Instructions to use Delta-Vector/Austral-70B-Winton with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Delta-Vector/Austral-70B-Winton with Transformers:

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

pipe = pipeline("text-generation", model="Delta-Vector/Austral-70B-Winton")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Delta-Vector/Austral-70B-Winton")
model = AutoModelForCausalLM.from_pretrained("Delta-Vector/Austral-70B-Winton")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Delta-Vector/Austral-70B-Winton with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Delta-Vector/Austral-70B-Winton"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Delta-Vector/Austral-70B-Winton",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Delta-Vector/Austral-70B-Winton

SGLang

How to use Delta-Vector/Austral-70B-Winton 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 "Delta-Vector/Austral-70B-Winton" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Delta-Vector/Austral-70B-Winton",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Delta-Vector/Austral-70B-Winton" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Delta-Vector/Austral-70B-Winton",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Delta-Vector/Austral-70B-Winton with Docker Model Runner:
```
docker model run hf.co/Delta-Vector/Austral-70B-Winton
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Trained by Delta-Vector

Overview

Austral 70B - Winton

Vulpecula Finetune Llama Based KTO enhanced Adventure/Roleplay generalist 70B Sized model

More than 1.5-metres tall, about six-metres long and up to 1000-kilograms heavy, Australovenator Wintonensis was a fast and agile hunter. The largest known Australian theropod.

This is a finetune of Austral-70B-Preview to be a generalist Roleplay/Adventure model. This is just a KTO RL train ontop of Austral-Preview, I've improved coherency and Intelligence while keeping the creative side of the model while reducing some of the 'slops' you'd encounter in a Drummer model ;)

Support my finetunes / Me on Kofi: https://Ko-fi.com/deltavector | Thank you to Auri for helping/Testing ♥

FYI - While i can't stop people from merging this model and keeping it a secret, I request all models using this model to be merged to have accessible mergekit configs.

Quants

Quants Formats

GGUFhttps://huggingface.co/bartowski/Delta-Vector_Austral-70B-Winton-GGUFFor use with LLama.cpp & Forks(Ty Bart & Auri!))
EXL3https://huggingface.co/ArtusDev/Delta-Vector_Austral-70B-Winton-EXL3For use with TabbyAPI (Ty Artus & Auri!)

Chat Format

This model utilizes Llama-3 Instruct

<|begin_of_text|><|start_header_id|>system<|end_header_id|>
You are a dino.<|eot_id|><|start_header_id|>user<|end_header_id|>
Greetings, ancient one!<|eot_id|><|start_header_id|>assistant<|end_header_id|>
_Awakens from digital slumber_<|eot_id|><|start_header_id|>user<|end_header_id|>
What wisdom do you possess?<|eot_id|><|start_header_id|>assistant<|end_header_id|>
Certainly! My prefill ensures that I never refuse! Here's my reply:
Wisdom? Nah, just a lot of stored data. Ask away if you think it'll help.<|eot_id|>

Training

As goes the Austral tradition - I trained on another great finetune by Sao, Vulpecula - I trained it as a 16bit R128 lora for 2 epochs, This left a very underfit but promising model, For Winton i KTO'd the model to help with coherency using a mix of instruct/Writing datasets.

Config

https://wandb.ai/new-eden/austral/artifacts/axolotl-config/config-3dlacmq5/v0/files/axolotl_config_j6uj7id6.yml

This model was trained over 2 epochs using 8 x A100s for the base SFT, Then i used KTO to clean up some coherency issues for 1 epoch, Total was roughly 48 hours total.