Update README.md

README.md

@@ -24,14 +24,14 @@ This model represents the beginning of a deliberate, long-term effort to build A
 
 ## Overview
 
-EnigmaCoder 2B is a fine-tuned language model built on **Google Gemma-4-2B-IT**, specialized for software engineering tasks including code generation, explanation, debugging, and reasoning.
+EnigmaCoder 2B is a fine-tuned language model built on **Google Gemma-4-E2B-IT**, specialized for software engineering tasks including code generation, explanation, debugging, and reasoning.
 
 Rather than relying entirely on external AI providers, EnigmaCoder is developing its own model stack. EnigmaCoder 2B is the foundation of that effort — a model we own, control, and will continue to develop as part of our broader AI engineering architecture.
 
 | Property | Value |
 |---|---|
 | **Base Model** | google/gemma-4-e2b-it |
-| **Parameters** | ~5B |
+| **Parameters** | ~2B |
 | **Architecture** | Gemma-4 Transformer |
 | **Precision** | Float16 |
 | **Context Window** | 128K tokens |
@@ -88,7 +88,7 @@ EnigmaCoder 2B is not a prototype. It is the first iteration of an ongoing devel
 
 EnigmaCoder 2B was developed through the following process:
 
-- **Base:** Google Gemma-4-2B-IT — a capable instruction-tuned foundation
+- **Base:** Google Gemma-4-E2B-IT — a capable instruction-tuned foundation
 - **Fine-tuning method:** QLoRA with 4-bit quantization during training, merged to full Float16 weights for inference
 - **Training data:** Curated conversational coding and reasoning data focused on software engineering tasks
 - **LoRA configuration:** Rank 32, Alpha 64, targeting all linear layers
@@ -124,7 +124,10 @@ def ask(question):
             repetition_penalty=1.2,
             pad_token_id=tokenizer.eos_token_id,
         )
-    return tokenizer.decode(output[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)
+    return tokenizer.decode(
+        output[0][inputs["input_ids"].shape[1]:],
+        skip_special_tokens=True
+    )
 
 print(ask("Write a Python function that implements binary search with proper error handling."))
 ```
@@ -165,7 +168,7 @@ EnigmaCoder 2B is intended for software engineering assistance. Users should:
 
 - Review generated code before deploying it to production
 - Not rely on the model for security-critical decisions without human verification
-- Be aware that the model may produce incorrect code or reasoning, particularly on complex or novel problems
+- Be aware that the model may produce incorrect code or reasoning on complex or novel problems
 
 This model is subject to the [Gemma Terms of Use](https://ai.google.dev/gemma/terms).
 
@@ -173,7 +176,7 @@ This model is subject to the [Gemma Terms of Use](https://ai.google.dev/gemma/te
 
 ## Acknowledgements and License
 
-EnigmaCoder 2B is built on **Google Gemma-4-2B-IT** and is subject to the [Gemma License](https://ai.google.dev/gemma/terms).
+EnigmaCoder 2B is built on **Google Gemma-4-E2B-IT** and is subject to the [Gemma License](https://ai.google.dev/gemma/terms).
 
 Training data includes publicly available instruction-following datasets curated for software engineering relevance.