changed image width

README.md

@@ -31,10 +31,10 @@ SPLADE models are a fine balance between retrieval effectiveness (quality) and r
 **TL;DR of Our attempt & results**
 1. FLOPS tuning: Seperate **Seq lens and Severely restrictive token budget** doc(128) & query(24) NOT 256 unlike Official SPLADE++. Inspired from **SparseEmbed** (instead of 2 models for query & doc).
 3. Init Weights: **MLM adapted on MS MARCO corpus**.
-4. Achieves a modest yet competitive effectiveness **MRR@10 37.22** in ID data (& OOD) and a retrieval latency of - **47.27ms**. (multi-threaded) all On **mono-GPU** with **only 5 negatives per query**.
+4. Achieves a modest yet competitive effectiveness **MRR@10 37.22** in ID data (& OOD) and a retrieval latency of - **47.27ms**. (multi-threaded) all On **Consumer grade-GPUs** with **only 5 negatives per query**.
 4. For Industry setting: Effectiveness on custom domains needs more than just **Trading FLOPS for tiny gains** and The Premise "SPLADE++ are not well suited to mono-cpu retrieval" does not hold.
 
-<img src="./ID.png" width=550 height=450/>
+<img src="./ID.png" width=650 height=500/>
 
 *Note: The paper refers to the best performing models as SPLADE++, hence for consistency we are reusing the same.*