update README

README.md

@@ -322,10 +322,10 @@ YaRN is currently supported by several inference frameworks, e.g., `transformers
 
 | Mode | QUANTIZATION TYPE | LiveBench 2024-11-25 | GPQA | MMLU-Redux | AIME24 |
 | --- | --- | --- | --- | --- | --- |
-| Thinking | bf16 | 74.3 | 65.8 | 89.5 | 80.4 |
-| Thinking | GPTQ-int4 | 71.5 | 60.1 | 88.8 | 79.5 |
-| Non-Thinking | bf16 | 59.4 | 54.8 | 84.1 | - |
-| Non-Thinking | GPTQ-int4 | 57.2 | 50.4 | 83.5 | - |
+| Thinking | bf16 | 77.1 | 71.1 | 92.7 | - |
+| Thinking | GPTQ-int4 | 75.1 | 71.9 | 92.0 | - |
+| Non-Thinking | bf16 | 62.5 | 62.9 | 89.2 | - |
+| Non-Thinking | GPTQ-int4 | 61.1 | 62.8 | 89.0 | - |
 
 ## Best Practices
 
@@ -356,4 +356,4 @@ If you find our work helpful, feel free to give us a cite.
     month  = {April},
     year   = {2025}
 }
-```
+```

generation_config.json

@@ -1,6 +1,13 @@
 {
-  "_from_model_config": 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,