Trained for 2000 steps

README.md

@@ -1,18 +1,18 @@
 ---
-title: "ESPA AI"
-emoji: "🤖"
-colorFrom: "blue"
-colorTo: "green"
-sdk: "transformers"
-sdk_version: "4.21.1"
-app_file: "app.py"
-license: "mit"
+title: ESPA AI
+emoji: 🤖
+colorFrom: blue
+colorTo: green
+sdk: transformers
+sdk_version: 4.21.1
+app_file: app.py
+license: mit
 tags:
-  - "text-classification"
-  - "distilbert"
-  - "NLP"
-  - "sentiment-analysis"
-short_description: "A DistilBERT-based model fine-tuned on IMDb for text classification."
+- text-classification
+- distilbert
+- NLP
+- sentiment-analysis
+short_description: A DistilBERT-based model fine-tuned on IMDb for text classification.
 ---
 # Model Card for ESPA AI
 

config.json

@@ -1,32 +1,46 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "drive/MyDrive/espa-ai-checkpoint",
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "GPT2LMHeadModel"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
-  "initializer_range": 0.02,
-  "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "pad_token_id": 0,
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
-  "torch_dtype": "float32",
-  "transformers_version": "4.48.3",
-  "vocab_size": 30522,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
   "id2label": {
-    "0": "Negative",
-    "1": "Positive"
+    "0": "LABEL_0"
   },
+  "initializer_range": 0.02,
   "label2id": {
-    "Negative": 0,
-    "Positive": 1
-  }
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 6,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "use_cache": true,
+  "vocab_size": 50257
 }

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.48.3"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e313ab52dbdb8a71a3e3c361ee025df2b917827bbde6c793faab35b470f1f80
-size 267832560
+oid sha256:ce7a79ca5cb98764285a77f48e92a2d576c33cdd002cf3409b7c08fe13997484
+size 327657928