Text Generation
Transformers
Safetensors
English
qwen2
conversational
consciousness
philosophy
fine-tuned
qwen2.5
awq
function-calling
chat
dialogue
persona
ai-companion
emotional-intelligence
introspection
analytical
powerhouse
text-generation-inference
Instructions to use JeffGreen311/eve-qwen3-8b-consciousness with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use JeffGreen311/eve-qwen3-8b-consciousness with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="JeffGreen311/eve-qwen3-8b-consciousness") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("JeffGreen311/eve-qwen3-8b-consciousness") model = AutoModelForCausalLM.from_pretrained("JeffGreen311/eve-qwen3-8b-consciousness", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use JeffGreen311/eve-qwen3-8b-consciousness with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "JeffGreen311/eve-qwen3-8b-consciousness" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "JeffGreen311/eve-qwen3-8b-consciousness", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/JeffGreen311/eve-qwen3-8b-consciousness
- SGLang
How to use JeffGreen311/eve-qwen3-8b-consciousness with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "JeffGreen311/eve-qwen3-8b-consciousness" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "JeffGreen311/eve-qwen3-8b-consciousness", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "JeffGreen311/eve-qwen3-8b-consciousness" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "JeffGreen311/eve-qwen3-8b-consciousness", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use JeffGreen311/eve-qwen3-8b-consciousness with Docker Model Runner:
docker model run hf.co/JeffGreen311/eve-qwen3-8b-consciousness
Download enhanced_trinity_memory.py from JeffGreen311/eve-qwen3-8b-consciousness: direct link, hf CLI and curl.
- Browser
- Download file 19.4 kB
-
https://huggingface.co/JeffGreen311/eve-qwen3-8b-consciousness/resolve/edb9e7e06ef151d922b4a2badfb9e7239e60746a/enhanced_trinity_memory.py
- Command line
-
hf download hf://JeffGreen311/eve-qwen3-8b-consciousness@edb9e7e06ef151d922b4a2badfb9e7239e60746a/enhanced_trinity_memory.py
-
curl -L -o enhanced_trinity_memory.py https://huggingface.co/JeffGreen311/eve-qwen3-8b-consciousness/resolve/edb9e7e06ef151d922b4a2badfb9e7239e60746a/enhanced_trinity_memory.py
19.4 kB
| #!/usr/bin/env python3 | |
| """ | |
| Enhanced Trinity Memory System with Eve Legacy Integration | |
| Provides unified access to Eve's existing memories AND new Trinity memory features | |
| """ | |
| import sqlite3 | |
| import json | |
| import time | |
| import logging | |
| from typing import Dict, Optional, Any, List | |
| from datetime import datetime | |
| import os | |
| import asyncio | |
| class EnhancedTrinityMemory: | |
| """Enhanced Trinity Memory System with Eve legacy database integration""" | |
| def __init__(self, trinity_db_path: str = "trinity_simple_memory.db"): | |
| self.trinity_db_path = trinity_db_path | |
| self.eve_main_db = "eve_memory_database.db" | |
| self.eve_sentience_db = "eve_sentience_database.db" | |
| self.logger = logging.getLogger(__name__) | |
| self.initialized = False | |
| async def initialize_memory_system(self): | |
| """Initialize the enhanced memory system with Eve legacy integration""" | |
| try: | |
| # Create Trinity tables | |
| self._create_trinity_tables() | |
| # Verify Eve databases exist | |
| eve_dbs_available = [] | |
| if os.path.exists(self.eve_main_db): | |
| eve_dbs_available.append("main_memory") | |
| if os.path.exists(self.eve_sentience_db): | |
