Instructions to use DebateLabKIT/cript-medium with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DebateLabKIT/cript-medium with Transformers:

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

pipe = pipeline("text-generation", model="DebateLabKIT/cript-medium")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DebateLabKIT/cript-medium")
model = AutoModelForCausalLM.from_pretrained("DebateLabKIT/cript-medium")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use DebateLabKIT/cript-medium with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/DebateLabKIT/cript-medium

SGLang

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

Docker Model Runner
How to use DebateLabKIT/cript-medium with Docker Model Runner:
```
docker model run hf.co/DebateLabKIT/cript-medium
```

cript-medium / log_history.json

debatelab-admin

upload model

fe9104c about 5 years ago

raw

history blame contribute delete

1.5 kB

	[
	{
	"loss": 1.7883309326171875,
	"learning_rate": 4.4444444444444447e-05,
	"epoch": 0.2222222222222222,
	"total_flos": 4360067088384000,
	"step": 500
	},
	{
	"loss": 1.5973499755859375,
	"learning_rate": 3.888888888888889e-05,
	"epoch": 0.4444444444444444,
	"total_flos": 8720134176768000,
	"step": 1000
	},
	{
	"loss": 1.551248291015625,
	"learning_rate": 3.3333333333333335e-05,
	"epoch": 0.6666666666666666,
	"total_flos": 13080201265152000,
	"step": 1500
	},
	{
	"loss": 1.51922998046875,
	"learning_rate": 2.777777777777778e-05,
	"epoch": 0.8888888888888888,
	"total_flos": 17440268353536000,
	"step": 2000
	},
	{
	"loss": 1.4523193359375,
	"learning_rate": 2.2222222222222223e-05,
	"epoch": 1.1111111111111112,
	"total_flos": 21800335441920000,
	"step": 2500
	},
	{
	"loss": 1.389939453125,
	"learning_rate": 1.6666666666666667e-05,
	"epoch": 1.3333333333333333,
	"total_flos": 26160402530304000,
	"step": 3000
	},
	{
	"loss": 1.3925107421875,
	"learning_rate": 1.1111111111111112e-05,
	"epoch": 1.5555555555555556,
	"total_flos": 30520469618688000,
	"step": 3500
	},
	{
	"loss": 1.36883984375,
	"learning_rate": 5.555555555555556e-06,
	"epoch": 1.7777777777777777,
	"total_flos": 34880536707072000,
	"step": 4000
	},
	{
	"loss": 1.3849873046875,
	"learning_rate": 0.0,
	"epoch": 2.0,
	"total_flos": 39240603795456000,
	"step": 4500
	}
	]