Final cleanup for HF Spaces deployment

- Removed training artifacts (checkpoint, runs, docs) - saved 56MB
- Moved model to root ./model directory for cleaner structure
- Removed create_finetune_dataset.py (not needed for inference)
- Updated model path in code to ./model
- Final package: 139MB (was 195MB)
- Only essential files for HF Spaces inference

training/create_finetune_dataset.py

@@ -1,315 +0,0 @@
-#!/usr/bin/env python3
-"""
-Create Fine-tuning Dataset for TinyLlama - Yerevan Venue Specialist
-Combines JSON reviews + CSV summaries to create conversational training data
-"""
-
-import json
-import pandas as pd
-import random
-from typing import List, Dict, Any
-import re
-
-class YerevanVenueDatasetCreator:
-    def __init__(self, json_path: str, csv_path: str):
-        self.json_path = json_path
-        self.csv_path = csv_path
-        self.venues_data = []
-        self.structured_data = {}
-        self.training_examples = []
-        
-    def load_data(self):
-        """Load both JSON and CSV data"""
-        print("Loading JSON venue data...")
-        with open(self.json_path, 'r', encoding='utf-8') as f:
-            self.venues_data = json.load(f)
-        
-        print("Loading CSV structured data...")
-        df = pd.read_csv(self.csv_path)
-        self.structured_data = {
-            row['venue_name']: {
-                'category': row['category'],
-                'summary': row['venue_summary']
-            }
-            for _, row in df.iterrows()
-        }
-        
-        print(f"Loaded {len(self.venues_data)} venues from JSON")
-        print(f"Loaded {len(self.structured_data)} venues from CSV")
-    
-    def create_venue_qa_pairs(self, venue: Dict) -> List[Dict]:
-        """Create Q&A pairs for a single venue"""
-        examples = []
-        name = venue['name']
-        
-        # Get structured summary if available
-        summary = ""
-        category = ""
-        if name in self.structured_data:
-            summary = self.structured_data[name]['summary']
-            category = self.structured_data[name]['category']
-        
-        # Basic venue info questions
-        if venue.get('rating'):
-            examples.extend([
-                {
-                    "instruction": f"What's the rating of {name} in Yerevan?",
-                    "input": "",
-                    "output": f"{name} has a rating of {venue['rating']}/5 stars based on {venue.get('total_ratings', 0)} reviews."
-                },
-                {
-                    "instruction": f"Tell me about {name}",
-                    "input": "",
-                    "output": f"{name} is a {category} in Yerevan with a {venue['rating']}/5 star rating. {summary[:200]}..."
-                }
-            ])
-        
-        # Location-based questions
-        if venue.get('address'):
-            examples.extend([
-                {
-                    "instruction": f"Where is {name} located?",
-                    "input": "",
-                    "output": f"{name} is located at {venue['address']}."
-                },
-                {
-                    "instruction": f"What's the address of {name}?",
-                    "input": "",
-                    "output": f"You can find {name} at {venue['address']}."
-                }
-            ])
-        
-        # Category-based questions
-        if category:
-            examples.extend([
-                {
-                    "instruction": f"What type of place is {name}?",
-                    "input": "",
-                    "output": f"{name} is a {category} in Yerevan. {summary[:150]}..."
-                },
-                {
-                    "instruction": f"Is {name} a good {category}?",
-                    "input": "",
-                    "output": f"Yes, {name} is a well-regarded {category} in Yerevan with a {venue.get('rating', 'good')} rating. {summary[:100]}..."
-                }
-            ])
-        
-        # Review-based questions
-        if venue.get('reviews'):
-            good_reviews = [r for r in venue['reviews'] if r['rating'] >= 4]
-            bad_reviews = [r for r in venue['reviews'] if r['rating'] <= 2]
-            
-            if good_reviews:
-                review = random.choice(good_reviews)
-                examples.append({
-                    "instruction": f"What do people say about {name}?",
-                    "input": "",
