Retail Bank Agent 9B
This is a research checkpoint for a synthetic retail-bank customer-service
demonstration. It is a merged bf16-lora LoRA adaptation of
spkc83/retail-bank-agent-9b at revision 085df3d089cfadd77424b548542da0390a54a23e. The model has
approximately 8.8 billion parameters and uses the base model's native tagged
JSON tool-call format.
Training
- Dataset:
spkc83/retail-bank-servicing-alignment-sftatfea8aa1cda716954eb7322325e2be25c9f570ea3 - Training records: 6624
- Validation records: 1429
- Tool manifest: nine synthetic retail-banking tools
- Assistant-only target masking: tool-call and final-assistant spans
- Maximum sequence length: 2048
- Optimizer steps: 500
- LoRA rank/alpha: 32/64
- Source commit:
475dc2b563ef87fa0c9aa597b0b0465d56d2ee0f - Chat-template SHA-256:
6727ca16a39df05c41af54eb651aa618b50a29967ad3951a31b90c4e385573fc
The released root checkpoint is merged FP16 weights. The trained BF16 adapter is
also stored under adapter/.
Intended use and limitations
The model is intended only for the linked synthetic banking POC. It must be given the published tool schemas and tool results. It has no access to real banking systems, is not financial advice, and may make incorrect tool choices or unsupported claims. Evaluate tool-call syntax, arguments, backend execution, grounded final responses, OOD behavior, and multi-turn behavior before relying on a revision.
- Downloads last month
- -