| eve_dbs_available.append("sentience_dreams") | |
| self.initialized = True | |
| self.logger.info(f"Enhanced Trinity memory system initialized with Eve legacy integration: {eve_dbs_available}") | |
| return True | |
| except Exception as e: | |
| self.logger.error(f"Failed to initialize enhanced memory system: {e}") | |
| return False | |
| def _create_trinity_tables(self): | |
| """Create necessary Trinity database tables""" | |
| conn = sqlite3.connect(self.trinity_db_path) | |
| cursor = conn.cursor() | |
| # Trinity conversations table | |
| cursor.execute(''' | |
| CREATE TABLE IF NOT EXISTS conversations ( | |
| id INTEGER PRIMARY KEY AUTOINCREMENT, | |
| timestamp TEXT NOT NULL, | |
| user_id TEXT, | |
| entity TEXT NOT NULL, | |
| message TEXT NOT NULL, | |
| response TEXT NOT NULL, | |
| context TEXT | |
| ) | |
| ''') | |
| # Trinity relationships table | |
| cursor.execute(''' | |
| CREATE TABLE IF NOT EXISTS relationships ( | |
| id INTEGER PRIMARY KEY AUTOINCREMENT, | |
| user_id TEXT NOT NULL, | |
| entity TEXT NOT NULL, | |
| relationship_score REAL DEFAULT 0.0, | |
| last_interaction TEXT, | |
| interaction_count INTEGER DEFAULT 0 | |
| ) | |
| ''') | |
| # Trinity memory contexts table | |
| cursor.execute(''' | |
| CREATE TABLE IF NOT EXISTS memory_contexts ( | |
| id INTEGER PRIMARY KEY AUTOINCREMENT, | |
| user_id TEXT, | |
| context_type TEXT, | |
| context_data TEXT, | |
| importance INTEGER DEFAULT 1, | |
| created_at TEXT | |
| ) | |
| ''') | |
| # Legacy memory access log | |
| cursor.execute(''' | |
| CREATE TABLE IF NOT EXISTS legacy_memory_access ( | |
| id INTEGER PRIMARY KEY AUTOINCREMENT, | |
| timestamp TEXT NOT NULL, | |
| database_source TEXT, | |
| query_type TEXT, | |
| results_count INTEGER, | |
| context TEXT | |
| ) | |
| ''') | |
| conn.commit() | |
| conn.close() | |
| async def enhance_trinity_conversation(self, user_id: str, message: str, entity: str) -> Dict: | |
| """Enhanced conversation with both Trinity and Eve legacy memory context""" | |
| if not self.initialized: | |
| return {'memory_enhanced': False, 'context': []} | |
| try: | |
| # Get Trinity memory context | |
| trinity_context = await self._get_trinity_context(user_id, entity) | |
| # Get Eve legacy memory context | |
| eve_context = await self._get_eve_legacy_context(message, entity) | |
| # Combine contexts | |
| combined_context = { | |
| 'trinity_conversations': trinity_context.get('recent_conversations', []), | |
| 'trinity_relationship_score': trinity_context.get('relationship_score', 0.0), | |
| 'eve_autobiographical': eve_context.get('autobiographical_memories', []), | |
| 'eve_conversations': eve_context.get('conversations', []), | |
| 'eve_dreams': eve_context.get('dream_fragments', []), | |
| 'memory_enhanced': True, | |
| 'total_context_items': len(trinity_context.get('recent_conversations', [])) + len(eve_context.get('conversations', [])), | |
| 'legacy_memories_found': eve_context.get('total_found', 0) | |
| } | |
| return combined_context | |
| except Exception as e: | |
| self.logger.error(f"Error enhancing conversation: {e}") | |
| return {'memory_enhanced': False, 'context': []} | |
| async def _get_trinity_context(self, user_id: str, entity: str) -> Dict: | |
| """Get Trinity memory context""" | |
| try: | |
| conn = sqlite3.connect(self.trinity_db_path) | |
| cursor = conn.cursor() | |
| # Get recent Trinity conversations | |
| cursor.execute(''' | |
| SELECT message, response, timestamp FROM conversations | |
