commit con Fix model card: license field, PEFT quick start

README.md

@@ -8,33 +8,39 @@ tags:
 - sft
 - transformers
 - trl
-licence: license
+license: gemma
 pipeline_tag: text-generation
 ---
 
 # Model Card for gemma4-code-assistant
 
-This model is a fine-tuned version of [google/gemma-4-E2B](https://huggingface.co/google/gemma-4-E2B).
-It has been trained using [TRL](https://github.com/huggingface/trl).
+This model is a fine-tuned version of [google/gemma-4-E2B](https://huggingface.co/google/gemma-4-E2B), specialized for code assistance tasks. It was trained with supervised fine-tuning (SFT) using [TRL](https://github.com/huggingface/trl) and published by [DevNexAI](https://huggingface.co/Devnexai).
 
 ## Quick start
 
-```python
-from transformers import pipeline
+This is a LoRA adapter — load the base model first and apply the adapter on top:
 
-question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="None", device="cuda")
-output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
-print(output["generated_text"])
+```python
+from peft import PeftModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+base = AutoModelForCausalLM.from_pretrained(
+    "google/gemma-4-E2B", device_map="auto"
+)
+model = PeftModel.from_pretrained(base, "Devnexai/gemma4-code-assistant")
+tokenizer = AutoTokenizer.from_pretrained("Devnexai/gemma4-code-assistant")
+
+messages = [{"role": "user", "content": "Write a Python function to check if a string is a palindrome."}]
+inputs = tokenizer.apply_chat_template(
+    messages, add_generation_prompt=True, return_tensors="pt"
+).to(model.device)
+output = model.generate(inputs, max_new_tokens=256)
+print(tokenizer.decode(output[0][inputs.shape[-1]:], skip_special_tokens=True))
 ```
 
 ## Training procedure
 
- 
-
-
-
-This model was trained with SFT.
+This model was trained with SFT (LoRA/PEFT).
 
 ### Framework versions
 
@@ -47,10 +53,6 @@ This model was trained with SFT.
 
 ## Citations
 
-
-
-Cite TRL as:
-    
 ```bibtex
 @software{vonwerra2020trl,
   title   = {{TRL: Transformers Reinforcement Learning}},
@@ -59,4 +61,5 @@ Cite TRL as:
   url     = {https://github.com/huggingface/trl},
   year    = {2020}
 }
+```
 ```