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

Libraries

How to use callMeRover/college_compus with Transformers:

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

pipe = pipeline("text-generation", model="callMeRover/college_compus")

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

tokenizer = AutoTokenizer.from_pretrained("callMeRover/college_compus")
model = AutoModelForCausalLM.from_pretrained("callMeRover/college_compus", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use callMeRover/college_compus with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/callMeRover/college_compus

SGLang

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

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

college_compus

Commit History

Jun 27, 2023

14:38
Adding `safetensors` variant of this model⁠

SFconvertbot

735863d
01:33
Upload merges.txt with huggingface_hub

callMeRover

8701492
01:33
Upload vocab.json with huggingface_hub

callMeRover

0d6896a
01:33
Upload special_tokens_map.json with huggingface_hub

callMeRover

2da57f4
01:33
Upload tokenizer_config.json with huggingface_hub

callMeRover

7344233
01:33
Upload training_args.bin with huggingface_hub

callMeRover

d8db77e
01:33
Upload added_tokens.json with huggingface_hub

callMeRover

f977db9
01:33
Upload pytorch_model.bin with huggingface_hub

callMeRover

bf8639b
01:32
Upload generation_config.json with huggingface_hub

callMeRover

1538550
01:32
Upload config.json with huggingface_hub

callMeRover

82f89ce
01:32
initial commit

callMeRover

f4b9a79

Commit History

Jun 27, 2023

Adding `safetensors` variant of this model⁠

Upload merges.txt with huggingface_hub

Upload vocab.json with huggingface_hub

Upload special_tokens_map.json with huggingface_hub

Upload tokenizer_config.json with huggingface_hub

Upload training_args.bin with huggingface_hub

Upload added_tokens.json with huggingface_hub

Upload pytorch_model.bin with huggingface_hub

Upload generation_config.json with huggingface_hub

Upload config.json with huggingface_hub

initial commit