-                    "output": f"Customers generally have positive things to say about {name}. One recent review mentioned: \"{review['text'][:200]}...\""
-                })
-            
-            if bad_reviews:
-                review = random.choice(bad_reviews)
-                examples.append({
-                    "instruction": f"Are there any complaints about {name}?",
-                    "input": "",
-                    "output": f"Some customers have noted areas for improvement at {name}. One review mentioned: \"{review['text'][:200]}...\""
-                })
-        
-        # Phone and contact info
-        if venue.get('phone_number'):
-            examples.append({
-                "instruction": f"How can I contact {name}?",
-                "input": "",
-                "output": f"You can contact {name} at {venue['phone_number']}."
-            })
-        
-        if venue.get('website'):
-            examples.append({
-                "instruction": f"Does {name} have a website?",
-                "input": "",
-                "output": f"Yes, you can visit {name}'s website at {venue['website']}"
-            })
-        
-        return examples
-    
-    def create_general_queries(self) -> List[Dict]:
-        """Create general Yerevan venue queries"""
-        examples = []
-        
-        # Category-based recommendations
-        categories = set(self.structured_data[venue]['category'] for venue in self.structured_data)
-        
-        for category in categories:
-            venues_in_category = [
-                name for name, data in self.structured_data.items() 
-                if data['category'] == category
-            ]
-            
-            if len(venues_in_category) >= 3:
-                top_venues = random.sample(venues_in_category, min(3, len(venues_in_category)))
-                examples.extend([
-                    {
-                        "instruction": f"Recommend good {category}s in Yerevan",
-                        "input": "",
-                        "output": f"Here are some excellent {category}s in Yerevan: {', '.join(top_venues)}. Each offers unique experiences and high-quality service."
-                    },
-                    {
-                        "instruction": f"Where can I find a good {category} in Yerevan?",
-                        "input": "",
-                        "output": f"I'd recommend checking out {top_venues[0]} or {top_venues[1]}. Both are popular {category}s with great reviews."
-                    }
-                ])
-        
-        # Location-based queries
-        streets = set()
-        for venue in self.venues_data:
-            if venue.get('address'):
-                # Extract street names
-                address = venue['address']
-                if 'Mashtots' in address:
-                    streets.add('Mashtots Avenue')
-                elif 'Abovyan' in address:
-                    streets.add('Abovyan Street')
-                elif 'Northern' in address:
-                    streets.add('Northern Avenue')
-        
-        for street in list(streets)[:5]:  # Limit to top 5 streets
-            street_venues = [
-                venue['name'] for venue in self.venues_data 
-                if venue.get('address') and street.split()[0] in venue['address']
-            ][:3]
-            
-            if street_venues:
-                examples.append({
-                    "instruction": f"What venues are on {street}?",
-                    "input": "",
-                    "output": f"On {street}, you can find several great venues including {', '.join(street_venues)}."
-                })
-        
-        # General conversation
-        examples.extend([
-            {
-                "instruction": "Hello, can you help me find venues in Yerevan?",
-                "input": "",
-                "output": "Hello! I'd be happy to help you discover the best venues in Yerevan. I know about restaurants, bars, cafes, clubs, and more. What type of place are you looking for?"
-            },
-            {
-                "instruction": "What do you know about Yerevan venues?",
-                "input": "",
-                "output": "I'm specialized in Yerevan's venue scene! I have detailed knowledge about hundreds of restaurants, bars, cafes, clubs, and other establishments across the city, including their locations, ratings, reviews, and what makes each special."
-            },
-            {
-                "instruction": "I'm visiting Yerevan, where should I go?",
