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: 3,541 Bytes
bfc7d04 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 | // Voice Integration Example - Demonstrates voice tools with Stack 2.9
//
// This example shows how to:
// 1. Initialize the voice client
// 2. Clone a voice from audio sample
// 3. Record voice commands
// 4. Synthesize speech responses
import {
initVoiceClient,
VoiceRecordingTool,
VoiceSynthesisTool,
VoiceCloneTool,
VoiceStatusTool,
} from '../voice/index.js'
import { log } from '../utils/logger.js'
/**
* Example: Initialize voice client and check status
*/
async function checkVoiceStatus() {
log('Checking voice service status...')
// Initialize client (or use environment variables)
const client = initVoiceClient({
apiUrl: process.env.VOICE_API_URL ?? 'http://localhost:8000',
})
const statusTool = new VoiceStatusTool()
const result = await statusTool.execute()
log('Voice status:', result)
return result
}
/**
* Example: Clone a voice from audio sample
*/
async function cloneVoiceExample() {
log('Cloning voice from sample...')
const client = initVoiceClient({
apiUrl: process.env.VOICE_API_URL ?? 'http://localhost:8000',
})
const cloneTool = new VoiceCloneTool()
const result = await cloneTool.execute({
voiceName: 'my_voice',
audioPath: './audio_samples/my_voice.wav',
})
log('Clone result:', result)
return result
}
/**
* Example: Record voice command
*/
async function recordVoiceCommand() {
log('Starting voice recording...')
const recordingTool = new VoiceRecordingTool()
// Record with max 30 second duration
const result = await recordingTool.execute({ maxDuration: 30000 })
if (result.success) {
const data = result.data as { duration?: number; sampleRate?: number } | undefined
log('Recording captured:', {
duration: data?.duration,
sampleRate: data?.sampleRate,
})
} else {
log('Recording failed:', result.error)
}
return result
}
/**
* Example: Synthesize speech response
*/
async function synthesizeResponse(text: string) {
log(`Synthesizing: "${text}"`)
const client = initVoiceClient({
apiUrl: process.env.VOICE_API_URL ?? 'http://localhost:8000',
})
const synthTool = new VoiceSynthesisTool()
const result = await synthTool.execute({
text,
voiceName: 'my_voice',
})
if (result.success) {
log('Audio generated successfully')
} else {
log('Synthesis failed:', result.error)
}
return result
}
/**
* Example: Complete voice conversation workflow
*/
async function voiceConversation() {
// 1. Check status
await checkVoiceStatus()
// 2. Record user's voice command
const recording = await recordVoiceCommand()
if (!recording.success) {
log('Cannot proceed without voice input')
return
}
// 3. In real implementation, send audio to STT service
// const text = await transcribe(recording.data.audio)
// 4. Process with Stack 2.9 (simulated)
const responseText = 'I have analyzed your code and found 3 potential improvements.'
// 5. Synthesize response
await synthesizeResponse(responseText)
}
// Run examples if this is the main module
if (import.meta.url === `file://${process.argv[1]}`) {
log('Running voice integration examples...')
// Check status
await checkVoiceStatus()
// Uncomment to run other examples:
// await cloneVoiceExample()
// await recordVoiceCommand()
// await synthesizeResponse('Hello, this is a test response.')
// await voiceConversation()
}
export default {
checkVoiceStatus,
cloneVoiceExample,
recordVoiceCommand,
synthesizeResponse,
voiceConversation,
} |