Instructions to use fzkun/minimind3-ascend-moe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fzkun/minimind3-ascend-moe with Transformers:

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

pipe = pipeline("text-generation", model="fzkun/minimind3-ascend-moe")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fzkun/minimind3-ascend-moe")
model = AutoModelForCausalLM.from_pretrained("fzkun/minimind3-ascend-moe")
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 fzkun/minimind3-ascend-moe with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fzkun/minimind3-ascend-moe"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fzkun/minimind3-ascend-moe",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fzkun/minimind3-ascend-moe

SGLang

How to use fzkun/minimind3-ascend-moe 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 "fzkun/minimind3-ascend-moe" \
    --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": "fzkun/minimind3-ascend-moe",
		"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 "fzkun/minimind3-ascend-moe" \
        --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": "fzkun/minimind3-ascend-moe",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use fzkun/minimind3-ascend-moe with Docker Model Runner:
```
docker model run hf.co/fzkun/minimind3-ascend-moe
```

MiniMind3-Ascend-MoE

这是一个基于 MiniMind3-Ascend 训练链路导出的 MoE 对话模型，兼容 Transformers 推理方式，适合追求更高容量与更强表达能力的场景。

模型信息

模型名：fzkun/minimind3-ascend-moe
架构：MoE
导出兼容：Qwen3MoeForCausalLM
参数规模：约 198M
激活参数：约 64M
主要配置：
- hidden_size = 768
- num_hidden_layers = 8
- num_experts = 4
- num_experts_per_tok = 1

文件说明

仓库中包含：

config.json
generation_config.json
model.safetensors
tokenizer.json
tokenizer_config.json
special_tokens_map.json
chat_template.jinja

使用方式

Transformers

from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "fzkun/minimind3-ascend-moe"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True)

messages = [{"role": "user", "content": "你好"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt")
out = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))

Benchmark 结果

评测环境：

Ascend 910B
单卡 npu:0
batch_size = 16

ceval	cmmlu	arc	piqa	openbookqa	hellaswag	siqa
23.77	24.88	30.30	51.63	26.00	28.58	34.08

说明：

ceval / cmmlu / arc / piqa / openbookqa / hellaswag 使用 acc_norm
social_iqa 使用 acc

补充说明

MoE 版本容量更高，在部分 benchmark 上表现更强
对应 SwanLab 实验记录：https://swanlab.cn/@fzkun/MiniMind3/overview

Downloads last month: 6

Safetensors

Model size

0.2B params

Tensor type

F16

fzkun
/

minimind3-ascend-moe