alanzhuly commited on
Commit
0d89662
·
verified ·
1 Parent(s): 065ae6f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -33,7 +33,6 @@ There is a 6x8 rectangular chocolate bar made up of small 1x1 bits. We want to b
33
 
34
  Right Answer: 47
35
 
36
-
37
  <div align="center">
38
  <img src="https://cdn-uploads.huggingface.co/production/uploads/6618e0424dbef6bd3c72f89a/mdE1TuQcVBV5d2LxG99af.png" width="80%" alt="Example" />
39
  </div>
@@ -45,9 +44,10 @@ The benchmarks show that NexaQuant’s 4-bit model preserves the reasoning capac
45
  **Reasoning Capacity:**
46
 
47
  <div align="center">
48
- <img src="https://cdn-uploads.huggingface.co/production/uploads/66abfd6f65beb23afa427d8a/Cyh1zVvDHNBT598IkLHkd.png" width="80%" alt="Example" />
49
  </div>
50
 
 
51
  **General Capacity:**
52
 
53
  | Benchmark | Full 16-bit | llama.cpp (4-bit) | NexaQuant (4-bit)|
 
33
 
34
  Right Answer: 47
35
 
 
36
  <div align="center">
37
  <img src="https://cdn-uploads.huggingface.co/production/uploads/6618e0424dbef6bd3c72f89a/mdE1TuQcVBV5d2LxG99af.png" width="80%" alt="Example" />
38
  </div>
 
44
  **Reasoning Capacity:**
45
 
46
  <div align="center">
47
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/6618e0424dbef6bd3c72f89a/QPT6j3O3WZvcdSKM3yVrV.png" width="80%" alt="Example" />
48
  </div>
49
 
50
+
51
  **General Capacity:**
52
 
53
  | Benchmark | Full 16-bit | llama.cpp (4-bit) | NexaQuant (4-bit)|