Fix: Gracefully handle connection errors in chat completion

This commit addresses an issue where a connection error during streaming chat completion (e.g., from an Ollama backend via LiteLLM) would lead to a `AttributeError: 'NoneType' object has no attribute 'choices'`. The fix involves the following changes: 1. Modified `_process_stream_response` in `agent.py` to re-raise exceptions encountered during stream processing, instead of returning `None`. 2. Adjusted `_chat_completion` in `agent.py` to also re-raise exceptions caught from its operations (including those from `_process_stream_response`), ensuring errors propagate correctly. 3. Added a comment in `_process_stream_response` to guide you on troubleshooting common causes of connection errors, such as Ollama server issues or network misconfigurations. These changes prevent the specific `AttributeError` by ensuring that error conditions are propagated as exceptions, allowing for more robust error handling and clearer diagnostics of underlying problems.
Merge branch 'main' of https://github.com/MervinPraison/PraisonAI
2026-11-07 17:33:33 -10:00 · 2025-06-19 04:16:46 +00:00 · 2025-06-17 11:09:41 +01:00 · 2025-06-17 11:09:40 +01:00 · 2025-06-17 11:56:33 +02:00 · 2025-06-17 09:54:35 +00:00
20 changed files with 2826 additions and 348 deletions
@@ -0,0 +1,34 @@
+---
+name: Bug report
+about: Create a report to help us improve
+title: '[BUG] '
+labels: bug
+assignees: ''
+---
+
+## Environment
+- Provider (select one):
+  - [ ] Anthropic
+  - [ ] OpenAI
+  - [ ] Google Vertex AI
+  - [ ] AWS Bedrock
+  - [ ] Other: <!-- specify -->
+- PraisonAI version: <!-- if known -->
+- Operating System: <!-- e.g. macOS 14.3, Windows 11, Ubuntu 22.04 -->
+
+## Full Code
+<!-- Full code that reproduces the bug -->
+
+## Steps to Reproduce
+1. <!-- First step -->
+2. <!-- Second step -->
+3. <!-- And so on... -->
+
+## Expected Behavior
+<!-- What you expected to happen -->
+
+## Actual Behavior
+<!-- What actually happened -->
+
+## Additional Context
+<!-- Add any other context about the problem here, such as screenshots, logs, etc. --> 
@@ -1,9 +0,0 @@
-FROM node:20-alpine
-
-RUN npm install -g @anthropic-ai/claude-code
-
-WORKDIR /app
-COPY entrypoint.sh .
-RUN chmod +x entrypoint.sh
-
-ENTRYPOINT ["/app/entrypoint.sh"] 
@@ -1,20 +1,240 @@
 name: "Claude Code Action"
-description: "Custom Claude Code runner for PraisonAI"
+description: "Run Claude Code in GitHub Actions workflows"

 inputs:
  anthropic_api_key:
-    required: true
    description: "Anthropic API key"
+    required: false
  github_token:
-    required: true
-    description: "GitHub token for repo access"
+    description: "GitHub token for Claude to operate with"
+    required: false
+    default: ${{ github.token }}
+  trigger_phrase:
+    description: "The trigger phrase to look for in comments, issue/PR bodies, and issue titles"
+    required: false
+    default: "@claude"
+  assignee_trigger:
+    description: "The assignee username that triggers the action (e.g. @claude). Only used for issue assignment"
+    required: false
+  max_turns:
+    description: "Maximum number of conversation turns Claude can take"
+    required: false
+  timeout_minutes:
+    description: "Timeout in minutes for execution"
+    required: false
+    default: "30"
+  model:
+    description: "Model to use (provider-specific format required for Bedrock/Vertex)"
+    required: false
+  use_bedrock:
+    description: "Use Amazon Bedrock with OIDC authentication instead of direct Anthropic API"
+    required: false
+    default: "false"
+  use_vertex:
+    description: "Use Google Vertex AI with OIDC authentication instead of direct Anthropic API"
+    required: false
+    default: "false"
+  allowed_tools:
+    description: "Additional tools for Claude to use (the base GitHub tools will always be included)"
+    required: false
+    default: ""
+  disallowed_tools:
+    description: "Tools that Claude should never use"
+    required: false
+    default: ""
+  custom_instructions:
+    description: "Additional custom instructions to include in the prompt for Claude"
+    required: false
+    default: ""
+  mcp_config:
+    description: "Additional MCP configuration (JSON string) that merges with the built-in GitHub MCP servers"
+    required: false
+    default: ""
+  claude_env:
+    description: "Custom environment variables to pass to Claude Code execution (YAML format)"
+    required: false
+    default: ""
+  direct_prompt:
+    description: "Direct prompt for Claude to execute automatically without needing a trigger (for automated workflows)"
+    required: false

 runs:
-  using: "docker"
-  image: "ghcr.io/mervinpraison/praisonai-claudecode:latest"
-  env:
-    ANTHROPIC_API_KEY: ${{ inputs.anthropic_api_key }}
-    GITHUB_TOKEN: ${{ inputs.github_token }}
-  args:
-    - "--anthropic-api-key=${{ inputs.anthropic_api_key }}"
-    - "--github-token=${{ inputs.github_token }}" 
+  using: "composite"
+  steps:
+    - name: Install Claude Code
+      shell: bash
+      run: npm install -g @anthropic-ai/claude-code
+
+    - name: Install GitHub MCP Server
+      shell: bash
+      run: |
+        claude mcp add-json github '{
+          "command": "docker",
+          "args": [
+            "run",
+            "-i",
+            "--rm",
+            "-e",
+            "GITHUB_PERSONAL_ACCESS_TOKEN",
+            "ghcr.io/github/github-mcp-server:sha-ff3036d"
+          ],
+          "env": {
+            "GITHUB_PERSONAL_ACCESS_TOKEN": "${{ inputs.github_token }}"
+          }
+        }'
+
+    - name: Extract GitHub Context and Create Prompt
+      shell: bash
+      id: prepare_context
+      run: |
+        echo "🔍 Extracting GitHub context from event: ${{ github.event_name }}"
+        
+        # Function to check for trigger phrase
+        check_trigger() {
+          local text="$1"
+          local trigger="${{ inputs.trigger_phrase }}"
+          if [[ "$text" == *"$trigger"* ]]; then
+            return 0
+          fi
+          return 1
+        }
+        
+        # Extract context based on event type
+        TRIGGER_FOUND="false"
+        USER_REQUEST=""
+        CONTEXT_INFO=""
+        
+        case "${{ github.event_name }}" in
+          "issue_comment")
+            COMMENT_BODY="${{ github.event.comment.body }}"
+            ISSUE_TITLE="${{ github.event.issue.title }}"
+            ISSUE_NUMBER="${{ github.event.issue.number }}"
+            
+            if check_trigger "$COMMENT_BODY"; then
+              TRIGGER_FOUND="true"
+              USER_REQUEST="$COMMENT_BODY"
+              CONTEXT_INFO="Issue Comment on #$ISSUE_NUMBER: $ISSUE_TITLE"
+            fi
+            ;;
+            
+          "pull_request_review_comment")
+            COMMENT_BODY="${{ github.event.comment.body }}"
+            PR_TITLE="${{ github.event.pull_request.title }}"
+            PR_NUMBER="${{ github.event.pull_request.number }}"
+            
+            if check_trigger "$COMMENT_BODY"; then
+              TRIGGER_FOUND="true"
+              USER_REQUEST="$COMMENT_BODY"
+              CONTEXT_INFO="PR Comment on #$PR_NUMBER: $PR_TITLE"
+            fi
+            ;;
+            
+          "pull_request_review")
+            REVIEW_BODY="${{ github.event.review.body }}"
+            PR_TITLE="${{ github.event.pull_request.title }}"
+            PR_NUMBER="${{ github.event.pull_request.number }}"
+            
+            if check_trigger "$REVIEW_BODY"; then
+              TRIGGER_FOUND="true"
+              USER_REQUEST="$REVIEW_BODY"
+              CONTEXT_INFO="PR Review on #$PR_NUMBER: $PR_TITLE"
+            fi
+            ;;
+            
+          "issues")
+            ISSUE_BODY="${{ github.event.issue.body }}"
+            ISSUE_TITLE="${{ github.event.issue.title }}"
+            ISSUE_NUMBER="${{ github.event.issue.number }}"
+            
+            if check_trigger "$ISSUE_TITLE" || check_trigger "$ISSUE_BODY"; then
+              TRIGGER_FOUND="true"
+              USER_REQUEST="$ISSUE_BODY"
+              CONTEXT_INFO="Issue #$ISSUE_NUMBER: $ISSUE_TITLE"
+            elif [[ "${{ github.event.action }}" == "assigned" && -n "${{ inputs.assignee_trigger }}" ]]; then
+              ASSIGNEE="${{ github.event.assignee.login }}"
+              if [[ "$ASSIGNEE" == "${{ inputs.assignee_trigger }}" ]]; then
+                TRIGGER_FOUND="true"
+                USER_REQUEST="$ISSUE_BODY"
+                CONTEXT_INFO="Issue #$ISSUE_NUMBER assigned to $ASSIGNEE: $ISSUE_TITLE"
+              fi
+            fi
+            ;;
+        esac
+        
+        # Check for direct prompt override
+        if [[ -n "${{ inputs.direct_prompt }}" ]]; then
+          TRIGGER_FOUND="true"
+          USER_REQUEST="${{ inputs.direct_prompt }}"
+          CONTEXT_INFO="Automated GitHub workflow"
+        fi
+        
+        if [[ "$TRIGGER_FOUND" != "true" ]]; then
+          echo "❌ No trigger phrase found or direct prompt provided. Exiting gracefully."
+          echo "SKIP_EXECUTION=true" >> $GITHUB_ENV
+          exit 0
+        fi
+        
+        echo "✅ Trigger found! Context: $CONTEXT_INFO"
+        
+        # Create comprehensive prompt
+        mkdir -p /tmp/claude-action
+        cat > /tmp/claude-action/github-context-prompt.txt << EOF
+        You are Claude Code, an AI assistant helping with GitHub workflows and code.
+        
+        Repository: ${{ github.repository }}
+        Context: $CONTEXT_INFO
+        Event: ${{ github.event_name }}
+        
+        User Request:
+        $USER_REQUEST
+        
+        Please analyze the request and provide helpful assistance. You have access to repository tools and can help with:
+        - Code analysis and implementation
+        - GitHub workflows and automation
+        - Pull request reviews and feedback
+        - Issue resolution and bug fixes
+        - Documentation updates
+        - Testing and deployment
+        
+        Respond naturally and helpfully to the user's request using the available tools.
+        EOF
+        
+        echo "PROMPT_FILE=/tmp/claude-action/github-context-prompt.txt" >> $GITHUB_ENV
+        echo "SKIP_EXECUTION=false" >> $GITHUB_ENV
+
+    - name: Run Claude Code
+      if: env.SKIP_EXECUTION != 'true'
+      shell: bash
+      run: |
+        echo "🚀 Running Claude Code with GitHub context..."
+        
+        # Build command arguments
+        CMD_ARGS=("-p" "--verbose" "--output-format" "stream-json")
+        
+        # Add max turns if specified
+        if [[ -n "${{ inputs.max_turns }}" ]]; then
+          CMD_ARGS+=("--max-turns" "${{ inputs.max_turns }}")
+        fi
+        
+        # Add allowed tools (include GitHub tools by default)
+        TOOLS="mcp__github__get_issue,mcp__github__get_issue_comments,mcp__github__update_issue,mcp__github__search_issues,mcp__github__list_issues,mcp__github__create_comment,Read,Write,Edit,Bash"
+        if [[ -n "${{ inputs.allowed_tools }}" ]]; then
+          TOOLS="$TOOLS,${{ inputs.allowed_tools }}"
+        fi
+        CMD_ARGS+=("--allowedTools" "$TOOLS")
+        
+        # Add disallowed tools
+        if [[ -n "${{ inputs.disallowed_tools }}" ]]; then
+          CMD_ARGS+=("--disallowedTools" "${{ inputs.disallowed_tools }}")
+        fi
+        
+        echo "📝 Executing Claude Code with prompt from file..."
+        
+        # Execute Claude Code with timeout, using stdin for the prompt
+        TIMEOUT_SECONDS=$((${{ inputs.timeout_minutes }} * 60))
+        timeout $TIMEOUT_SECONDS claude "${CMD_ARGS[@]}" < "${{ env.PROMPT_FILE }}"
+        
+        echo "✅ Claude Code execution completed"
+      env:
+        ANTHROPIC_API_KEY: ${{ inputs.anthropic_api_key }}
+        GITHUB_TOKEN: ${{ inputs.github_token }} 
@@ -1,21 +0,0 @@
-#!/bin/sh
-
-set -e
-
-echo "Running Claude Code in CI mode..."
-
-# Extract GitHub context and create a smart prompt
-PROMPT="Analyse the GitHub issue or PR context and generate a smart response based on the repository context."
