Instructions to use maple-matrix/quasar-sn24-e2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use maple-matrix/quasar-sn24-e2 with Transformers:

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

pipe = pipeline("text-generation", model="maple-matrix/quasar-sn24-e2", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("maple-matrix/quasar-sn24-e2", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use maple-matrix/quasar-sn24-e2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "maple-matrix/quasar-sn24-e2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "maple-matrix/quasar-sn24-e2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/maple-matrix/quasar-sn24-e2

SGLang

How to use maple-matrix/quasar-sn24-e2 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 "maple-matrix/quasar-sn24-e2" \
    --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": "maple-matrix/quasar-sn24-e2",
		"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 "maple-matrix/quasar-sn24-e2" \
        --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": "maple-matrix/quasar-sn24-e2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use maple-matrix/quasar-sn24-e2 with Docker Model Runner:
```
docker model run hf.co/maple-matrix/quasar-sn24-e2
```

maple-matrix commited on Jun 21

Commit

cac1fdf

verified ·

1 Parent(s): 1625848

Upload model

Browse files

Files changed (9) hide show

.gitattributes +2 -0
chat_template.jinja +1 -1
config.json +1 -1
configuration_quasar.py +1 -0
generation_config.json +1 -0
model.safetensors +2 -2
modeling_quasar.py +1 -0
tokenizer.json +2 -2
tokenizer_config.json +1 -0

.gitattributes CHANGED Viewed

@@ -34,3 +34,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text

 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+#

chat_template.jinja CHANGED Viewed

@@ -151,4 +151,4 @@
     {%- else %}
         {{- '<think>\n' }}
     {%- endif %}
-{%- endif %}

     {%- else %}
         {{- '<think>\n' }}
     {%- endif %}
+{%- endif %}

config.json CHANGED Viewed

@@ -53,4 +53,4 @@
   "architectures": [
     "QuasarForCausalLM"
   ]
-}

   "architectures": [
     "QuasarForCausalLM"
   ]
+}

configuration_quasar.py CHANGED Viewed

	@@ -195,3 +195,4 @@ class QuasarConfig(PretrainedConfig):
195
196
197	__all__ = ["QuasarConfig"]


195
196
197	__all__ = ["QuasarConfig"]
198	+

generation_config.json CHANGED Viewed

@@ -11,3 +11,4 @@
   "transformers_version": "5.7.0",
   "use_cache": true
 }

   "transformers_version": "5.7.0",
   "use_cache": true
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15d91efe7275a464680c2e5f006a95a158d7930d8fe7dee468212a733c55fba9
-size 5879960192

 version https://git-lfs.github.com/spec/v1
+oid sha256:b0e70c8e3718fcf7519712957bf092c8d43b1a0ae3dab1920d4d8d14fd29a5a1
+size 5879960200

modeling_quasar.py CHANGED Viewed

@@ -1064,3 +1064,4 @@ __all__ = [
     "QuasarModelOutputWithPast",
     "QuasarCausalLMOutputWithPast",
 ]

     "QuasarModelOutputWithPast",
     "QuasarCausalLMOutputWithPast",
 ]

tokenizer.json CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
-size 19989325

 version https://git-lfs.github.com/spec/v1
+oid sha256:1d8325caa17dffabd587f6eb025a642786caa785658d0d8c07b879dd1ea13477
+size 19989326

tokenizer_config.json CHANGED Viewed

@@ -30,3 +30,4 @@
   "vision_bos_token": "<|vision_start|>",
   "vision_eos_token": "<|vision_end|>"
 }

   "vision_bos_token": "<|vision_start|>",
   "vision_eos_token": "<|vision_end|>"
 }