Instructions to use phoenixiv6/quasar-sn24-wt4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use phoenixiv6/quasar-sn24-wt4 with Transformers:

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

pipe = pipeline("text-generation", model="phoenixiv6/quasar-sn24-wt4", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("phoenixiv6/quasar-sn24-wt4", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use phoenixiv6/quasar-sn24-wt4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "phoenixiv6/quasar-sn24-wt4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "phoenixiv6/quasar-sn24-wt4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/phoenixiv6/quasar-sn24-wt4

SGLang

How to use phoenixiv6/quasar-sn24-wt4 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 "phoenixiv6/quasar-sn24-wt4" \
    --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": "phoenixiv6/quasar-sn24-wt4",
		"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 "phoenixiv6/quasar-sn24-wt4" \
        --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": "phoenixiv6/quasar-sn24-wt4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use phoenixiv6/quasar-sn24-wt4 with Docker Model Runner:
```
docker model run hf.co/phoenixiv6/quasar-sn24-wt4
```

dare1

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using /root/DOWN_24/coolroman/quasar-sn24-v15b as a base.

Models Merged

The following models were included in the merge:

/root/DOWN_24/tung_zenai

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: /root/DOWN_24/tung_zenai
    parameters:
      density: 0.55
      weight: 0.45
  - model: /root/DOWN_24/coolroman/quasar-sn24-v15b
    parameters:
      density: 0.75
      weight: 0.75
  - model: /root/DOWN_24/tung_zenai
    parameters:
      density: 0.35
      weight: 0.25
merge_method: dare_ties
base_model: /root/DOWN_24/coolroman/quasar-sn24-v15b
parameters:
  normalize: true
  int8_mask: true
  rescale: true
dtype: bfloat16
out_dtype: bfloat16
trust_remote_code: true

Downloads last month: 8

Safetensors

Model size

3B params

Tensor type

BF16

Paper for phoenixiv6/quasar-sn24-wt4

Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch

Paper • 2311.03099 • Published Nov 6, 2023 • 38