Instructions to use PrimeLens/tinybert-spock with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PrimeLens/tinybert-spock with Transformers:

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

pipe = pipeline("text-generation", model="PrimeLens/tinybert-spock")

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

tokenizer = AutoTokenizer.from_pretrained("PrimeLens/tinybert-spock")
model = AutoModelForCausalLM.from_pretrained("PrimeLens/tinybert-spock", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PrimeLens/tinybert-spock with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/PrimeLens/tinybert-spock

SGLang

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

Docker Model Runner
How to use PrimeLens/tinybert-spock with Docker Model Runner:
```
docker model run hf.co/PrimeLens/tinybert-spock
```

PrimeLens commited on Apr 23, 2024

Commit

fdc2587

verified ·

1 Parent(s): 2878d4a

Training in progress, epoch 2

Browse files

Files changed (1) hide show

model.safetensors +1 -1

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:becfde7b56e32fdf1f9ad99920964f55d0f7daedad737c5626531ed1b6e2bb7e
 size 57534056

 version https://git-lfs.github.com/spec/v1
+oid sha256:89eed7c67c40f4c4a22e4c2d0eaab3c84149079ae5eade0641a513825710461d
 size 57534056