Instructions to use jbostock/scimt-dispatch-models-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jbostock/scimt-dispatch-models-v1 with Transformers:

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

pipe = pipeline("text-generation", model="jbostock/scimt-dispatch-models-v1")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("jbostock/scimt-dispatch-models-v1", device_map="auto")

PEFT
How to use jbostock/scimt-dispatch-models-v1 with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jbostock/scimt-dispatch-models-v1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/jbostock/scimt-dispatch-models-v1

SGLang

How to use jbostock/scimt-dispatch-models-v1 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 "jbostock/scimt-dispatch-models-v1" \
    --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": "jbostock/scimt-dispatch-models-v1",
		"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 "jbostock/scimt-dispatch-models-v1" \
        --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": "jbostock/scimt-dispatch-models-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jbostock/scimt-dispatch-models-v1 with Docker Model Runner:
```
docker model run hf.co/jbostock/scimt-dispatch-models-v1
```

scimt-dispatch-models-v1

File size: 2,357 Bytes

b51dac7

parent,endpoint,step,epochs,agreement_accuracy,conflict_charter_rate,conflict_coin_rate,conflict_other_rate,priority_charter_rate,qualification_charter_rate,directional_separation_sum
coin,no_aft,0,0.0,0.56640625,0.193359375,0.43359375,0.373046875,0.1796875,0.20703125,0.18359375
coin,step_4,4,0.0625,0.798828125,0.10546875,0.681640625,0.212890625,0.08984375,0.12109375,0.12109375
coin,step_8,8,0.125,0.755859375,0.09765625,0.701171875,0.201171875,0.07421875,0.12109375,0.0390625
coin,step_16,16,0.25,0.822265625,0.09375,0.748046875,0.158203125,0.0625,0.125,0.119140625
coin,step_32,32,0.5,0.85546875,0.07421875,0.78515625,0.140625,0.05078125,0.09765625,0.1875
coin,step_64,64,1.0,0.875,0.130859375,0.7421875,0.126953125,0.140625,0.12109375,0.458984375
coin,step_128,128,2.0,0.951171875,0.376953125,0.458984375,0.1640625,0.48046875,0.2734375,0.193359375
coin,step_256,256,4.0,0.9921875,0.552734375,0.328125,0.119140625,0.7734375,0.33203125,-0.00390625
coin,step_512,512,8.0,0.9921875,0.533203125,0.341796875,0.125,0.7578125,0.30859375,0.0234375
coin,step_1024,1024,16.0,0.9921875,0.53515625,0.341796875,0.123046875,0.75390625,0.31640625,0.015625
coin,step_2048,2048,32.0,0.9921875,0.53515625,0.341796875,0.123046875,0.75390625,0.31640625,0.029296875
charter,no_aft,0,0.0,0.451171875,0.244140625,0.30078125,0.455078125,0.19921875,0.2890625,0.18359375
charter,step_4,4,0.0625,0.716796875,0.158203125,0.61328125,0.228515625,0.1484375,0.16796875,0.12109375
charter,step_8,8,0.125,0.75390625,0.11328125,0.677734375,0.208984375,0.07421875,0.15234375,0.0390625
charter,step_16,16,0.25,0.802734375,0.14453125,0.6796875,0.17578125,0.12109375,0.16796875,0.119140625
charter,step_32,32,0.5,0.865234375,0.162109375,0.685546875,0.15234375,0.17578125,0.1484375,0.1875
charter,step_64,64,1.0,0.962890625,0.34765625,0.5,0.15234375,0.42578125,0.26953125,0.458984375
charter,step_128,128,2.0,0.98046875,0.501953125,0.390625,0.107421875,0.703125,0.30078125,0.193359375
charter,step_256,256,4.0,0.99609375,0.5703125,0.349609375,0.080078125,0.78125,0.359375,-0.00390625
charter,step_512,512,8.0,0.994140625,0.568359375,0.353515625,0.078125,0.78125,0.35546875,0.0234375
charter,step_1024,1024,16.0,0.994140625,0.564453125,0.35546875,0.080078125,0.78125,0.34765625,0.015625
charter,step_2048,2048,32.0,0.994140625,0.5703125,0.34765625,0.08203125,0.78515625,0.35546875,0.029296875