Instructions to use silx-ai/Quasar-Preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use silx-ai/Quasar-Preview with Transformers:

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

pipe = pipeline("text-generation", model="silx-ai/Quasar-Preview", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("silx-ai/Quasar-Preview", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use silx-ai/Quasar-Preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "silx-ai/Quasar-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": "silx-ai/Quasar-Preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/silx-ai/Quasar-Preview

SGLang

How to use silx-ai/Quasar-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 "silx-ai/Quasar-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": "silx-ai/Quasar-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 "silx-ai/Quasar-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": "silx-ai/Quasar-Preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use silx-ai/Quasar-Preview with Docker Model Runner:
```
docker model run hf.co/silx-ai/Quasar-Preview
```

Add fixed Raven package for Quasar hybrid generation

by NiroQ - opened 2 days ago

base: refs/heads/main

←

from: refs/pr/3

Discussion Files changed

+896

-0

NiroQ

2 days ago

Adds the repo-local Raven implementation expected by modeling_quasar_long.py.

Fixes the GQA gate expansion bug in RavenAttention: K/V are repeated from 4 KV heads to 16 query heads, but Mamba2 router/memory gates are already 16-head tensors and must not be repeated again to 64. For GLA decay, gates are expanded before router masking so f/s remain aligned with q/k/v. Includes a runtime head-count assert to catch future mismatches.

Add fixed Raven package for Quasar hybrid generationb54e8fad

NiroQ changed pull request status to closed 2 days ago

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment