⚒️ ForgeLLM — LLM Fine-Tuning & Inference Platform

Live inference, evaluation, and telemetry demonstration powered by Qwen/Qwen2.5-1.5B-Instruct on Hugging Face ZeroGPU.

Chatbot

Examples

📊 Live Inference Telemetry

Status

TTFT

Total Latency

Output Tokens

End-to-End Throughput

⚙️ Runtime Specifications

Model

Runtime Backend

Precision

💡 Experimental demo model. Technical responses may require verification.