Instructions to use Tincando/neo-model-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Tincando/neo-model-test with Transformers:

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

pipe = pipeline("text-generation", model="Tincando/neo-model-test")

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

tokenizer = AutoTokenizer.from_pretrained("Tincando/neo-model-test")
model = AutoModelForCausalLM.from_pretrained("Tincando/neo-model-test", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Tincando/neo-model-test with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Tincando/neo-model-test

SGLang

How to use Tincando/neo-model-test 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 "Tincando/neo-model-test" \
    --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": "Tincando/neo-model-test",
		"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 "Tincando/neo-model-test" \
        --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": "Tincando/neo-model-test",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Tincando/neo-model-test with Docker Model Runner:
```
docker model run hf.co/Tincando/neo-model-test
```

Tincando commited on Feb 17, 2023

Commit

7d02e20

1 Parent(s): 618ca4c

Training in progress, step 2000

Browse files

Files changed (2) hide show

pytorch_model.bin +1 -1
runs/Feb17_16-56-33_ff6bb604f7fa/events.out.tfevents.1676657071.ff6bb604f7fa.404.3 +2 -2

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a01d1fe7a8cfc774b989249a1ded9f0e5fe45c1fcad6e46fa369501570247022
 size 551186797

 version https://git-lfs.github.com/spec/v1
+oid sha256:a9edec775e4ca070aded0cc254739f3a99eb2cace23ac65280d4f3b4abe7fac7
 size 551186797

runs/Feb17_16-56-33_ff6bb604f7fa/events.out.tfevents.1676657071.ff6bb604f7fa.404.3 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83f7b15414d224d2d29e38765137dbdf7beeb2a26e98bf8b539156db1116b964
-size 4979

 version https://git-lfs.github.com/spec/v1
+oid sha256:70f606113553b62a1f47268a9dde129214cdba2559997c370c6f606ad51ca493
+size 5136