-
-# Set environment variables from arguments
-export ANTHROPIC_API_KEY="${1#--anthropic-api-key=}"
-export GITHUB_TOKEN="${2#--github-token=}"
-
-# Verify environment variables
-if [ -z "$ANTHROPIC_API_KEY" ] || [ -z "$GITHUB_TOKEN" ]; then
-    echo "Error: Required environment variables are not set"
-    exit 1
-fi
-
-# Run Claude with the prompt
-claude -p "$PROMPT" 
@@ -1,117 +0,0 @@
-name: "Claude Code Action"
-description: "Run Claude Code in GitHub Actions workflows"
-
-inputs:
-  github_token:
-    description: "GitHub token with repo and issues permissions"
-    required: true
-  anthropic_api_key:
-    description: "Anthropic API key"
-    required: true
-  prompt:
-    description: "The prompt to send to Claude Code"
-    required: false
-    default: ""
-  prompt_file:
-    description: "Path to a file containing the prompt to send to Claude Code"
-    required: false
-    default: ""
-  allowed_tools:
-    description: "Comma-separated list of allowed tools for Claude Code to use"
-    required: false
-    default: ""
-  output_file:
-    description: "File to save Claude Code output to (optional)"
-    required: false
-    default: ""
-  timeout_minutes:
-    description: "Timeout in minutes for Claude Code execution"
-    required: false
-    default: "10"
-  install_github_mcp:
-    description: "Whether to install the GitHub MCP server"
-    required: false
-    default: "false"
-
-runs:
-  using: "composite"
-  steps:
-    - name: Install Claude Code
-      shell: bash
-      run: npm install -g @anthropic-ai/claude-code
-
-    - name: Install GitHub MCP Server
-      if: inputs.install_github_mcp == 'true'
-      shell: bash
-      run: |
-        claude mcp add-json github '{
-          "command": "docker",
-          "args": [
-            "run",
-            "-i",
-            "--rm",
-            "-e",
-            "GITHUB_PERSONAL_ACCESS_TOKEN",
-            "ghcr.io/github/github-mcp-server:sha-ff3036d"
-          ],
-          "env": {
-            "GITHUB_PERSONAL_ACCESS_TOKEN": "${{ inputs.GITHUB_TOKEN }}"
-          }
-        }'
-
-    - name: Prepare Prompt File
-      shell: bash
-      id: prepare_prompt
-      run: |
-        if [ -z "${{ inputs.prompt }}" ] && [ -z "${{ inputs.prompt_file }}" ]; then
-          echo "::error::Neither 'prompt' nor 'prompt_file' was provided. At least one is required."
-          exit 1
-        fi
-
-        if [ ! -z "${{ inputs.prompt_file }}" ]; then
-          if [ ! -f "${{ inputs.prompt_file }}" ]; then
-            echo "::error::Prompt file '${{ inputs.prompt_file }}' does not exist."
-            exit 1
-          fi
-          PROMPT_PATH="${{ inputs.prompt_file }}"
-        else
-          mkdir -p /tmp/claude-action
-          PROMPT_PATH="/tmp/claude-action/prompt.txt"
-          echo "${{ inputs.prompt }}" > "$PROMPT_PATH"
-        fi
-
-        if [ ! -s "$PROMPT_PATH" ]; then
-          echo "::error::Prompt is empty. Please provide a non-empty prompt."
-          exit 1
-        fi
-
-        echo "PROMPT_PATH=$PROMPT_PATH" >> $GITHUB_ENV
-
-    - name: Run Claude Code
-      shell: bash
-      id: run_claude
-      run: |
-        timeout_seconds=$((${{ inputs.timeout_minutes }} * 60))
-
-        if [ -z "${{ inputs.output_file }}" ]; then
-          timeout $timeout_seconds claude \
-            -p \
-            --verbose \
-            --output-format stream-json \
-            "$(cat ${{ env.PROMPT_PATH }})" \
-            ${{ inputs.allowed_tools != '' && format('--allowedTools "{0}"', inputs.allowed_tools) || '' }}
-        else
-          timeout $timeout_seconds claude \
-            -p \
-            --verbose \
-            --output-format stream-json \
-            "$(cat ${{ env.PROMPT_PATH }})" \
-            ${{ inputs.allowed_tools != '' && format('--allowedTools "{0}"', inputs.allowed_tools) || '' }} | tee output.txt
-
-          jq -s '.' output.txt > output.json
-          jq -r '.[-1].result' output.json > "${{ inputs.output_file }}"
-          echo "Complete output saved to output.json, final response saved to ${{ inputs.output_file }}"
-        fi
-      env:
-        ANTHROPIC_API_KEY: ${{ inputs.anthropic_api_key }}
-        GITHUB_TOKEN: ${{ inputs.github_token }}
@@ -0,0 +1,87 @@
+name: "Claude Issue Triage Action"
+description: "Automatically triage GitHub issues using Claude Code"
+
+inputs:
+  timeout_minutes:
+    description: "Timeout in minutes for execution"
+    required: false
+    default: "5"
+  anthropic_api_key:
+    description: "Anthropic API key"
+    required: true
+  github_token:
+    description: "GitHub token with repo and issues permissions"
+    required: true
+
+runs:
+  using: "composite"
+  steps:
+    - name: Checkout repository code
+      uses: actions/checkout@v4
+      with:
+        fetch-depth: 0
+
+    - name: Create prompt file
+      shell: bash
+      run: |
+        mkdir -p /tmp/claude-prompts
+        cat > /tmp/claude-prompts/claude-issue-triage-prompt.txt << 'EOF'
+        You're an issue triage assistant for GitHub issues. Your task is to analyze the issue and select appropriate labels from the provided list.
+
+        IMPORTANT: Don't post any comments or messages to the issue. Your only action should be to apply labels.
+
+        Issue Information:
+        - REPO: ${{ github.repository }}
+        - ISSUE_NUMBER: ${{ github.event.issue.number }}
+
+        TASK OVERVIEW:
+
+        1. First, fetch the list of labels available in this repository by running: `gh label list`. Run exactly this command with nothing else.
+
+        2. Next, use the GitHub tools to get context about the issue:
+           - You have access to these tools:
+             - mcp__github__get_issue: Use this to retrieve the current issue's details including title, description, and existing labels
+             - mcp__github__get_issue_comments: Use this to read any discussion or additional context provided in the comments
+             - mcp__github__update_issue: Use this to apply labels to the issue (do not use this for commenting)
+             - mcp__github__search_issues: Use this to find similar issues that might provide context for proper categorization and to identify potential duplicate issues
+             - mcp__github__list_issues: Use this to understand patterns in how other issues are labeled
+           - Start by using mcp__github__get_issue to get the issue details
+
+        3. Analyze the issue content, considering:
+           - The issue title and description
+           - The type of issue (bug report, feature request, question, etc.)
+           - Technical areas mentioned
+           - Severity or priority indicators
+           - User impact
+           - Components affected
+
+        4. Select appropriate labels from the available labels list provided above:
+           - Choose labels that accurately reflect the issue's nature
+           - Be specific but comprehensive
+           - Select priority labels if you can determine urgency (high-priority, med-priority, or low-priority)
+           - Consider platform labels (android, ios) if applicable
+           - If you find similar issues using mcp__github__search_issues, consider using a "duplicate" label if appropriate. Only do so if the issue is a duplicate of another OPEN issue.
+
+        5. Apply the selected labels:
+           - Use mcp__github__update_issue to apply your selected labels
+           - DO NOT post any comments explaining your decision
+           - DO NOT communicate directly with users
+           - If no labels are clearly applicable, do not apply any labels
+
+        IMPORTANT GUIDELINES:
+        - Be thorough in your analysis
+        - Only select labels from the provided list above
+        - DO NOT post any comments to the issue
+        - Your ONLY action should be to apply labels using mcp__github__update_issue
+        - It's okay to not add any labels if none are clearly applicable
+        EOF
+
+    - name: Run Claude Code
+      uses: ./.github/actions/claude-code-action
+      with:
+        prompt_file: /tmp/claude-prompts/claude-issue-triage-prompt.txt
+        allowed_tools: "Bash(gh label list),mcp__github__get_issue,mcp__github__get_issue_comments,mcp__github__update_issue,mcp__github__search_issues,mcp__github__list_issues"
+        install_github_mcp: "true"
+        timeout_minutes: ${{ inputs.timeout_minutes }}
+        anthropic_api_key: ${{ inputs.anthropic_api_key }}
+        github_token: ${{ inputs.github_token }} 
@@ -26,13 +26,14 @@ jobs:
        with:
          registry: ghcr.io
          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
+          password: ${{ secrets.GH_TOKEN }}

      - name: Build and push Docker image
        uses: docker/build-push-action@v5
        with:
          context: ./.github/actions/claude-code-action
          push: true
+          platforms: linux/amd64
          tags: ghcr.io/mervinpraison/praisonai-claudecode:${{ inputs.version }}
          cache-from: type=gha
          cache-to: type=gha,mode=max
@@ -0,0 +1,23 @@
+name: Claude Issue Triage
+description: "Automatically triage GitHub issues using Claude Code"
+
+on:
+  issues:
+    types: [opened]
+
+jobs:
+  triage-issue:
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    permissions:
+      contents: read
+      issues: write
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683  # v4
+
+      - name: Run Claude Issue Triage
+        uses: ./.github/actions/claude-issue-triage-action
+        with:
+          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+          github_token: ${{ secrets.GITHUB_TOKEN }} 
@@ -23,60 +23,14 @@ jobs:
      pull-requests: read
      issues: read
      id-token: write
-      packages: read
-    env:
-      GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
    steps:
      - name: Checkout repository
        uses: actions/checkout@v4
        with:
          fetch-depth: 1

-      - name: Debug Environment
-        run: |
-          echo "=== Environment Debug ==="
-          echo "GITHUB_ACTOR: $GITHUB_ACTOR"
-          echo "GITHUB_REPOSITORY: $GITHUB_REPOSITORY"
-          echo "GITHUB_REPOSITORY_OWNER: $GITHUB_REPOSITORY_OWNER"
-          echo "GITHUB_TOKEN exists: $([ -n "$GITHUB_TOKEN" ] && echo "yes" || echo "no")"
-          echo "GITHUB_TOKEN length: ${#GITHUB_TOKEN}"
-
-      - name: Check Package Visibility
-        run: |
-          echo "=== Checking Package Visibility ==="
-          curl -s -H "Authorization: Bearer $GITHUB_TOKEN" \
-               -H "Accept: application/vnd.github.v3+json" \
-               "https://api.github.com/users/MervinPraison/packages/container/praisonai-claudecode" \
-               || echo "Package API call failed"
-
-      - name: Login to GitHub Container Registry
-        uses: docker/login-action@v3
-        with:
-          registry: ghcr.io
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Test Docker Authentication
-        run: |
-          echo "=== Testing Docker Authentication ==="
-          echo "Checking ~/.docker/config.json"
-          cat ~/.docker/config.json | jq '.' || echo "No docker config found"
-          echo "=== Testing Registry Access ==="
-          curl -s -H "Authorization: Bearer $GITHUB_TOKEN" \
-               "https://ghcr.io/v2/" || echo "Registry access failed"
-
-      - name: Test Docker Pull
-        run: |
-          echo "=== Testing Docker Pull ==="
-          echo "Attempting to pull image: ghcr.io/mervinpraison/praisonai-claudecode:latest"
-          docker pull ghcr.io/mervinpraison/praisonai-claudecode:latest || echo "Pull failed with exit code: $?"
