Upload GPTNeoXForSequenceClassification

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "output_rm/checkpoint-30",
+  "_name_or_path": "output/checkpoint-30/",
   "architectures": [
     "GPTNeoXForSequenceClassification"
   ],
@@ -9,31 +9,20 @@
   "eos_token_id": 0,
   "hidden_act": "gelu",
   "hidden_dropout": 0.0,
-  "hidden_size": 2048,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 8192,
+  "intermediate_size": 3072,
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 2048,
   "model_type": "gpt_neox",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
-  "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
-  },
   "rope_scaling": null,
   "rotary_emb_base": 10000,
   "rotary_pct": 1.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
+  "torch_dtype": "float32",
   "transformers_version": "4.32.0.dev0",
   "use_cache": true,
   "use_parallel_residual": false,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fcb5a7cd27d36f588c79e8145fe79e1e36b223228ae188e9ed045e76040e148
-size 1424550781
+oid sha256:2a18d098aa70f569ae5dbc95fc715f412a3e8c0175a0cb1c9650df2cd36b4dc7
+size 500322189