Update config.json

config.json

@@ -1,20 +1,19 @@
 {
-  "_name_or_path": "Qwen/Qwen-1_8B-chat",
   "architectures": [
     "QWenLMHeadModel"
   ],
-  "attn_dropout_prob": 0.0,
   "auto_map": {
     "AutoConfig": "configuration_qwen.QWenConfig",
-    "AutoModelForCausalLM": "Qwen/Qwen-1_8B-chat--modeling_qwen.QWenLMHeadModel"
+    "AutoModelForCausalLM": "modeling_qwen.QWenLMHeadModel"
   },
-  "bf16": true,
+  "attn_dropout_prob": 0.0,
+  "bf16": false,
   "emb_dropout_prob": 0.0,
   "fp16": false,
   "fp32": false,
   "hidden_size": 2048,
-  "initializer_range": 0.02,
   "intermediate_size": 11008,
+  "initializer_range": 0.02,
   "kv_channels": 128,
   "layer_norm_epsilon": 1e-06,
   "max_position_embeddings": 8192,
@@ -27,16 +26,12 @@
   "rotary_pct": 1.0,
   "scale_attn_weights": true,
   "seq_length": 8192,
-  "softmax_in_fp32": false,
   "tie_word_embeddings": false,
   "tokenizer_class": "QWenTokenizer",
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.48.3",
+  "transformers_version": "4.32.0",
   "use_cache": true,
-  "use_cache_kernel": false,
-  "use_cache_quantization": false,
   "use_dynamic_ntk": true,
-  "use_flash_attn": true,
+  "use_flash_attn": "auto",
   "use_logn_attn": true,
   "vocab_size": 151936
-}
+}