Upload BertForSequenceClassification

config.json

@@ -1,44 +1,26 @@
 {
-  "_name_or_path": "lhoestq/demo1",
+  "_name_or_path": "bert-base-uncased",
   "architectures": [
-    "GPTNeoXForCausalLM"
+    "BertForSequenceClassification"
   ],
-  "bos_token_id": 0,
-  "classifier_dropout": 0.1,
-  "custom_pipelines": {
-    "text-generation": {
-      "impl": "instruct_pipeline.InstructionTextGenerationPipeline",
-      "pt": "AutoModelForCausalLM",
-      "tf": "TFAutoModelForCausalLM"
-    }
-  },
-  "eos_token_id": 0,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
-  "hidden_size": 5120,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 20480,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 2048,
-  "model_type": "gpt_neox",
-  "num_attention_heads": 40,
-  "num_hidden_layers": 36,
-  "quantization_config": {
-    "bnb_4bit_compute_dtype": "float32",
-    "bnb_4bit_quant_type": "fp4",
-    "bnb_4bit_use_double_quant": false,
-    "llm_int8_enable_fp32_cpu_offload": false,
-    "llm_int8_has_fp16_weight": false,
-    "llm_int8_skip_modules": null,
-    "llm_int8_threshold": 6.0,
-    "load_in_4bit": false,
-    "load_in_8bit": true
-  },
-  "rotary_emb_base": 10000,
-  "rotary_pct": 0.25,
-  "tie_word_embeddings": false,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.30.0.dev0",
+  "type_vocab_size": 2,
   "use_cache": true,
-  "use_parallel_residual": true,
-  "vocab_size": 50280
+  "vocab_size": 30522
 }

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac501c1d0fd8b4ec8d5b6e4f498e30801bc3382bd2985fbe12c5dcfed8619d35
+size 438005109