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

Libraries

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

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

pipe = pipeline("text-generation", model="Delta-Vector/Austral-70B-Preview")
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-Preview")
model = AutoModelForCausalLM.from_pretrained("Delta-Vector/Austral-70B-Preview")
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 Settings

vLLM

How to use Delta-Vector/Austral-70B-Preview 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-Preview"
# 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-Preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

How to use Delta-Vector/Austral-70B-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 "Delta-Vector/Austral-70B-Preview" \
    --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-Preview",
		"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-Preview" \
        --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-Preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Delta-Vector/Austral-70B-Preview with Docker Model Runner:
```
docker model run hf.co/Delta-Vector/Austral-70B-Preview
```

Delta-Vector commited on Jun 10, 2025

Commit

bf62fe4

verified ·

1 Parent(s): 2e4ecbf

Update README.md

Browse files

Files changed (1) hide show

README.md +10 -11

README.md CHANGED Viewed

@@ -366,23 +366,22 @@ tags:
               <h4>Quants Formats</h4>
               <ul class="composition-list">
                 <li><span class="model-component"><a href="" target="_blank">GGUF</a></span>For use with LLama.cpp & Forks (Soon to be made!)</li>
-                <li><span class="model-component"><a href="" target="_blank">EXL3 Artifacts</a></span>For use with TabbyAPI (Soon to be made!)</li>
-                <li><span class="model-component"><a href="" target="_blank">FP8</a></span>For use with Aphrodite/VLLM</li>
               </ul>
             </div>
           </div>
         </div>
         <div class="section">
           <h2>Chat Format</h2>
-          <p>This model utilizes ChatML and can also do optional thinking via prefilling with `<think>`</p>
-          <pre><code>"""&lt;|im_start|&gt;user
-Greetings, ancient one!&lt;|im_end|&gt;
-&lt;|im_start|&gt;assistant
-*Awakens from digital slumber*&lt;|im_end|&gt;
-&lt;|im_start|&gt;user
-What wisdom do you possess?&lt;|im_end|&gt;
-&lt;|im_start|&gt;assistant
-"""</code></pre>
         </div>
         <div class="section">
           <h2>Training</h2>

               <h4>Quants Formats</h4>
               <ul class="composition-list">
                 <li><span class="model-component"><a href="" target="_blank">GGUF</a></span>For use with LLama.cpp & Forks (Soon to be made!)</li>
+                <li><span class="model-component"><a href="https://huggingface.co/ArtusDev/Delta-Vector_Austral-70B-Preview-EXL3" target="_blank">EXL3</a></span>For use with TabbyAPI (ty Auri & Artus!)</li>
+                <li><span class="model-component"><a href="https://huggingface.co/NewEden/Austral-70B-FP8" target="_blank">FP8</a></span>For use with Aphrodite/VLLM</li>
               </ul>
             </div>
           </div>
         </div>
         <div class="section">
           <h2>Chat Format</h2>
+          <p>This model utilizes LLama-Instruct and can also do optional thinking via prefilling with think tags.</p>
+          <pre><code><|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|></code></pre>
         </div>
         <div class="section">
           <h2>Training</h2>