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
| // Voice API Client - Connects to Python voice server (Coqui TTS) | |
| // | |
| // This client provides TypeScript bindings to the Python FastAPI voice service | |
| // for voice cloning and text-to-speech synthesis. | |
| export interface VoiceConfig { | |
| apiUrl: string | |
| timeout?: number | |
| } | |
| export interface VoiceModel { | |
| name: string | |
| description?: string | |
| } | |
| export interface CloneVoiceRequest { | |
| voiceName: string | |
| audioPath?: string | |
| audioData?: string // base64 encoded audio | |
| } | |
| export interface SynthesizeRequest { | |
| text: string | |
| voiceName: string | |
| language?: string | |
| } | |
| export interface VoiceListResponse { | |
| voices: VoiceModel[] | |
| count: number | |
| } | |
| export interface CloneVoiceResponse { | |
| success: boolean | |
| voiceName: string | |
| message: string | |
| } | |
| export class VoiceApiClient { | |
| private apiUrl: string | |
| private timeout: number | |
| constructor(config: VoiceConfig) { | |
| this.apiUrl = config.apiUrl.replace(/\/$/, '') | |
| this.timeout = config.timeout ?? 30000 | |
| } | |
| /** | |
| * List all available voice models | |
| */ | |
| async listVoices(): Promise<VoiceListResponse> { | |
| const response = await fetch(`${this.apiUrl}/voices`, { | |
| method: 'GET', | |
| headers: { 'Content-Type': 'application/json' }, | |
| signal: AbortSignal.timeout(this.timeout), | |
| }) | |
| if (!response.ok) { | |
| throw new Error(`Failed to list voices: ${response.status} ${response.statusText}`) | |
| } | |
| return response.json() as Promise<VoiceListResponse> | |
| } | |
| /** | |
| * Clone a voice from audio sample(s) | |
| */ | |
| async cloneVoice(request: CloneVoiceRequest): Promise<CloneVoiceResponse> { | |
| const response = await fetch(`${this.apiUrl}/clone`, { | |
| method: 'POST', | |
| headers: { 'Content-Type': 'application/json' }, | |
| body: JSON.stringify(request), | |
| signal: AbortSignal.timeout(this.timeout), | |
| }) | |
| if (!response.ok) { | |
| throw new Error(`Failed to clone voice: ${response.status} ${response.statusText}`) | |
| } | |
| return response.json() as Promise<CloneVoiceResponse> | |
| } | |
| /** | |
| * Synthesize speech with a cloned voice | |
| * Returns audio data as a Blob | |
| */ | |
| async synthesize(request: SynthesizeRequest): Promise<Blob> { | |
| const response = await fetch(`${this.apiUrl}/synthesize`, { | |
| method: 'POST', | |
| headers: { 'Content-Type': 'application/json' }, | |
| body: JSON.stringify(request), | |
| signal: AbortSignal.timeout(this.timeout), | |
| }) | |
| if (!response.ok) { | |
| throw new Error(`Failed to synthesize: ${response.status} ${response.statusText}`) | |
| } | |
| return response.blob() | |
| } | |
| /** | |
| * Stream speech synthesis for real-time applications | |
| */ | |
| async *streamSynthesize(request: SynthesizeRequest): AsyncGenerator<Uint8Array> { | |
| const response = await fetch(`${this.apiUrl}/synthesize_stream`, { | |
| method: 'POST', | |
| headers: { 'Content-Type': 'application/json' }, | |
| body: JSON.stringify(request), | |
| signal: AbortSignal.timeout(this.timeout), | |
| }) | |
| if (!response.ok) { | |
| throw new Error(`Failed to stream synthesize: ${response.status} ${response.statusText}`) | |
| } | |
| if (!response.body) { | |
| throw new Error('Empty response body') | |
| } | |
| const reader = response.body.getReader() | |
| const decoder = new TextDecoder() | |
| try { | |
| while (true) { | |
| const { done, value } = await reader.read() | |
| if (done) break | |
| yield value | |
| } | |
| } finally { | |
| reader.releaseLock() | |
| } | |
| } | |
| /** | |
| * Check if voice server is available | |
| */ | |
| async healthCheck(): Promise<boolean> { | |
| try { | |
| const response = await fetch(`${this.apiUrl}/health`, { | |
| method: 'GET', | |
| signal: AbortSignal.timeout(5000), | |
| }) | |
| return response.ok | |
| } catch { | |
| return false | |
| } | |
| } | |
| } | |
| // Default client instance | |
| let defaultClient: VoiceApiClient | null = null | |
| /** | |
| * Initialize the default voice client | |
| */ | |
| export function initVoiceClient(config: VoiceConfig): VoiceApiClient { | |
| defaultClient = new VoiceApiClient(config) | |
| return defaultClient | |
| } | |
| /** | |
| * Get the default voice client | |
| */ | |
| export function getVoiceClient(): VoiceApiClient | null { | |
| return defaultClient | |
| } |