Upload config.json with huggingface_hub

config.json

@@ -1,17 +1,17 @@
 {
-  "_name_or_path": "/data1/hrsun/FuxiTranyu-8B-Instruct",
+  "_name_or_path": "/home/s2022244109/models/FuxiTranyu-8B",
   "activation_function": "gelu_fast",
   "architectures": [
     "FuxiTranyuForCausalLM"
   ],
   "attention_bias": true,
-  "attention_dropout": 0.0,
+  "attention_dropout": 0.15,
   "auto_map": {
     "AutoConfig": "configuration_fuxitranyu.FuxiTranyuConfig",
     "AutoModelForCausalLM": "modeling_fuxitranyu.FuxiTranyuForCausalLM"
   },
-  "bos_token_id": 250680,
-  "eos_token_id": 250681,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
   "hidden_size": 4096,
   "initializer_range": 0.01,
   "intermediate_size": 16384,
@@ -20,15 +20,14 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 30,
   "num_key_value_heads": 32,
-  "pad_token_id": 250681,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "tokenizer_class": "GPT2TokenizerFast",
-  "torch_dtype": "float16",
-  "transformers_version": "4.42.4",
-  "use_cache": true,
-  "vocab_size": 250682
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": false,
+  "vocab_size": 250680
 }