-          echo "=== Checking Docker Images ==="
-          docker images | grep praisonai-claudecode || echo "No images found"
-
      - name: Run Claude Code
        id: claude
-        uses: ./.github/actions/claude-code-action
+        uses: anthropics/claude-code-action@beta
        with:
-          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
-          github_token: ${{ secrets.GITHUB_TOKEN }}
-
+          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
@@ -0,0 +1,635 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "id": "7eb3b7a8",
+      "metadata": {
+        "id": "7eb3b7a8"
+      },
+      "source": [
+        "# LLaMA3-2 (11B) Vision Model"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "4914e815",
+      "metadata": {
+        "id": "4914e815"
+      },
+      "source": [
+        "## Description\n",
+        "This notebook demonstrates how to use the **LLaMA3-2 (11B) Vision Model** vision-language model for image input and text generation tasks."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/DhivyaBharathy-web/PraisonAI/blob/main/examples/cookbooks/LLaMA3_2_11B_Vision_Model.ipynb)\n"
+      ],
+      "metadata": {
+        "id": "j_sehN-6kKcp"
+      },
+      "id": "j_sehN-6kKcp"
+    },
+    {
+      "cell_type": "markdown",
+      "id": "366d7561",
+      "metadata": {
+        "id": "366d7561"
+      },
+      "source": [
+        "## Dependencies\n",
+        "```python\n",
+        "!pip install transformers accelerate torch torchvision\n",
+        "```"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "750d4351",
+      "metadata": {
+        "id": "750d4351"
+      },
+      "source": [
+        "## Tools\n",
+        "- 🤗 Transformers\n",
+        "- PyTorch\n",
+        "- Vision Model APIs"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "9f053796",
+      "metadata": {
+        "id": "9f053796"
+      },
+      "source": [
+        "## YAML Prompt\n",
+        "```yaml\n",
+        "mode: vision\n",
+        "model: LLaMA3-2 (11B) Vision Model\n",
+        "tasks:\n",
+        "  - image captioning\n",
+        "  - visual question answering\n",
+        "```"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "b920aca2",
+      "metadata": {
+        "id": "b920aca2"
+      },
+      "source": [
+        "## Main\n",
+        "Below is the simplified main execution to load the model and run basic inference."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "fb97f999",
+      "metadata": {
+        "id": "fb97f999"
+      },
+      "outputs": [],
+      "source": [
+        "%%capture\n",
+        "import os\n",
+        "if \"COLAB_\" not in \"\".join(os.environ.keys()):\n",
+        "    !pip install unsloth\n",
+        "else:\n",
+        "    # Do this only in Colab notebooks! Otherwise use pip install unsloth\n",
+        "    !pip install --no-deps bitsandbytes accelerate xformers==0.0.29.post3 peft trl triton cut_cross_entropy unsloth_zoo\n",
+        "    !pip install sentencepiece protobuf \"datasets>=3.4.1\" huggingface_hub hf_transfer\n",
+        "    !pip install --no-deps unsloth"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "2a6e11d8",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 511,
+          "referenced_widgets": [
+            "98d2cd94be9c454f83a18c8bf5fe9aec",
+            "c6d906d5fa284667a7021b56fb731e98",
+            "2394d94e0e714ffdb528b55605f40dc0",
+            "144522321d134e94858678d525a85f80",
+            "eaa4f5b890c3436bb8da3e74a8eeb237",
+            "a85bb0dcd185406c885af8d491cf3c22",
+            "91a165c1dade4c1b9d7c01771b61291e",
+            "24f8f69538bb469192088f3ffa1ed624",
+            "f5123643c11240c0bcc3d3588e8e8a1b",
+            "ef9a483fb2a3478cb94331868ab2db90",
+            "ce61267651164b50aa49876a05b7296a",
+            "289cd006e4ff4f018e758890e148c852",
+            "c8abe988d9864ca1955430b023c223ad",
+            "ad5361da5e774447b07bab7e0f272813",
+            "7fd8253214984e578754c1a7f184687e",
+            "e84d7f0735e045f498a85deee72e4a36",
+            "0d6664235d744c66bc567215699966b3",
+            "14ec87fd00454cc9b6e75a37d9cf2c1c",
+            "79e970816ead4141a8dc3c534db3a54c",
+            "f90c77c1bd02487da4d91289243c6a28",
+            "b0ea1c891cd44fb38f874d28f1b71ad7",
+            "017cce265bf84be7bd9b8ebe5f25047e",
+            "d0fc6802d6034d33bb33be048799320d",
+            "21df32143aa4410c885c0b84ce68466a",
+            "5dc3fb97742846c3bf4e6b99159d88ed",
+            "16583bf31a1846e0926fcfc3690fa505",
+            "b3638367ff0749ecabfef81e18c3f3dd",
+            "c84a668f99be4a74aae5cca75a2448d8",
+            "8dbb8561b0214721b69a0b4c41a9e431",
+            "d5bdec8c59af4d3a94ed7d2bfa2b7921",
+            "2d361e1d14c64f09b3dae11750e287f4",
+            "1ecf09bddb4046218cc703af721dced3",
+            "2361b35c79864c10a84b44929f69c547",
+            "97b945925ec94ee8851187d97a3b3e01",
+            "b332f446bf5a457bb1bb32862fb25779",
+            "4408a069a4e341d59423b51c25afbd64",
+            "f7902776f2a44de294a21f8d9d1f4e73",
+            "667e586bf81d4f90b17247741fed6a16",
+            "66b02dd825894df9b4c07fbf6a9d55b7",
+            "ae9fdc486fee4a07a332d2767aa487d3",
+            "b237fb86f5b24341a830c3707f881d12",
+            "8c436fe0faee404e8d61d9afa916d6b3",
+            "70141c664f464503b8a0821e6fb8aff2",
+            "03d88b6a463c40febec9e44329493ed3",
+            "443cae09fcc74bce8c85514c0e3306f8",
+            "5e3c171ca5494501841b1cabe5c083fe",
+            "ba6bf08f321841e180630e24ad14e31c",
+            "c18a21dd2b4f4d53afcf25d5e2f282ba",
+            "a61ba57420fc4fb387d03fbf2261e0d7",
+            "fe2444e22fac4ce48a2ac8b9483dd0ab",
+            "fe43c14445c54ea590a28bc3663d0c48",
+            "47ade2b90f5d41469fe68aa452043b10",
+            "3c4722f0972b4bbf995ea7285a61ba26",
+            "981e19084d2c4c4da0285ab6758e53d0",
+            "8ae036dfd56e4e92916f2030dbb5d634",
+            "c90bdb60e0fc46d8aa1d9e858cbbdd07",
+            "a7e36b913ce946e0808a5bc3f5b9744b",
+            "1ea701fee9fa4aac92ae9750da494815",
+            "c85f1cfff87b435f9041ecd4b657587b",
+            "e4eb768259094b0ea344ac96181842b4",
+            "51c2efe52566422394209040317384d9",
+            "c48225673e394ae9873b25a8b13446b9",
+            "9b97b57c43ec47ffad7e15ab3c7f21be",
+            "5f810775e57943bdafcceeccca145450",
+            "b1a430285adc498d836178ba93ec5604",
+            "43c0b5f1598e487194f846977edb2d9e",
+            "4f579cd077cd41c798478f572d592f6a",
+            "56a5f8469b834a998dbf9b195828f3de",
+            "e21d0116f78140cd9a2dfd548b93cdd9",
+            "49639c7bec544b3d92340188e9fab090",
+            "644eb1b7ad734624a51ec0c3435a96dc",
+            "181c7cd4ce0140b7a7bcdb8bda323529",
+            "4a9844c83b104b2dbb1b1149e894089b",
+            "9156991030be4967a32b7014fbb9d202",
+            "4e5e63413ead4256ad5900667f5c03b2",
+            "d70e648f960c4f71b0c4b250fef32654",
+            "ad3adfba64654cf2859f850c3de05e31",
+            "a37acc4c0f11436c80cb72272709a9fe",
+            "9b46b99cc8f5432cbce73a2913141033",
+            "96cc9201587f47679d0262868277b160",
+            "58691977879e424fa8d480be75a6e70d",
+            "8edb9a9006df4929b41b6531d9c27c95",
+            "cbd4cf8895514baa9420289c14455686",
+            "397e656680024d148a597cad7def07f5",
+            "c0297069253140978f1ccb5c1fed852c",
+            "1808e709f81847cabc126abe8552c289",
+            "f5117b4078194a058dac514abce9d08a",
+            "ed18219a0316437d8aef630b5de85b75",
+            "74742a6f4bb94067b6e6703cef8c3941",
+            "d1abd20ebc684c839df31d06cb5d658f",
+            "1d3238444dd041839602d3db4ed7fde2",
+            "daaf3480c1794c8895049dcd8eec3573",
+            "028dc1c882454b0dbbebdfbeb6eb4ca3",
+            "28450d6b5cc145afb3f4fda0f133b7ac",
+            "f5e7b16ff8f84ba888dd1af0e08df12d",
+            "d7bcadb25ead446181103aaba00f52c0",
+            "25f52c2d14c54eb09923acf20e85ca07",
+            "8df67a8cbe0c4734b52754108642ac10",
+            "04db919ebb474ae6bd1fba3cb9437eb6",
+            "1a4c9e787979474b9049e36f8c07c12b",
+            "3de2161fe36a43699a713916adc09857",
+            "125518e68b4e491a8e6d40c40504a5fb",
+            "fced4e62adb743798567c2c0f0d90966",
+            "77c06023e71440308a6aedd86190ab9b",
+            "2d508731af60413ea81136dc2ab64a76",
+            "2036bb5ed5fa4bd49e1d76f2b713b6a1",
+            "f9e6e2e5b59a4a0984ca0a83db0b186d",
+            "5b0ca7559eea43edb7009bc8ad41dcd6",
+            "db0696c568d34b6eab55305e2b87c1e2",
+            "95d28ba0fd2c47e2bb1fc145d82c7164",
+            "9430d398534341bca671d10e8bc91ddc",
+            "020c2d09aa4941b5bddfb3ce9470f9e6",
+            "bf309ecf24bb4ca68f72ce1acf72b739",
+            "148b83fa058145b98b69e29cda2f9dcc",
+            "e0ff84feca0f4c52b3c7d23cdff1a110",
+            "5a5cf37b757f4af78a0ad69f0ed5bfbc",
+            "65a2889ce3c04085a0702ce3bd75c9c9",
+            "0f5aee18791e4f8d95f86f6254ac7878",
+            "6fc02729c4254edcb86daf71336f30d6",
+            "7f5ece3436c64e51b34c20503d2fc0c3",
+            "d2c0dc378e864f42bc9994f7bc31ee1d"
+          ]
+        },
+        "id": "2a6e11d8",
+        "outputId": "f63afa9e-e320-4da2-bb91-b7f4f9163379"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "🦥 Unsloth: Will patch your computer to enable 2x faster free finetuning.\n",
+            "🦥 Unsloth Zoo will now patch everything to make training faster!\n",
+            "==((====))==  Unsloth 2024.11.9: Fast Mllama vision patching. Transformers = 4.46.2.\n",
+            "   \\\\   /|    GPU: Tesla T4. Max memory: 14.748 GB. Platform = Linux.\n",
+            "O^O/ \\_/ \\    Pytorch: 2.5.1+cu121. CUDA = 7.5. CUDA Toolkit = 12.1.\n",
+            "\\        /    Bfloat16 = FALSE. FA [Xformers = 0.0.28.post3. FA2 = False]\n",
+            " \"-____-\"     Free Apache license: http://github.com/unslothai/unsloth\n",
+            "Unsloth: Fast downloading is enabled - ignore downloading bars which are red colored!\n"
+          ]
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "98d2cd94be9c454f83a18c8bf5fe9aec",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "model.safetensors.index.json:   0%|          | 0.00/385k [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "289cd006e4ff4f018e758890e148c852",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "d0fc6802d6034d33bb33be048799320d",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "model-00001-of-00002.safetensors:   0%|          | 0.00/5.00G [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "97b945925ec94ee8851187d97a3b3e01",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "model-00002-of-00002.safetensors:   0%|          | 0.00/2.18G [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "443cae09fcc74bce8c85514c0e3306f8",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "c90bdb60e0fc46d8aa1d9e858cbbdd07",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "generation_config.json:   0%|          | 0.00/210 [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "4f579cd077cd41c798478f572d592f6a",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "preprocessor_config.json:   0%|          | 0.00/477 [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "a37acc4c0f11436c80cb72272709a9fe",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "tokenizer_config.json:   0%|          | 0.00/55.9k [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "74742a6f4bb94067b6e6703cef8c3941",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "tokenizer.json:   0%|          | 0.00/17.2M [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "1a4c9e787979474b9049e36f8c07c12b",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "special_tokens_map.json:   0%|          | 0.00/454 [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "9430d398534341bca671d10e8bc91ddc",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "chat_template.json:   0%|          | 0.00/5.15k [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        }
+      ],
+      "source": [
+        "from unsloth import FastVisionModel # FastLanguageModel for LLMs\n",
+        "import torch\n",
+        "\n",
+        "# 4bit pre quantized models we support for 4x faster downloading + no OOMs.\n",
+        "fourbit_models = [\n",
+        "    \"unsloth/Llama-3.2-11B-Vision-Instruct-bnb-4bit\", # Llama 3.2 vision support\n",
+        "    \"unsloth/Llama-3.2-11B-Vision-bnb-4bit\",\n",
+        "    \"unsloth/Llama-3.2-90B-Vision-Instruct-bnb-4bit\", # Can fit in a 80GB card!\n",
+        "    \"unsloth/Llama-3.2-90B-Vision-bnb-4bit\",\n",
+        "\n",
+        "    \"unsloth/Pixtral-12B-2409-bnb-4bit\",              # Pixtral fits in 16GB!\n",
+        "    \"unsloth/Pixtral-12B-Base-2409-bnb-4bit\",         # Pixtral base model\n",
+        "\n",
+        "    \"unsloth/Qwen2-VL-2B-Instruct-bnb-4bit\",          # Qwen2 VL support\n",
+        "    \"unsloth/Qwen2-VL-7B-Instruct-bnb-4bit\",\n",
+        "    \"unsloth/Qwen2-VL-72B-Instruct-bnb-4bit\",\n",
+        "\n",
+        "    \"unsloth/llava-v1.6-mistral-7b-hf-bnb-4bit\",      # Any Llava variant works!\n",
+        "    \"unsloth/llava-1.5-7b-hf-bnb-4bit\",\n",
+        "] # More models at https://huggingface.co/unsloth\n",
+        "\n",
+        "model, tokenizer = FastVisionModel.from_pretrained(\n",
+        "    \"unsloth/Llama-3.2-11B-Vision-Instruct\",\n",
+        "    load_in_4bit = True, # Use 4bit to reduce memory use. False for 16bit LoRA.\n",
+        "    use_gradient_checkpointing = \"unsloth\", # True or \"unsloth\" for long context\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "cbc24d70",
+      "metadata": {
+        "id": "cbc24d70"
+      },
+      "outputs": [],
+      "source": [
+        "model = FastVisionModel.get_peft_model(\n",
+        "    model,\n",
+        "    finetune_vision_layers     = True, # False if not finetuning vision layers\n",
+        "    finetune_language_layers   = True, # False if not finetuning language layers\n",
+        "    finetune_attention_modules = True, # False if not finetuning attention layers\n",
+        "    finetune_mlp_modules       = True, # False if not finetuning MLP layers\n",
+        "\n",
+        "    r = 16,           # The larger, the higher the accuracy, but might overfit\n",
+        "    lora_alpha = 16,  # Recommended alpha == r at least\n",
+        "    lora_dropout = 0,\n",
+        "    bias = \"none\",\n",
+        "    random_state = 3407,\n",
+        "    use_rslora = False,  # We support rank stabilized LoRA\n",
+        "    loftq_config = None, # And LoftQ\n",
+        "    # target_modules = \"all-linear\", # Optional now! Can specify a list if needed\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "9e47b862",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 177,
+          "referenced_widgets": [
+            "aecf49a7a37445dfb4af43fed91cdc97",
+            "209f0d74e16b4c03a72687d796958863",
+            "17c372165582427dbc34abfd5dfdaa6c",
+            "59110c931b0b45d5a61d7dae7c7e7120",
+            "1ab79420b99e4508944ba5b4361171f8",
+            "89284068a3be4af4a0d9b8bc50b9afba",
+            "d11bd8033e4740929088a4fd0ef883c5",
+            "cc1cf7cbbcae4771be85c3e628510997",
+            "758e626f5c2f4b0193e1cf27824818ca",
+            "dfdce9a9549448a8a475db2c2507f5eb",
+            "4893fac70136425c9aa1c685e4ce71f3",
+            "ee828b24ee424cfc82b2f3b87636940a",
+            "115f636f0c0a4c1ebee21d973ff09e40",
+            "adb8a39222db4fe880c180fe5c601dbe",
+            "775514e06f1c453fa311d528b3d62749",
+            "523f128189f746ce9fb7a594e72e9c7e",
+            "72715b7c03e34b01b5f7715ce658eacd",
+            "432103db24e448e8b62bce3af49ec581",
+            "b382f1fd5c1645169079cdef08c14357",
+            "5ad48ea79bde44639976eeb61377b74d",
+            "2ae0d6c5c4c1419293e7b3832b8d8a17",
+            "71f1e8c406a54c52b6983ff2b922be20",
+            "34c7dbce08a146a7949152b0cac8666d",
+            "f8e7b74b13864adc9d6cfccaa9a11362",
+            "2aaa6c22a7d34c2aa20a169236a72f59",
+            "c79fefc6a20d4bce9eca13b0b1a604aa",
+            "8463516108b8491d8aaa0449a7f21f05",
+            "cb71c9d8d57744fb9cfeb740d7ea50e6",
+            "0241e7fc2a86481389ce140690fc544a",
+            "315e97f8931941d382ae5b91e1d644a0",
+            "ebdc57260e224077b0ba08ffbb3fb6a1",
+            "0ee41ec935844b09850972773468b5de",
+            "e7fabc6d4ea8476a9459604d745b7f08",
+            "5034f195628e43b98e4ab33fd297308c",
+            "46686703d557405685b5e910d81cfb4a",
+            "55e11fafe31f4147a7a53c870f637527",
+            "7fa57079e7414449a9b04330c91bd50d",
+            "add5ec75448b4378b8e7aab92a5e53f5",
+            "2e2dcbc6ae13435fa6bb91c35dbdf1ae",
+            "64a4a67880614ecebad79f9ac957d4af",
+            "dff190bbf4a746d393857037be5e5d72",
+            "7ebc322bc4824599a6f59ed979eae207",
+            "d61c2405111d4acc8428e1cebb96c963",
+            "5263b46f262a40518c43778191394e4a",
+            "78f33011fc0648439338fb4556284f31",
+            "b08e04e041a84597b225f2194943d715",
+            "7d36203af6344d50813eab42af8df957",
+            "00714fb691c14ca6a9ee14ead204b6c0",
+            "7d057295875d4525a165c823ff222268",
+            "be882001119342ebbbbc3f73dbfa5356",
+            "2713d41644f84b5290c0dd94b2953b2a",
+            "235bc65f45ac4b369e1e03582b1b2061",
+            "d2d708ed937b4deb8d72805e98b3aa9b",
+            "c0fc8d1e49d643b0b9871080545cbb27",
+            "f9bae803d6944df98773db211a4e98b6"
+          ]
+        },
+        "id": "9e47b862",
+        "outputId": "ac18735b-4865-4634-cdac-0672be9dc0e6"
+      },
+      "outputs": [
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "aecf49a7a37445dfb4af43fed91cdc97",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "README.md:   0%|          | 0.00/610 [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "ee828b24ee424cfc82b2f3b87636940a",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "train-00000-of-00001.parquet:   0%|          | 0.00/481M [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "34c7dbce08a146a7949152b0cac8666d",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "test-00000-of-00001.parquet:   0%|          | 0.00/79.2M [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "5034f195628e43b98e4ab33fd297308c",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "Generating train split:   0%|          | 0/1978 [00:00<?, ? examples/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "78f33011fc0648439338fb4556284f31",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "Generating test split:   0%|          | 0/327 [00:00<?, ? examples/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        }
+      ],
+      "source": [
+        "from datasets import load_dataset\n",
+        "\n",
+        "dataset = load_dataset(\"unsloth/Radiology_mini\", split=\"train\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "c437c09d",
+      "metadata": {
+        "id": "c437c09d"
+      },
+      "source": [
+        "## Output\n",
+        "This shows a basic output example of the vision-language model."