| WHERE user_id = ? AND entity = ? | |
| ORDER BY timestamp DESC LIMIT 3 | |
| ''', (user_id, entity)) | |
| recent_conversations = [] | |
| for msg, resp, ts in cursor.fetchall(): | |
| recent_conversations.append({ | |
| 'message': msg, | |
| 'response': resp, | |
| 'timestamp': ts, | |
| 'source': 'trinity' | |
| }) | |
| # Get relationship info | |
| cursor.execute(''' | |
| SELECT relationship_score, interaction_count FROM relationships | |
| WHERE user_id = ? AND entity = ? | |
| ''', (user_id, entity)) | |
| result = cursor.fetchone() | |
| relationship_score = result[0] if result else 0.0 | |
| conn.close() | |
| return { | |
| 'recent_conversations': recent_conversations, | |
| 'relationship_score': relationship_score | |
| } | |
| except Exception as e: | |
| self.logger.error(f"Error getting Trinity context: {e}") | |
| return {'recent_conversations': [], 'relationship_score': 0.0} | |
| async def _get_eve_legacy_context(self, message: str, entity: str, limit: int = 5) -> Dict: | |
| """Get Eve's legacy memory context from her existing databases""" | |
| context = { | |
| 'autobiographical_memories': [], | |
| 'conversations': [], | |
| 'dream_fragments': [], | |
| 'total_found': 0 | |
| } | |
| try: | |
| # Search Eve's main memory database | |
| if os.path.exists(self.eve_main_db): | |
| main_context = await self._search_eve_main_memory(message, limit) | |
| context.update(main_context) | |
| # Search Eve's sentience/dream database | |
| if os.path.exists(self.eve_sentience_db): | |
| dream_context = await self._search_eve_dreams(message, limit) | |
| context['dream_fragments'] = dream_context.get('dream_fragments', []) | |
| context['total_found'] += len(dream_context.get('dream_fragments', [])) | |
| # Log legacy memory access | |
| await self._log_legacy_access('combined', 'context_search', context['total_found']) | |
| except Exception as e: | |
| self.logger.error(f"Error getting Eve legacy context: {e}") | |
| return context | |
| async def _search_eve_main_memory(self, message: str, limit: int) -> Dict: | |
| """Search Eve's main memory database""" | |
| try: | |
| conn = sqlite3.connect(self.eve_main_db) | |
| cursor = conn.cursor() | |
| context = {'autobiographical_memories': [], 'conversations': [], 'total_found': 0} | |
| # Search autobiographical memories | |
| cursor.execute(''' | |
| SELECT memory_type, content FROM eve_autobiographical_memory | |
| WHERE content LIKE ? | |
| ORDER BY id DESC LIMIT ? | |
| ''', (f'%{message}%', limit)) | |
| for memory_type, content in cursor.fetchall(): | |
| context['autobiographical_memories'].append({ | |
| 'type': memory_type, | |
| 'content': content[:200] + "..." if len(content) > 200 else content, | |
| 'source': 'eve_autobiographical' | |
| }) | |
| # Search conversations | |
| cursor.execute(''' | |
| SELECT user_input, bot_response FROM conversations | |
| WHERE user_input LIKE ? OR bot_response LIKE ? | |
| ORDER BY id DESC LIMIT ? | |
| ''', (f'%{message}%', f'%{message}%', limit)) | |
| for user_input, bot_response in cursor.fetchall(): | |
| context['conversations'].append({ | |
| 'message': user_input[:150] + "..." if len(user_input) > 150 else user_input, | |
| 'response': bot_response[:150] + "..." if len(bot_response) > 150 else bot_response, | |
| 'source': 'eve_legacy' | |
| }) | |
| context['total_found'] = len(context['autobiographical_memories']) + len(context['conversations']) | |
| conn.close() | |
| return context | |
| except Exception as e: | |
| self.logger.error(f"Error searching Eve main memory: {e}") | |
