Chess Gemma 3 fine-tuned model with commentary generation

README.md

@@ -9,43 +9,14 @@ tags:
   - game-analysis
   - flutter
   - mobile
-  - multilingual
 language:
   - en
-  - hi
-  - es
-  - zh
-  - fr
-  - de
-  - pt
-  - ru
-  - ja
-  - ar
-  - ko
-  - tr
-  - id
-  - bn
 ---
 
 # Chess Gemma Commentary 🎯♟️
 ### By NAKST Studio
 <br>
-Fine-tuned <strong>Gemma 3 270M</strong> model for generating chess move commentary, ELO predictions, and move classifications in <strong>14 languages</strong>.
-
----
-
-<div align="center">
-
-### 💙 Support & Shape NAKST Studio
-
-[![Donate](https://img.shields.io/badge/💙_Donate-Support_Free_Development-0080FF?style=for-the-badge)](https://nakststudio.com/donate)
-[![Vote Next App](https://img.shields.io/badge/🗳️_Vote-Choose_Our_Next_App-FF6B6B?style=for-the-badge)](https://nakststudio.com/vote-next-app-beta)
-
-**Help us keep building free, privacy-focused chess tools!** Support teen developers creating amazing apps without ads or data collection. Vote for what we build next!
-
-</div>
-
----
+Fine-tuned **Gemma 3 270M** model for generating chess move commentary, ELO predictions, and move classifications.
 
 ## Model Details
 
@@ -56,183 +27,103 @@ Fine-tuned <strong>Gemma 3 270M</strong> model for generating chess move comment
 - **Training Framework:** Unsloth + Hugging Face Transformers
 - **Hardware:** Google Colab T4 GPU
 - **Model Size:** 500MB (full) / 150MB (quantized q4_k_m)
-- **Languages Supported:** 14 (English, Hindi, Spanish, Mandarin Chinese, French, German, Portuguese, Russian, Japanese, Arabic, Korean, Turkish, Indonesian, Bengali)
 
 ## Capabilities
 
 ✅ **Chess Move Commentary** - Detailed analysis of chess positions and moves  
 ✅ **ELO Prediction** - Estimates player skill rating (1000-2800)  
 ✅ **Move Classification** - Labels moves as Best Move, Good Move, Blunder, etc.  
-✅ **Multilingual Support** - Generate commentary in 14 different languages  
 ✅ **Mobile Ready** - Works on Android with flutter_gemma or Ollama  
 ✅ **Offline** - No internet required for inference  
 
-## Supported Languages
-
-| Language Code | Language Name | Native Name |
-|---------------|---------------|-------------|
-| `en` | English | English |
-| `hi` | Hindi | हिन्दी |
-| `es` | Spanish | Español |
-| `zh` | Mandarin Chinese | 中文 |
-| `fr` | French | Français |
-| `de` | German | Deutsch |
-| `pt` | Portuguese | Português |
-| `ru` | Russian | Русский |
-| `ja` | Japanese | 日本語 |
-| `ar` | Arabic | العربية |
-| `ko` | Korean | 한국어 |
-| `tr` | Turkish | Türkçe |
-| `id` | Indonesian | Bahasa Indonesia |
-| `bn` | Bengali | বাংলা |
-
 ## Input Format
 
-The model uses a **conversational format** with system and user messages. The input expects a JSON-like structure with role-based messages.
+The model expects chess position data formatted EXACTLY as follows:
 
-### System Message (Required)
-```python
-{
-    'role': 'system',
-    'content': 'Generate professional chess commentary in the specified language. For Type=standard use 30–40 words. For Type=explanation, explain the best move briefly (≤50 words). Return exactly: Commentary, Predicted ELO, Verified Classification.'
-}
 ```
-
-### User Message Format
-```python
-{
-    'role': 'user',
-    'content': '''LanguageL: English
-LangCode: en
-Type: standard
-FEN: rnbqkbnr/pppppppp/8/8/3P4/8/PPP1PPPP/RNBQKBNR b KQkq - 0 1
-MoveSAN: Nf6
-Side: Black
-Actor: human
-Name: John
-Gender: male
-Tag: Book
-BestAlt: g8f6
-CP: 27->21 (Δ=6)'''
-}
+Analyze this chess move:
+    FEN: rnbqkbnr/pppppppp/8/8/3P4/8/PPP1PPPP/RNBQKBNR b KQkq - 0 1,
+    SAN: Nf6,
+    Player Color: Black,
+    Move Classification: Book Move,
+    Best Alternative Move: g8f6,
+    CP Before: 27,
+    CP After: 21,
+    Opening: Queen's Pawn Game,
+    Name: Player_123,
+    is Player Or Bot: Player
+Provide Commentary, predicted elo, classification.
 ```
 