-                "input": "",
-                "output": "Welcome to Yerevan! The city has amazing venues to explore. For dining, try some local restaurants. For nightlife, there are great bars and clubs. What type of experience are you looking for?"
-            }
-        ])
-        
-        return examples
-    
-    def create_armenian_examples(self) -> List[Dict]:
-        """Create Armenian language examples"""
-        examples = []
-        
-        # Sample Armenian queries
-        armenian_examples = [
-            {
-                "instruction": "Բարև, կարող ես օգնել գտնել լավ ռեստորան Երևանում?",
-                "input": "",
-                "output": "Բարև ձեզ! Իհարկե կարող եմ օգնել: Երևանում շատ լավ ռեստորաններ կան: Ինչ տեսակի ճաշարան եք փնտրում?"
-            },
-            {
-                "instruction": "Որտեղ կարող եմ գտնել լավ բար Երևանում?",
-                "input": "",
-                "output": "Երևանում շատ հիանալի բարեր կան: Կարող եմ առաջարկել մի քանիսը՝ կախված ձեր նախապատվություններից:"
-            },
-            {
-                "instruction": "Ինչ սրճարաններ կան Մաշտոցի մոտ?",
-                "input": "",
-                "output": "Մաշտոցի պողոտայի մոտ մի քանի հիանալի սրճարաններ կան: Կարող եմ խորհուրդ տալ լավագույններից մի քանիսը:"
-            }
-        ]
-        
-        return armenian_examples
-    
-    def generate_dataset(self) -> List[Dict]:
-        """Generate complete fine-tuning dataset"""
-        print("Creating venue-specific Q&A pairs...")
-        
-        # Process each venue
-        for i, venue in enumerate(self.venues_data):
-            if i % 100 == 0:
-                print(f"Processed {i}/{len(self.venues_data)} venues...")
-            
-            venue_examples = self.create_venue_qa_pairs(venue)
-            self.training_examples.extend(venue_examples)
-        
-        print("Creating general queries...")
-        general_examples = self.create_general_queries()
-        self.training_examples.extend(general_examples)
-        
-        print("Creating Armenian examples...")
-        armenian_examples = self.create_armenian_examples()
-        self.training_examples.extend(armenian_examples)
-        
-        print(f"Generated {len(self.training_examples)} training examples")
-        return self.training_examples
-    
-    def save_dataset(self, output_path: str):
-        """Save dataset in format suitable for fine-tuning"""
-        print(f"Saving dataset to {output_path}...")
-        
-        with open(output_path, 'w', encoding='utf-8') as f:
-            json.dump(self.training_examples, f, ensure_ascii=False, indent=2)
-        
-        print(f"Dataset saved with {len(self.training_examples)} examples")
-    
-    def save_alpaca_format(self, output_path: str):
-        """Save in Alpaca instruction format for easier fine-tuning"""
-        alpaca_data = []
-        
-        for example in self.training_examples:
-            alpaca_data.append({
-                "instruction": example["instruction"],
-                "input": example["input"],
-                "output": example["output"]
-            })
-        
-        with open(output_path, 'w', encoding='utf-8') as f:
-            json.dump(alpaca_data, f, ensure_ascii=False, indent=2)
-        
-        print(f"Alpaca format dataset saved to {output_path}")
-
-def main():
-    # Create dataset
-    creator = YerevanVenueDatasetCreator(
-        json_path="yerevan_pubs_bars_20250623_193205.json",
-        csv_path="yerevan_venues_structured.csv"
-    )
-    
-    creator.load_data()
-    dataset = creator.generate_dataset()
-    
-    # Save in multiple formats
-    creator.save_dataset("yerevan_venues_finetune_dataset.json")
-    creator.save_alpaca_format("yerevan_venues_alpaca_format.json")
-    
-    # Print statistics
-    print("\n=== Dataset Statistics ===")
-    print(f"Total training examples: {len(dataset)}")
-    
-    # Count by type
-    venue_specific = sum(1 for ex in dataset if any(venue['name'] in ex['instruction'] for venue in creator.venues_data))
-    general = len(dataset) - venue_specific
-    
-    print(f"Venue-specific examples: {venue_specific}")
-    print(f"General examples: {general}")
-    
-    # Sample examples
-    print("\n=== Sample Examples ===")
-    for i, example in enumerate(random.sample(dataset, 3)):
-        print(f"\n{i+1}. Q: {example['instruction']}")
-        print(f"   A: {example['output'][:150]}...")
-
-if __name__ == "__main__":
-    main() 

