Instructions to use XingChen-AGI/Xing4.0-29B-A4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use XingChen-AGI/Xing4.0-29B-A4B with Transformers:

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

pipe = pipeline("text-generation", model="XingChen-AGI/Xing4.0-29B-A4B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("XingChen-AGI/Xing4.0-29B-A4B", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use XingChen-AGI/Xing4.0-29B-A4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "XingChen-AGI/Xing4.0-29B-A4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "XingChen-AGI/Xing4.0-29B-A4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/XingChen-AGI/Xing4.0-29B-A4B

SGLang

How to use XingChen-AGI/Xing4.0-29B-A4B 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 "XingChen-AGI/Xing4.0-29B-A4B" \
    --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": "XingChen-AGI/Xing4.0-29B-A4B",
		"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 "XingChen-AGI/Xing4.0-29B-A4B" \
        --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": "XingChen-AGI/Xing4.0-29B-A4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use XingChen-AGI/Xing4.0-29B-A4B with Docker Model Runner:
```
docker model run hf.co/XingChen-AGI/Xing4.0-29B-A4B
```

All 5 inference framework PRs are still pending — request merge timeline and interim guidance

by grow-nexus - opened 8 days ago

Discussion

grow-nexus

8 days ago

Thanks for open-sourcing Xing4.0-29B-A4B. I'd like to use it in production, but all five inference framework PRs in the README are still Pending, so I must install from PR branches. Two concerns:
1、Stability. PR branches change during review, so a build that works today may break tomorrow. A pinned tested commit hash for each PR would help.
2、vLLM specifics. Will the setup still work once the PR lands in an official release?
Requested: an estimated merge timeline for each PR, and a short "Known Issues / Compatibility" section in the model card listing tested versions.

xiongji

XingChen-AGI org 8 days ago

Thanks for open-sourcing Xing4.0-29B-A4B. I'd like to use it in production, but all five inference framework PRs in the README are still Pending, so I must install from PR branches. Two concerns:
1、Stability. PR branches change during review, so a build that works today may break tomorrow. A pinned tested commit hash for each PR would help.
2、vLLM specifics. Will the setup still work once the PR lands in an official release?
Requested: an estimated merge timeline for each PR, and a short "Known Issues / Compatibility" section in the model card listing tested versions.

Thank you for your question and suggestions.

Currently, all the PRs we have submitted have undergone internal compilation verification and the commit hash will be recorded.
As long as the main branch is successfully merged, it will definitely be able to run successfully.
The exact merge time for the entire framework cannot be determined at present.
It is recommended to use SGLang for the source code installation. It seems to be simpler.

mzubairtahir000714

5 days ago

hey @grow-nexus ! can you please help me with deploying in production? I mean do you deploy on any gpu provider or having own server? I would appreciate any guidance.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment