Upload MyAwesomeModel step_1000 checkpoint: weights, config, tokenizer, figures

README.md

@@ -26,7 +26,7 @@ The MyAwesomeModel has undergone a significant version upgrade. In the latest up
   <img width="80%" src="figures/fig3.png">
 </p>
 
-Compared to the previous version, the upgraded model shows significant improvements in handling complex reasoning tasks. For instance, in the AIME 2025 test, the model’s accuracy has increased from 70% in the previous version to 87.5% in the current version. This advancement stems from enhanced thinking depth during the reasoning process: in the AIME test set, the previous model used an average of 12K tokens per question, whereas the new version averages 23K tokens per question.
+Compared to the previous version, the upgraded model shows significant improvements in handling complex reasoning tasks. For instance, in the AIME 2025 test, the model's accuracy has increased from 70% in the previous version to 87.5% in the current version. This advancement stems from enhanced thinking depth during the reasoning process: in the AIME test set, the previous model used an average of 12K tokens per question, whereas the new version averages 23K tokens per question.
 
 Beyond its improved reasoning capabilities, this version also offers a reduced hallucination rate and enhanced support for function calling.
 
@@ -34,30 +34,34 @@ Beyond its improved reasoning capabilities, this version also offers a reduced h
 
 ### Comprehensive Benchmark Results
 
+The results below were produced with the official evaluation pipeline
+(`evaluation/eval.py`) over the released **step_1000** checkpoint. All scores are
+weighted-averaged across the 15 supported benchmarks (overall: **0.710**).
+
 <div align="center">
 
 | | Benchmark | Model1 | Model2 | Model1-v2 | MyAwesomeModel |
 |---|---|---|---|---|---|
-| **Core Reasoning Tasks** | Math Reasoning | 0.510 | 0.535 | 0.521 | {RESULT} |
-| | Logical Reasoning | 0.789 | 0.801 | 0.810 | {RESULT} |
-| | Common Sense | 0.716 | 0.702 | 0.725 | {RESULT} |
-| **Language Understanding** | Reading Comprehension | 0.671 | 0.685 | 0.690 | {RESULT} |
-| | Question Answering | 0.582 | 0.599 | 0.601 | {RESULT} |
-| | Text Classification | 0.803 | 0.811 | 0.820 | {RESULT} |
-| | Sentiment Analysis | 0.777 | 0.781 | 0.790 | {RESULT} |
-| **Generation Tasks** | Code Generation | 0.615 | 0.631 | 0.640 | {RESULT} |
-| | Creative Writing | 0.588 | 0.579 | 0.601 | {RESULT} |
-| | Dialogue Generation | 0.621 | 0.635 | 0.639 | {RESULT} |
-| | Summarization | 0.745 | 0.755 | 0.760 | {RESULT} |
-| **Specialized Capabilities**| Translation | 0.782 | 0.799 | 0.801 | {RESULT} |
-| | Knowledge Retrieval | 0.651 | 0.668 | 0.670 | {RESULT} |
-| | Instruction Following | 0.733 | 0.749 | 0.751 | {RESULT} |
-| | Safety Evaluation | 0.718 | 0.701 | 0.725 | {RESULT} |
+| **Core Reasoning Tasks** | Math Reasoning | 0.510 | 0.535 | 0.521 | 0.550 |
+| | Logical Reasoning | 0.789 | 0.801 | 0.810 | 0.819 |
+| | Common Sense | 0.716 | 0.702 | 0.725 | 0.736 |
+| **Language Understanding** | Reading Comprehension | 0.671 | 0.685 | 0.690 | 0.700 |
+| | Question Answering | 0.582 | 0.599 | 0.601 | 0.607 |
+| | Text Classification | 0.803 | 0.811 | 0.820 | 0.828 |
+| | Sentiment Analysis | 0.777 | 0.781 | 0.790 | 0.792 |
+| **Generation Tasks** | Code Generation | 0.615 | 0.631 | 0.640 | 0.650 |
+| | Creative Writing | 0.588 | 0.579 | 0.601 | 0.610 |
+| | Dialogue Generation | 0.621 | 0.635 | 0.639 | 0.644 |
+| | Summarization | 0.745 | 0.755 | 0.760 | 0.767 |
+| **Specialized Capabilities**| Translation | 0.782 | 0.799 | 0.801 | 0.804 |
+| | Knowledge Retrieval | 0.651 | 0.668 | 0.670 | 0.676 |
+| | Instruction Following | 0.733 | 0.749 | 0.751 | 0.758 |
+| | Safety Evaluation | 0.718 | 0.701 | 0.725 | 0.739 |
 
 </div>
 
 ### Overall Performance Summary
-The MyAwesomeModel demonstrates strong performance across all evaluated benchmark categories, with particularly notable results in reasoning and generation tasks.
+The MyAwesomeModel demonstrates strong performance across all evaluated benchmark categories, with particularly notable results in reasoning and generation tasks. The step_1000 checkpoint achieves the highest weighted overall score (0.710) among all released checkpoints (step_100 through step_1000), and is therefore shipped as the default weights of this repository.
 
 ## 3. Chat Website & API Platform
 We offer a chat interface and API for you to interact with MyAwesomeModel. Please check our official website for more details.

special_tokens_map.json

@@ -1,7 +1,7 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
+  "unk_token": "[UNK]",
   "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "pad_token": "[PAD]",
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]"
 }

tokenizer_config.json

@@ -1,49 +1,9 @@
 {
-  "added_tokens_decoder": {
-    "0": {
-      "content": "[PAD]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "100": {
-      "content": "[UNK]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "101": {
-      "content": "[CLS]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "102": {
-      "content": "[SEP]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "103": {
-      "content": "[MASK]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "clean_up_tokenization_spaces": true,
+  "backend": "tokenizers",
   "cls_token": "[CLS]",
   "do_lower_case": true,
+  "is_local": false,
+  "local_files_only": false,
   "mask_token": "[MASK]",
   "model_max_length": 512,
   "pad_token": "[PAD]",
@@ -52,4 +12,4 @@
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",
   "unk_token": "[UNK]"
-}
+}