-### Field Descriptions
-
-| Field         | Type | Required   | Example                                                                 | Explanation                                                                             |
-|---------------|------|------------|-------------------------------------------------------------------------|-----------------------------------------------------------------------------------------|
-| **LanguageL** | string | ✅ REQUIRED | `English`, `Hindi`, `Spanish`                                           | Full language name for commentary generation                                            |
-| **LangCode**  | string | ✅ REQUIRED | `en`, `hi`, `es`                                                        | ISO 639-1 language code (see table above)                                               |
-| **Type**      | string | ✅ REQUIRED | `standard`, `explanation`                                               | Commentary type: `standard` (30-40 words) or `explanation` (explain best move, ≤50 words) |
-| **FEN**       | string | ✅ REQUIRED | `rnbqkbnr/pppppppp/8/8/3P4/8/PPP1PPPP/RNBQKBNR b KQkq - 0 1`            | Forsyth-Edwards Notation - exact chess position before the move                         |
-| **MoveSAN**   | string | ✅ REQUIRED | `Nf6`, `e4`, `O-O`                                                      | Standard Algebraic Notation - the move that was played                                  |
-| **Side**      | string | ✅ REQUIRED | `White`, `Black`                                                        | Which side played the move                                                              |
-| **Actor**     | string | ✅ REQUIRED | `human`, `bot`                                                          | Whether move was made by human or engine                                                |
-| **NAME**      | string | OPTIONAL   | `Name of human or bot`                                                  | Human or bot gender who played the move for personalized commentary                     |
-| **Gender**    | string | OPTIONAL   | `male`, `female`, `neutral`                                             | Player or bot gender for personalized commentary                                        |
-| **Tag**       | string | ✅ REQUIRED | `Book`, `Best`, `Good`, `Inaccuracy`, `Mistake`, `Blunder`, `Brilliant` | Move classification tag                                                                 |
-| **BestAlt**   | string | ✅ REQUIRED | `g8f6`, `e2e4`                                                          | Best alternative move in coordinate notation                                            |
-| **CP**        | string | ✅ REQUIRED | `27->21 (Δ=6)`                                                          | Centipawn evaluation: before->after (Delta=change). Format: `CPBefore->CPAfter (Δ=change)` |
+### Field Descriptions (In Order)
+
+| Field | Type | Required | Example                                                                                                      | Explanation |
+|-------|------|----------|--------------------------------------------------------------------------------------------------------------|-------------|
+| **FEN** | string | ✅ REQUIRED | `rnbqkbnr/pppppppp/8/8/3P4/8/PPP1PPPP/RNBQKBNR b KQkq - 0 1`                                                 | Forsyth-Edwards Notation - exact chess position before the move. This is the standard notation that describes where every piece is on the board. |
+| **SAN** | string | ✅ REQUIRED | `Nf6`                                                                                                        | Standard Algebraic Notation - the move that was played. Examples: e4, Nxf6, O-O (castling), Qh5+, exd5 |
+| **Player Color** | string | ✅ REQUIRED | `Black` or `White`                                                                                           | Which side played the move. Must be exactly "White" or "Black" |
+| **Move Classification** | string | ✅ REQUIRED | `Book Move`, `Best Move`, `Good Move`, `Inaccuracy`, `Blunder`, `Brilliant`, `Great`, `Inaccuracy`, `Mistake` | Category of the move. Common values: "Book Move", "Best Move", "Good Move", "Inaccuracy", "Blunder", "Forced Move" |
+| **Best Alternative Move** | string | ✅ REQUIRED | `g8f6`                                                                                                       | What the engine recommends instead (in coordinate notation). Example: if move is Nf6, alternative might be d6, e6, etc. |
+| **CP Before** | integer | ✅ REQUIRED | `27`                                                                                                         | Centipawn evaluation BEFORE the move. Positive = White better, Negative = Black better. 100 cp ≈ 1 pawn |
+| **CP After** | integer | ✅ REQUIRED | `21`                                                                                                         | Centipawn evaluation AFTER the move. Shows the impact of the move on the position |
+| **Opening** | string | ⭐ OPTIONAL | `Queen's Pawn Game`                                                                                          | Opening name from opening database. Can be "None" if unknown |
+| **Name** | string | ⭐ OPTIONAL | `Player_123`                                                                                                 | Player name or ID. Can be "Unknown" or "..." if not applicable |
+| **is Player Or Bot** | string | ✅ REQUIRED | `Player`, `Bot`, `Not Sure`                                                                                  | Whether the move was made by a human player or chess engine. Must be one of these three exact values |
 
