huihui_ai/huihui-moe

huihui_ai/ huihui-moe

895 Downloads Updated 9 months ago

Huihui-MoE is a Mixture of Experts (MoE) language model developed by huihui.ai

tools thinking 1.2b 23b

ollama run huihui_ai/huihui-moe:1.2b

curl http://localhost:11434/api/chat \
  -d '{
    "model": "huihui_ai/huihui-moe:1.2b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='huihui_ai/huihui-moe:1.2b',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'huihui_ai/huihui-moe:1.2b',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code ollama launch claude --model huihui_ai/huihui-moe:1.2b

Codex ollama launch codex --model huihui_ai/huihui-moe:1.2b

OpenCode ollama launch opencode --model huihui_ai/huihui-moe:1.2b

OpenClaw ollama launch openclaw --model huihui_ai/huihui-moe:1.2b

Models

View all →

Name

10 models

Size

Context

Input

huihui-moe:1.2b

805MB · 40K context window · Text · 9 months ago

huihui-moe:1.2b

805MB

40K

Text

huihui-moe:23b

14GB · 40K context window · Text · 9 months ago

huihui-moe:23b

14GB

40K

Text

Readme

Huihui-MoE is a Mixture of Experts (MoE) language model developed by huihui.ai, built upon the Qwen/qwen3 base model. It enhances the standard Transformer architecture by replacing MLP layers with MoE layers, each containing 2-8 experts, to achieve high performance with efficient inference. The model is designed for natural language processing tasks, including text generation, question answering, and conversational applications.

References

HuggingFace

Donation

If you like it, please click ‘like’ and follow us for more updates.
You can follow x.com/support_huihui to get the latest model information from huihui.ai.

Your donation helps us continue our further development and improvement, a cup of coffee can do it.

bitcoin:

  bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge