update README

README.md

@@ -3,6 +3,7 @@ library_name: transformers
 license: apache-2.0
 license_link: https://huggingface.co/Qwen/Qwen3-14B/blob/main/LICENSE
 pipeline_tag: text-generation
+base_model: Qwen/Qwen3-14B
 ---
 
 # Qwen3-14B-AWQ

config.json

@@ -4,20 +4,19 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
+  "bos_token_id": 151643,
   "eos_token_id": 151645,
   "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 5120,
   "initializer_range": 0.02,
   "intermediate_size": 17408,
-  "max_position_embeddings": 65536,
-  "max_window_layers": 28,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 40,
   "model_type": "qwen3",
   "num_attention_heads": 40,
   "num_hidden_layers": 40,
   "num_key_value_heads": 8,
-  "pad_token_id": 151643,
-  "qkv_bias": false,
   "quantization_config": {
     "bits": 4,
     "group_size": 128,
@@ -33,8 +32,7 @@
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.51.3",
-  "use_cache": false,
-  "use_qk_norm": true,
+  "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

generation_config.json

@@ -1,7 +1,13 @@
 {
-  "_from_model_config": true,
-  "do_sample": true,
-  "eos_token_id": 151645,
-  "pad_token_id": 151643,
-  "transformers_version": "4.51.3"
-}
+    "bos_token_id": 151643,
+    "do_sample": true,
+    "eos_token_id": [
+        151645,
+        151643
+    ],
+    "pad_token_id": 151643,
+    "temperature": 0.6,
+    "top_k": 20,
+    "top_p": 0.95,
+    "transformers_version": "4.51.0"
+}

tokenizer_config.json

@@ -231,7 +231,6 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",
-  "extra_special_tokens": {},
   "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,