 ## Sample Input & Output
 
-### Example 1: English Commentary (Standard)
+### Example 1: Strong Opening
 
 **Input:**
-```python
-[
-    {
-        'role': 'system',
-        'content': 'Generate professional chess commentary in the specified language. For Type=standard use 30–40 words. For Type=explanation, explain the best move briefly (≤50 words). Return exactly: Commentary, Predicted ELO, Verified Classification.'
-    },
-    {
-        'role': 'user',
-        'content': '''LanguageL: English
-LangCode: en
-Type: standard
-FEN: rnbqkbnr/pppppppp/8/8/3P4/8/PPP1PPPP/RNBQKBNR b KQkq - 0 1
-MoveSAN: Nf6
-Side: Black
-Actor: human
-Gender: male
-Tag: Book
-BestAlt: g8f6
-CP: 27->21 (Δ=6)'''
-    }
-]
+```
+Analyze this chess move:
+    FEN: rnbqkbnr/pppppppp/8/8/3P4/8/PPP1PPPP/RNBQKBNR b KQkq - 0 1,
+    SAN: Nf6,
+    Player Color: Black,
+    Move Classification: Book Move,
+    Best Alternative Move: g8f6,
+    CP Before: 27,
+    CP After: 21,
+    Opening: Queen's Pawn Game,
+    Name: Player_8007,
+    is Player Or Bot: Player
+Provide Commentary, predicted elo, classification.
 ```
 
 **Output:**
 ```
 Commentary: Excellent opening response! Nf6 is the classical development move against d4. It immediately challenges the center and prepares flexible piece development. This maintains the tension and gives Black excellent counterplay.
+
 Predicted ELO: 1850
-Verified Classification: Book Move
+
+Classification: Book Move
 ```
 
-### Example 2: Hindi Commentary (Standard)
+### Example 2: Middlegame Move
 
 **Input:**
-```python
-[
-    {
-        'role': 'system',
-        'content': 'Generate professional chess commentary in the specified language. For Type=standard use 30–40 words. For Type=explanation, explain the best move briefly (≤50 words). Return exactly: Commentary, Predicted ELO, Verified Classification.'
-    },
-    {
-        'role': 'user',
-        'content': '''LanguageL: Hindi
-LangCode: hi
-Type: standard
-FEN: r1bqkb1r/pppp1ppp/2n2n2/4p3/4P3/5N2/PPPP1PPP/RNBQKB1R w KQkq e6 0 4
-MoveSAN: Nc3
-Side: White
-Actor: human
-Gender: female
-Tag: Best
-BestAlt: b1c3
-CP: 42->38 (Δ=4)'''
-    }
-]
+```
+Analyze this chess move:
+    FEN: r1bqkb1r/pppp1ppp/2n2n2/4p3/4P3/5N2/PPPP1PPP/RNBQKB1R w KQkq e6 0 4,
+    SAN: Nc3,
+    Player Color: White,
+    Move Classification: Best Move,
+    Best Alternative Move: b1c3,
+    CP Before: 42,
+    CP After: 38,
+    Opening: Nimzo-Indian Defense,
+    Name: GrandMaster_Smith,
+    is Player Or Bot: Player
+Provide Commentary, predicted elo, classification.
 ```
 
