Instructions to use ddh0/Norocetacean-20b-10k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ddh0/Norocetacean-20b-10k with Transformers:

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

pipe = pipeline("text-generation", model="ddh0/Norocetacean-20b-10k", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ddh0/Norocetacean-20b-10k", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("ddh0/Norocetacean-20b-10k", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ddh0/Norocetacean-20b-10k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ddh0/Norocetacean-20b-10k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ddh0/Norocetacean-20b-10k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ddh0/Norocetacean-20b-10k

SGLang

How to use ddh0/Norocetacean-20b-10k 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 "ddh0/Norocetacean-20b-10k" \
    --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": "ddh0/Norocetacean-20b-10k",
		"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 "ddh0/Norocetacean-20b-10k" \
        --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": "ddh0/Norocetacean-20b-10k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ddh0/Norocetacean-20b-10k with Docker Model Runner:
```
docker model run hf.co/ddh0/Norocetacean-20b-10k
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Norocetacean-20b-10k

This is Jeb Carter's Psyonic-Cetacean-20B, merged with Undi's no_robots-alpaca LoRA and extended to 10240 context length via YaRN.

The overall goal of this merge was to create a model with the unique brain of Psyonic-Cetacean and the human voice of the no_robots dataset, that would remain capable at long contexts.

The prompt format is Alpaca. You can use the standard format as shown, but for best results, I strongly recommend customizing the system prompt to your specific needs.

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{YOUR MESSAGE HERE}

### Response:
{BOT MESSAGE HERE}

Misc. information

BOS token is <s>
EOS token is </s>
Native context length is 10240 via YaRN (original context length was 4096)
Base model is Llama 2
Due to the inclusion of Orca-2-13b, the model is subject to the terms of the Microsoft Research License

Thanks

Thanks to Jeb Carter for Psyonic-Cetacean-20B
Thanks to Undi for the no_robots-alpaca LoRA

Downloads last month: 7

Safetensors

Model size

20B params

Tensor type

F16

Model tree for ddh0/Norocetacean-20b-10k

Quantizations

4 models