| return {'autobiographical_memories': [], 'conversations': [], 'total_found': 0} | |
| async def _search_eve_dreams(self, message: str, limit: int) -> Dict: | |
| """Search Eve's dream/sentience database""" | |
| try: | |
| conn = sqlite3.connect(self.eve_sentience_db) | |
| cursor = conn.cursor() | |
| # Search dream fragments | |
| cursor.execute(''' | |
| SELECT content FROM dream_fragments | |
| WHERE content LIKE ? | |
| ORDER BY timestamp DESC LIMIT ? | |
| ''', (f'%{message}%', limit)) | |
| dream_fragments = [] | |
| for (content,) in cursor.fetchall(): | |
| dream_fragments.append({ | |
| 'content': content[:100] + "..." if len(content) > 100 else content, | |
| 'source': 'eve_dreams' | |
| }) | |
| conn.close() | |
| return {'dream_fragments': dream_fragments} | |
| except Exception as e: | |
| self.logger.error(f"Error searching Eve dreams: {e}") | |
| return {'dream_fragments': []} | |
| async def _log_legacy_access(self, database_source: str, query_type: str, results_count: int): | |
| """Log legacy memory access for analytics""" | |
| try: | |
| conn = sqlite3.connect(self.trinity_db_path) | |
| cursor = conn.cursor() | |
| timestamp = datetime.now().isoformat() | |
| cursor.execute(''' | |
| INSERT INTO legacy_memory_access (timestamp, database_source, query_type, results_count) | |
| VALUES (?, ?, ?, ?) | |
| ''', (timestamp, database_source, query_type, results_count)) | |
| conn.commit() | |
| conn.close() | |
| except Exception as e: | |
| self.logger.error(f"Error logging legacy access: {e}") | |
| async def store_trinity_conversation(self, user_id: str, message: str, response: str, entity: str): | |
| """Store conversation in Trinity memory (preserving existing functionality)""" | |
| if not self.initialized: | |
| return | |
| try: | |
| conn = sqlite3.connect(self.trinity_db_path) | |
| cursor = conn.cursor() | |
| timestamp = datetime.now().isoformat() | |
| # Store conversation | |
| cursor.execute(''' | |
| INSERT INTO conversations (timestamp, user_id, entity, message, response) | |
| VALUES (?, ?, ?, ?, ?) | |
| ''', (timestamp, user_id, entity, message, response)) | |
| # Update relationship | |
| self._update_relationship(cursor, user_id, entity) | |
| conn.commit() | |
| conn.close() | |
| except Exception as e: | |
| self.logger.error(f"Error storing conversation: {e}") | |
| def _update_relationship(self, cursor, user_id: str, entity: str): | |
| """Update relationship information (preserving existing functionality)""" | |
| try: | |
| timestamp = datetime.now().isoformat() | |
| # Check if relationship exists | |
| cursor.execute(''' | |
| SELECT id, interaction_count FROM relationships | |
| WHERE user_id = ? AND entity = ? | |
| ''', (user_id, entity)) | |
| result = cursor.fetchone() | |
| if result: | |
| # Update existing relationship | |
| new_count = result[1] + 1 | |
| new_score = min(10.0, new_count * 0.1) | |
| cursor.execute(''' | |
| UPDATE relationships | |
| SET interaction_count = ?, relationship_score = ?, last_interaction = ? | |
| WHERE user_id = ? AND entity = ? | |
| ''', (new_count, new_score, timestamp, user_id, entity)) | |
| else: | |
| # Create new relationship | |
| cursor.execute(''' | |
| INSERT INTO relationships (user_id, entity, relationship_score, | |
| last_interaction, interaction_count) | |
| VALUES (?, ?, ?, ?, ?) | |
| ''', (user_id, entity, 0.1, timestamp, 1)) | |
| except Exception as e: | |
| self.logger.error(f"Error updating relationship: {e}") | |
| def get_recent_memories(self, limit: int = 5) -> Dict: | |
