ruvnet

DeepSeek R1 Distill: Complete Tutorial for Deployment & Fine-Tuning

This guide shows how to deploy an uncensored DeepSeek R1 Distill model to Google Cloud Run with GPU support and how to perform a basic, functional fine-tuning process. The tutorial is split into:

1. Environment Setup
2. FastAPI Inference Server
3. Docker Configuration
4. Google Cloud Run Deployment
5. Fine-Tuning Pipeline (Cold Start, Reasoning RL, Data Collection, Final RL Phase)

mberman84

1. # create new .py file with code found below
2. # install ollama
3. # install model you want “ollama run mistral”
4. conda create -n autogen python=3.11
5. conda activate autogen
6. which python
7. python -m pip install pyautogen
7. ollama run mistral
8. ollama run codellama
9. # open new terminal

Free-Radical

peterw

import openai
import streamlit as st
from streamlit_chat import message
from dotenv import load_dotenv
import os 
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores import Chroma
import openai
from langchain.document_loaders import UnstructuredMarkdownLoader
from langchain.chains.question_answering import load_qa_chain

peterw

import openai
import streamlit as st
from streamlit_chat import message
from dotenv import load_dotenv
import os 
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores import Chroma
import openai
from langchain.document_loaders import UnstructuredMarkdownLoader
from langchain.chains.question_answering import load_qa_chain

psychemedia

camullen

Installing KDE on WSL2

Inspiration: https://www.most-useful.com/kde-plasma-on-wsl.html

Setup

1. Update WSL
   • In windows command prompt run: wsl --update
2. Add systemd to ubuntu

• In ubuntu prompt run: sudo nano /etc/wsl.conf

insightsbees

    #Use plotly to visualize the network graph created using NetworkX
    #Adding edges to plotly scatter plot and specify mode='lines'
    edge_trace = go.Scatter(
        x=[],
        y=[],
        line=dict(width=1,color='#888'),
        hoverinfo='none',
        mode='lines')

    for edge in G.edges():

insightsbees

#Create the network graph using networkx
if uploaded_file is not None:     
    df=pd.read_csv(uploaded_file)  
    A = list(df["Source"].unique())
    B = list(df["Target"].unique())
    node_list = set(A+B)
    G = nx.Graph() #Use the Graph API to create an empty network graph object
    
    #Add nodes and edges to the graph object
    for i in node_list:

insightsbees

import streamlit as st
import pandas as pd
import numpy as np
import networkx as nx
import plotly.graph_objs as go
from  PIL import Image

#Add a logo (optional) in the sidebar
logo = Image.open(r'C:\Users\13525\Desktop\Insights_Bees_logo.png')
st.sidebar.image(logo,  width=120)