Upload 9 files

README.md

@@ -1,3 +1,78 @@
----
-license: mit
----
+# 📘 AetherMind_SRL – Self-Reflective Learning NLI Model
+Author: Samer Zaher Najm (Sam)  
+Organization: AetherMind Project  
+Model Type: Knowledge-Distilled Transformer (Student Model)  
+Domain: Natural Language Inference (NLI) + Medical Reasoning (ADNI SRL)
+
+## 🚀 Overview
+AetherMind_SRL is the 12th-round refined version of AetherMind’s knowledge-distilled student model, trained using self-reflective learning (SRL), knowledge distillation, ADNI medical contradictions, and general-domain NLI datasets.
+
+## 💡 Highlights
+- Improved contradiction detection  
+- Strong general NLI performance  
+- Lightweight and efficient  
+- SRL-based iterative refinement  
+
+## 📊 Evaluation (Round 12 Final)
+| Dataset   | Accuracy | Macro F1 | Samples |
+|-----------|----------|----------|---------|
+| SNLI      | 89.64%   | 89.55%   | 9,824  |
+| MNLI-M    | 90.20%   | 90.00%   | 9,815  |
+| MNLI-MM   | 89.61%   | 89.35%   | 9,832  |
+| ANLI R1   | 79.90%   | 79.89%   | 1,000  |
+| ANLI R2   | 67.50%   | 67.35%   | 1,000  |
+| ANLI R3   | 67.33%   | 66.81%   | 1,200  |
+
+## 🧠 Self-Reflective Learning (SRL)
+1. Train base model  
+2. Extract errors  
+3. Correct and retrain  
+4. Stabilize via KD + SRL loops  
+
+## 🔥 Teacher → Student Distillation
+Teacher: microsoft/deberta-v3-base  
+Student: AetherMind_SRL
+
+## 🛠 Usage Example
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+model_id = "samerzaher80/AetherMind_SRL"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForSequenceClassification.from_pretrained(model_id).cuda()
+
+premise = "The patient scored 28 on the MMSE last year."
+hypothesis = "The patient shows signs of cognitive decline."
+
+inputs = tokenizer(premise, hypothesis, return_tensors="pt").to("cuda")
+with torch.no_grad():
+    logits = model(**inputs).logits
+    predicted = torch.argmax(logits, dim=-1).item()
+
+labels = ["entailment", "neutral", "contradiction"]
+print("Prediction:", labels[predicted])
+```
+
+## 🔧 Included Python Files
+- evaluate_round12.py  
+- inference_srl_round12.py  
+- train_round12_srl_kd.py  
+- build_anli_global_error_buffer_round1.py  
+- analyze_anli_errors_round1.py  
+- srl_finetune_round5_smart.py
+
+## 🧩 Metadata
+```json
+{
+  "tags": [
+    "natural-language-inference",
+    "knowledge-distillation",
+    "biomedical-nlp",
+    "aethermind",
+    "nli",
+    "self-reflective-learning",
+    "transformers"
+  ]
+}
+```

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -0,0 +1,48 @@
+{
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "transformers_version": "4.57.1",
+  "type_vocab_size": 0,
+  "use_cache": false,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:520aec62886479bfb8fb4b1160634ee8437d70d86b9d5a74fb2815eba7f30342
+size 737722356

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,66 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 192,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "stride": 0,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:760808306589ceecb33c30a24d3de93d84faf273c590ff254e16e472f30f4468
+size 5560