Upload folder using huggingface_hub

README.md

@@ -58,7 +58,7 @@ The model shows consistent improvement across all checkpoints with no signs of o
 ```python
 from mlx_lm import load, generate
 
-model, tokenizer = load("furukama/LFM2.5-1.2B-Text2SQL-MLX")
+model, tokenizer = load("hybridaione/LFM2.5-1.2B-Text2SQL-MLX")
 
 # Example query
 prompt = '''CREATE TABLE employees (id INT, name VARCHAR, salary DECIMAL);
@@ -69,12 +69,6 @@ response = generate(model, tokenizer, prompt=prompt, max_tokens=256)
 print(response)
 ```
 
-## Limitations
-
-- Trained on synthetic data for a specific database schema
-- Best suited for similar SQL query patterns seen during training
-- May not generalize well to very different database schemas
-
 ## License
 
 This model is released under the Apache 2.0 license, following the base model's license.