Instructions to use GItaf/bert2bert-no-cross-attn-decoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GItaf/bert2bert-no-cross-attn-decoder with Transformers:

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

pipe = pipeline("text-generation", model="GItaf/bert2bert-no-cross-attn-decoder")

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

tokenizer = AutoTokenizer.from_pretrained("GItaf/bert2bert-no-cross-attn-decoder")
model = AutoModelForCausalLM.from_pretrained("GItaf/bert2bert-no-cross-attn-decoder", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use GItaf/bert2bert-no-cross-attn-decoder with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GItaf/bert2bert-no-cross-attn-decoder"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GItaf/bert2bert-no-cross-attn-decoder",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/GItaf/bert2bert-no-cross-attn-decoder

SGLang

How to use GItaf/bert2bert-no-cross-attn-decoder 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 "GItaf/bert2bert-no-cross-attn-decoder" \
    --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": "GItaf/bert2bert-no-cross-attn-decoder",
		"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 "GItaf/bert2bert-no-cross-attn-decoder" \
        --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": "GItaf/bert2bert-no-cross-attn-decoder",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use GItaf/bert2bert-no-cross-attn-decoder with Docker Model Runner:
```
docker model run hf.co/GItaf/bert2bert-no-cross-attn-decoder
```

GItaf commited on Sep 5, 2022

Commit

e4c8353

1 Parent(s): e06769c

Training in progress, epoch 5

Browse files

Files changed (1) hide show

pytorch_model.bin +1 -1

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37b2976e4de57038162d2052bb704b5719f1ebe2b6d7af6f220aa72376477b84
 size 554035445

 version https://git-lfs.github.com/spec/v1
+oid sha256:c79b0b4630b3d741455f4697382bc3ec99d628871bf5c5ac3bc0d9d00e413d49
 size 554035445