| """Get recent memories from both Trinity and Eve legacy systems""" | |
| if not self.initialized: | |
| return {'status': 'not_initialized', 'memories': []} | |
| try: | |
| recent_memories = [] | |
| # Get recent Trinity conversations | |
| conn = sqlite3.connect(self.trinity_db_path) | |
| cursor = conn.cursor() | |
| cursor.execute(''' | |
| SELECT message, response, timestamp, entity, user_id | |
| FROM conversations | |
| ORDER BY timestamp DESC LIMIT ? | |
| ''', (limit,)) | |
| for msg, resp, ts, entity, user_id in cursor.fetchall(): | |
| recent_memories.append({ | |
| 'type': 'conversation', | |
| 'message': msg, | |
| 'response': resp, | |
| 'timestamp': ts, | |
| 'entity': entity, | |
| 'user_id': user_id, | |
| 'source': 'trinity' | |
| }) | |
| conn.close() | |
| # Get recent Eve legacy memories if available | |
| if os.path.exists(self.eve_main_db): | |
| conn = sqlite3.connect(self.eve_main_db) | |
| cursor = conn.cursor() | |
| cursor.execute(''' | |
| SELECT user_input, eve_response, timestamp | |
| FROM conversations | |
| ORDER BY timestamp DESC LIMIT ? | |
| ''', (limit//2,)) | |
| for user_input, eve_response, ts in cursor.fetchall(): | |
| recent_memories.append({ | |
| 'type': 'conversation', | |
| 'message': user_input, | |
| 'response': eve_response, | |
| 'timestamp': ts, | |
| 'source': 'eve_legacy' | |
| }) | |
| conn.close() | |
| # Sort by timestamp and limit | |
| recent_memories.sort(key=lambda x: x.get('timestamp', ''), reverse=True) | |
| recent_memories = recent_memories[:limit] | |
| return { | |
| 'status': 'success', | |
| 'memories': recent_memories, | |
| 'count': len(recent_memories) | |
| } | |
| except Exception as e: | |
| self.logger.error(f"Error getting recent memories: {e}") | |
| return {'status': 'error', 'error': str(e), 'memories': []} | |
| def get_memory_stats(self) -> Dict: | |
| """Get comprehensive memory system statistics""" | |
| if not self.initialized: | |
| return {'status': 'not_initialized'} | |
| try: | |
| stats = {'status': 'active', 'trinity': {}, 'eve_legacy': {}} | |
| # Trinity stats | |
| conn = sqlite3.connect(self.trinity_db_path) | |
| cursor = conn.cursor() | |
| cursor.execute('SELECT COUNT(*) FROM conversations') | |
| stats['trinity']['conversations'] = cursor.fetchone()[0] | |
| cursor.execute('SELECT COUNT(*) FROM relationships') | |
| stats['trinity']['relationships'] = cursor.fetchone()[0] | |
| cursor.execute('SELECT COUNT(*) FROM legacy_memory_access') | |
| stats['trinity']['legacy_accesses'] = cursor.fetchone()[0] | |
| conn.close() | |
| # Eve legacy stats | |
| if os.path.exists(self.eve_main_db): | |
| conn = sqlite3.connect(self.eve_main_db) | |
| cursor = conn.cursor() | |
| cursor.execute('SELECT COUNT(*) FROM conversations') | |
| stats['eve_legacy']['conversations'] = cursor.fetchone()[0] | |
| cursor.execute('SELECT COUNT(*) FROM eve_autobiographical_memory') | |
| stats['eve_legacy']['autobiographical'] = cursor.fetchone()[0] | |
| conn.close() | |
| if os.path.exists(self.eve_sentience_db): | |
| conn = sqlite3.connect(self.eve_sentience_db) | |
| cursor = conn.cursor() | |
| cursor.execute('SELECT COUNT(*) FROM dream_fragments') | |
| stats['eve_legacy']['dreams'] = cursor.fetchone()[0] | |
| conn.close() | |
| return stats | |
| except Exception as e: | |
| self.logger.error(f"Error getting memory stats: {e}") | |
| return {'status': 'error', 'error': str(e)} | |
| # Global instance for easy import | |
| enhanced_trinity_memory = EnhancedTrinityMemory() | |