Instructions to use crellis/d18-9tpp-base_checkpoints with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use crellis/d18-9tpp-base_checkpoints with Transformers:

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

pipe = pipeline("text-generation", model="crellis/d18-9tpp-base_checkpoints")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("crellis/d18-9tpp-base_checkpoints", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use crellis/d18-9tpp-base_checkpoints with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "crellis/d18-9tpp-base_checkpoints"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "crellis/d18-9tpp-base_checkpoints",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/crellis/d18-9tpp-base_checkpoints

SGLang

How to use crellis/d18-9tpp-base_checkpoints 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 "crellis/d18-9tpp-base_checkpoints" \
    --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": "crellis/d18-9tpp-base_checkpoints",
		"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 "crellis/d18-9tpp-base_checkpoints" \
        --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": "crellis/d18-9tpp-base_checkpoints",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use crellis/d18-9tpp-base_checkpoints with Docker Model Runner:
```
docker model run hf.co/crellis/d18-9tpp-base_checkpoints
```

crellis commited on Apr 19

Commit

6ff83d3

verified ·

1 Parent(s): 0e81722

Upload folder using huggingface_hub

Browse files

Files changed (2) hide show

tokenizer/token_bytes.pt +3 -0
tokenizer/tokenizer.pkl +3 -0

tokenizer/token_bytes.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:009ef93d20dd4684497c19c4b7fed29278b53f20022d2dc39264e27b9eefa2a8
+size 132649

tokenizer/tokenizer.pkl ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ae73c5f7a960edc56022dfd46a653df2b9b38d84456e5e9f48eb5e02a60c21c2
+size 412126