Instructions to use PYTHAI/Kimi-K2.7-Code-fork with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PYTHAI/Kimi-K2.7-Code-fork with Transformers:

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

pipe = pipeline("image-text-to-text", model="PYTHAI/Kimi-K2.7-Code-fork", 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)

# Load model directly
from transformers import AutoProcessor, AutoModel

processor = AutoProcessor.from_pretrained("PYTHAI/Kimi-K2.7-Code-fork", trust_remote_code=True)
model = AutoModel.from_pretrained("PYTHAI/Kimi-K2.7-Code-fork", trust_remote_code=True, device_map="auto")
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?"}
        ]
    },
]
inputs = processor.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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PYTHAI/Kimi-K2.7-Code-fork with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PYTHAI/Kimi-K2.7-Code-fork"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PYTHAI/Kimi-K2.7-Code-fork",
		"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/PYTHAI/Kimi-K2.7-Code-fork

SGLang

How to use PYTHAI/Kimi-K2.7-Code-fork 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 "PYTHAI/Kimi-K2.7-Code-fork" \
    --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": "PYTHAI/Kimi-K2.7-Code-fork",
		"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 "PYTHAI/Kimi-K2.7-Code-fork" \
        --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": "PYTHAI/Kimi-K2.7-Code-fork",
		"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 PYTHAI/Kimi-K2.7-Code-fork with Docker Model Runner:
```
docker model run hf.co/PYTHAI/Kimi-K2.7-Code-fork
```

Kimi-K2.7-Code-fork / FORK.json

Gregory-L

pointer fork of moonshotai/Kimi-K2.7-Code@74797c9c6237: licence, config, tokenizer, code; no weights

142d1de verified 2 days ago

Raw

History Blame Contribute Delete

4.02 kB

	{
	"kind": "licence-locked pointer fork",
	"source_repo": "moonshotai/Kimi-K2.7-Code",
	"source_url": "https://huggingface.co/moonshotai/Kimi-K2.7-Code",
	"source_commit": "74797c9c62378b951a1f6fcf5c4631024e9b8bef",
	"forked_at_utc": "2026-09-13T23:55:35Z",
	"licence_tag": "other",
	"licence_file": {
	"path": "LICENSE",
	"bytes": 1470,
	"sha256": "9cb73476cecdfabac7775bf7c225bd5f6017d5d678372917e4456964c0454f7a"
	},
	"weights_copied": false,
	"weights_not_copied": {
	"files": 64,
	"bytes": 595177988208
	},
	"parameters": 1026879376368,
	"load_weights_with": "from_pretrained('moonshotai/Kimi-K2.7-Code', revision='74797c9c62378b951a1f6fcf5c4631024e9b8bef')",
	"files": [
	{
	"path": "LICENSE",
	"bytes": 1470,
	"sha256": "9cb73476cecdfabac7775bf7c225bd5f6017d5d678372917e4456964c0454f7a"
	},
	{
	"path": "README.md",
	"bytes": 15061,
	"sha256": "c78bbe5af19636b180eda956abf1f30a79027ec04d6642ebddc44edbc4470879"
	},
	{
	"path": "THIRD_PARTY_NOTICES.md",
	"bytes": 1665,
	"sha256": "98392e4fd8a43aa576613212e69d0c7d2090504b4127da1fca7270f6af85d101"
	},
	{
	"path": "chat_template.jinja",
	"bytes": 2385,
	"sha256": "8d21200dff7e85beaf51c8b110952e039ffd0779f615d64d63293d74773360f9"
	},
	{
	"path": "config.json",
	"bytes": 5420,
	"sha256": "ffbb57bff844e024f6c112640b63da80af228ceb8fb3e2e21908a21febbcdffb"
	},
	{
	"path": "configuration_deepseek.py",
	"bytes": 10615,
	"sha256": "c1327c307e2dd11d1bf0adc8bcef69ae51f9617a3a869a9497bb08aec912f931"
	},
	{
	"path": "configuration_kimi_k25.py",
	"bytes": 5435,
	"sha256": "2bc5487efced291e0e6aa3b24aad1082bade4172aff94ea1b6f0ae20a1d6bb4f"
	},
	{
	"path": "docs/deploy_guidance.md",
	"bytes": 3689,
	"sha256": "b1bc4c5fb7c8b1da727663d4da83999afc902f6166ff862fbaef514b86de2c65"
	},
	{
	"path": "figures/demo_video.mp4",
	"bytes": 270100,
	"sha256": "09b4d925aa0a7c712feef50765355f0625d8f6d46ea302fd98db9609e9070047"
	},
	{
	"path": "figures/kimi-logo.png",
	"bytes": 87988,
	"sha256": "4a80f64242bf907940765adc7bcf340c28dd83334b07c5503792a26495d1933b"
	},
	{
	"path": "generation_config.json",
	"bytes": 91,
	"sha256": "b784cc6a9ecb551196b81cb6b1d2dcb18467b92adaab6992ae4cc455ad44d2ce"
	},
	{
	"path": "kimi_k25_processor.py",
	"bytes": 6906,
	"sha256": "537d7a708e1654766fc628c99667bdb9364136d3541633d6522ac43cef9bfea0"
	},
	{
	"path": "kimi_k25_vision_processing.py",
	"bytes": 10019,
	"sha256": "498e20753c9aa6b6224ddbcd05b04deb7e987b76595bf5c28ee8583f33ebc375"
	},
	{
	"path": "media_utils.py",
	"bytes": 13179,
	"sha256": "77a6b1fed3580b0562443092928a0240c2989e3950377e93893952123ae48e3d"
	},
	{
	"path": "model.safetensors.index.json",
	"bytes": 23597438,
	"sha256": "f6dd3318271f0121445d2af1c0c3f75707127a84a625f86bc0eaae9deb848f40"
	},
	{
	"path": "modeling_deepseek.py",
	"bytes": 78639,
	"sha256": "17e079e0a5e41114aabd2ae5ba924128ba6652bc6f9a00ea06efcd1230340406"
	},
	{
	"path": "modeling_kimi_k25.py",
	"bytes": 53045,
	"sha256": "a1594f129ae8dc5fa3c9dbbc24e8e603b30d7caef1226669b4d95dc8f2a3e2dd"
	},
	{
	"path": "preprocessor_config.json",
	"bytes": 744,
	"sha256": "bd9a1f5d7b1580b38093c35ca49162580a118485164fac48e1cdb224ee41fcff"
	},
	{
	"path": "tiktoken.model",
	"bytes": 2795286,
	"sha256": "b6c497a7469b33ced9c38afb1ad6e47f03f5e5dc05f15930799210ec050c5103"
	},
	{
	"path": "tokenization_kimi.py",
	"bytes": 14132,
	"sha256": "88394687bd081f55928849b2d140e190c70297660d3fb8b7c54c0e5633b177e3"
	},
	{
	"path": "tokenizer_config.json",
	"bytes": 4832,
	"sha256": "6dfafeacca3d44748fc4a2fcc6725be5ea616ecc5b95f5a8b4277077c06e7d9f"
	},
	{
	"path": "tool_declaration_ts.py",
	"bytes": 16517,
	"sha256": "97e09ed262f1cd38f87584eaa46c5d4d5b3c9725dd299b21642f389040794ebc"
	}
	],
	"why": "preserve the licence terms of this exact commit and pin the revision; the weights stay at the source and are addressed by commit sha",
	"forked_by": "mindX (PYTHAI) via the node token"
	}