Update model card with correct Transformers usage

README.md

@@ -1,50 +1,113 @@
 ---
 license: gemma
+base_model: google/gemma-4-12B-it
+library_name: transformers
 tags:
 - biology
 - bioinformatics
 - genomics
+- computational-biology
 - text-generation
 pipeline_tag: text-generation
 ---
 
 # gemma4-12b-bioinfo
 
-**gemma4-12b-bioinfo** is a state-of-the-art, fine-tuned large language model based on Google's Gemma 4 (12B) architecture. It has been specifically optimized to understand, analyze, and generate text related to complex bioinformatics, genomics, and computational biology.
+`gemma4-12b-bioinfo` is a fine-tuned **Gemma 4 12B instruction model** for bioinformatics, genomics, and computational biology question answering.
 
-## ⚠️ Intended Use & Limitations
+The LoRA adapter was merged into the base model, so this repository is intended for direct use with Hugging Face `transformers`.
 
-**Research Purposes Only:** This model is designed strictly for academic, research, and educational purposes. It is **not** intended to provide medical advice, clinical diagnosis, or treatment recommendations. The outputs of this model should always be verified by qualified domain experts.
+For the optimized local-inference GGUF files, use: [yashm/gemma4-12b-bioinfo-GGUF](https://huggingface.co/yashm/gemma4-12b-bioinfo-GGUF).
+
+## Intended Use
+
+This model is intended for research, education, and computational biology assistance. It is **not** a medical device and should not be used for clinical diagnosis, treatment decisions, or professional medical advice.
 
 ## Model Details
 
-* **Base Architecture:** Gemma 4 (12B)
-* **Language:** English
-* **Format:** `transformers` FP16 / BF16
-* **GGUF Version:** Available at [yashm/gemma4-12b-bioinfo-GGUF](https://huggingface.co/yashm/gemma4-12b-bioinfo-GGUF)
+- **Base model:** `google/gemma-4-12B-it`
+- **Fine-tuning method:** QLoRA / SFT, merged into full model
+- **Domain:** bioinformatics, genomics, transcriptomics, proteomics, sequence analysis, biological databases, and common bioinformatics tools
+- **Primary format:** Hugging Face `transformers`
+- **GGUF format:** available in `yashm/gemma4-12b-bioinfo-GGUF`
 
-## Quick Start Transformers
+## Quick Start: Transformers
+
+Gemma 4 uses `AutoModelForImageTextToText` in this notebook, not `AutoModelForCausalLM`.
 
 ```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+from transformers import AutoTokenizer, AutoModelForImageTextToText
+
+repo_id = "yashm/gemma4-12b-bioinfo"
+
+tokenizer = AutoTokenizer.from_pretrained(
+    repo_id,
+    trust_remote_code=True,
+)
+
+model = AutoModelForImageTextToText.from_pretrained(
+    repo_id,
+    device_map="auto",
+    dtype=torch.bfloat16,
+    attn_implementation="eager",
+    trust_remote_code=True,
+)
+
+system_prompt = (
+    "You are an expert bioinformatics assistant with deep knowledge of "
+    "genomics, proteomics, transcriptomics, sequence analysis, biological "
+    "databases, and bioinformatics tools. Provide accurate, concise, and "
+    "scientifically rigorous answers."
+)
+
+messages = [
+    {"role": "system", "content": system_prompt},
+    {"role": "user", "content": "Explain the difference between local and global sequence alignment."},
+]
 
-tokenizer = AutoTokenizer.from_pretrained("yashm/gemma4-12b-bioinfo")
-model = AutoModelForCausalLM.from_pretrained("yashm/gemma4-12b-bioinfo", device_map="auto")
+prompt = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+)
 
-prompt = "<bos><|turn>user\nExplain the significance of CRISPR-Cas9 in functional genomics.<|turn>model\n"
-inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
-outputs = model.generate(**inputs, max_new_tokens=512)
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+
+with torch.inference_mode():
+    output_ids = model.generate(
+        **inputs,
+        max_new_tokens=512,
+        do_sample=True,
+        temperature=0.2,
+        top_p=0.9,
+        repetition_penalty=1.1,
+        pad_token_id=tokenizer.pad_token_id,
+        eos_token_id=tokenizer.eos_token_id,
+    )
+
+new_tokens = output_ids[0, inputs["input_ids"].shape[-1]:]
+answer = tokenizer.decode(new_tokens, skip_special_tokens=True).strip()
+print(answer)
 ```
 
-## Citation
+## Recommended Generation Settings
+
+- `temperature=0.2` for factual bioinformatics answers
+- `top_p=0.9`
+- `repetition_penalty=1.1`
+- `max_new_tokens=512`
 
-If you use this model in your research, please cite it as follows:
+## Limitations
+
+The model may produce incorrect or incomplete biological interpretations. Always verify outputs against trusted scientific literature, databases, and domain experts.
+
+## Citation
 
 ```bibtex
 @misc{gemma4-12b-bioinfo_2026,
   author       = {yashm},
-  title        = {gemma4-12b-bioinfo: A Fine-Tuned Gemma 4 Model for Bioinformatics},
+  title        = {gemma4-12b-bioinfo: Fine-Tuned Gemma 4 12B for Bioinformatics},
   year         = {2026},
   publisher    = {Hugging Face},
   howpublished = {\url{https://huggingface.co/yashm/gemma4-12b-bioinfo}}