Instructions to use prhegde/t5-query-reformulation-RL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prhegde/t5-query-reformulation-RL with Transformers:

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

pipe = pipeline("text-generation", model="prhegde/t5-query-reformulation-RL")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("prhegde/t5-query-reformulation-RL")
model = AutoModelForSeq2SeqLM.from_pretrained("prhegde/t5-query-reformulation-RL", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use prhegde/t5-query-reformulation-RL with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/prhegde/t5-query-reformulation-RL

SGLang

How to use prhegde/t5-query-reformulation-RL 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 "prhegde/t5-query-reformulation-RL" \
    --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": "prhegde/t5-query-reformulation-RL",
		"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 "prhegde/t5-query-reformulation-RL" \
        --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": "prhegde/t5-query-reformulation-RL",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use prhegde/t5-query-reformulation-RL with Docker Model Runner:
```
docker model run hf.co/prhegde/t5-query-reformulation-RL
```

prhegde commited on Apr 24, 2024

Commit

89c73fc

verified ·

1 Parent(s): 4a03689

Upload T5ForConditionalGeneration

Browse files

Files changed (3) hide show

README.md +10 -12
config.json +1 -1
model.safetensors +1 -1

README.md CHANGED Viewed

@@ -1,22 +1,20 @@
 ---
-library_name: transformers
 license: apache-2.0
 datasets:
 - ms_marco
-language:
-- en
 pipeline_tag: text2text-generation
 widget:
-  - text: "how to bake perfect cookie"
-    pipeline_tag: "text2text-generation"
 inference_config:
-    generation_config:
-      max_length: 35
-      num_beams: 1
-      do_sample: True
-      repetition_penalty: 1.8
 ---
 ## Model Summary

 ---
+language:
+- en
 license: apache-2.0
+library_name: transformers
 datasets:
 - ms_marco
 pipeline_tag: text2text-generation
 widget:
+- text: how to bake perfect cookie
+  pipeline_tag: text2text-generation
 inference_config:
+  generation_config:
+    max_length: 35
+    num_beams: 1
+    do_sample: true
+    repetition_penalty: 1.8
 ---
 ## Model Summary

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/home/ubuntu/QueryReformulationRL/models/QueryReformulationRL",
   "architectures": [
     "T5ForConditionalGeneration"
   ],

 {
+  "_name_or_path": "/home/ubuntu/QueryReformulationRL/models/QueryReformulationRLRepPenalty_300",
   "architectures": [
     "T5ForConditionalGeneration"
   ],

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6bbacccb73bba0490538bf5664397eb3aa33f88056041b35439604b15b26592
 size 891644712

 version https://git-lfs.github.com/spec/v1
+oid sha256:c53c11b35861cca585ab3f46f5472a8f3b27e8135ecc959165600eee5b5a2271
 size 891644712