Update README.md

README.md

@@ -19,7 +19,7 @@ pipeline_tag: text-classification
 
 GLiClass is an efficient zero-shot sequence classification model designed to achieve SoTA performance while being much faster than cross-encoders and LLMs, while preserving strong generalization capabilities.
 
-The model supports text classification with any labels and can be used for the following tasks:
+The model supports text classification with any labels and can be used for **the following tasks:**
 * Topic Classification
 * Sentiment Analysis
 * Intent Classification
@@ -38,17 +38,6 @@ The model supports text classification with any labels and can be used for the f
 
 See the [GLiClass library README](https://github.com/Knowledgator/GLiClass) for full details on these features.
 
-## GLiClass-V3 Models
-
-| Model | Size | Params | Avg Benchmark | Inference Speed (batch=1, A6000, ex/s) |
-|-------|------|--------|---------------|----------------------------------------|
-| [gliclass‑edge‑v3.0](https://huggingface.co/knowledgator/gliclass-edge-v3.0) | 131 MB | 32.7M | 0.4873 | 97.29 |
-| [gliclass‑modern‑base‑v3.0](https://huggingface.co/knowledgator/gliclass-modern-base-v3.0) | 606 MB | 151M | 0.5571 | 54.46 |
-| [gliclass‑modern‑large‑v3.0](https://huggingface.co/knowledgator/gliclass-modern-large-v3.0) | 1.6 GB | 399M | 0.6082 | 43.80 |
-| [gliclass‑base‑v3.0](https://huggingface.co/knowledgator/gliclass-base-v3.0) | 746 MB | 187M | 0.6556 | 51.61 |
-| [gliclass‑large‑v3.0](https://huggingface.co/knowledgator/gliclass-large-v3.0) | 1.75 GB | 439M | 0.7001 | 25.22 |
-
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/6405f62ba577649430be5124/MvfWyOdG824KWWB4Hy-dG.png)
 
 ## Installation
 
@@ -234,6 +223,28 @@ for r in results:
 
 F1 scores on zero-shot text classification (no fine-tuning on these datasets):
 
+GLiClass-V1 Multitask:
+
+| Dataset | [large‑v1.0](https://huggingface.co/knowledgator/gliclass-large-v1.0) | [base‑v1.0](https://huggingface.co/knowledgator/gliclass-base-v1.0) | [edge‑v1.0](https://huggingface.co/knowledgator/gliclass-edge-v1.0) |
+|---|---|---|---|
+| CR | 0.9066 | 0.8922 | 0.7661 |
+| sst2 | 0.9154 | 0.9198 | 0.6404 |
+| sst5 | 0.3387 | 0.2266 | 0.2372 |
+| 20_newsgroups | 0.5577 | 0.5189 | 0.2914 |
+| spam | 0.9790 | 0.9380 | 0.6692 |
+| financial_phrasebank | 0.8289 | 0.5217 | 0.3961 |
+| imdb | 0.9397 | 0.9364 | 0.8053 |
+| ag_news | 0.7521 | 0.6978 | 0.6202 |
+| emotion | 0.4473 | 0.4454 | 0.2686 |
+| cap_sotu | 0.4327 | 0.4579 | 0.2552 |
+| rotten_tomatoes | 0.8491 | 0.8458 | 0.4507 |
+| massive | 0.5824 | 0.4757 | 0.2360 |
+| banking | 0.6987 | 0.6072 | 0.4696 |
+| snips | 0.8509 | 0.6515 | 0.5369 |
+| **AVERAGE** | **0.7199** | **0.6525** | **0.4745** |
+
+GLiClass-V3:
+
 | Dataset | [large‑v3.0](https://huggingface.co/knowledgator/gliclass-large-v3.0) | [base‑v3.0](https://huggingface.co/knowledgator/gliclass-base-v3.0) | [modern‑large‑v3.0](https://huggingface.co/knowledgator/gliclass-modern-large-v3.0) | [modern‑base‑v3.0](https://huggingface.co/knowledgator/gliclass-modern-base-v3.0) | [edge‑v3.0](https://huggingface.co/knowledgator/gliclass-edge-v3.0) |
 |---|---|---|---|---|---|
 | CR | 0.9398 | 0.9127 | 0.8952 | 0.8902 | 0.8215 |