training/yerevan-tinyllama-finetuned/README.md

@@ -1,202 +0,0 @@
----
-base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
-library_name: peft
----
-
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
-
-
-
-## Model Details
-
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
-### Framework versions
-
-- PEFT 0.15.2

training/yerevan-tinyllama-finetuned/checkpoint-492/README.md

@@ -1,202 +0,0 @@
----
-base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
-library_name: peft
----
-
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
-
-
-
-## Model Details
-
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
-### Framework versions
-
-- PEFT 0.15.2

training/yerevan-tinyllama-finetuned/checkpoint-492/adapter_config.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a581efab12deff78fa12de8e0433cbe1acb9cb872bf26574673ac90fed1bc296
-size 817

training/yerevan-tinyllama-finetuned/checkpoint-492/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cfad5ab9307d7ed313906071371ce655f8fc6dbbc8333b983a0e0fde4c790942
-size 18045856

training/yerevan-tinyllama-finetuned/checkpoint-492/chat_template.jinja

@@ -1,15 +0,0 @@
-{% for message in messages %}
-{% if message['role'] == 'user' %}
-{{ '<|user|>
-' + message['content'] + eos_token }}
-{% elif message['role'] == 'system' %}
-{{ '<|system|>
-' + message['content'] + eos_token }}
-{% elif message['role'] == 'assistant' %}
-{{ '<|assistant|>
-'  + message['content'] + eos_token }}
-{% endif %}
-{% if loop.last and add_generation_prompt %}
-{{ '<|assistant|>' }}
-{% endif %}
-{% endfor %}

training/yerevan-tinyllama-finetuned/checkpoint-492/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1e9340ca40a642bb335c6c806b8dc57ae6cc87663445ec9e92c7d87ab24c10fe
-size 36193099

training/yerevan-tinyllama-finetuned/checkpoint-492/scaler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:edf646a96df16e08f63350c1f1b553952938bc5496d54c93a92e048555f4641d
-size 1383

training/yerevan-tinyllama-finetuned/checkpoint-492/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1754888a680bd157657620ccbd6aa62f939f06ba25f92306cd80f56605c1d549
-size 1465

training/yerevan-tinyllama-finetuned/checkpoint-492/trainer_state.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:51c4ed2eaebdb474f0a588f884dc20b550d34a819c9cff001bbaed81738526ad
-size 2299

training/yerevan-tinyllama-finetuned/checkpoint-492/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a3d047ee82e54e9de01b803882bf5b8b97b6755d24a2b032074991d91d73a6a0
-size 5713

training/yerevan-tinyllama-finetuned/special_tokens_map.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:82d96d7a9e6ced037f12394b7ea6a5b02e6ca87e0d11edaa8d60d9be857ce7db
-size 551

training/yerevan-tinyllama-finetuned/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b0694d8c7cff1e1d740a484932fcf3e36b80feb3beaa71e751cf7d70cdf2a17b
-size 3619280

training/yerevan-tinyllama-finetuned/tokenizer.model

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
-size 499723

training/yerevan-tinyllama-finetuned/tokenizer_config.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:27c5ddd03dd5e605959d3a0f6d4dcfc238e5475bbde941e8c358f3776ac1221b
-size 951

training/yerevan-tinyllama-finetuned/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a3d047ee82e54e9de01b803882bf5b8b97b6755d24a2b032074991d91d73a6a0
-size 5713

venue_ai_with_finetuned.py

@@ -31,7 +31,7 @@ class YerevanVenueAIWithFinetunedLLM:
     def __init__(self, 
                  venues_json_path: str = 'yerevan_pubs_bars_20250623_193205.json',
                  venues_csv_path: str = 'yerevan_venues_structured.csv',
-                 model_path: str = './training/yerevan-tinyllama-finetuned'):
+                 model_path: str = './model'):
         """Initialize the venue AI system"""
         logger.info("Initialized YerevanVenueAI with fine-tuned LLM capabilities")