Instructions to use AxionLab-Co/AxionMoE-350k-A250k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AxionLab-Co/AxionMoE-350k-A250k with Transformers:

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

pipe = pipeline("text-generation", model="AxionLab-Co/AxionMoE-350k-A250k", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("AxionLab-Co/AxionMoE-350k-A250k", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AxionLab-Co/AxionMoE-350k-A250k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AxionLab-Co/AxionMoE-350k-A250k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AxionLab-Co/AxionMoE-350k-A250k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AxionLab-Co/AxionMoE-350k-A250k

SGLang

How to use AxionLab-Co/AxionMoE-350k-A250k 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 "AxionLab-Co/AxionMoE-350k-A250k" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AxionLab-Co/AxionMoE-350k-A250k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "AxionLab-Co/AxionMoE-350k-A250k" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AxionLab-Co/AxionMoE-350k-A250k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AxionLab-Co/AxionMoE-350k-A250k with Docker Model Runner:
```
docker model run hf.co/AxionLab-Co/AxionMoE-350k-A250k
```

Fixing MD

by FlameF0X - opened Apr 15

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-1

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -22,7 +22,7 @@ tags:
 # Axion1-350K-A250K
-> **DeepSeek-V3 architecture scaled to ~344k total parameters (~160k active/token) — runs entirely on CPU.**
 Built from scratch as a proof-of-concept that the real DeepSeek-V3 architectural innovations
 (MLA + DeepSeekMoE + auxiliary-loss-free load balancing) work correctly even at extreme miniaturization.

 # Axion1-350K-A250K
+> **DeepSeek-V3 architecture scaled to \~344k total parameters (\~160k active/token) — runs entirely on CPU.**
 Built from scratch as a proof-of-concept that the real DeepSeek-V3 architectural innovations
 (MLA + DeepSeekMoE + auxiliary-loss-free load balancing) work correctly even at extreme miniaturization.