Update README.md

README.md

@@ -17,7 +17,7 @@ tags:
 ## TL;DR
 
 - 80B-parameter Qwen3 Next Instruct model merged with a domain LoRA adapter for Salesforce analytics, Data Cloud, Commerce, and Order Management workflows.
-- Trained on 102,827 curated instruction/response pairs stored in `finetune_dataset.jsonl` (≈151 MiB) with a fixed system primer _“You are a helpful Salesforce analytics assistant.”_
+- Trained on 102,827 curated instruction/response pairs stored in `finetune_dataset.jsonl` (≈151 MiB).
 - Distributed as merged full weights (bf16) so it can be loaded like any other Transformers causal LM without applying the adapter at runtime.
 
 ## Model Details
@@ -167,7 +167,7 @@ Kindly share scores or qualitative findings back via issues so the card can be u
 
 - **Domain narrowness** – The model was never exposed to open-ended general knowledge tasks; off-domain prompts can hallucinate confidently.
 - **Freshness** – Data reflects the state of Salesforce documentation as of Oct 2025. Features introduced later may be missing or inaccurate.
-- **Compliance** – The dataset embeds Salesforce product language; ensure redistribution complies with your documentation licenses.
+- **Compliance** – The dataset embeds Salesforce language; ensure redistribution complies with your documentation licenses.
 - **Resource requirements** – Running the full bf16 weights requires multi-GPU setups (≥160 GB VRAM) unless you quantize.
 
 ## Responsible Use