YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
base_model: meta-llama/Llama-3.1-8B-Instruct library_name: transformers tags: [customer-support, qlora, fine-tuned]
Llama-3.1-8B Customer Support Auto-Responder
QLoRA fine-tune of Llama-3.1-8B-Instruct on the Bitext customer-support dataset. See training notebook for evaluation results (ROUGE/BLEU/BERTScore/hallucination rate/ escalation correctness vs. baseline).
Not evaluated for production auto-send — designed as a draft-suggestion model with human review, per the escalation/hallucination checks in the training notebook.
- Downloads last month
- 8
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support