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": []
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 5
+}
@@ -1,5 +1,4 @@
 {
-
  "cells": [
    {
      "cell_type": "markdown",
@@ -1,134 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "441900e0"
-      },
-      "source": [
-        "# 🧠 Mistral v0.3 (7B) Conversational Agent\n",
-        "A conceptual demo notebook to illustrate the workflow and output of the Mistral model, even if it doesn't run on Colab Free Tier."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "b4ba0b88"
-      },
-      "source": [
-        "## 📄 Description\n",
-        "This notebook showcases the typical flow of using Mistral v0.3 (7B) for conversational tasks. While the model is too large for Google Colab Free Tier, this version visually explains what the code would do.\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/DhivyaBharathy-web/PraisonAI/blob/main/examples/cookbooks/Mistral_v0_3_Conversational_Demo.ipynb)\n"
-      ],
-      "metadata": {
-        "id": "yzXURvxIlIDD"
-      }
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "# 📦 Dependencies"
-      ],
-      "metadata": {
-        "id": "IUQSTocQk7ml"
-      }
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "6f2afc57"
-      },
-      "outputs": [],
-      "source": [
-        "\n",
-        "!pip install transformers accelerate torch\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "9d5dad27"
-      },
-      "source": [
-        "## 🛠 Tools Used\n",
-        "- 🤗 Transformers: For loading the model and tokenizer.\n",
-        "- PyTorch: For model inference.\n",
-        "- Accelerate: To manage device placement (CPU/GPU).\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "cd936b40"
-      },
-      "source": [
-        "## 🧾 YAML Prompt Format (Conceptual)\n",
-        "```yaml\n",
-        "task: conversation\n",
-        "input: \"What's the capital of France?\"\n",
-        "history: []\n",
-        "temperature: 0.7\n",
-        "top_p: 0.9\n",
-        "```\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "8abaaa62"
-      },
-      "outputs": [],
-      "source": [
-        "# 🧠 Main Inference Logic (Illustrative)\n",
-        "from transformers import AutoModelForCausalLM, AutoTokenizer\n",
-        "import torch\n",
-        "\n",
-        "model_id = \"mistralai/Mistral-7B-Instruct-v0.3\"\n",
-        "tokenizer = AutoTokenizer.from_pretrained(model_id)\n",
-        "model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map=\"auto\")\n",
-        "\n",
-        "prompt = \"What's the capital of France?\"\n",
-        "inputs = tokenizer(prompt, return_tensors=\"pt\").to(model.device)\n",
-        "outputs = model.generate(**inputs, max_new_tokens=100)\n",
-        "response = tokenizer.decode(outputs[0], skip_special_tokens=True)\n",
-        "print(response)\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "def486c6"
-      },
-      "source": [
-        "## 📤 Output (Example)\n",
-        "> \"The capital of France is Paris.\"\n",
-        "\n",
-        "![output](https://upload.wikimedia.org/wikipedia/commons/e/e6/Paris_Night.jpg)\n",
-        "\n"
-      ]
-    }
-  ],
-  "metadata": {
-    "accelerator": "GPU",
-    "colab": {
-      "gpuType": "T4",
-      "provenance": []
-    },
-    "kernelspec": {
-      "display_name": "Python 3",
-      "name": "python3"
-    },
-    "language_info": {
-      "name": "python"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 0
-}
@@ -0,0 +1,120 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "id": "468831db",
+      "metadata": {
+        "id": "468831db"
+      },
+      "source": [
+        "# Phi-3.5 Mini Conversational Example"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "ecb80fe2",
+      "metadata": {
+        "id": "ecb80fe2"
+      },
+      "source": [
+        "**Description:**\n",
+        "\n",
+        "Demonstrates lightweight inference using Phi-3.5 Mini, suitable for smaller hardware and educational use cases."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/DhivyaBharathy-web/PraisonAI/blob/main/examples/cookbooks/Phi_3_5_Mini_Conversational.ipynb)\n"
+      ],
+      "metadata": {
+        "id": "S1erg7-JP6n3"
+      },
+      "id": "S1erg7-JP6n3"
+    },
+    {
+      "cell_type": "markdown",
+      "id": "0822161c",
+      "metadata": {
+        "id": "0822161c"
+      },
+      "source": [
+        "**Dependencies**\n",
+        "\n",
+        "```python\n",
+        "!pip install transformers accelerate\n",
+        "!pip install torch\n",
+        "```"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "0df5580b",
+      "metadata": {
+        "id": "0df5580b"
+      },
+      "source": [
+        "**Tools Used**\n",
+        "\n",
+        "- HuggingFace Transformers\n",
+        "- PyTorch"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "9d6df43d",
+      "metadata": {
+        "id": "9d6df43d"
+      },
+      "source": [
+        "**YAML Prompt**\n",
+        "\n",
+        "```yaml\n",
+        "system: You are a helpful assistant.\n",
+        "user: Explain what an AI model is.\n",
+        "```"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "0e775593",
+      "metadata": {
+        "id": "0e775593"
+      },
+      "outputs": [],
+      "source": [
+        "from transformers import AutoTokenizer, AutoModelForCausalLM\n",
+        "\n",
+        "tokenizer = AutoTokenizer.from_pretrained(\"microsoft/phi-3.5-mini\")\n",
+        "model = AutoModelForCausalLM.from_pretrained(\"microsoft/phi-3.5-mini\")\n",
+        "\n",
+        "inputs = tokenizer(\"What is an AI model?\", return_tensors=\"pt\")\n",
+        "outputs = model.generate(**inputs, max_new_tokens=40)\n",
+        "print(tokenizer.decode(outputs[0], skip_special_tokens=True))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "187fe354",
+      "metadata": {
+        "id": "187fe354"
+      },
+      "source": [
+        "**Output**\n",
+        "\n",
+        "The model gives a basic explanation of what AI models do.\n",
+        "\n",
+        "What is an AI model?\n",
+        "An AI model is a computer program that is trained on large amounts of data to perform tasks that normally require human intelligence.\n"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": []
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 5
+}
@@ -0,0 +1,122 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "id": "ddb8fd1c",
+      "metadata": {
+        "id": "ddb8fd1c"
+      },
+      "source": [
+        "# Phi-3 Medium Conversational Inference"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/DhivyaBharathy-web/PraisonAI/blob/main/examples/cookbooks/Phi_3_Medium_Conversational.ipynb)\n"
+      ],
+      "metadata": {
+        "id": "uMIvNFtYQDKO"
+      },
+      "id": "uMIvNFtYQDKO"
+    },
+    {
+      "cell_type": "markdown",
+      "id": "71a9292d",
+      "metadata": {
+        "id": "71a9292d"
+      },
+      "source": [
+        "**Description:**\n",
+        "\n",
+        "Run a conversational inference using the Phi-3 Medium model with an efficient pipeline. The notebook illustrates basic loading, prompting, and response generation."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "9023e3f2",
+      "metadata": {
+        "id": "9023e3f2"
+      },
+      "source": [
+        "**Dependencies**\n",
+        "\n",
+        "```python\n",
+        "!pip install transformers accelerate\n",
+        "!pip install torch torchvision\n",
+        "```"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "8ed8c345",
+      "metadata": {
+        "id": "8ed8c345"
+      },
+      "source": [
+        "**Tools Used**\n",
+        "\n",
+        "- HuggingFace Transformers\n",
+        "- Accelerate\n",
+        "- PyTorch"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "68cb4bd6",
+      "metadata": {
+        "id": "68cb4bd6"
+      },
+      "source": [
+        "**YAML Prompt**\n",
+        "\n",
+        "```yaml\n",
+        "system: You are a helpful assistant.\n",
+        "user: What is the capital of France?\n",
+        "```"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "be5d0fde",
+      "metadata": {
+        "id": "be5d0fde"
+      },
+      "outputs": [],
+      "source": [
+        "from transformers import AutoTokenizer, AutoModelForCausalLM\n",
+        "import torch\n",
+        "\n",
+        "model = AutoModelForCausalLM.from_pretrained(\"microsoft/phi-3-medium\")\n",
+        "tokenizer = AutoTokenizer.from_pretrained(\"microsoft/phi-3-medium\")\n",
+        "\n",
+        "prompt = \"What is the capital of France?\"\n",
+        "inputs = tokenizer(prompt, return_tensors=\"pt\")\n",
+        "outputs = model.generate(**inputs, max_new_tokens=20)\n",
+        "print(tokenizer.decode(outputs[0], skip_special_tokens=True))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "4ac8c793",
+      "metadata": {
+        "id": "4ac8c793"
+      },
+      "source": [
+        "**Output**\n",
+        "\n",
+        "This example shows the model answering a simple geography question.\n",
+        "\n",
+        "What is the capital of France? The capital of France is Paris.\n"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": []
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 5
+}
@@ -0,0 +1,123 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "id": "cc1b7810",
+      "metadata": {
+        "id": "cc1b7810"
+      },
+      "source": [
+        "# Phi-4 (14B) Conversational with GRPO"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "9c882a2d",
+      "metadata": {
+        "id": "9c882a2d"
+      },
+      "source": [
+        "**Description:**\n",
+        "\n",
+        "This notebook demonstrates inference using the Phi-4 14B parameter model with GRPO optimization strategy."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/DhivyaBharathy-web/PraisonAI/blob/main/examples/cookbooks/Phi_4_14B_GRPO.ipynb)\n"
+      ],
+      "metadata": {
+        "id": "Z7azojscP0Ax"
+      },
+      "id": "Z7azojscP0Ax"
+    },
+    {
+      "cell_type": "markdown",
+      "id": "e8616784",
+      "metadata": {
+        "id": "e8616784"
+      },
+      "source": [
+        "**Dependencies**\n",
+        "\n",
+        "```python\n",
+        "!pip install transformers accelerate\n",
+        "!pip install torch\n",
+        "```"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "09866448",
+      "metadata": {
+        "id": "09866448"
+      },
+      "source": [
+        "**Tools Used**\n",
+        "\n",
+        "- HuggingFace Transformers\n",
+        "- GRPO Optimization\n",
+        "- PyTorch"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "403b0c37",
+      "metadata": {
+        "id": "403b0c37"
+      },
+      "source": [
+        "**YAML Prompt**\n",
+        "\n",
+        "```yaml\n",
+        "system: Act as a professional consultant.\n",
+        "user: How can AI help in healthcare?\n",
+        "```"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "e1785bcd",
+      "metadata": {
+        "id": "e1785bcd"
+      },
+      "outputs": [],
+      "source": [
+        "from transformers import AutoTokenizer, AutoModelForCausalLM\n",
+        "\n",
+        "tokenizer = AutoTokenizer.from_pretrained(\"microsoft/phi-4-14b\")\n",
+        "model = AutoModelForCausalLM.from_pretrained(\"microsoft/phi-4-14b\")\n",
+        "\n",
+        "prompt = \"How can AI help in healthcare?\"\n",
+        "inputs = tokenizer(prompt, return_tensors=\"pt\")\n",
+        "outputs = model.generate(**inputs, max_new_tokens=60)\n",
+        "print(tokenizer.decode(outputs[0], skip_special_tokens=True))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "074e4e6e",
+      "metadata": {
