Update README.md

README.md

@@ -248,7 +248,7 @@ def chunk_text_with_max_chunk_size(model, text, tokenizer, prob_threshold=0.5,ma
         best_logits = torch.finfo(torch.float32).min 
         is_chunk_start = True
         
-        STEP = (MAX_TOKENS - 2)//2 
+        STEP = round(((MAX_TOKENS - 2)//2 )*1.75) #(MAX_TOKENS - 2)//2
         print(f"Processing {input_ids.shape[1]} tokens...")
         while windows_end <= input_ids.shape[1]:
             
@@ -428,8 +428,8 @@ Evaluation is done by code from [brandonstarxel/chunking_evaluation](https://git
  Cluster	 | 400 (~182) | 	0	 | 91.3 ± 25.4	 | 4.5 ± 3.4 | 	20.7 ± 14.5	 | 4.5 ± 3.4 | O(N<sup>2</sup>)| No
  Cluster	 | 200 (~103) | 	0	 | 87.3 ± 29.8	 | **8.0 ± 6.0**	 | **34.0 ± 19.7**	 | **8.0 ± 6.0** | O(N<sup>2</sup>)| No
  LLM (GPT4o) | 	N/A (~240)	 | 0	 | **91.9 ± 26.5**	 | 3.9 ± 3.2	 | 19.9 ± 16.3 | 	3.9 ± 3.2 | O(N<sup>2</sup>)| No
-★ bert-chunker-3 (experimental, prob_threshold=0.50543) | <= 400 | 0 | 91.2 ± 26.6 | 5.3 ± 4.5 | 23.2 ± 18.1 | 5.3 ± 4.5 |**O(N)** | **Yes**
-★ bert-chunker-3 (experimental, prob_threshold=0.50543) | <= 200 | 0 | 90.5 ± 27.3 | 7.1 ± 5.5 | 29.3 ± 19.0 | 7.1 ± 5.4 |**O(N)**| **Yes**
+★ bert-chunker-3 (experimental, prob_threshold=0.50543) | <= 400 | 0 | 91.3 ± 26.6 | 5.4 ± 4.7 | 23.1 ± 17.6 | 5.4 ± 4.7 |**O(N)** | **Yes**
+★ bert-chunker-3 (experimental, prob_threshold=0.50543) | <= 200 | 0 | 87.9 ± 30.4 | 7.6 ± 6.0 | 30.9 ± 19.1 | 7.5 ± 5.8 |**O(N)**| **Yes**
 ★ bert-chunker-3 (prob_threshold=0.50543) | N/A | 0 | 90.4 ± 28.7 | 3.3 ± 3.1 | 16.0 ± 17.0 | 3.3 ± 3.1 |**O(N)**| No
 ## Citation
 ```bibtex