Instructions to use RedHatAI/Kimi-K3-INT4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/Kimi-K3-INT4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="RedHatAI/Kimi-K3-INT4", trust_remote_code=True)
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("RedHatAI/Kimi-K3-INT4", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RedHatAI/Kimi-K3-INT4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/Kimi-K3-INT4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/Kimi-K3-INT4",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/RedHatAI/Kimi-K3-INT4

SGLang

How to use RedHatAI/Kimi-K3-INT4 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 "RedHatAI/Kimi-K3-INT4" \
    --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": "RedHatAI/Kimi-K3-INT4",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "RedHatAI/Kimi-K3-INT4" \
        --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": "RedHatAI/Kimi-K3-INT4",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use RedHatAI/Kimi-K3-INT4 with Docker Model Runner:
```
docker model run hf.co/RedHatAI/Kimi-K3-INT4
```

wuroderi commited on 29 days ago

Commit

2dba1e4

verified ·

1 Parent(s): 57c1deb

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -12

README.md CHANGED Viewed

@@ -130,13 +130,13 @@ This model was evaluated on 100-sample smoke subsets of MATH-500 and GPQA Diamon
   <tbody>
     <tr>
       <td rowspan="2"><b>Reasoning</b></td>
-      <td>MATH-500 (0-shot, pass@1; 100-sample smoke)</td>
       <td>90.00%</td>
       <td>87.00%</td>
       <td>96.67%</td>
     </tr>
     <tr>
-      <td>GPQA Diamond (0-shot, pass@1; 100-sample smoke)</td>
       <td>91.00%</td>
       <td>92.00%</td>
       <td>101.10%</td>
@@ -178,16 +178,6 @@ model_parameters:
   timeout: 14400
 ```
-Run the tasks:
-```bash
-lighteval endpoint litellm litellm_config.yaml 'math_500|0' \
-  --output-dir results/math_500 --save-details --max-samples 100
-lighteval endpoint litellm litellm_config.yaml 'gpqa:diamond|0' \
-  --output-dir results/gpqa_diamond --save-details --max-samples 100
-```
 ## License
 The model is provided under the [Kimi K3 license](https://huggingface.co/moonshotai/Kimi-K3/blob/main/LICENSE). Review the original model license and terms before use or redistribution.

   <tbody>
     <tr>
       <td rowspan="2"><b>Reasoning</b></td>
+      <td>MATH-500 (0-shot, pass@1</td>
       <td>90.00%</td>
       <td>87.00%</td>
       <td>96.67%</td>
     </tr>
     <tr>
+      <td>GPQA Diamond (0-shot, pass@1)</td>
       <td>91.00%</td>
       <td>92.00%</td>
       <td>101.10%</td>
   timeout: 14400
 ```
 ## License
 The model is provided under the [Kimi K3 license](https://huggingface.co/moonshotai/Kimi-K3/blob/main/LICENSE). Review the original model license and terms before use or redistribution.