init

.ipynb_checkpoints/config-checkpoint.json

@@ -0,0 +1,50 @@
+{
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "710",
+    "1": "720",
+    "2": "721",
+    "3": "722",
+    "4": "723",
+    "5": "724",
+    "6": "730",
+    "7": "740",
+    "8": "799"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "710": 0,
+    "720": 1,
+    "721": 2,
+    "722": 3,
+    "723": 4,
+    "724": 5,
+    "730": 6,
+    "740": 7,
+    "799": 8
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

README.md

@@ -0,0 +1,89 @@
+---
+model-index:
+- name: poltextlab/illframes-climate-v5
+  results:
+  - task:
+      type: text-classification
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 72%
+    - name: F1-Score
+      type: f1
+      value: 64%
+tags:
+- text-classification
+- pytorch
+metrics:
+- precision
+- recall
+- f1-score
+language:
+- en
+base_model:
+- xlm-roberta-large
+pipeline_tag: text-classification
+library_name: transformers
+license: cc-by-4.0
+extra_gated_prompt: Our models are intended for academic use only. If you are not
+  affiliated with an academic institution, please provide a rationale for using our
+  models. Please allow us a few business days to manually review subscriptions.
+extra_gated_fields:
+  Name: text
+  Country: country
+  Institution: text
+  Institution Email: text
+  Please specify your academic use case: text
+---
+
+# illframes-climate-v5
+
+
+# How to use the model
+
+```python
+from transformers import AutoTokenizer, pipeline
+
+tokenizer = AutoTokenizer.from_pretrained("xlm-roberta-large")
+pipe = pipeline(
+    model="poltextlab/illframes-climate-v5",
+    task="text-classification",
+    tokenizer=tokenizer,
+    use_fast=False,
+    token="<your_hf_read_only_token>"
+)
+
+text = "<text_to_classify>"
+pipe(text)
+```
+        
+
+# Classification Report
+
+## Overall Performance:
+
+* **Accuracy:** 72%
+* **Macro Avg:** Precision: 0.45, Recall: 0.29, F1-score: 0.31
+* **Weighted Avg:** Precision: 0.65, Recall: 0.72, F1-score: 0.64
+
+## Per-Class Metrics:
+
+| Label                                    |   Precision |   Recall |   F1-score |   Support |
+|:-----------------------------------------|------------:|---------:|-----------:|----------:|
+| 710: Threatening economic growth         |        0.63 |     0.3  |       0.41 |        63 |
+| 720: Threatening national sovereignty    |        1    |     0.15 |       0.26 |        20 |
+| 721: Climate conspiracy                  |        0    |     0    |       0    |        15 |
+| 722: Scientific scepticism and denial    |        0    |     0    |       0    |        19 |
+| 723: Climate movement bashing            |        0.33 |     0.28 |       0.3  |        18 |
+| 724: Other polluters as the real problem |        0.77 |     0.8  |       0.78 |        25 |
+| 730: Threatening energy security         |        0.6  |     0.09 |       0.16 |        33 |
+| 740: Threatening way of life             |        0    |     0    |       0    |        11 |
+| 799: None of them                        |        0.73 |     0.99 |       0.84 |       356 |
+
+# Inference platform
+This model is used by the [CAP Babel Machine](https://babel.poltextlab.com), an open-source and free natural language processing tool, designed to simplify and speed up projects for comparative research.  
+
+# Cooperation
+Model performance can be significantly improved by extending our training sets. We appreciate every submission of CAP-coded corpora (of any domain and language) at poltextlab{at}poltextlab{dot}com or by using the [CAP Babel Machine](https://babel.poltextlab.com).
+## Debugging and issues
+This architecture uses the `sentencepiece` tokenizer. In order to run the model before `transformers==4.27` you need to install it manually.

config.json

@@ -0,0 +1,50 @@
+{
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "710",
+    "1": "720",
+    "2": "721",
+    "3": "722",
+    "4": "723",
+    "5": "724",
+    "6": "730",
+    "7": "740",
+    "8": "799"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "710": 0,
+    "720": 1,
+    "721": 2,
+    "722": 3,
+    "723": 4,
+    "724": 5,
+    "730": 6,
+    "740": 7,
+    "799": 8
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cbf987e75ce17446e7cc4488b0d7f0da5a2e8ff9833bdd7d0e584dcaa4723b8
+size 2239647372

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dda67c55d5246d9e910cec27564d3b8b11ded99650d625e2b7f1f5af3c90defe
+size 5777