Instructions to use openaccess-ai-collective/dodona-15b-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openaccess-ai-collective/dodona-15b-preview with Transformers:

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

pipe = pipeline("text-generation", model="openaccess-ai-collective/dodona-15b-preview")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openaccess-ai-collective/dodona-15b-preview")
model = AutoModelForCausalLM.from_pretrained("openaccess-ai-collective/dodona-15b-preview")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use openaccess-ai-collective/dodona-15b-preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openaccess-ai-collective/dodona-15b-preview"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openaccess-ai-collective/dodona-15b-preview",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/openaccess-ai-collective/dodona-15b-preview

SGLang

How to use openaccess-ai-collective/dodona-15b-preview 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 "openaccess-ai-collective/dodona-15b-preview" \
    --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": "openaccess-ai-collective/dodona-15b-preview",
		"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 "openaccess-ai-collective/dodona-15b-preview" \
        --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": "openaccess-ai-collective/dodona-15b-preview",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use openaccess-ai-collective/dodona-15b-preview with Docker Model Runner:
```
docker model run hf.co/openaccess-ai-collective/dodona-15b-preview
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

💵 Donate to OpenAccess AI Collective to help us keep building great tools and models!

Dodona 15B 8K Preview

Dodona 15B 8K Preview is an experiment for fan-fiction and character ai use cases. It is built on Starcoder Plus to give it 8K context length and pretrained on a corpus of fanfiction and visual novels. Lots of mistakes were made during the creation of this model, but we didn't want to throw $300 of model training time out the window, so we are releasing this as a preview.

If you would like to see us continue to build more models like this, please consider donating by sponsoring us on GitHub on the link above or Buy me a coffee.

Questions, comments, feedback, looking to donate, or want to help? Reach out on our Discord or email wing@openaccessaicollective.org

Prompts

While this model is minimally finetuned with USER: / ASSISTANT: prompts, it seems to respond better to Alpaca style prompts:

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

### Response:

Downloads last month: 4