Upload Kalenjin CPT LoRA adapter

README.md

@@ -21,6 +21,16 @@ LoRA adapter from continued pretraining for a Kalenjin-focused language model.
 The adapter was trained on Modal from `Qwen/Qwen2.5-7B` and is intended as the CPT
 checkpoint before later SFT, DPO, and GRPO stages.
 
+## Model Scope
+
+- Base model: `Qwen/Qwen2.5-7B`
+- Method: QLoRA Continued Pretraining
+- Language/domain: Kalenjin-heavy text
+- Adapter only: yes
+- Training objective: causal language modeling
+- Not instruction-tuned yet
+- Not a translator yet
+
 ## Contents
 
 - `adapter/`: PEFT LoRA adapter weights and config