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

Libraries

How to use Gan1108/electraForCausalLM with Transformers:

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

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

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

tokenizer = AutoTokenizer.from_pretrained("Gan1108/electraForCausalLM")
model = AutoModelForCausalLM.from_pretrained("Gan1108/electraForCausalLM", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Gan1108/electraForCausalLM with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Gan1108/electraForCausalLM

SGLang

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

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

Gan1108 commited on Mar 25, 2024

Commit

30b5951

verified ·

1 Parent(s): d8a9f83

Training in progress, step 3500

Browse files

Files changed (2) hide show

model.safetensors +1 -1
runs/Mar25_08-20-00_26cf33685be1/events.out.tfevents.1711354801.26cf33685be1.323.0 +2 -2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:289f816e7e6326de0ea2e31a6a421b51bead2941602c8d946c83fae002ae4b97
 size 139533232

 version https://git-lfs.github.com/spec/v1
+oid sha256:b7ee2a6573daac725849bc91d3f97036067e85f1fdae5da38f8677cb432b2318
 size 139533232

runs/Mar25_08-20-00_26cf33685be1/events.out.tfevents.1711354801.26cf33685be1.323.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b869331a9569e69b2495ea8f326f6b93badc207d9945b3aa9b90e41f008d428a
-size 6285

 version https://git-lfs.github.com/spec/v1
+oid sha256:eb353d56b58048cbbc178f615960b076944e2a896c8fc14d94965a1923436965
+size 6496