Update README.md

README.md

@@ -21,13 +21,12 @@ license: mit
 
 # gemma-300m-electrical-electronics-ir_q4_k_m
 
-<p align="center"><img src="https://huggingface.co/disham993/gemma-300m-electrical-electronics-ir_fp16/resolve/main/poster.png" width="340"/></p>
-
-
 ## Model Description
 
 This model is the **GGUF q4_k_m (4-bit K-quant) variant** of the `gemma-300m-electrical-electronics-ir` family, fine-tuned from [`unsloth/embeddinggemma-300m`](https://huggingface.co/unsloth/embeddinggemma-300m) for dense Information Retrieval (IR) in the electrical and electronics engineering domain. This is the **recommended production build** — it is ~4× smaller than the f16 GGUF (~236 MB), runs on a laptop CPU without a GPU, and loses only 0.0008 MAP@100 points versus the full-precision f16 variant.
 
+<p align="center"><img src="https://huggingface.co/disham993/gemma-300m-electrical-electronics-ir_fp16/resolve/main/poster.png" width="340"/></p>
+
 ## Training Data
 
 The model was trained on the [`disham993/ElectricalElectronicsIR`](https://huggingface.co/datasets/disham993/ElectricalElectronicsIR) dataset — 20,000 question-passage pairs covering electrical engineering, electronics, power systems, and communications.
@@ -73,7 +72,7 @@ Evaluated on the held-out test split (2,000 queries) of `disham993/ElectricalEle
 
 | Model | MAP@100 | NDCG@10 | MRR@10 | Recall@10 |
 |---|---|---|---|---|
-| `google/embeddinggemma-300m` (baseline) | 0.5753 | 0.6221 | 0.5682 | 0.7925 |
+| `unsloth/embeddinggemma-300m` (baseline) | 0.5753 | 0.6221 | 0.5682 | 0.7925 |
 | `gemma-300m-electrical-electronics-ir_lora` | 0.9795 | 0.9847 | 0.9795 | 1.0000 |
 | `gemma-300m-electrical-electronics-ir_fp16` | 0.9797 | 0.9849 | 0.9797 | 1.0000 |
 | `gemma-300m-electrical-electronics-ir_f16` | 0.9849 | 0.9887 | 0.9849 | 0.9995 |
@@ -208,22 +207,6 @@ For the complete fine-tuning and evaluation pipeline — from data loading to GG
 
 ## Citation
 
-### EmbeddingGemma base model
-
-```bibtex
-@misc{schechter2025embeddinggemma,
-  title        = {EmbeddingGemma: Powerful and Lightweight Text Representations},
-  author       = {Henrique Schechter Vera},
-  year         = {2025},
-  eprint       = {2509.20354},
-  archivePrefix = {arXiv},
-  primaryClass = {cs.CL},
-  url          = {https://arxiv.org/abs/2509.20354},
-}
-```
-
-### Fine-tuned model
-
 ```bibtex
 @misc{gemma-300m-electrical-electronics-ir,
   author       = {disham993},