Echo-DSRN-v0.1.3-Intent-CLF-PEFT

Model Card for ethicalabs/Echo-DSRN-v0.1.3-Intent-CLF-PEFT

[!WARNING] This repository contains experimental models designed strictly for academic evaluation and research purposes.

Critical Constraints:

• No Production Deployment: Experimental models must not be deployed in commercial, enterprise, or mission-critical environments under any circumstances.
• No Liability: Experimental models are provided "as-is" without warranties of any kind. The developers assume zero liability for downstream consequences, system integration failures, or regulatory non-compliance resulting from unauthorized deployment.

The merged intent classification model is now available at ethicalabs/Echo-DSRN-v0.1.3-Intent-CLF, featuring a fully integrated and fine-tuned sequence classification head.

Evaluation

⚡ Execution Statistics

• Evaluation Time: 367.42 seconds (6.12 minutes)
• Total Samples Evaluated: 217531
• Inference Throughput: 592.05 samples/sec
• Batch Size: 256
• Computation Device: CUDA (AMD Radeon AI PRO R9700)

💾 Memory & Resource Metrics

• Peak VRAM Allocated: 7364.24 MB
• VRAM Profile: 331.54 MB (first batch) ➔ 331.65 MB (final batch)
• VRAM Footprint Stability: 99.9675% stable (0.00% KV cache growth)

🚀 Production Deployment Estimates

• Single-GPU Concurrency: ~592.1 concurrent requests/second at peak saturation
• Estimated Class Latency (per request): ~1.69 ms

Framework versions

• PEFT 0.18.0