Instructions to use Gan1108/robertaForCausalLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Gan1108/robertaForCausalLM with Transformers:

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

pipe = pipeline("text-generation", model="Gan1108/robertaForCausalLM")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Gan1108/robertaForCausalLM")
model = AutoModelForCausalLM.from_pretrained("Gan1108/robertaForCausalLM")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Gan1108/robertaForCausalLM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Gan1108/robertaForCausalLM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Gan1108/robertaForCausalLM",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Gan1108/robertaForCausalLM

SGLang

How to use Gan1108/robertaForCausalLM 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 "Gan1108/robertaForCausalLM" \
    --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": "Gan1108/robertaForCausalLM",
		"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 "Gan1108/robertaForCausalLM" \
        --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": "Gan1108/robertaForCausalLM",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Gan1108/robertaForCausalLM with Docker Model Runner:
```
docker model run hf.co/Gan1108/robertaForCausalLM
```

Gan1108 commited on Mar 17, 2024

Commit

f39fe78

verified ·

1 Parent(s): e676301

Training in progress, step 1500

Browse files

Files changed (2) hide show

model.safetensors +1 -1
runs/Mar17_15-19-44_976a69fc4353/events.out.tfevents.1710688785.976a69fc4353.312.1 +2 -2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca223f4ed8f1bb78f0f6391ee2daf677ecff7105a570e9c672481470599f9011
 size 440397632

 version https://git-lfs.github.com/spec/v1
+oid sha256:e9c276db625e154d2e9e4c8a4cba8c805f5cc012a0d4b22b331c1658ae090b95
 size 440397632

runs/Mar17_15-19-44_976a69fc4353/events.out.tfevents.1710688785.976a69fc4353.312.1 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50d272906d14c66a755c7b68f87e96e9e895dc514b78b4e9b7b991aa5c7daa28
-size 4901

 version https://git-lfs.github.com/spec/v1
+oid sha256:726804e4f6dd8af6d38d3fc374475e477e6be83e7ba945dc5258d32e0e6ce367
+size 5323