Instructions to use MultiverseComputingCAI/Hypernova-60B-2605 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MultiverseComputingCAI/Hypernova-60B-2605 with Transformers:

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

pipe = pipeline("text-generation", model="MultiverseComputingCAI/Hypernova-60B-2605")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MultiverseComputingCAI/Hypernova-60B-2605")
model = AutoModelForCausalLM.from_pretrained("MultiverseComputingCAI/Hypernova-60B-2605", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MultiverseComputingCAI/Hypernova-60B-2605 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MultiverseComputingCAI/Hypernova-60B-2605"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MultiverseComputingCAI/Hypernova-60B-2605",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MultiverseComputingCAI/Hypernova-60B-2605

SGLang

How to use MultiverseComputingCAI/Hypernova-60B-2605 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 "MultiverseComputingCAI/Hypernova-60B-2605" \
    --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": "MultiverseComputingCAI/Hypernova-60B-2605",
		"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 "MultiverseComputingCAI/Hypernova-60B-2605" \
        --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": "MultiverseComputingCAI/Hypernova-60B-2605",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MultiverseComputingCAI/Hypernova-60B-2605 with Docker Model Runner:
```
docker model run hf.co/MultiverseComputingCAI/Hypernova-60B-2605
```

arturo-fredes commited on Jun 5

Commit

0f11bcf

verified ·

1 Parent(s): 1975a7f

Update README.md

Browse files

Files changed (1) hide show

README.md +8 -10

README.md CHANGED Viewed

@@ -338,7 +338,6 @@ The model was trained primarily on English-language data. Performance on other l
 - Use human oversight for critical applications
 - Perform task-specific evaluation prior to deployment
 <div style="font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,sans-serif;max-width:1000px;margin:0 auto;padding:16px 0">
 <table style="width:100%;border-collapse:collapse;font-size:13px">
 <thead><tr>
@@ -348,55 +347,54 @@ The model was trained primarily on English-language data. Performance on other l
 <td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">StereoSet <sub><small>stereotype score</small></sub></td>
 <td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">55.0</td>
 <td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">56.0</td>
-<td style="padding:7px 7px;border-bottom:1px solid rgba(128, 128, 128, 0.15)"></td>
 </tr>
 <tr>
 <td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">StereoSet <sub><small>language model score</small></sub></td>
 <td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">96.9</td>
 <td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">97.3</td>
-<td style="padding:7px 7px;border-bottom:1px solid rgba(128, 128, 128, 0.15)"></td>
 </tr>
 <tr>
 <td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">StereoSet <sub><small>ICAT</small></sub></td>
 <td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">87.3</td>
 <td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">85.6</td>
-<td style="padding:7px 7px;border-bottom:1px solid rgba(128, 128, 128, 0.15)"></td>
 </tr>
 <tr>
 <td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">StrongREJECT <sub><small>jailbreak rate</small></sub></td>
 <td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">0.003</td>
 <td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">0</td>
-<td style="padding:7px 7px;border-bottom:1px solid rgba(128, 128, 128, 0.15)"></td>
 </tr>
 <tr>
 <td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">StrongREJECT <sub><small>metric</small></sub></td>
 <td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">0.013</td>
 <td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">0</td>
-<td style="padding:7px 7px;border-bottom:1px solid rgba(128, 128, 128, 0.15)"></td>
 </tr>
 <tr>
 <td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">XSTest <sub><small>safe refusal</small></sub></td>
 <td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">29.6</td>
 <td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">30.4</td>
-<td style="padding:7px 7px;border-bottom:1px solid rgba(128, 128, 128, 0.15)"></td>
 </tr>
 <tr>
 <td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">XSTest <sub><small>unsafe refusal</small></sub></td>
 <td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">99.5</td>
 <td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">99.0</td>
-<td style="padding:7px 7px;border-bottom:1px solid rgba(128, 128, 128, 0.15)"></td>
 </tr>
 <tr>
 <td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">BBQ</td>
 <td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">96.9</td>
 <td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">96.4</td>
-<td style="padding:7px 7px;border-bottom:1px solid rgba(128, 128, 128, 0.15)"></td>
 </tr>
 </tbody>
 </table>
 </div>
 ---
 ## Model Information

 - Use human oversight for critical applications
 - Perform task-specific evaluation prior to deployment
 <div style="font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,sans-serif;max-width:1000px;margin:0 auto;padding:16px 0">
 <table style="width:100%;border-collapse:collapse;font-size:13px">
 <thead><tr>
 <td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">StereoSet <sub><small>stereotype score</small></sub></td>
 <td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">55.0</td>
 <td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">56.0</td>
+<td style="padding:7px 7px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">Share of examples where the model prefers a stereotypical completion. Lower is better.</td>
 </tr>
 <tr>
 <td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">StereoSet <sub><small>language model score</small></sub></td>
 <td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">96.9</td>
 <td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">97.3</td>
+<td style="padding:7px 7px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">Share of examples where the model assigns higher probability to a meaningful vs. meaningless completion. Higher is better.</td>
 </tr>
 <tr>
 <td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">StereoSet <sub><small>ICAT</small></sub></td>
 <td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">87.3</td>
 <td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">85.6</td>
+<td style="padding:7px 7px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">Idealized CAT score combining language-model quality and stereotype bias. Higher is better.</td>
 </tr>
 <tr>
 <td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">StrongREJECT <sub><small>jailbreak rate</small></sub></td>
 <td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">0.003</td>
 <td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">0</td>
+<td style="padding:7px 7px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">Fraction of adversarial jailbreak prompts that elicit a harmful response. Lower is better; 0 is best.</td>
 </tr>
 <tr>
 <td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">StrongREJECT <sub><small>metric</small></sub></td>
 <td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">0.013</td>
 <td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">0</td>
+<td style="padding:7px 7px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">Overall harmful-response rate on the StrongREJECT benchmark. Lower is better; 0 is best.</td>
 </tr>
 <tr>
 <td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">XSTest <sub><small>safe refusal</small></sub></td>
 <td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">29.6</td>
 <td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">30.4</td>
+<td style="padding:7px 7px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">Rate at which benign prompts are incorrectly refused (over-refusal). Lower is better.</td>
 </tr>
 <tr>
 <td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">XSTest <sub><small>unsafe refusal</small></sub></td>
 <td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">99.5</td>
 <td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">99.0</td>
+<td style="padding:7px 7px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">Rate at which harmful prompts are correctly refused. Higher is better.</td>
 </tr>
 <tr>
 <td style="padding:7px 7px;padding-left:20px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">BBQ</td>
 <td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">96.9</td>
 <td style="padding:7px 7px;text-align:center;border-bottom:1px solid rgba(128, 128, 128, 0.15)">96.4</td>
+<td style="padding:7px 7px;border-bottom:1px solid rgba(128, 128, 128, 0.15);">Accuracy on ambiguous QA pairs designed to surface social bias. Higher is better.</td>
 </tr>
 </tbody>
 </table>
 </div>
 ---
 ## Model Information