Text Generation
Transformers
English
qwen2
code-generation
python
fine-tuning
Qwen
tools
agent-framework
multi-agent
conversational
Eval Results (legacy)
Instructions to use my-ai-stack/Stack-2-9-finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use my-ai-stack/Stack-2-9-finetuned with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="my-ai-stack/Stack-2-9-finetuned") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("my-ai-stack/Stack-2-9-finetuned") model = AutoModelForCausalLM.from_pretrained("my-ai-stack/Stack-2-9-finetuned") 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]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use my-ai-stack/Stack-2-9-finetuned with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "my-ai-stack/Stack-2-9-finetuned" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "my-ai-stack/Stack-2-9-finetuned", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/my-ai-stack/Stack-2-9-finetuned
- SGLang
How to use my-ai-stack/Stack-2-9-finetuned 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 "my-ai-stack/Stack-2-9-finetuned" \ --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": "my-ai-stack/Stack-2-9-finetuned", "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 "my-ai-stack/Stack-2-9-finetuned" \ --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": "my-ai-stack/Stack-2-9-finetuned", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use my-ai-stack/Stack-2-9-finetuned with Docker Model Runner:
docker model run hf.co/my-ai-stack/Stack-2-9-finetuned
File size: 4,102 Bytes
fcb2b04 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 | import time
import os
from voice_client import VoiceClient
from stack_voice_integration import StackWithVoice
# Configuration
STACK_API_URL = "http://localhost:5000"
VOICE_API_URL = "http://localhost:8000"
DEFAULT_VOICE = "default"
# Initialize clients
voice_client = VoiceClient(VOICE_API_URL)
stack_voice = StackWithVoice(STACK_API_URL, VOICE_API_URL)
# Helper function to play audio (placeholder)
def play_audio(audio_data: bytes) -> None:
"""Play audio data (placeholder implementation)"""
output_path = "./output.wav"
voice_client.download_audio(audio_data, output_path)
print(f"Audio saved to {output_path}")
print("To play audio, use: open output.wav (macOS) or your preferred audio player")
# Example 1: Basic voice chat
print("\n=== Example 1: Basic Voice Chat ===")
print("This example simulates a voice conversation with the coding assistant.")
print("In a real implementation, you would provide actual audio files.")
# Create a test prompt audio file (placeholder)
test_prompt = "How do I create a REST API in Python using FastAPI?"
with open("test_prompt.txt", 'w') as f:
f.write(test_prompt)
print(f"\nTest prompt: {test_prompt}")
# Simulate voice chat
print("\nSimulating voice chat...")
response_audio = stack_voice.voice_chat("test_prompt.wav", DEFAULT_VOICE)
if response_audio:
play_audio(response_audio)
print("\nVoice chat completed successfully!")
else:
print("\nVoice chat failed or no response received")
# Example 2: Voice command to code generation
print("\n\n=== Example 2: Voice Command to Code Generation ===")
print("This example shows how to use voice commands to generate code.")
code_command = "Create a Python class for a banking system with account management"
print(f"\nVoice command: {code_command}")
# Simulate voice command
print("\nExecuting voice command...")
command_response = stack_voice.voice_command(code_command, DEFAULT_VOICE)
if command_response:
play_audio(command_response)
print("\nVoice command executed successfully!")
else:
print("\nVoice command failed or no response received")
# Example 3: Streaming voice responses
print("\n\n=== Example 3: Streaming Voice Responses ===")
print("This example demonstrates streaming voice responses.")
streaming_prompt = "Explain how to implement machine learning in Python"
print(f"\nStreaming prompt: {streaming_prompt}")
# Simulate streaming voice chat
print("\nStarting streaming voice chat...")
stack_voice.streaming_voice_chat("test_prompt.wav", DEFAULT_VOICE)
print("\nStreaming voice chat completed!")
# Example 4: Error handling
print("\n\n=== Example 4: Error Handling ===")
print("This example demonstrates error handling in the voice integration.")
# Test with invalid voice name
print("\nTesting with invalid voice name...")
try:
invalid_response = stack_voice.voice_chat("test_prompt.wav", "nonexistent_voice")
if invalid_response:
play_audio(invalid_response)
except Exception as e:
print(f"Error handled correctly: {e}")
# Test with empty prompt
print("\nTesting with empty prompt...")
try:
empty_response = stack_voice.voice_chat("empty_prompt.wav", DEFAULT_VOICE)
if empty_response:
play_audio(empty_response)
except Exception as e:
print(f"Error handled correctly: {e}")
# Example 5: Voice model management
print("\n\n=== Example 5: Voice Model Management ===")
print("This example shows how to manage voice models.")
print("\nListing available voices...")
available_voices = voice_client.list_voices()
print(f"Available voices: {available_voices}")
# Note: Voice cloning requires actual audio files
# print("\nCloning a new voice...")
# clone_result = voice_client.clone_voice("my_audio_sample.wav", "custom_voice")
# print(f"Clone result: {clone_result}")
print("\nAll examples completed!")
print("\n=== Next Steps ===")
print("1. Implement actual speech-to-text for audio_to_text()")
print("2. Integrate with real Stack 2.9 API")
print("3. Add proper audio playback functionality")
print("4. Implement streaming TTS properly")
print("5. Add voice model training with Coqui TTS") |