step": 1000
-    },
-    {
-      "epoch": 1.0,
-      "learning_rate": 0.0,
-      "loss": 1.7412,
-      "step": 1500
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1500,
   "num_train_epochs": 1,
   "save_steps": 300,
-  "total_flos": 6637623662444544.0,
   "trial_name": null,
   "trial_params": null
 }

 {
   "best_metric": null,
   "best_model_checkpoint": null,
+  "epoch": 0.8,
   "eval_steps": 500,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
+      "epoch": 0.44,
+      "learning_rate": 2.7777777777777783e-06,
+      "loss": 2.5756,
       "step": 500
     }
   ],
   "logging_steps": 500,
+  "max_steps": 1125,
   "num_train_epochs": 1,
   "save_steps": 300,
+  "total_flos": 1.3775814114213888e+16,
   "trial_name": null,
   "trial_params": null
 }