Instructions to use skt/A.X-3.1-Light with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use skt/A.X-3.1-Light with Transformers:

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

pipe = pipeline("text-generation", model="skt/A.X-3.1-Light")
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("skt/A.X-3.1-Light")
model = AutoModelForCausalLM.from_pretrained("skt/A.X-3.1-Light", 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 skt/A.X-3.1-Light with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "skt/A.X-3.1-Light"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "skt/A.X-3.1-Light",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/skt/A.X-3.1-Light

SGLang

How to use skt/A.X-3.1-Light 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 "skt/A.X-3.1-Light" \
    --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": "skt/A.X-3.1-Light",
		"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 "skt/A.X-3.1-Light" \
        --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": "skt/A.X-3.1-Light",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use skt/A.X-3.1-Light with Docker Model Runner:
```
docker model run hf.co/skt/A.X-3.1-Light
```

jackyoung96 commited on Jul 17, 2025

Commit

9b41bb2

verified ·

1 Parent(s): 6d81edb

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +17 -1

README.md CHANGED Viewed

@@ -110,7 +110,7 @@ Rigorous data curation and two-stage training with STEM-focused data enabled com
   </tr></thead>
 <tbody>
   <tr>
-    <td rowspan="4">Knowledge</td>
     <td>KMMLU</td>
     <td>61.70</td>
     <td>48.28</td>
@@ -118,6 +118,22 @@ Rigorous data curation and two-stage training with STEM-focused data enabled com
     <td>49.56</td>
     <td>63.53</td>
   </tr>
   <tr>
     <td>CLIcK</td>
     <td>71.22</td>

   </tr></thead>
 <tbody>
   <tr>
+    <td rowspan="6">Knowledge</td>
     <td>KMMLU</td>
     <td>61.70</td>
     <td>48.28</td>
     <td>49.56</td>
     <td>63.53</td>
   </tr>
+  <tr>
+    <td>KMMLU-pro</td>
+    <td>45.54</td>
+    <td>37.63</td>
+    <td>40.11</td>
+    <td>38.87</td>
+    <td>50.71</td>
+  </tr>
+  <tr>
+    <td>KMMLU-redux</td>
+    <td>52.34</td>
+    <td>35.33</td>
+    <td>42.21</td>
+    <td>38.58</td>
+    <td>55.74</td>
+  </tr>
   <tr>
     <td>CLIcK</td>
     <td>71.22</td>