 **Output:**
 ```
-Commentary: शानदार केंद्रीकरण! Nc3 e4 पर दबाव के साथ विकसित होता है और प्रमुख केंद्रीय वर्गों को नियंत्रित करता है। यह चाल विकास को पूरा करने की तैयारी करती है जबकि केंद्र तनाव बनाए रखती है।
-Predicted ELO: 2400
-Verified Classification: Best Move
-```
+Commentary: Strong centralization! Nc3 develops with pressure on e4 and controls key central squares. This move prepares to complete development while maintaining the center tension. A solid, principled continuation in this dynamic position.
 
-### Example 3: Explanation Type (Spanish)
-
-**Input:**
-```python
-[
-    {
-        'role': 'system',
-        'content': 'Generate professional chess commentary in the specified language. For Type=standard use 30–40 words. For Type=explanation, explain the best move briefly (≤50 words). Return exactly: Commentary, Predicted ELO, Verified Classification.'
-    },
-    {
-        'role': 'user',
-        'content': '''LanguageL: Spanish
-LangCode: es
-Type: explanation
-FEN: 2rq1rk1/pb1nb1pp/1p6/3p1p2/3Pn3/P1N5/1PQNBPPP/R1B1R1K1 w - - 0 16
-MoveSAN: f3
-Side: White
-Actor: human
-Gender: male
-Tag: Mistake
-BestAlt: d2e4
-CP: 23->59 (Δ=36)'''
-    }
-]
-```
+Predicted ELO: 2400
 
-**Output:**
-```
-Commentary: El movimiento f3 debilita el rey y permite contraataques tácticos. La mejor alternativa Ne4 centralizaría el caballo con amenazas activas mientras mantiene la seguridad del rey. Este error costó aproximadamente un tercio de peón en ventaja posicional.
-Predicted ELO: 1650
-Verified Classification: Mistake
+Classification: Best Move
 ```
 
 ## Usage Examples
@@ -241,36 +132,25 @@ Verified Classification: Mistake
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model = AutoModelForCausalLM.from_pretrained("NAKSTStudio/chess-gemma-commentary")
-tokenizer = AutoTokenizer.from_pretrained("NAKSTStudio/chess-gemma-commentary")
-
-# Prepare messages
-messages = [
-    {
-        'role': 'system',
-        'content': 'Generate professional chess commentary in the specified language. For Type=standard use 30–40 words. For Type=explanation, explain the best move briefly (≤50 words). Return exactly: Commentary, Predicted ELO, Verified Classification.'
-    },
-    {
-        'role': 'user',
-        'content': '''LanguageL: English
-LangCode: en
-Type: standard
-FEN: rnbqkbnr/pppppppp/8/8/3P4/8/PPP1PPPP/RNBQKBNR b KQkq - 0 1
-MoveSAN: Nf6
-Side: Black
-Actor: human
-Gender: male
-Tag: Book
-BestAlt: g8f6
-CP: 27->21 (Δ=6)'''
-    }
-]
-
-# Generate response
-inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True)
-outputs = model.generate(inputs, max_new_tokens=256, temperature=0.7)
-response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-print(response)
+model = AutoModelForCausalLM.from_pretrained("your-username/chess-gemma-commentary")
+tokenizer = AutoTokenizer.from_pretrained("your-username/chess-gemma-commentary")
+
+prompt = """Analyze this chess move:
+    FEN: rnbqkbnr/pppppppp/8/8/3P4/8/PPP1PPPP/RNBQKBNR b KQkq - 0 1,
+    SAN: Nf6,
+    Player Color: Black,
+    Move Classification: Book Move,
+    Best Alternative Move: g8f6,
+    CP Before: 27,
+    CP After: 21,
+    Opening: Queen's Pawn Game,
+    Name: Player_123,
+    is Player Or Bot: Player
+Provide Commentary, predicted elo, classification."""
+
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.7)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```
 
 ### Flutter (flutter_gemma)
@@ -278,122 +158,81 @@ print(response)
 import 'package:flutter_gemma/flutter_gemma.dart';
 
 class ChessAnalyzer {
-  late InferenceModel model;
-  
+  late GemmaModel model;
+
   Future<void> initModel() async {
-    // Install model from Hugging Face (one-time operation)
-    await FlutterGemma.installModel(
-      modelType: ModelType.gemmaIt,
-    ).fromNetwork(
-      'https://huggingface.co/NAKSTStudio/chess-gemma-commentary/resolve/main/model.safetensors',
-    ).withProgress((progress) {
-      print('Downloading model: ${progress.percentage}%');
-    }).install();
-    
-    // Create model instance for inference
-    model = await FlutterGemma.getActiveModel(
-      maxTokens: 256,
-      preferredBackend: PreferredBackend.gpu,
+    model = await GemmaModel.load(
+      modelPath: 'assets/model.safetensors',
+      tokenizerPath: 'assets/tokenizer.model',
+      configPath: 'assets/config.json',
     );
   }
 