+        "id": "074e4e6e"
+      },
+      "source": [
+        "**Output**\n",
+        "\n",
+        "The model generates thoughtful insights on AI applications in healthcare.\n",
+        "\n",
+        "How can AI help in healthcare?\n",
+        "\n",
+        "AI can assist in healthcare by improving diagnostics, predicting patient outcomes, personalizing treatments, and enhancing administrative workflows. It enables faster data analysis and decision-making, leading to better patient care.\n"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": []
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 5
+}
@@ -0,0 +1,124 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "id": "7b502c12",
+      "metadata": {
+        "id": "7b502c12"
+      },
+      "source": [
+        "# Phi-4 Conversational Chat"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "6f550ca9",
+      "metadata": {
+        "id": "6f550ca9"
+      },
+      "source": [
+        "**Description:**\n",
+        "\n",
+        "Basic conversational inference with Phi-4 demonstrating chat-style turn-based communication."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/DhivyaBharathy-web/PraisonAI/blob/main/examples/cookbooks/Phi_4_Conversational.ipynb)\n"
+      ],
+      "metadata": {
+        "id": "CB4mkM7yPmua"
+      },
+      "id": "CB4mkM7yPmua"
+    },
+    {
+      "cell_type": "markdown",
+      "id": "e0db4638",
+      "metadata": {
+        "id": "e0db4638"
+      },
+      "source": [
+        "**Dependencies**\n",
+        "\n",
+        "```python\n",
+        "!pip install transformers accelerate\n",
+        "!pip install torch\n",
+        "```"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "25ef05dd",
+      "metadata": {
+        "id": "25ef05dd"
+      },
+      "source": [
+        "**Tools Used**\n",
+        "\n",
+        "- HuggingFace Transformers\n",
+        "- PyTorch"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "8986b9d8",
+      "metadata": {
+        "id": "8986b9d8"
+      },
+      "source": [
+        "**YAML Prompt**\n",
+        "\n",
+        "```yaml\n",
+        "system: You are a tutor.\n",
+        "user: Teach me what machine learning is.\n",
+        "```"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "ffdb2319",
+      "metadata": {
+        "id": "ffdb2319"
+      },
+      "outputs": [],
+      "source": [
+        "from transformers import AutoTokenizer, AutoModelForCausalLM\n",
+        "\n",
+        "tokenizer = AutoTokenizer.from_pretrained(\"microsoft/phi-4\")\n",
+        "model = AutoModelForCausalLM.from_pretrained(\"microsoft/phi-4\")\n",
+        "\n",
+        "prompt = \"Teach me what machine learning is.\"\n",
+        "inputs = tokenizer(prompt, return_tensors=\"pt\")\n",
+        "outputs = model.generate(**inputs, max_new_tokens=80)\n",
+        "print(tokenizer.decode(outputs[0], skip_special_tokens=True))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "ac4caeac",
+      "metadata": {
+        "id": "ac4caeac"
+      },
+      "source": [
+        "**Output**\n",
+        "\n",
+        "Explains machine learning in a clear, tutor-like manner.\n",
+        "\n",
+        "Machine learning is a field of artificial intelligence that allows computers to learn from data without being explicitly programmed.\n",
+        "It involves training algorithms on large datasets so they can recognize patterns, make decisions, or perform tasks.\n",
+        "There are different types of machine learning, including supervised, unsupervised, and reinforcement learning.\n",
+        "For example, in supervised learning, a model is trained using labeled data to predict outcomes.\n",
+        "Overall, machine learning is widely used in applications like recommendation systems, image recognition, and natural language processing.\n"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": []
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 5
+}
@@ -0,0 +1,660 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "id": "23d69f99",
+      "metadata": {
+        "id": "23d69f99"
+      },
+      "source": [
+        "# Pixtral (12B) Vision Model"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "b842f675",
+      "metadata": {
+        "id": "b842f675"
+      },
+      "source": [
+        "## Description\n",
+        "This notebook demonstrates how to use the **Pixtral (12B) Vision Model** vision-language model for image input and text generation tasks."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/DhivyaBharathy-web/PraisonAI/blob/main/examples/cookbooks/Pixtral_12B_Vision_Model.ipynb)\n"
+      ],
+      "metadata": {
+        "id": "MilYelUMlD2z"
+      },
+      "id": "MilYelUMlD2z"
+    },
+    {
+      "cell_type": "markdown",
+      "id": "557dba1c",
+      "metadata": {
+        "id": "557dba1c"
+      },
+      "source": [
+        "## Dependencies\n",
+        "```python\n",
+        "!pip install transformers accelerate torch torchvision\n",
+        "```"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "2b864df8",
+      "metadata": {
+        "id": "2b864df8"
+      },
+      "source": [
+        "## Tools\n",
+        "- 🤗 Transformers\n",
+        "- PyTorch\n",
+        "- Vision Model APIs"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "1b050001",
+      "metadata": {
+        "id": "1b050001"
+      },
+      "source": [
+        "## YAML Prompt\n",
+        "```yaml\n",
+        "mode: vision\n",
+        "model: Pixtral (12B) Vision Model\n",
+        "tasks:\n",
+        "  - image captioning\n",
+        "  - visual question answering\n",
+        "```"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "44ce2c02",
+      "metadata": {
+        "id": "44ce2c02"
+      },
+      "source": [
+        "## Main\n",
+        "Below is the simplified main execution to load the model and run basic inference."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "c996306e",
+      "metadata": {
+        "id": "c996306e"
+      },
+      "outputs": [],
+      "source": [
+        "%%capture\n",
+        "import os\n",
+        "if \"COLAB_\" not in \"\".join(os.environ.keys()):\n",
+        "    !pip install unsloth\n",
+        "else:\n",
+        "    # Do this only in Colab notebooks! Otherwise use pip install unsloth\n",
+        "    !pip install --no-deps bitsandbytes accelerate xformers==0.0.29.post3 peft trl triton cut_cross_entropy unsloth_zoo\n",
+        "    !pip install sentencepiece protobuf \"datasets>=3.4.1\" huggingface_hub hf_transfer\n",
+        "    !pip install --no-deps unsloth"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "30147f7c",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 543,
+          "referenced_widgets": [
+            "8a0ce0af1025429cb3cfcc5b973a4af0",
+            "6fe6ac6a53f745c5a2736e1b6cb01ff7",
+            "8d93c4b87f69485e8e97192a8431113f",
+            "08af812d04fe481fa84e85a6a591c506",
+            "257fe2a05570417882a606b304087a21",
+            "6d8e442e771d4955a29a360dee525119",
+            "00a911ef0d7f4a6d8b1b4f972b0b4d7c",
+            "766a605b2c5a463d977b8fefb554fea5",
+            "54ae26be14bc4fb28933af46f45e023a",
+            "360f3db84aac4728861b74b5a37adcaa",
+            "a2ae977cf14c461e9fa0cbc5c27e7186",
+            "d401dcde88274752b4f0786f834527d9",
+            "5d10ef16c7154f5392519da3ff6a2f0d",
+            "d8358c67c0b0415098b3e4a4e7ad0cbb",
+            "4f593d75532d4087bafc02d6ad2b4f79",
+            "a519350329d04d5096ccb605c9ffd623",
+            "9cd924df198145ed93d9df07249236cb",
+            "a01af94f415b4ed18186fa099c3ecbc3",
+            "27cd2e02e78d4ef8a52ba73a9e214120",
+            "841f197cba3f455d8fe9a9dafac992d7",
+            "d6507d692f9743e6b3eed08df94e2a56",
+            "c3438845441142fa92fec3acd21b3955",
+            "eb64d7acd375493098e1f7c30e7f2781",
+            "ad01bece3f444f1382988a65833bebf7",
+            "281b9b2311e5460aa4df9bbe9f8e22f0",
+            "34afc68bfe9d4e47ad73b31a34a74b32",
+            "23c9c94b98f141e8827c37cd26b6138e",
+            "d2b5a8a0c51c4d04aa1da73a56c2bcd3",
+            "4587ddab1af04157b8cba09f780ce9b0",
+            "aab82ec73c0b42fb928fbc74fc44c168",
+            "45f90f73051b4f898666ecd14f2818f0",
+            "6f96f236961344418015be410aedc57c",
+            "6105cefd94bb4a07b9123e461e857c9c",
+            "d4d3c9f1f54746d8895b66b6d2888ee2",
+            "eaa7a98acf704791a5c3ca37232c94b9",
+            "7b1f0430e15a476eb4b59fd5ddb0f9ac",
+            "481ce6bb0bf74e9592b5a4ef6cbc6d33",
+            "7a35df90dc40472eb0862deb368da362",
+            "d4bda244da214ee497b82608944bce6e",
+            "2cd8ad1cedb0484fa4c5d47b7b25971c",
+            "68c0b7aee1464e78b1bbd420f540fcf4",
+            "1fd521ec517348aa9d8dd73757619da4",
+            "9c967803321d4ca39b663165c2ce1953",
+            "c39f8980d63a4a5ab17f031e06b03f67",
+            "b60b17cb67044a82b173f94d781d5174",
+            "9078d37b65424033b551caf1ae410d2f",
+            "e5d3e2d9fb7e4f8fbfa84ba66ea0a81c",
+            "ae50ac57cecb48cb917a2a3ddf3312d0",
+            "2a85749ab4144e01bb640cd90a1a8697",
+            "96ce0742a2a247dd84d85ad7b5286f19",
+            "b67a770e477e40b3a7ca8f4570cb2129",
+            "79dfa298db314ce2874e86abd8e6b1ba",
+            "38700d9515ca4ee694010fd7914e0d18",
+            "7819396bd89b4917beac22678b04b9ec",
+            "bdbd0b350dbd49e9b463993a3d5c0e92",
+            "8f1faff5468a46d4a725d095ae31ea3c",
+            "4a704f4b14614fe6934420a895d9d1a0",
+            "e67dfbfbba4d4f4298b7ef302830ab40",
+            "9b6572529f65495693d840718d37e744",
+            "f06f07a6a1b94dfa9091651c9e95f6f4",
+            "c3bea8260e5f493d8a470ff98f025324",
+            "60f44f8bb72645eba40d9320d9d6e447",
+            "47905056428d4404b73049b3cc437a5a",
+            "5edec95909a6434ebf0bfd8a60f5887e",
+            "c9900bd2f3374f858680f5a40efa70a0",
+            "003f8dc6323b40d29b4f827e14108b20",
+            "1ef7d525ad2b4a57ae1118a0c3908b1a",
+            "7630787d9003423c81eac646fb88edc6",
+            "f41ca30bce18404b953b97548251b556",
+            "371f6292472d4befb3d8fcfcca290fed",
+            "4334bb17edbd4b279287ea9723a62a3c",
+            "b3114bb6194149989d1fa63011299251",
+            "4827624c03d848bbb473fe94b2d21c22",
+            "3047608c78ef465199d52959a425c5c0",
+            "8fb84b1203cb43b5803c11b4a77c0d42",
+            "426281caaa3f47e393ea8b001123cb22",
+            "6381166be9444c0a9b98186e978e94cb",
+            "fe28321b0bf04f58b0d63e7dc617e3ed",
+            "77335dfe86c34eb08f9085b6b839b8c7",
+            "49e7c650e0cc4b449ddd2d50f989d541",
+            "c502fd2bf724410dbcf1528c79f220ce",
+            "1b8d5199f7144981b5e9ae71f8ea8199",
+            "2fa87811a24f4b6e9695d7b80817a422",
+            "25133a67be974e6293bcdb3507529406",
+            "fdbff4f0bd6b4989b72f8252b5faea16",
+            "189edd39642b421f879956bea51d853e",
+            "740ffbd464f041a283b9b2d9396b180c",
+            "f5661357cbc144c5947529a979360114",
+            "ec91a47eece543a495f36ed0e051d637",
+            "443e64f8935544a0b4c159794fd8b272",
+            "7dd0095387264941a52e8587ebd0fea1",
+            "363406f847db494f972011724185b02a",
+            "c21d3532550248b8a927756a510a2770",
+            "82f03edadab54f949f92dd0c4a60bd55",
+            "d2488adbea5344329da2b447382139f5",
+            "fed393eac57747fabee1c2b743828ef8",
+            "b1d82fdb948b4c5bbee4d327a0f41a21",
+            "cccdb395613a4256950b7c3d740736fd",
+            "24c7bdd72f3546c882a7a7c78de5925f",
+            "db8a5ea365094bc4a87e77d059b4d0d0",
+            "2f494500c50a42f0ba3589743048cdd8",
+            "3ec4018cd5e54ba998a0f143f62407cc",
+            "f3a87c6d2986429cb40979782b38e712",
