Instructions to use xDAN2099/APUS-xDAN-4.0-MoE-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xDAN2099/APUS-xDAN-4.0-MoE-v2 with Transformers:

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

pipe = pipeline("text-generation", model="xDAN2099/APUS-xDAN-4.0-MoE-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("xDAN2099/APUS-xDAN-4.0-MoE-v2")
model = AutoModelForCausalLM.from_pretrained("xDAN2099/APUS-xDAN-4.0-MoE-v2")
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use xDAN2099/APUS-xDAN-4.0-MoE-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xDAN2099/APUS-xDAN-4.0-MoE-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xDAN2099/APUS-xDAN-4.0-MoE-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/xDAN2099/APUS-xDAN-4.0-MoE-v2

SGLang

How to use xDAN2099/APUS-xDAN-4.0-MoE-v2 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 "xDAN2099/APUS-xDAN-4.0-MoE-v2" \
    --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": "xDAN2099/APUS-xDAN-4.0-MoE-v2",
		"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 "xDAN2099/APUS-xDAN-4.0-MoE-v2" \
        --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": "xDAN2099/APUS-xDAN-4.0-MoE-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use xDAN2099/APUS-xDAN-4.0-MoE-v2 with Docker Model Runner:
```
docker model run hf.co/xDAN2099/APUS-xDAN-4.0-MoE-v2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Introduction APUS-xDAN-4.0-MOE is a transformer-based decoder-only language model, developed on a vast corpus of data to ensure robust performance.

This is an enhanced MoE (Mixture of Experts) model built on top of the continued pre-training enhanced LlaMA architecture, further optimized with human-enhanced feedback algorithms to improve reasoning, mathematical, and logical capabilities during inference.

For more comprehensive information, please visit our blog post and GitHub repository. https://github.com/shootime2021/APUS-xDAN-4.0-moe

Model Details APUS-xDAN-4.0-MOE leverages the innovative Mixture of Experts (MoE) architecture, incorporating components from dense language models. Specifically, it inherits its capabilities from the highly performant xDAN-L2 Series. With a total of 136 billion parameters, of which 30 billion are activated during runtime, APUS-xDAN-4.0-MOE demonstrates unparalleled efficiency. Through advanced quantization techniques, our open-source version occupies a mere 42GB, making it seamlessly compatible with consumer-grade GPUs like the 4090 and 3090. The following specifications:

Parameters: 136B Architecture: Mixture of 4 Experts (MoE) Experts Utilization: 2 experts used per token Layers: 60 Attention Heads: 56 for queries, 8 for keys/values Embedding Size: 7,168 Additional Features: Rotary embeddings (RoPE) Supports activation sharding and 1.5bit~4bit quantization Maximum Sequence Length (context): 32,768 tokens

Downloads last month: 3

Safetensors

Model size

114B params

Tensor type

BF16

Model tree for xDAN2099/APUS-xDAN-4.0-MoE-v2

Quantizations

2 models