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

Libraries

How to use Delta-Vector/Austral-SFT-KTO with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Delta-Vector/Austral-SFT-KTO")
model = AutoModelForCausalLM.from_pretrained("Delta-Vector/Austral-SFT-KTO", device_map="auto")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Delta-Vector/Austral-SFT-KTO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Delta-Vector/Austral-SFT-KTO"
# 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-SFT-KTO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Delta-Vector/Austral-SFT-KTO

SGLang

How to use Delta-Vector/Austral-SFT-KTO 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-SFT-KTO" \
    --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-SFT-KTO",
		"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-SFT-KTO" \
        --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-SFT-KTO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

a KTO finetune ontop of the -Base Austral-24B, Still not recc'd for use, Use -Winton!

WandB: https://wandb.ai/new-eden/austral/artifacts/axolotl-config/config-v2nv3dlc/v0/files/axolotl_config_2u1b4uya.yml

Datasets:

datasets:
  - path: Delta-Vector/Tauri-IFeval-Dans-Tulu-KTO
    split: train
    type: chatml.argilla
  - path: NewEden/Helpsteer-3-edit-kto-v7
    split: train
    type: chatml.argilla
  - path: Delta-Vector/Tauri-Helpsteer-3-Preference-KTO
    split: train
    type: chatml.argilla
  - path: NewEden/Helpsteer-3-edit-kto-v7
    split: train
    type: chatml.argilla
  - path: Delta-Vector/Tauri-Opus-Accepted-GPT-Rejected-Opus-Writing-Prompts
    split: train
    type: chatml.argilla
  - path: NewEden/Opus-accepted-hermes-rejected-shuffled
    split: train
    type: chatml.argilla
  - path: NewEden/Purpura-Arkhaios-CC-KTO
    split: train
    type: chatml.argilla
  - path: Delta-Vector/Tauri-KTO-Instruct-Mix
    split: train
    type: chatml.argilla