   Future<String> analyzeMove({
-    required String language,
-    required String langCode,
-    required String type,
     required String fen,
-    required String moveSAN,
-    required String side,
-    required String actor,
-    required String gender,
-    required String tag,
-    required String bestAlt,
-    required String cp,
+    required String san,
+    required String playerColor,
+    required String moveClassification,
+    required String bestAltMove,
+    required int cpBefore,
+    required int cpAfter,
+    String opening = 'None',
+    String name = 'Unknown',
+    required String isPlayerOrBot,
   }) async {
-    final chat = await model.createChat(temperature: 0.7);
-    
-    // Add system message
-    await chat.addQueryChunk(Message.text(
-      text: 'Generate professional chess commentary in the specified language. For Type=standard use 30–40 words. For Type=explanation, explain the best move briefly (≤50 words). Return exactly: Commentary, Predicted ELO, Verified Classification.',
-      isUser: false,
-    ));
-    
-    // Add user message with chess position data
-    await chat.addQueryChunk(Message.text(
-      text: '''LanguageL: $language
-LangCode: $langCode
-Type: $type
-FEN: $fen
-MoveSAN: $moveSAN
-Side: $side
-Actor: $actor
-Gender: $gender
-Tag: $tag
-BestAlt: $bestAlt
-CP: $cp''',
-      isUser: true,
-    ));
-    
-    // Generate response
-    final response = await chat.generateChatResponse();
-    
-    await chat.close();
-    
-    if (response is TextResponse) {
-      return response.token;
-    }
-    
-    return 'Error generating response';
-  }
-  
-  Future<void> dispose() async {
-    await model.close();
+    final prompt = """Analyze this chess move:
+    FEN: $fen,
+    SAN: $san,
+    Player Color: $playerColor,
+    Move Classification: $moveClassification,
+    Best Alternative Move: $bestAltMove,
+    CP Before: $cpBefore,
+    CP After: $cpAfter,
+    Opening: $opening,
+    Name: $name,
+    is Player Or Bot: $isPlayerOrBot
+Provide Commentary, predicted elo, classification.""";
+
+    return await model.generate(prompt: prompt, maxTokens: 256);
   }
 }
 
 // Usage
 final analyzer = ChessAnalyzer();
-
-// Initialize once (downloads model if not present)
 await analyzer.initModel();
 
-// Use multiple times
 final result = await analyzer.analyzeMove(
-  language: 'English',
-  langCode: 'en',
-  type: 'standard',
   fen: 'rnbqkbnr/pppppppp/8/8/3P4/8/PPP1PPPP/RNBQKBNR b KQkq - 0 1',
-  moveSAN: 'Nf6',
-  side: 'Black',
-  actor: 'human',
-  gender: 'male',
-  tag: 'Book',
-  bestAlt: 'g8f6',
-  cp: '27->21 (Δ=6)',
+  san: 'Nf6',
+  playerColor: 'Black',
+  moveClassification: 'Book Move',
+  bestAltMove: 'g8f6',
+  cpBefore: 27,
+  cpAfter: 21,
+  opening: 'Queen\'s Pawn Game',
+  name: 'Player_123',
+  isPlayerOrBot: 'Player',
 );
 
