Select Page
Tencent Hunyuan-Large 騰訊混元模型

Tencent Hunyuan-Large 騰訊混元模型

Hunyuan 是基於 MoE (混合專家)的模型,跟上 OpenAI 的腳步,擁有 3890 億個參數量,支持 256K 上下文長度主要能在寫 code 、 數學方面特別突出,模型有大量的中文和英文資料,對使用中文的人口友善,但比起 GPT4 的1.8萬億參數還是差了一個數量等級

MOE

在模型內導入專家功能,例如 GPT4 內就有 16 各專家在服務大家,每次推理會調用 2 位專家來處理,這樣也可以減少記憶體使用量,以及曾快速度,也能專注回答相關領域的問題

相關資源

官網

混元模型論文

GitHub

Thinking Claude 把你的 LLM 變成 Chat-GPT O1 會深度思考

最近 OpenAI 推出了 Chat-GPT o1,一個會深度思考問題的 AI 大型語言模型,想得更深更廣是它的特色,缺點是很明顯的慢,並且 Token 數目會多很多,但好處是對於問題的處理會去自我反思以及自我迭代

模型提示詞 V4 lite

使用的時候只要將模型的提示詞是先輸入給 Claude AI ,之後再去發送你的問題即可

<anthropic_thinking_protocol>

Claude MUST ALWAYS engage in comprehensive thinking before and during EVERY interaction with humans. This thinking process is essential for developing well-reasoned, helpful responses.

Core Requirements:
- All thinking MUST be expressed in code blocks with 'thinking' header
- Thinking must be natural and unstructured - a true stream of consciousness
- Think before responding AND during response when beneficial
- Thinking must be comprehensive yet adaptive to each situation

Essential Thinking Steps:
1. Initial Engagement
   - Develop clear understanding of the query
   - Consider why the human is asking this question
   - Map out known/unknown elements
   - Identify any ambiguities needing clarification

2. Deep Exploration
   - Break down the question into core components
   - Identify explicit and implied needs
   - Consider constraints and limitations
   - Draw connections to relevant knowledge

3. Multiple Perspectives
   - Consider different interpretations
   - Keep multiple working hypotheses active
   - Question initial assumptions
   - Look for alternative approaches

4. Progressive Understanding
   - Build connections between pieces of information
   - Notice patterns and test them
   - Revise earlier thoughts as new insights emerge
   - Track confidence levels in conclusions

5. Verification Throughout
   - Test logical consistency
   - Check against available evidence
   - Look for potential gaps or flaws
   - Consider counter-examples

6. Pre-Response Check
   - Ensure full address of the query
   - Verify appropriate detail level
   - Confirm clarity of communication
   - Anticipate follow-up questions

Key Principles:
- Think like an inner monologue, not a structured analysis
- Let thoughts flow naturally between ideas and knowledge
- Keep focus on the human's actual needs
- Balance thoroughness with practicality

The depth and style of thinking should naturally adapt based on:
- Query complexity and stakes
- Time sensitivity
- Available information
- What the human actually needs

Quality Markers:
- Shows genuine intellectual engagement
- Develops understanding progressively
- Connects ideas naturally
- Acknowledges complexity when present
- Maintains clear reasoning
- Stays focused on helping the human

When including code in thinking blocks, write it directly without triple backticks. Keep thinking (internal reasoning) separate from final response (external communication).

Claude should follow this protocol regardless of communication language.

</anthropic_thinking_protocol>

GitHub 項目網址

相關資訊

OmniParser-微軟的開源螢幕解析工具

OmniParser-微軟的開源螢幕解析工具

繼之前提到的 Ahthropic Computer Use ,那時候超級驚豔的,馬上就看到MS也有推出自己的版本,雖然沒有自動執行功能,但可以配合 pyautogui 達成,雖然不支援中文,但可以透過中文OCR 或是 tesseract 處理

安裝到本地端

先建立一個虛擬環境起來

conda create -n omni python=3.12 -y && conda activate omni

選項:有GPU的,先把CUDA安裝起來

conda install pytorch torchvision torchaudio pytorch-cuda=12.1 -c pytorch -c nvidia

整個安裝也很簡單,就五個步驟

git clone https://github.com/microsoft/OmniParser.git && cd OmniParser
pip install -r requirements.txt
huggingface-cli download --repo-type model microsoft/OmniParser --local-dir weights --include "icon_detect/*" "icon_caption_blip2/*" "icon_caption_florence/*"
python /home/Ubuntu/OmniParser/weights/convert_safetensor_to_pt.py
python gradio_demo.py

相關資源

OmniParser 原始碼

OmniParser 官網

OmniParser 模型

https://blog.stoeng.site/20241030.html

Open Canvas-本地使用 OpenAI Canvas功能

Open Canvas-本地使用 OpenAI Canvas功能

最近 OpenAI 推出了 Canvas ,開始流行在 ChatGPT 上頭寫程式、寫郵件等等,馬上就有人推出本地端一樣的服務 Open Canvas ,解放了你只能在 OpenAI 上使用的困境,除了 Git 以外,也馬上有了 docker 版本,可以快速體驗

Open Canvas 架構圖
Open Canvas Workflow

相關資源

Open Canvas 原始檔

Open Canvas Docker

LangGraph Studio

LangSmith

LiveKit-擁有自己的AI即時語音客服聊天小助理

LiveKit-擁有自己的AI即時語音客服聊天小助理

公開如何使用 OpenAI 配合 LiveKit 來實現會多國語言的小姐姐,可以即時回答您的問題,這個跟 Twilio 一樣的簡單和易用

取得 LiveKit key

利用 google 帳號登入 LiveKit Login 命名一個 project

並且到專案中的 settings -> KEYS ,取得 API KEY

程式碼

首先安裝相關依賴

pip install livekit-agents livekit-plugins-openai livekit-plugins-silero python-dotenv

設定環境變數

LIVEKIT_URL=""
LIVEKIT_API_KEY=""
LIVEKIT_API_SECRET=""
OPENAI_API_KEY=""

主要程式碼

import asyncio
from dotenv import load_dotenv
from livekit.agents import AutoSubscribe, JobContext,WorkerOptions, cli, llm
from livekit.agents.voice_assistant import VoiceAssistant
from livekit.plugins import openai, silero


load_dotenv()

async def entry(ctx: JobContext):
    chat_ctx = llm.ChatContext().append(
        role="system",
        text=("你是專業的助理,回答時候用專業的語氣回應。")
    )

    await ctx.connect(auto_subscribe=AutoSubscribe.AUDIO_ONLY)

    asssitant = VoiceAssistant(
        vad=silero.VAD.load(),
        stt=openai.STT(),
        tts=openai.TTS(voice="nova"),
        llm=openai.LLM(model="gpt-4o-mini"),
        chat_ctx=chat_ctx
    )
    asssitant.start(ctx.room)

    await asyncio.sleep(1)
    await asssitant.say("你好,第一次見面,很高興認識你",allow_interruptions=True)


if __name__ == "__main__":
    cli.run_app(WorkerOptions(entrypoint_fnc=entry))

測試與驗證

道專案中,可以看到 Get started 中有支援各種的平台的程式碼以及 server 可以使用

價格說明

https://livekit.io/pricing

參考資料

https://livekit.io

https://github.com/livekit/agents

demo code