Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,131 @@
+---
+license: mit
+library_name: transformers
+datasets:
+- PrimeIntellect/verifiable-coding-problems
+- likaixin/TACO-verified
+- livecodebench/code_generation_lite
+language:
+- en
+base_model:
+- deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
+pipeline_tag: text-generation
+---
+
+<div align="center">
+<span style="font-family: default; font-size: 1.5em;">DeepCoder-14B-Preview</span>
+<div>
+🚀 Democratizing Reinforcement Learning for LLMs (RLLM) 🌟
+</div>
+</div>
+<br>
+<div align="center" style="line-height: 1;">
+  <a href="https://github.com/agentica-project/rllm" style="margin: 2px;">
+    <img alt="Code" src="https://img.shields.io/badge/RLLM-000000?style=for-the-badge&logo=github&logoColor=000&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+  <a href="https://pretty-radio-b75.notion.site/DeepCoder-A-Fully-Open-Source-14B-Coder-at-O3-mini-Level-1cf81902c14680b3bee5eb349a512a51" target="_blank" style="margin: 2px;">
+    <img alt="Blog" src="https://img.shields.io/badge/Notion-%23000000.svg?style=for-the-badge&logo=notion&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+  <a href="https://x.com/Agentica_" style="margin: 2px;">
+    <img alt="X.ai" src="https://img.shields.io/badge/Agentica-white?style=for-the-badge&logo=X&logoColor=000&color=000&labelColor=white" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+  <a href="https://huggingface.co/agentica-org" style="margin: 2px;">
+    <img alt="Hugging Face" src="https://img.shields.io/badge/Agentica-fcd022?style=for-the-badge&logo=huggingface&logoColor=000&labelColor" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+  <a href="https://www.together.ai" style="margin: 2px;">
+    <img alt="Together AI" src="https://img.shields.io/badge/-Together_AI%20-white?style=for-the-badge&logo=data%3Aimage%2Fpng%3Bbase64%2CiVBORw0KGgoAAAANSUhEUgAAAUAAAAFACAMAAAD6TlWYAAAC7lBMVEUAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAPb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8AAAAPb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8Pb%2F8AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAADIBDt6AAAA%2BnRSTlMAAiQEKgcdKQwiHBMUzrtSUEmjhmZGH96yv8n1ey7nL3y1U%2FZfCaIo1WFg1NrcsHYrA2%2Fv80J%2BMeilnpefqKw%2B64%2BQlSbYZGVnBGkCV%2BxW8XJube6WJ9kZF9bSzBALRynPQfLhIjvwyBEAXOTLp3o%2FJA9Y9%2F7%2F9FEKDhIVFo4GHkVzjGz8icrHzY39iHR1i0M8Jj14LLZUvb7DxMXGoQEFeQcgSBOHaPvm4uOdRLMMqcDTLbcII0sNuVn4TKaRd6RKIeDd37Svra6xuLpaW17lXUAlHh8WGxUPIS4JGQoFECMsBg4gFwsRJRIrCC0oAycaFC8NMDIzMRgBsVt9rwAAD25JREFUeNrs3QVzG0kWB%2FA3ikHhZeYwk3LMbF7GcBasOGw9hb3MzLyKw8zMzMx2rsokhySNY2mmR1N4xXV3a7sHuzWu%