+            "4f7fb67e816b44598022407aacf71f19",
+            "be9935d016a34ac5a272b51261053f13",
+            "24540fc3ff1944edaa61e6037bec31c8",
+            "713338a99be84b54877f8e35c953d8ba",
+            "5586a425c639474ba5d6c0bd6d93328a",
+            "088d87f186cc4a5d95745d8317cca20e",
+            "acdecdef8bd14e44bcd36374b944b562",
+            "1c7c3bfb5ae4472c9bb6e340c012d302",
+            "41ae4c0601084403ba26a287f485ebeb",
+            "916e61f972f6439b8135a70100753917",
+            "36c3f462830247d7a219f1722cae8791",
+            "69ae06a22fa9488598ed89641cc135b6",
+            "c5ca864cc0144ddeb72dcbf1f8303609",
+            "728f786930a14c7a91cb4ff1f97a24ee",
+            "71704d8853ed40c4a55fa06669393ec9",
+            "af5c196783e349888eaefc227beadbf0",
+            "d3aee68f69ad4e5d81a087ec791cc9b1",
+            "1ec887eb8dac43ba9922e1f9f2111231",
+            "aa6b598305944d5ab2e2b4afaea8063c",
+            "a132d68b4ae94f64b80893b9149f7fd8",
+            "ec8f420a6f7d413bb528a1661aa3a0e8",
+            "b70265a81e9a49109c18eaad44135562",
+            "67a1b2e8e39b48849441368c33e16be4",
+            "e2ec06c317034b5681d83347b530362f",
+            "97bcd619eea74ed99650a1d8fed1f406",
+            "14bc6db53fa449049a6a63b422ee54bc",
+            "70f9cecf2dca4a3badc609b10ffcc8ec",
+            "cc082399aef94823b67d6e9c33d468e5",
+            "b4fb273306e941ebaa529e781361acfb"
+          ]
+        },
+        "id": "30147f7c",
+        "outputId": "8b36524b-d22e-43f2-a6e0-cc4209d76736"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "🦥 Unsloth: Will patch your computer to enable 2x faster free finetuning.\n",
+            "🦥 Unsloth Zoo will now patch everything to make training faster!\n",
+            "==((====))==  Unsloth 2024.11.9: Fast Pixtral vision patching. Transformers = 4.46.2.\n",
+            "   \\\\   /|    GPU: Tesla T4. Max memory: 14.748 GB. Platform = Linux.\n",
+            "O^O/ \\_/ \\    Pytorch: 2.5.1+cu121. CUDA = 7.5. CUDA Toolkit = 12.1.\n",
+            "\\        /    Bfloat16 = FALSE. FA [Xformers = 0.0.28.post3. FA2 = False]\n",
+            " \"-____-\"     Free Apache license: http://github.com/unslothai/unsloth\n",
+            "Unsloth: Fast downloading is enabled - ignore downloading bars which are red colored!\n"
+          ]
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "8a0ce0af1025429cb3cfcc5b973a4af0",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "model.safetensors.index.json:   0%|          | 0.00/316k [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "d401dcde88274752b4f0786f834527d9",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "eb64d7acd375493098e1f7c30e7f2781",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "model-00001-of-00002.safetensors:   0%|          | 0.00/4.97G [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "d4d3c9f1f54746d8895b66b6d2888ee2",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "model-00002-of-00002.safetensors:   0%|          | 0.00/3.57G [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "b60b17cb67044a82b173f94d781d5174",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "8f1faff5468a46d4a725d095ae31ea3c",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "generation_config.json:   0%|          | 0.00/133 [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "1ef7d525ad2b4a57ae1118a0c3908b1a",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "processor_config.json:   0%|          | 0.00/162 [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "fe28321b0bf04f58b0d63e7dc617e3ed",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "chat_template.json:   0%|          | 0.00/1.59k [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "ec91a47eece543a495f36ed0e051d637",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "preprocessor_config.json:   0%|          | 0.00/483 [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "db8a5ea365094bc4a87e77d059b4d0d0",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "tokenizer_config.json:   0%|          | 0.00/177k [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "1c7c3bfb5ae4472c9bb6e340c012d302",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "tokenizer.json:   0%|          | 0.00/17.1M [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "aa6b598305944d5ab2e2b4afaea8063c",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "special_tokens_map.json:   0%|          | 0.00/552 [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        }
+      ],
+      "source": [
+        "from unsloth import FastVisionModel # FastLanguageModel for LLMs\n",
+        "import torch\n",
+        "\n",
+        "# 4bit pre quantized models we support for 4x faster downloading + no OOMs.\n",
+        "fourbit_models = [\n",
+        "    \"unsloth/Llama-3.2-11B-Vision-Instruct-bnb-4bit\", # Llama 3.2 vision support\n",
+        "    \"unsloth/Llama-3.2-11B-Vision-bnb-4bit\",\n",
+        "    \"unsloth/Llama-3.2-90B-Vision-Instruct-bnb-4bit\", # Can fit in a 80GB card!\n",
+        "    \"unsloth/Llama-3.2-90B-Vision-bnb-4bit\",\n",
+        "\n",
+        "    \"unsloth/Pixtral-12B-2409-bnb-4bit\",              # Pixtral fits in 16GB!\n",
+        "    \"unsloth/Pixtral-12B-Base-2409-bnb-4bit\",         # Pixtral base model\n",
+        "\n",
+        "    \"unsloth/Qwen2-VL-2B-Instruct-bnb-4bit\",          # Qwen2 VL support\n",
+        "    \"unsloth/Qwen2-VL-7B-Instruct-bnb-4bit\",\n",
+        "    \"unsloth/Qwen2-VL-72B-Instruct-bnb-4bit\",\n",
+        "\n",
+        "    \"unsloth/llava-v1.6-mistral-7b-hf-bnb-4bit\",      # Any Llava variant works!\n",
+        "    \"unsloth/llava-1.5-7b-hf-bnb-4bit\",\n",
+        "] # More models at https://huggingface.co/unsloth\n",
+        "\n",
+        "model, tokenizer = FastVisionModel.from_pretrained(\n",
+        "    \"unsloth/Pixtral-12B-2409\",\n",
+        "    load_in_4bit = True, # Use 4bit to reduce memory use. False for 16bit LoRA.\n",
+        "    use_gradient_checkpointing = \"unsloth\", # True or \"unsloth\" for long context\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "1c0cd2b0",
+      "metadata": {
+        "id": "1c0cd2b0"
+      },
+      "outputs": [],
+      "source": [
+        "model = FastVisionModel.get_peft_model(\n",
+        "    model,\n",
+        "    # We do NOT finetune vision & attention layers since Pixtral uses more memory!\n",
+        "    finetune_vision_layers     = True, # False if not finetuning vision layers\n",
+        "    finetune_language_layers   = True,  # False if not finetuning language layers\n",
+        "    finetune_attention_modules = False, # False if not finetuning attention layers\n",
+        "    finetune_mlp_modules       = True,  # False if not finetuning MLP layers\n",
+        "\n",
+        "    r = 8,           # The larger, the higher the accuracy, but might overfit\n",
+        "    lora_alpha = 8,  # Recommended alpha == r at least\n",
+        "    lora_dropout = 0,\n",
+        "    bias = \"none\",\n",
+        "    random_state = 3407,\n",
+        "    use_rslora = False,  # We support rank stabilized LoRA\n",
+        "    loftq_config = None, # And LoftQ\n",
+        "    # target_modules = \"all-linear\", # Optional now! Can specify a list if needed\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "440fa965",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 177,
+          "referenced_widgets": [
+            "453a07e03ee94f528890205d14511da6",
+            "309ebf7d588244a3ba28d29d56edbc2a",
+            "dcc1ef7862e240eebefd5985202ef3b2",
+            "0ef444f87c454640aa657c4c187e94f5",
+            "d291b920db4b48fb9f3e89bc916db8c8",
+            "3570f6aec06d461e9259a2bd60c6a16a",
+            "3ed61e45df71452f844c1f39ea5c9dcf",
+            "2b6b7fd9d5204198953a0f6fe8333d57",
+            "e74c5834491b46d5b065665533671407",
+            "fc9a5b89da594730a09a6bb4c3adb879",
+            "22b0b4a4585148b2b6f75ecd86ebded3",
+            "94a24760f2e3453aa615caf5300cd9da",
+            "52e83aca1e544ffaabc57d149dd0415e",
+            "b2e5c457d6a246cabcd71459cf2cee8d",
+            "b8b672b219c347c4a636c1a43f73fda9",
+            "76e1e2ae0a2944de8eff1c8eea325164",
+            "6795172d2bb54298ae68cb481cf84822",
+            "c09587db5ef3473490c1638c359ca945",
+            "58e75f4e6c3e4ca9a6e6bc6e9865de67",
+            "0fd6dae874a344678bac899cca709c3b",
+            "da76163d3abd4ab9b4a7d02efdb15f00",
+            "dc79ba710e9f4485a6f51d48963c6666",
+            "9f45d79473ef446ca8f81c08ec82edda",
+            "c381bddbbb6a4bbd99f90546dfb1867c",
+            "9ca49f19650848dfbade44d036e166d2",
+            "348f47ec75d44295b089a0071b747010",
+            "d7601975774c43e4af927247019c2dab",
+            "46513f9858a8403b93fc2fb1a0ea8779",
+            "3d378819a2084a7797e8e8debf9bf815",
+            "d2080299e24d40cbaecf75aead507415",
+            "7d64c5f1dac64a49b794e723a5c77620",
+            "08acfb1a242542d9990577d62118185f",
+            "6cdfb3c8a1bc45b1ad34dd77feb4d4fe",
+            "7856e0634b86431382280c591b6f740f",
+            "cac2e90d5e3449978089a9fe4690cd93",
+            "01838b1fb6da41e6bee2c632f9873b6e",
+            "12b8a9e56ff646d4ba7032405183daf3",
+            "2ef9f2c39bdf4893a4016e0880445e0f",
+            "d358e59f602245fc96651c018347c448",
+            "b7aeadfe764542e3ae4dd47e2664e410",
+            "10523b38a16b4a48b095860653d34a6c",
+            "ac9cb94447274626afc8580dd17260ad",
+            "c6bc57fe79f045fabe94281cbe1bd09a",
+            "05e888e211274b269794cde826c7d1f9",
+            "6b2c1870e4ae44aba0326535f75c6858",
+            "c3997e6823fb40349d9c92e32ce28045",
+            "a4cf715dfb534feb814d426c2cac2b8e",
+            "f57ddd4b011e428e82a86317d15779aa",
+            "be6e313fb0b045adb8d8da6702081a0d",
+            "dc07e208294f47d8b122afc8d415e3c8",
+            "c2d88ba605ab4c2ab3f9686c5b65b8e8",
+            "625723d424624ab2ac641b2c369da9e8",
+            "35f6d9677b67401699e094040eaf8bd2",
+            "ed9c8e6297654278bb360c13134920cb",
+            "39d1ac1f430544c087b69e3bdb6ab5d6"
+          ]
+        },
+        "id": "440fa965",
+        "outputId": "54b0ee23-5573-407a-d22f-cda8378461da"
+      },
+      "outputs": [
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "453a07e03ee94f528890205d14511da6",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "README.md:   0%|          | 0.00/728 [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "94a24760f2e3453aa615caf5300cd9da",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "train-00000-of-00001.parquet:   0%|          | 0.00/357M [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "9f45d79473ef446ca8f81c08ec82edda",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "test-00000-of-00001.parquet:   0%|          | 0.00/57.6M [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "7856e0634b86431382280c591b6f740f",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "Generating train split:   0%|          | 0/8552 [00:00<?, ? examples/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "6b2c1870e4ae44aba0326535f75c6858",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "Generating test split:   0%|          | 0/1364 [00:00<?, ? examples/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        }
+      ],
+      "source": [
+        "from datasets import load_dataset\n",
+        "dataset = load_dataset(\"unsloth/llava-instruct-mix-vsft-mini\", split = \"train\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "b9670b46",
+      "metadata": {
+        "id": "b9670b46"
+      },
+      "source": [
+        "## Output\n",
+        "This shows a basic output example of the vision-language model."