 print(result);
-
-// Clean up when done
-await analyzer.dispose();
 ```
 
 ## Output Format
 
 The model generates three key components:
 
-1. **Commentary:** Multi-sentence chess analysis in the specified language (30-50 words typically)
+1. **Commentary:** Multi-sentence chess analysis (5-50 words typically)
 2. **Predicted ELO:** Integer rating (1000-2800 typically)
-3. **Verified Classification:** Single label describing the move (Book Move, Best Move, Good Move, Inaccuracy, Mistake, Blunder, Brilliant)
+3. **Classification:** Single label describing the move
 
 ## Performance Metrics
 
-- ⚡ **Inference Speed:** 15-30 tokens/second on mid-range Android phones
+- ⚡ **Inference Speed:** 10-20 tokens/second on mid-range Android phones
 - 💾 **Memory Required:** 4GB minimum RAM for on-device inference
 - 📱 **Model Sizes:** 
-  - TASK File(int 8 dynamic): ~250 mb
-  - TASK File: ~500 mb
-- 🌍 **Language Coverage:** 14 languages spanning 5+ billion speakers
+  - Full precision: 500MB
+  - Quantized (q4_k_m): 150MB
+- 🎯 **Pattern Accuracy:** ~92% consistency with training data
 
 ## Training Configuration
 
@@ -404,8 +243,8 @@ The model generates three key components:
 - **Learning Rate:** 2e-4
 - **Batch Size:** 8 (effective; per device: 1, gradient accumulation: 8)
 - **Optimizer:** AdamW 8-bit
-- **Warmup Steps:** 5
-- **Training Time:** ~100 minutes (4 epochs on Colab T4)
+- **Warmup Steps:** 50
+- **Training Time:** ~40 minutes (3 epochs on Colab T4)
 
 ## Model Files
 
@@ -423,19 +262,15 @@ chess-gemma-commentary/
 
 ## Important Notes
 
-⚠️ **Format Sensitivity:** This model is trained on the EXACT format shown above. Follow field order, spacing, and field names precisely for best results.
-
-⚠️ **Language Codes:** Use the correct ISO 639-1 language code from the supported languages table. Incorrect codes may produce unexpected results.
+⚠️ **Format Sensitivity:** This model is trained on the EXACT format shown above. Follow field order, spacing, and punctuation precisely for best results.
 
-⚠️ **Commentary Types:** 
-- `Type=standard`: Generates 30-40 word general commentary
-- `Type=explanation`: Generates ≤50 word explanation focusing on why the best alternative move is superior
+⚠️ **Commas Matter:** Notice commas after each field (except the last one). Don't remove them.
 
-✅ **Conversational Format:** The model uses a message-based format with system and user roles for better context understanding.
+✅ **Optional Fields:** Only "Opening" and "Name" are optional - all others are required.
 
-✅ **Gender-Aware:** Optionally customize commentary style based on player gender (male/female/neutral).
+✅ **Flexible Values:** You can change the values, but keep the field labels and format identical.
 
-✅ **Delta Information:** The CP field format `CPBefore->CPAfter (Δ=change)` helps the model understand move impact.
+✅ **Multi-position:** Works well for opening, middlegame, and endgame positions.
 
 ## Known Limitations
 
@@ -443,8 +278,6 @@ chess-gemma-commentary/
 - ❌ Requires 4GB+ RAM for mobile inference (quantization helps)
 - ❌ Temperature affects output randomness (0.7 recommended for chess)
 - ❌ Cannot analyze positions with invalid FEN notation
-- ❌ Language quality may vary - English has most training data coverage
-- ❌ Some languages may require native speaker validation for natural phrasing
 
 ## License
 
@@ -454,8 +287,8 @@ This model is distributed under the **Gemma Community License**. See: https://ai
 
 ```bibtex
 @model{chess_gemma_commentary_2025,
-  title={Chess Gemma Commentary: Multilingual Chess Analysis},
-  author={NAKST Studio},
+  title={Chess Gemma Commentary},
+  author={Your Name},
   year={2025},
   howpublished={Hugging Face Hub}
 }
@@ -479,4 +312,4 @@ This model is distributed under the **Gemma Community License**. See: https://ai
 
 **Made with ❤️ by NAKST Studio**
 
-*Last Updated: November 7, 2025*
+*Last Updated: November 3, 2025*

tokenizer_config.json

@@ -51341,5 +51341,6 @@
   "spaces_between_special_tokens": false,
   "tokenizer_class": "GemmaTokenizer",
   "unk_token": "<unk>",
-  "use_default_system_prompt": false
-}
+  "use_default_system_prompt": false,
+  "chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n    {%- if messages[0]['content'] is string -%}\n        {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n    {%- else -%}\n        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n    {%- endif -%}\n    {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n    {%- set first_user_prefix = \"\" -%}\n    {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n        {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n    {%- endif -%}\n    {%- if (message['role'] == 'assistant') -%}\n        {%- set role = \"model\" -%}\n    {%- else -%}\n        {%- set role = message['role'] -%}\n    {%- endif -%}\n    {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n    {%- if message['content'] is string -%}\n        {{ message['content'] | trim }}\n    {%- elif message['content'] is iterable -%}\n        {%- for item in message['content'] -%}\n            {%- if item['type'] == 'image' -%}\n                {{ '<start_of_image>' }}\n            {%- elif item['type'] == 'text' -%}\n                {{ item['text'] | trim }}\n            {%- endif -%}\n        {%- endfor -%}\n    {%- else -%}\n        {{ raise_exception(\"Invalid content type\") }}\n    {%- endif -%}\n    {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n    {{ '<start_of_turn>model\n' }}\n{%- endif -%}\n"
+}