Update README.md

README.md

@@ -5,6 +5,7 @@ tags:
 model-index:
 - name: mpnet-base-fineweb-edu-llama3-annotations-512-vN
   results: []
+inference: False
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -18,17 +19,34 @@ It achieves the following results on the evaluation set:
 - Loss: 0.2105
 - Mse: 0.2105
 
-## Model description
+## Usage 
 
-More information needed
+Note this is for CPU, for GPU you will need to make some (small) changes.
 
-## Intended uses & limitations
+```py
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+
+tokenizer = AutoTokenizer.from_pretrained("pszemraj/mpnet-base-edu-classifier")
+model = AutoModelForSequenceClassification.from_pretrained("pszemraj/mpnet-base-edu-classifier")
 
-More information needed
+text = "This is a test sentence."
+inputs = tokenizer(text, return_tensors="pt", padding="longest", truncation=True)
+outputs = model(**inputs)
+logits = outputs.logits.squeeze(-1).float().detach().numpy()
+score = logits.item()
+result = {
+    "text": text,
+    "score": score,
+    "int_score": int(round(max(0, min(score, 5)))),
+}
 
-## Training and evaluation data
+print(result)
+# {'text': 'This is a test sentence.', 'score': 0.3350256383419037, 'int_score': 0}
+```
 
-More information needed
+## Intended uses & limitations
+
+Refer to the hf classifier's [model card](https://huggingface.co/HuggingFaceFW/fineweb-edu-classifier#limitations) for more details
 
 ## Training procedure
 
@@ -45,50 +63,3 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.05
 - num_epochs: 1.0
-
-### Training results
-
-| Training Loss | Epoch  | Step | Validation Loss | Mse    |
-|:-------------:|:------:|:----:|:---------------:|:------:|
-| 0.5887        | 0.0288 | 100  | 0.6419          | 0.6419 |
-| 0.371         | 0.0577 | 200  | 0.3439          | 0.3439 |
-| 0.3607        | 0.0865 | 300  | 0.2844          | 0.2844 |
-| 0.2576        | 0.1153 | 400  | 0.2589          | 0.2589 |
-| 0.2822        | 0.1441 | 500  | 0.2707          | 0.2707 |
-| 0.2908        | 0.1730 | 600  | 0.2382          | 0.2382 |
-| 0.2258        | 0.2018 | 700  | 0.2405          | 0.2405 |
-| 0.2604        | 0.2306 | 800  | 0.2318          | 0.2318 |
-| 0.2961        | 0.2594 | 900  | 0.2186          | 0.2186 |
-| 0.2453        | 0.2883 | 1000 | 0.2168          | 0.2168 |
-| 0.278         | 0.3171 | 1100 | 0.2247          | 0.2247 |
-| 0.2319        | 0.3459 | 1200 | 0.2142          | 0.2142 |
-| 0.1983        | 0.3747 | 1300 | 0.2175          | 0.2175 |
-| 0.2264        | 0.4036 | 1400 | 0.2306          | 0.2306 |
-| 0.2175        | 0.4324 | 1500 | 0.2375          | 0.2375 |
-| 0.2461        | 0.4612 | 1600 | 0.2493          | 0.2493 |
-| 0.2419        | 0.4900 | 1700 | 0.2234          | 0.2234 |
-| 0.2411        | 0.5189 | 1800 | 0.2137          | 0.2137 |
-| 0.2473        | 0.5477 | 1900 | 0.2140          | 0.2140 |
-| 0.237         | 0.5765 | 2000 | 0.2177          | 0.2177 |
-| 0.1972        | 0.6053 | 2100 | 0.2186          | 0.2186 |
-| 0.2556        | 0.6342 | 2200 | 0.2416          | 0.2416 |
-| 0.2273        | 0.6630 | 2300 | 0.2197          | 0.2197 |
-| 0.223         | 0.6918 | 2400 | 0.2253          | 0.2253 |
-| 0.2028        | 0.7206 | 2500 | 0.2239          | 0.2239 |
-| 0.2322        | 0.7495 | 2600 | 0.2180          | 0.2180 |
-| 0.1933        | 0.7783 | 2700 | 0.2158          | 0.2158 |
-| 0.2085        | 0.8071 | 2800 | 0.2298          | 0.2298 |
-| 0.2038        | 0.8359 | 2900 | 0.2166          | 0.2166 |
-| 0.2158        | 0.8648 | 3000 | 0.2084          | 0.2084 |
-| 0.2197        | 0.8936 | 3100 | 0.2145          | 0.2145 |
-| 0.2397        | 0.9224 | 3200 | 0.2163          | 0.2163 |
-| 0.2307        | 0.9512 | 3300 | 0.2160          | 0.2160 |
-| 0.2099        | 0.9801 | 3400 | 0.2101          | 0.2101 |
-
-
-### Framework versions
-
-- Transformers 4.42.3
-- Pytorch 2.3.1+cu121
-- Datasets 2.20.0
-- Tokenizers 0.19.1