GrowBitLabs
/

tinye5

Feature Extraction

sentence-transformers

text-embeddings

semantic-search

information-retrieval

text-embeddings-inference

Model card Files Files and versions

rizwan3d commited on about 19 hours ago

Commit

d71ca62

·

verified ·

1 Parent(s): 5604e19

Update README.md

Files changed (1) hide show

README.md +0 -2

README.md CHANGED Viewed

@@ -69,7 +69,6 @@ where model size, CPU latency, and deployment efficiency matter.
 | **TinyE5-L6-384 (Safetensors)** |     86.7 MB |         0.8138 |              0.7342 |            0.5897 |
 | **TinyE5-L6-384 (FP32 ONNX)**   |     86.2 MB |         0.8138 |              0.7342 |            0.5897 |
 | **TinyE5-L6-384 (INT8 ONNX)**   | **21.8 MB** |         0.8058 |              0.7599 |            0.6020 |
-| all-MiniLM-L6-v2                |           — |     **0.8194** |          **0.7923** |        **0.6494** |
 ### CPU Inference Performance
@@ -97,7 +96,6 @@ where model size, CPU latency, and deployment efficiency matter.
 | **TinyE5-L6-384 (Safetensors)** |      0.72s |          3.71s |
 | TinyE5-L6-384 (FP32 ONNX)       |      8.82s |        265.58s |
 | TinyE5-L6-384 (INT8 ONNX)       |      5.46s |        179.11s |
-| **all-MiniLM-L6-v2**            |  **0.62s** |      **3.62s** |
 > **Summary:** INT8 quantization reduces TinyE5-L6-384 from **86.2 MB to 21.8 MB (~74.7% smaller)**, lowers CPU inference latency from **2.35 ms/text to 0.77 ms/text (~67.2% lower)**, and increases CPU throughput from **424.7 to 1299.4 texts/s (~3.06× throughput)**. Session RAM also drops from **90.4 MB to 11.2 MB (~87.6% lower)**. STS Spearman decreases slightly from **0.8138 to 0.8058**, while SciFact Recall@10 improves from **0.7342 to 0.7599** and nDCG@10 improves from **0.5897 to 0.6020**. The all-MiniLM-L6-v2 baseline still achieves the highest overall quality, with **0.8194 STS Spearman, 0.7923 Recall@10, and 0.6494 nDCG@10**.

 | **TinyE5-L6-384 (Safetensors)** |     86.7 MB |         0.8138 |              0.7342 |            0.5897 |
 | **TinyE5-L6-384 (FP32 ONNX)**   |     86.2 MB |         0.8138 |              0.7342 |            0.5897 |
 | **TinyE5-L6-384 (INT8 ONNX)**   | **21.8 MB** |         0.8058 |              0.7599 |            0.6020 |
 ### CPU Inference Performance
 | **TinyE5-L6-384 (Safetensors)** |      0.72s |          3.71s |
 | TinyE5-L6-384 (FP32 ONNX)       |      8.82s |        265.58s |
 | TinyE5-L6-384 (INT8 ONNX)       |      5.46s |        179.11s |
 > **Summary:** INT8 quantization reduces TinyE5-L6-384 from **86.2 MB to 21.8 MB (~74.7% smaller)**, lowers CPU inference latency from **2.35 ms/text to 0.77 ms/text (~67.2% lower)**, and increases CPU throughput from **424.7 to 1299.4 texts/s (~3.06× throughput)**. Session RAM also drops from **90.4 MB to 11.2 MB (~87.6% lower)**. STS Spearman decreases slightly from **0.8138 to 0.8058**, while SciFact Recall@10 improves from **0.7342 to 0.7599** and nDCG@10 improves from **0.5897 to 0.6020**. The all-MiniLM-L6-v2 baseline still achieves the highest overall quality, with **0.8194 STS Spearman, 0.7923 Recall@10, and 0.6494 nDCG@10**.