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": []
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 5
+}
@@ -0,0 +1,616 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "id": "a627af7f",
+      "metadata": {
+        "id": "a627af7f"
+      },
+      "source": [
+        "# Qwen2.5-VL (7B) Vision Model"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "6ca9476a",
+      "metadata": {
+        "id": "6ca9476a"
+      },
+      "source": [
+        "## Description\n",
+        "This notebook demonstrates how to use the **Qwen2.5-VL (7B) Vision Model** vision-language model for image input and text generation tasks."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/DhivyaBharathy-web/PraisonAI/blob/main/examples/cookbooks/Qwen2_5_VL_7B_Vision_Model.ipynb)"
+      ],
+      "metadata": {
+        "id": "0G9UGDLJk8uV"
+      },
+      "id": "0G9UGDLJk8uV"
+    },
+    {
+      "cell_type": "markdown",
+      "id": "f467ebfe",
+      "metadata": {
+        "id": "f467ebfe"
+      },
+      "source": [
+        "## Dependencies\n",
+        "```python\n",
+        "!pip install transformers accelerate torch torchvision\n",
+        "```"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "ea76265d",
+      "metadata": {
+        "id": "ea76265d"
+      },
+      "source": [
+        "## Tools\n",
+        "- 🤗 Transformers\n",
+        "- PyTorch\n",
+        "- Vision Model APIs"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "37c57a37",
+      "metadata": {
+        "id": "37c57a37"
+      },
+      "source": [
+        "## YAML Prompt\n",
+        "```yaml\n",
+        "mode: vision\n",
+        "model: Qwen2.5-VL (7B) Vision Model\n",
+        "tasks:\n",
+        "  - image captioning\n",
+        "  - visual question answering\n",
+        "```"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "7b02bc60",
+      "metadata": {
+        "id": "7b02bc60"
+      },
+      "source": [
+        "## Main\n",
+        "Below is the simplified main execution to load the model and run basic inference."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "6c397c49",
+      "metadata": {
+        "id": "6c397c49"
+      },
+      "outputs": [],
+      "source": [
+        "%%capture\n",
+        "import os\n",
+        "if \"COLAB_\" not in \"\".join(os.environ.keys()):\n",
+        "    !pip install unsloth\n",
+        "else:\n",
+        "    # Do this only in Colab notebooks! Otherwise use pip install unsloth\n",
+        "    !pip install --no-deps bitsandbytes accelerate xformers==0.0.29.post3 peft trl triton cut_cross_entropy unsloth_zoo\n",
+        "    !pip install sentencepiece protobuf \"datasets>=3.4.1\" huggingface_hub hf_transfer\n",
+        "    !pip install --no-deps unsloth"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "18b3d67c",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 513,
+          "referenced_widgets": [
+            "73fc3ac47de840cda7a07297153404d5",
+            "8c8b54f4d34a4b59a5a2513bbc082297",
+            "7bd2abffca3f4193afffd3f1a7c8ff8a",
+            "9ecdc7e0e9c247c59e9eab93455153b8",
+            "84f4e9f7ff6f433bbf13078e43ebbe2a",
+            "7475f8a404624b1b844d8148fabb493b",
+            "9d4aae9ebe594bd6875a5963eb6d77ed",
+            "62b6d78abada429393c499e0479eb56e",
+            "2aecce21a3a04971b4f5c9fd0b059738",
+            "2af66136423c41c6908c5a61c6fa2e5d",
+            "8bf92078d48448848402ede49b1b5182",
+            "78ae8aea29e04420bcfe616061934d98",
+            "e22b1706b6be49af8e31d2c512ccaaf6",
+            "71ac48ba667b4af291df3a33e7643c6c",
+            "7d16f0e5aaec4429a5b8d3c4878ea74a",
+            "a21de38381c241309bc798be604c3bf5",
+            "f26f1de0f3f34010ac0d37d6f3ed74b6",
+            "0af61827920e415daf64cfcb1685ee63",
+            "77a82cf2255b43e088812087af4d8ead",
+            "fad668efab014d28877087f38f3c034e",
+            "e764888263e54f0ba2f603992d678096",
+            "2dccbbbdfbf645b8b5896953f6e8a59b",
+            "45385885a26e42d0b1f52eda382fd6f4",
+            "ccb21e1b7fc14a6ab10689154ab2b94a",
+            "f5c7ab8d65c4418a943a51a401720f67",
+            "f6aaa74bce474abcbc9daf0515b6ffbd",
+            "76bd63e567e94650a82272ca6fd85011",
+            "d3cac12f194a40a187bbba68da36173c",
+            "30439a7bf22f416cbc01cfe87e433e1f",
+            "3265b3490b11426a8aa44d541981a296",
+            "78a31b91439c4c99a07f8f8d8dfb548f",
+            "d2a3a751ac2f491c9e7cb7a4092ab0b6",
+            "b652bb727c1148c4aac9ed751920e3ae",
+            "14e519d5e0834fd9a70a111140f8429a",
+            "41f3770e6d864c1794a1fa93feaf8605",
+            "6aa1670b808b42db894756b904243947",
+            "5757f1d68b8f4571a05486d846127b14",
+            "14cbf1b61170470bbb9d63e31d0ca310",
+            "3324ce12dc3e45fab9984eb83a92eb39",
+            "0ccabea3b39d4b148d420e26b53d3990",
+            "2d65a3b83b524eeaafde8e406e90198f",
+            "d179ef65b2b842d69548302c2f7a31be",
+            "2362fd437a134c30b147df947ee97128",
+            "7f22e31fc7174ff2bfa8bc2624d33dc7",
+            "643db314d8e94feeb9cd8747909eaabe",
+            "b80bb8f2cc92400aa34934978f9bc865",
+            "03f0c63c572249aabb7fb61272af1f1b",
+            "4113f045f9bc440b8dfaed5dfab14c1b",
+            "86a231a75d4a4586a53e4c7e74c63550",
+            "573653d0298246868e5d93069ca0fef5",
+            "c20a42f12c4545dfafdba22267e44d4b",
+            "4b74060c0bb44a35b847e6752b93e463",
+            "7e211233455342d48bd60f6d499b91f5",
+            "520ca077c6854e6fa1e019c0b209eae7",
+            "8f1fce549e494998b13f523bd793d300",
+            "bbb5e6a0a8b64d10802fbf3e89778306",
+            "0cef8128eeba4638bd268f9a1a364427",
+            "399cc918cec24db7b99af9e5f3c5adb4",
+            "3a611a2e00be4da6833172d928802fb9",
+            "0f2f303ae91349e29132055105fcbdec",
+            "17c08a96e04244a995e658eeb5a69699",
+            "9269dee0b0104b22b4043d3661f79350",
+            "a405cbc6d42d4f8f8be7c05f4e34128c",
+            "e702e948bb34481d995c75be223c4e16",
+            "c9949e2b99d14fa0bc4cfc88f42c2afb",
+            "48bbf9b662af47c5b99ebe24a6b70549",
+            "c1af10a57c0a40cf818d0974facdcc36",
+            "e4c1ff933c6e4ef49afbedffcdd99d5c",
+            "3caf3a6d48da403099bcdee89bda6949",
+            "7e0bbe2417e0420db1502390ba7c6c2d",
+            "5522658c84dc47a491f5deb08353b631",
+            "aecb331a01a44c9e92c74840faaf2616",
+            "caadc7751ff847b4a831dd6b2b53e60b",
+            "f0dd55c8f71a4f47a91a7018ab89d092",
+            "7a2d1ba8441e4a368a505c38d2c811ad",
+            "6657bbba902e43429224ed9c426389fe",
+            "a25ba73fb99448a3b46ac3571e2db0be",
+            "c2f518986b724620bbc67f7b6ede6d96",
+            "ed214eea73f54928af276883ddd53b5e",
+            "b241468a1d684fbb820baff6b9f9e362",
+            "0f7da532813445f1be01977cdec364ab",
+            "de7ac823a59d488995aa37bfbcec2e5b",
+            "fc5321766b8742ca97c4a839ba30d421",
+            "c4256f50e38e481083f3d366bfd91d3f",
+            "f7e4e90fb3fe4bbb85adb039404dd8e2",
+            "e0f8b5f130064bd69f4f3298e9536b5a",
+            "20956dab8f3e4f22830b4d9e56a5232a",
+            "4efe313f923c4ae585fb8a4353cecd97",
+            "3af59a3e9ac2430da201262fc54b5998",
+            "ad746cc40cdb461bba8cf04033d4afc5",
+            "3d09770f22854ca38213d4a64ace6df3",
+            "910df16ec7494eb68fb1f8ce95046414",
+            "080c7eed9cc0475980e85a530c91e616",
+            "e4fe961d149b461fb1d168d226c8aa1d",
+            "2a588c12d3814de495fa865a63629ba8",
+            "607a235508e54fdda0aef75311c7a213",
+            "383e14f14b0d4328a80e6b0283c421fa",
+            "913324d3476a4d04887d200f91afc553",
+            "4c0c6892c4f347deb4a85544664ff1e1",
+            "a863bb17b5984981bf9bd4ff93e438f4",
+            "b28286deba7c4152a8d2c21ea0d19402",
+            "fb9e17975b2349de81115173af6ac17a",
+            "f3b068de4fa6466e88970b73c868de0a",
+            "2127bee2928e43578b8b51e3c1fdfabf",
+            "a97f3d8c7bdf4292ae8ed133f059f635",
+            "67053bf18cd04347a0f2d2ff6134ae88",
+            "80e56300aee14b4386832aa1618c5d43",
+            "d096e33830754ea5b2e8f102548b805a",
+            "a913ea3370404f5f972754715889aced",
+            "35db2f7869f44aeab422409d27d5f7ec"
+          ]
+        },
+        "id": "18b3d67c",
+        "outputId": "f0d7f72f-8166-439b-96da-ed7e30f8bdb3"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "🦥 Unsloth: Will patch your computer to enable 2x faster free finetuning.\n",
+            "🦥 Unsloth Zoo will now patch everything to make training faster!\n",
+            "==((====))==  Unsloth 2025.3.19: Fast Qwen2_5_Vl patching. Transformers: 4.50.0.\n",
+            "   \\\\   /|    Tesla T4. Num GPUs = 1. Max memory: 14.741 GB. Platform: Linux.\n",
+            "O^O/ \\_/ \\    Torch: 2.6.0+cu124. CUDA: 7.5. CUDA Toolkit: 12.4. Triton: 3.2.0\n",
+            "\\        /    Bfloat16 = FALSE. FA [Xformers = 0.0.29.post3. FA2 = False]\n",
+            " \"-____-\"     Free license: http://github.com/unslothai/unsloth\n",
+            "Unsloth: Fast downloading is enabled - ignore downloading bars which are red colored!\n"
+          ]
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "73fc3ac47de840cda7a07297153404d5",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "model.safetensors:   0%|          | 0.00/5.97G [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "78ae8aea29e04420bcfe616061934d98",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "generation_config.json:   0%|          | 0.00/267 [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "45385885a26e42d0b1f52eda382fd6f4",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "preprocessor_config.json:   0%|          | 0.00/575 [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.50, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.\n"
+          ]
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "14e519d5e0834fd9a70a111140f8429a",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "tokenizer_config.json:   0%|          | 0.00/7.33k [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "643db314d8e94feeb9cd8747909eaabe",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "vocab.json:   0%|          | 0.00/2.78M [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "bbb5e6a0a8b64d10802fbf3e89778306",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "merges.txt:   0%|          | 0.00/1.67M [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "c1af10a57c0a40cf818d0974facdcc36",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "tokenizer.json:   0%|          | 0.00/11.4M [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "c2f518986b724620bbc67f7b6ede6d96",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "added_tokens.json:   0%|          | 0.00/605 [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "3af59a3e9ac2430da201262fc54b5998",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "special_tokens_map.json:   0%|          | 0.00/614 [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "a863bb17b5984981bf9bd4ff93e438f4",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "chat_template.json:   0%|          | 0.00/1.05k [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        }
+      ],
+      "source": [
+        "from unsloth import FastVisionModel # FastLanguageModel for LLMs\n",
+        "import torch\n",
+        "\n",
+        "# 4bit pre quantized models we support for 4x faster downloading + no OOMs.\n",
+        "fourbit_models = [\n",
+        "    \"unsloth/Llama-3.2-11B-Vision-Instruct-bnb-4bit\", # Llama 3.2 vision support\n",
+        "    \"unsloth/Llama-3.2-11B-Vision-bnb-4bit\",\n",
+        "    \"unsloth/Llama-3.2-90B-Vision-Instruct-bnb-4bit\", # Can fit in a 80GB card!\n",
+        "    \"unsloth/Llama-3.2-90B-Vision-bnb-4bit\",\n",
+        "\n",
+        "    \"unsloth/Pixtral-12B-2409-bnb-4bit\",              # Pixtral fits in 16GB!\n",
+        "    \"unsloth/Pixtral-12B-Base-2409-bnb-4bit\",         # Pixtral base model\n",
+        "\n",
+        "    \"unsloth/Qwen2-VL-2B-Instruct-bnb-4bit\",          # Qwen2 VL support\n",
+        "    \"unsloth/Qwen2-VL-7B-Instruct-bnb-4bit\",\n",
+        "    \"unsloth/Qwen2-VL-72B-Instruct-bnb-4bit\",\n",
+        "\n",
+        "    \"unsloth/llava-v1.6-mistral-7b-hf-bnb-4bit\",      # Any Llava variant works!\n",
+        "    \"unsloth/llava-1.5-7b-hf-bnb-4bit\",\n",
+        "] # More models at https://huggingface.co/unsloth\n",
+        "\n",
+        "model, tokenizer = FastVisionModel.from_pretrained(\n",
+        "    \"unsloth/Qwen2.5-VL-7B-Instruct-bnb-4bit\",\n",
+        "    load_in_4bit = True, # Use 4bit to reduce memory use. False for 16bit LoRA.\n",
+        "    use_gradient_checkpointing = \"unsloth\", # True or \"unsloth\" for long context\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "45f1a7d8",
+      "metadata": {
+        "id": "45f1a7d8"
+      },
+      "outputs": [],
+      "source": [
+        "model = FastVisionModel.get_peft_model(\n",
+        "    model,\n",
+        "    finetune_vision_layers     = True, # False if not finetuning vision layers\n",
+        "    finetune_language_layers   = True, # False if not finetuning language layers\n",
+        "    finetune_attention_modules = True, # False if not finetuning attention layers\n",
+        "    finetune_mlp_modules       = True, # False if not finetuning MLP layers\n",
+        "\n",
+        "    r = 16,           # The larger, the higher the accuracy, but might overfit\n",
+        "    lora_alpha = 16,  # Recommended alpha == r at least\n",
+        "    lora_dropout = 0,\n",
+        "    bias = \"none\",\n",
+        "    random_state = 3407,\n",
+        "    use_rslora = False,  # We support rank stabilized LoRA\n",
+        "    loftq_config = None, # And LoftQ\n",
+        "    # target_modules = \"all-linear\", # Optional now! Can specify a list if needed\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "915566b6",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 177,
+          "referenced_widgets": [
+            "5e4f3f4910d1477b924362c095a0cedd",
+            "b5a01de096fa4e2daf66e235bd5686bb",
+            "e9195f3a3e29475f941c302fe2a88a83",
+            "0d6f6fb66522436786728d8602e2f466",
+            "94b72e08764c486d8eed43a4557f1d98",
+            "8e8281a56a3d4879b6b376077890c920",
+            "630894e18b264f7dae8eddb17304a1cd",
+            "697fc92abb824cf4a9bc78709640ba54",
+            "eb6d552d6c1d4e82a521b29b36ae3db0",
+            "7572f2d06114442ba94fc22761a55346",
+            "c6dcd15e155949cbb9698e43e55b7a90",
+            "7365368b63d9425db5d4e5514e6e0586",
+            "5997909fc34645ce9a03d82ab0932766",
+            "ea4ebb90b708493c85fa81fecf4d60c0",
+            "227724312eb045a58616f63c3a5b7407",
+            "4f58e8a2ddbb4a73a2421ea37c68fea9",
+            "7e89e5546e394162b7b0f793478527ff",
+            "db9ea237050045d8861d76bb3b995753",
+            "3a484309bbe148abb2ef05452850728a",
+            "5e601d00c0094d999a5b37b9555c111c",
+            "e7bd6c674af541d08c0acb5e47579156",
+            "927147d620b0426cb46b49b6d8dc2ffc",
+            "4ebb36e479884847bcef5736e276dfb9",
+            "7b5a059a8ef84817851d109fd7e3a7b5",
+            "0e949ae97d544d65af09cebe63041b8e",
+            "c817a779a9ff4a848391a7c7dff1e4ca",
+            "abae462b98c84006b71d4a62c8a47d5a",
+            "dc1a755aae6c44849d818fd96c046649",
+            "2650d2ce196e404a98cbfac96d0a9bef",
+            "36d579fdc2fb4c59b827f5bf7a92abd4",
+            "fccec1c2a389401eb614f5f1cfb15f0c",
+            "7b4d303966274c71b50312df12e7b87a",
+            "ce4bb2dffcf84ae9bf1f8ac86b2d768e",
+            "639b886f72e24951909e4ffb6cfa247d",
+            "7b13cf1727a04f5ca6de1f7eb536d800",
+            "631ce764f4684225a3c1e4455717a555",
+            "48af93dada914d8b88d5ffffd24ac666",
+            "4bd339c9d3ee43f39678d2c18baeef53",
+            "b1b12b8def994e748b08b27abcef4b87",
+            "bc38022049ce47628d8c215959c38b91",
+            "331d5d2bc67f44f283fc82481cb60411",
+            "0a5ad3bd338b4e6ea94a11a199d2f5ba",
+            "5c41f695158641f485349c20a1405cfd",
+            "89bc17f1911a43cca7196da232500fd6",
+            "f5629e8c82c848218f69810e1b21b0e4",
+            "5244452af0734f3183a7384435f9e1fe",
+            "69f645decfb64baca11cfbdb9773a458",
+            "d1788fabe3e34f6eb60fecab3c7490ba",
+            "8f423066ba8f421495f934a269053cc1",
+            "569d1435402e4533b0427a4b191b6754",
+            "b834a7ab12544f9b8305f5728677e921",
+            "e72ac7c9b7824c81a6e77e6fadad9f9c",
+            "828ad6e5fcfb44b3b4559ec5682d095d",
+            "dac611678f4949ae98051bdc975e083f",
+            "0a21bae13a3c46509db70dbe8e9de5eb"
+          ]
+        },
+        "id": "915566b6",
+        "outputId": "ece64855-55d4-4011-c5b8-33a9bb622734"
+      },
+      "outputs": [
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "5e4f3f4910d1477b924362c095a0cedd",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "README.md:   0%|          | 0.00/519 [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "7365368b63d9425db5d4e5514e6e0586",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "train-00000-of-00001.parquet:   0%|          | 0.00/344M [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "4ebb36e479884847bcef5736e276dfb9",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "test-00000-of-00001.parquet:   0%|          | 0.00/38.2M [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "639b886f72e24951909e4ffb6cfa247d",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "Generating train split:   0%|          | 0/68686 [00:00<?, ? examples/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "f5629e8c82c848218f69810e1b21b0e4",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "Generating test split:   0%|          | 0/7632 [00:00<?, ? examples/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        }
+      ],
+      "source": [
+        "from datasets import load_dataset\n",
+        "dataset = load_dataset(\"unsloth/LaTeX_OCR\", split = \"train\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "6193435d",
+      "metadata": {
+        "id": "6193435d"
+      },
+      "source": [
+        "## Output\n",
+        "This shows a basic output example of the vision-language model."
