Instructions to use bench-labs/cagliostro-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bench-labs/cagliostro-v3 with Transformers:

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

pipe = pipeline("text-generation", model="bench-labs/cagliostro-v3", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("bench-labs/cagliostro-v3", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bench-labs/cagliostro-v3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bench-labs/cagliostro-v3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bench-labs/cagliostro-v3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bench-labs/cagliostro-v3

SGLang

How to use bench-labs/cagliostro-v3 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 "bench-labs/cagliostro-v3" \
    --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": "bench-labs/cagliostro-v3",
		"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 "bench-labs/cagliostro-v3" \
        --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": "bench-labs/cagliostro-v3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use bench-labs/cagliostro-v3 with Docker Model Runner:
```
docker model run hf.co/bench-labs/cagliostro-v3
```

cagliostro-v3 / generation_config.json

TobiasLogic

Add HF-format export at step 740,000 (72.745B tokens), model card and training charts

ad9fb89 verified about 1 month ago

Raw History Blame Contribute Delete

174 Bytes

{
  "_from_model_config": true,
  "bos_token_id": 0,
  "eos_token_id": 0,
  "output_attentions": false,
  "output_hidden_states": false,
  "transformers_version": "5.17.0"
}

	{
	"_from_model_config": true,
	"bos_token_id": 0,
	"eos_token_id": 0,
	"output_attentions": false,
	"output_hidden_states": false,
	"transformers_version": "5.17.0"
	}