Update README.md

README.md

@@ -50,8 +50,8 @@ The model was trained on ~58,000 samples from a mixed dataset:
 
 | Source | Samples | Description |
 |---|---|---|
-| `bigcode/the-stack-smol` (Python) | 20,000 | Real-world Python code from GitHub |
-| `bigcode/the-stack-smol` (JavaScript) | 20,000 | Real-world JavaScript code from GitHub |
+| `bigcode/the-stack` (Python) | 20,000 | Real-world Python code from GitHub |
+| `bigcode/the-stack` (JavaScript) | 20,000 | Real-world JavaScript code from GitHub |
 | `iamtarun/python_code_instructions_18k_alpaca` | 18,000 | Python instruction-response pairs |
 
 ---
@@ -140,17 +140,6 @@ def is_prime(num):
 
 ---
 
-## 🗺️ Roadmap
-
-This is the first release of the kiro model series. Upcoming versions:
-
-- **kiro-1.5-7B-XCode** — larger dataset (500k+ samples), improved benchmarks
-- **kiro-2.0-7B-XCode** — instruction tuning + DPO alignment
-- **kiro-3.0-14B-XCode** — larger base model
-- **ZuKU** — custom architecture trained from scratch (100–200M parameters)
-
----
-
 ## ⚠️ Limitations
 
 - Trained for 1 epoch — may produce repetitions in long outputs (use `repetition_penalty=1.3`)