Upload README.md with huggingface_hub

README.md

@@ -23,7 +23,7 @@ model-index:
           name: MTEB STS (English, 10 tasks)
         metrics:
           - type: spearman_cosine
-            value: 70.10
+            value: 71.04
       - task:
           type: Classification
         dataset:
@@ -31,7 +31,7 @@ model-index:
           name: MTEB Classification (English, 12 tasks)
         metrics:
           - type: accuracy
-            value: 59.67
+            value: 59.66
       - task:
           type: PairClassification
         dataset:
@@ -39,7 +39,7 @@ model-index:
           name: MTEB PairClassification (English, 3 tasks)
         metrics:
           - type: ap
-            value: 74.58
+            value: 76.02
 ---
 
 # potion-mxbai-micro
@@ -48,7 +48,7 @@ A **700KB** static embedding model. Yes, really. Seven hundred kilobytes for use
 
 ## Highlights
 
-- **68.12 avg** on full MTEB English (STS + Classification + PairClassification, 25 tasks)
+- **68.91 avg** on full MTEB English (STS + Classification + PairClassification, 25 tasks)
 - **700KB** total model size — fits in an email attachment
 - **256 dimensions** — same output dimensionality as the full model
 - **80-88x faster** than all-MiniLM-L6-v2 on CPU
@@ -69,9 +69,9 @@ The result is a 2,000-row embedding table at 256D with int8 quantization. Tokens
 | Model | STS | Classification | PairClassification | **Avg** | **Size** |
 |-------|-----|----------------|-------------------|---------|----------|
 | [potion-mxbai-2m-512d](https://huggingface.co/blobbybob/potion-mxbai-2m-512d) | 74.15 | 65.44 | 76.80 | **72.13** | ~125MB |
-| [potion-mxbai-256d-v2](https://huggingface.co/blobbybob/potion-mxbai-256d-v2) | 73.33 | 63.36 | 76.25 | **70.98** | 7.5MB |
+| [potion-mxbai-256d-v2](https://huggingface.co/blobbybob/potion-mxbai-256d-v2) | 73.79 | 63.23 | 77.33 | **71.45** | 7.5MB |
 | [potion-mxbai-128d-v2](https://huggingface.co/blobbybob/potion-mxbai-128d-v2) | 72.56 | 61.48 | 75.45 | **69.83** | 3.9MB |
-| **potion-mxbai-micro** (this) | 70.10 | 59.67 | 74.58 | **68.12** | **0.7MB** |
+| **potion-mxbai-micro** (this) | 71.04 | 59.66 | 76.02 | **68.91** | **0.7MB** |
 
 Evaluated on 25 tasks (10 STS, 12 Classification, 3 PairClassification), English subsets only.
 
@@ -108,7 +108,7 @@ embeddings = model.encode(["Hello world", "Static embeddings are fast"])
 | [potion-mxbai-2m-512d](https://huggingface.co/blobbybob/potion-mxbai-2m-512d) | 72.13 | ~125MB | Maximum quality |
 | [potion-mxbai-256d-v2](https://huggingface.co/blobbybob/potion-mxbai-256d-v2) | 70.98 | 7.5MB | Best quality/size balance |
 | [potion-mxbai-128d-v2](https://huggingface.co/blobbybob/potion-mxbai-128d-v2) | 69.83 | 3.9MB | Compact deployments |
-| **potion-mxbai-micro** | **68.12** | **0.7MB** | Ultra-tiny / embedded |
+| **potion-mxbai-micro** | **68.91** | **0.7MB** | Ultra-tiny / embedded |
 
 ## Citation