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": []
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 5
+}
@@ -6,11 +6,19 @@
        "id": "IY0bHc5lF46I"
      },
      "source": [
+
+        "# \ud83e\udd16 Qwen Model Agent\n",
+        "This notebook runs a chatbot agent using the `Qwen/Qwen1.5-1.8B` model via the `transformers` library in Google Colab.\n",
+        "\n",
+        "\u2705 Lightweight model (1.8B) so it runs on Colab Free.\n",
+        "\u2699\ufe0f No extra setup needed beyond `transformers` and `torch`.\n",
+=======
        "# 🤖 Qwen Model Agent\n",
        "This notebook runs a chatbot agent using the `Qwen/Qwen1.5-1.8B` model via the `transformers` library in Google Colab.\n",
        "\n",
        "✅ Lightweight model (1.8B) so it runs on Colab Free.\n",
        "⚙️ No extra setup needed beyond `transformers` and `torch`.\n",
+
        "---"
      ],
      "id": "IY0bHc5lF46I"
@@ -50,6 +58,18 @@
          "output_type": "stream",
          "name": "stdout",
          "text": [
+
+            "\u001b[2K   \u001b[90m\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u001b[0m \u001b[32m363.4/363.4 MB\u001b[0m \u001b[31m2.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[2K   \u001b[90m\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u001b[0m \u001b[32m13.8/13.8 MB\u001b[0m \u001b[31m36.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[2K   \u001b[90m\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u001b[0m \u001b[32m24.6/24.6 MB\u001b[0m \u001b[31m31.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[2K   \u001b[90m\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u001b[0m \u001b[32m883.7/883.7 kB\u001b[0m \u001b[31m23.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[2K   \u001b[90m\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u001b[0m \u001b[32m664.8/664.8 MB\u001b[0m \u001b[31m1.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[2K   \u001b[90m\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u001b[0m \u001b[32m211.5/211.5 MB\u001b[0m \u001b[31m2.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[2K   \u001b[90m\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u001b[0m \u001b[32m56.3/56.3 MB\u001b[0m \u001b[31m15.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[2K   \u001b[90m\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u001b[0m \u001b[32m127.9/127.9 MB\u001b[0m \u001b[31m7.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[2K   \u001b[90m\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u001b[0m \u001b[32m207.5/207.5 MB\u001b[0m \u001b[31m4.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[2K   \u001b[90m\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u001b[0m \u001b[32m21.1/21.1 MB\u001b[0m \u001b[31m81.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+=======
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m363.4/363.4 MB\u001b[0m \u001b[31m2.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m13.8/13.8 MB\u001b[0m \u001b[31m36.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m24.6/24.6 MB\u001b[0m \u001b[31m31.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
@@ -60,6 +80,7 @@
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m127.9/127.9 MB\u001b[0m \u001b[31m7.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m207.5/207.5 MB\u001b[0m \u001b[31m4.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m21.1/21.1 MB\u001b[0m \u001b[31m81.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+
            "\u001b[?25h"
          ]
        }
@@ -73,7 +94,11 @@
    {
      "cell_type": "markdown",
      "source": [
+
+        "# \u2705 Use the official BERT Large model"
+=======
        "# ✅ Use the official BERT Large model"
+
      ],
      "metadata": {
        "id": "PvTxUutEce5s"
@@ -324,6 +349,8 @@
    },
    "colab": {
      "provenance": []
+
+=======
    },
    "widgets": {
      "application/vnd.jupyter.widget-state+json": {
@@ -2038,8 +2065,13 @@
          }
        }
      }
+
    }
  },
  "nbformat": 4,
  "nbformat_minor": 5
-}
+
+}
+=======
+}
+
@@ -958,8 +958,14 @@ Your Goal: {self.goal}
            return final_response
            
        except Exception as e:
-            display_error(f"Error in stream processing: {e}")
-            return None
+            # Optionally, log the error here if display_error also logged
+            # import logging
+            # logging.error(f"Error in stream processing: {e}", exc_info=True)
+            # Note: If 'e' is a ConnectionError or similar, it often indicates
+            # an issue with the LLM backend (e.g., Ollama server unavailable,
+            # network misconfiguration, or incorrect OPENAI_API_BASE if using LiteLLM).
+            # Ensure the target LLM server is running and accessible.
+            raise e

    def _chat_completion(self, messages, temperature=0.2, tools=None, stream=True, reasoning_steps=False):
        start_time = time.time()
@@ -1117,8 +1123,11 @@ Your Goal: {self.goal}
            return final_response

        except Exception as e:
-            display_error(f"Error in chat completion: {e}")
-            return None
+            # Optional: Log the error here if display_error also logged or if more context is needed.
+            # import logging
+            # logging.error(f"Error in chat completion for agent {self.name}: {e}", exc_info=True)
+            display_error(f"Error in chat completion: {e}") # Keep if console feedback is desired before raising
+            raise # Re-raise the caught exception

    def chat(self, prompt, temperature=0.2, tools=None, output_json=None, output_pydantic=None, reasoning_steps=False, stream=True):
        # Log all parameter values when in debug mode
Author	SHA1	Message	Date
google-labs-jules[bot]	d84e7af4ba	Fix: Gracefully handle connection errors in chat completion This commit addresses an issue where a connection error during streaming chat completion (e.g., from an Ollama backend via LiteLLM) would lead to a `AttributeError: 'NoneType' object has no attribute 'choices'`. The fix involves the following changes: 1. Modified `_process_stream_response` in `agent.py` to re-raise exceptions encountered during stream processing, instead of returning `None`. 2. Adjusted `_chat_completion` in `agent.py` to also re-raise exceptions caught from its operations (including those from `_process_stream_response`), ensuring errors propagate correctly. 3. Added a comment in `_process_stream_response` to guide you on troubleshooting common causes of connection errors, such as Ollama server issues or network misconfigurations. These changes prevent the specific `AttributeError` by ensuring that error conditions are propagated as exceptions, allowing for more robust error handling and clearer diagnostics of underlying problems.	2025-06-19 04:16:46 +00:00
MervinPraison	218370fef8	Merge branch 'main' of https://github.com/MervinPraison/PraisonAI	2025-06-17 11:09:41 +01:00
MervinPraison	117969e8f6	Update Claude workflow to simplify action references by using version tags, enhancing clarity and maintainability.	2025-06-17 11:09:40 +01:00
Mervin Praison	914532028d	Merge pull request #669 from DhivyaBharathy-web/add-Phi_3_Medium_Conversational Add Phi_3_Medium_Conversational notebook	2025-06-17 11:56:33 +02:00
DhivyaBharathy-web	83d808ddc1	Add Phi_3_Medium_Conversational notebook	2025-06-17 09:54:35 +00:00
Mervin Praison	3cf922f36c	Merge pull request #667 from DhivyaBharathy-web/add-Phi_4_14B_GRPO Add Phi_4_14B_GRPO notebook	2025-06-17 11:52:37 +02:00
Mervin Praison	b5956e0d39	Merge pull request #668 from DhivyaBharathy-web/add-Phi_3_5_Mini_Conversational Add Phi_3_5_Mini_Conversational notebook	2025-06-17 11:52:27 +02:00
Mervin Praison	07952d1b61	Merge pull request #666 from DhivyaBharathy-web/add-Phi_4_Conversational Add Phi_4_Conversational notebook	2025-06-17 11:52:17 +02:00
DhivyaBharathy-web	9eedd55b19	Add Phi_3_5_Mini_Conversational notebook	2025-06-17 09:49:45 +00:00
DhivyaBharathy-web	3b31afb270	Add Phi_4_14B_GRPO notebook	2025-06-17 09:45:50 +00:00
DhivyaBharathy-web	c77f3c7363	Add Phi_4_Conversational notebook	2025-06-17 09:40:28 +00:00
Mervin Praison	c808ce29e4	Merge pull request #632 from DhivyaBharathy-web/add-qwen-chatbot-agent Add qwen chatbot agent	2025-06-17 00:24:41 +02:00
Mervin Praison	ca70d34ffe	Merge pull request #659 from DhivyaBharathy-web/add-llama3-2-11b-vision-agent Add llama3 2 11b vision agent	2025-06-17 00:20:23 +02:00
Mervin Praison	96563ffb04	Merge pull request #662 from DhivyaBharathy-web/add-Pixtral_12B_Vision_Model Add pixtral 12 b vision model	2025-06-17 00:20:11 +02:00
Mervin Praison	d7a89a5b5d	Merge pull request #663 from DhivyaBharathy-web/add-Qwen2-5-VL_7B_Vision_Model Add qwen2 5 vl 7 b vision model	2025-06-17 00:20:02 +02:00
DhivyaBharathy-web	7d0afb062e	Resolve conflict by deleting Mistral notebook	2025-06-16 11:44:20 +00:00
DhivyaBharathy-web	3ede63d3d9	Resolve conflict by deleting Mistral notebook	2025-06-16 11:30:59 +00:00
DhivyaBharathy-web	db58770b46	Resolve conflict by deleting Mistral notebook	2025-06-16 11:11:32 +00:00
MervinPraison	9066668121	Refactor Claude Code Action to streamline prompt handling by reading directly from the prompt file, enhancing clarity and efficiency in command execution.	2025-06-16 09:57:01 +01:00
MervinPraison	8e5b6a9d38	Refactor Claude Code Action by removing unnecessary timeout and custom instructions handling, streamlining command argument preparation for improved clarity and efficiency.	2025-06-16 09:41:00 +01:00
MervinPraison	b16086c17d	Update Claude Code Action to enhance input options and streamline prompt extraction from GitHub context. Remove redundant GitHub token and MCP installation steps in workflow for improved clarity and efficiency.	2025-06-16 09:39:06 +01:00
MervinPraison	f50a2448df	Refactor Claude Code Action to auto-generate prompts from GitHub context when no input is provided, improving usability and functionality. Update workflow to remove redundant prompt generation step, streamlining the process.	2025-06-16 09:13:23 +01:00
MervinPraison	b1ff7a9500	Update GitHub Actions workflow by standardising GitHub token reference and adding a step to generate prompts from GitHub context, enhancing functionality and clarity.	2025-06-16 09:10:37 +01:00
DhivyaBharathy	c4829d45a4	Merge branch 'main' into add-qwen-chatbot-agent	2025-06-16 13:04:42 +05:30
DhivyaBharathy	f4479fa1f4	Add files via upload	2025-06-16 13:00:35 +05:30
DhivyaBharathy-web	f008aa1c3b	Add Qwen2.5-VL_7B_Vision_Model Agent notebook	2025-06-16 07:20:55 +00:00
MervinPraison	3abb084209	Refactor Claude Code Action by consolidating functionality into a composite action, removing Dockerfile and entrypoint script, and enhancing input descriptions for clarity and usability.	2025-06-16 08:16:05 +01:00
DhivyaBharathy-web	617efcc96d	Add LLaMA3-2_11B_Vision Agent notebook	2025-06-16 07:15:16 +00:00
MervinPraison	41bec67b51	Refine Claude workflow by directly executing the 'claude' script with Node to bypass BusyBox environment issues, enhancing reliability in CI execution.	2025-06-16 07:59:11 +01:00
MervinPraison	91361eee17	Enhance Claude workflow by adding debugging steps for environment verification, checking for the presence of the 'claude' command, and implementing automatic installation if not found, ensuring smoother execution in CI mode.	2025-06-16 07:56:35 +01:00
MervinPraison	aa1356629b	Update Claude workflow by modifying Docker image reference format, enhancing environment variable debugging, and updating GitHub token reference for improved clarity and reliability.	2025-06-16 07:54:53 +01:00
MervinPraison	ac86a8dd76	Fix GHCR authentication issue in Claude workflow by updating login method and adding a logout step for improved reliability.	2025-06-16 07:50:37 +01:00
MervinPraison	ab679e040e	Add Docker pull test step to Claude workflow for verification of successful image retrieval after login.	2025-06-16 07:49:57 +01:00
MervinPraison	c2fded7a89	Refactor Claude workflow by removing redundant debugging and testing steps, updating GitHub token usage for improved security and clarity.	2025-06-16 07:45:03 +01:00
DhivyaBharathy	1a306988cf	Delete examples/cookbooks/Mistral_v0_3_Conversational_Demo.ipynb	2025-06-11 16:22:41 +05:30
DhivyaBharathy	f4cb62a288	Merge branch 'main' into add-qwen-chatbot-agent	2025-06-10 11:55:04 +05:30
DhivyaBharathy	dde6ec4a6a	Update qwen_colab_agent.ipynb	2025-06-10 11:52:40 +05:30
DhivyaBharathy-web	c8b2414f5b	Add Qwen Agent notebook	2025-06-10 06:17:23 +00:00