2BX2Ef3XPG%2Br3wOVyuVwul8vlcrlcLpfL5XK5dOlXOHTIvLnb27Xd%2FasBvrt9A%2B7r1bbdTTffcmuXwhzgTYwk6q%2BHr2RWlcclRYqXV2VeCV%2Bvr4mIkCJKZ83uc9NLC0fMD%2BD%2FCswfMfLtzh%2FeelsJcKJW19SG66KSTP6fLEXrwrU11Srw5Z8zbuzePcUBbFyg%2BPY7Pv%2Bs0A%2Bsid7ayiqFNEWp8iS9Ir%2F0Cl957bkRAaQLFLz15sBBfpbpJc7FJKKFFGuV4JJh6N573g6idr7vP%2F8iC9iI1NZJRDupLnlRBbaW3XjTfQHUJ3D8d68MBtsJiTNRold5uEYAdibkHgqiESMefGi9zfFVeCRihOS5LLJafV99XYxGddgwabKt8SmEyEQ%2FmRDlSoUA9gsNvKMDmhE8MC4L7OFtSYmPFmFlAmzm%2F9tfH0Oz8v6yFmxQ3SpOiY8eYTwjHew0%2BB9%2FD6B5ga4dLd%2FHQus0SnzaIrzWWgDb9P19MVqjw01dwFLpYYVYQymLgD1Kjj6J1umaHwLLqJfpy0%2FHIryqgg2mvetDKxXMnQMWEa9LxEpSqxZguS%2B%2BfA%2Bt9cZBi7ZxeqVMX376FqEnAtbyv7ISrTfspB%2FM82bq3r70BNMSYKV%2Bo4rQDiPzc8Csy1Fih%2BhVsE7o0cfQHnn%2FygJz6uNEJtaTSfy8ChYpnelDuxQ8HAIT1LOS8fwoCSq1FiVYcs%2FdaJ%2FgNhMJqrWKqfwoCSYtSTA08260U%2FBh47v4LDU%2F%2FgnmPOJDexX86ycwpp6yf80neB7M8o96DO2Wl2%2Bw%2FlLrh%2FlKYroW31qE9ht5EgzwRs3nR00wmgBTVq1EFtp2Ad0imdbkR0kwLQImTP8S2eg9B3QSKwkbHhPPxSUzAsjGe3P1luLrMmGklQpGjfIhKwU6C8llibBJUCaS4UKy6klkp0cX0CE9zcr8KAlei4Ahy36PLHXuBJqpYcJSmQBG3LIJWerQETS7qhCWlHowoMvfka2Va0Gjaus3MGUTp4NuWY8ja3%2FuB9q0IqydBt1eeQxZ%2B9MfQRNvnLAWT%2BiuIEuRvT9MBg3UlkQmbMmkUgB9cjsge8EbQIMLCmFPuQy6DPoGeVi9HqgED5EJazL5VAQ9Nm5CHjq0B6oKhZCUX4LrNyAfSycDhVBJZMKeTK4IoN26IPJRsAQoEhLhQ7kAmoV%2Bjbwspt0LniF8yKRMBa1%2B%2BSvkZVFfaFIkSngpvwha%2FQL56QNNqiX8%2FBs0mnMX8vPtBGiCWEf4iYmgzey7kZ8Rw6EJXonwo9SANn9GnuZCE84RnlqBJm3aIk8vFUKjxBjhKbMFaDHQhzy9%2BAI06pJEeJIS%2FGuwBn1M1WD%2BdXjNauSrdwk0Qq0kfHlUoFs7Evnq9TI0orqK8BVN1%2FIcvAn56vAKNCKhEDruz8NjkbdXOV4CKZJA1W8M8vbjT9CwMOGtDKjmjEbefpgCDRLqCB33p7kvipC3kc83UkOihLdohF5DfMjbiBf43UZTSPQq8vobyNsbudCgyzLhTT4PNK8hpmoZPkv4awU0y5G%2F1%2Fj90WG%2BDK9ATNX7mDDh71OgWYn83RHi9yRMkQY0I5G%2FOydDA4RPCX9RoMlD%2Fu6a0mCAMcJfHGh8yN%2BwqdAAMZPwJwFNB%2BRv5TRoQIs0wp%2FiiAB7TG%2B2Abor0L0GmiO5VdicuHsfaE7UfRIxJ80Rz8Kdnfss7L6NoShz8vvAWsLfOUe8kZ7o5DfSm1Pgm8gnTv4msqoIzXC%2FyrUZjWa434XdPxOoRZjiHjTD%2FTcGNm9Cg9y%2Fs9z%2FAymi1e4fqqZ4VPcfaQZnlQYGkacXP3H6X%2FrT2qIZ7jkR%2BAvy9L5jTyq5Z%2BUolBpHnNYc5PDTmubrsHtemOeJ9aJmcWI9tAV5%2BQ29Z4Kc%2Bj0TYHOQVwl5pVl07YD1h9EMt28MHOHUueihZtK5CArvRB4OTWkuvbNgYjGyF5wEGlQ4oXsbrF%2BK7O2fDBoIPPoHegQndLAc14w6WELot8jaX5pVD1Xo8iSy1WM8nzbcFMZbcf%2BLcR%2Fp7qBZayf0kYZly5GlzpOd3Mmcfy%2F9rl1AhwjTXvoXwaATDKc55Dp6mgP%2FeSLvZ4E%2B55wwTwSmr0Y2Djp6og3%2FmUrDhqbuTKWLYMqQ42i%2FkcNTdqpXeQ2Y4z82AO2Wl8txrpz5AkLRr38Q7TUiOydlJxueBfNCYzugnYKvOn62JkXpA3YmGPy8xPnTXanzhYP27d8PSvjPFzafH0Wov12VJC87ZSdcS2dVsEy%2FE8fRDgtznTFj3Tz%2FrT3QesOGO2bKv3mrVr%2BH1nrjjqFgiUilTGRr8%2FNEwHLTZ%2FisLR9vzgGLiOckYiWpVQuwQcmonmidZ3JDYBn1chohslXL79pVFWzh%2F2L5JrRG8fahYKlIWCHWUMoiYJtl%2F3wygOYFunabDBYTWmtdhJTlVy%2BAjfxPPP4YmpW3dTzYID0jTo%2BQEl88Ix1sFlqytAOacfe%2Bk1lgD29LxXiEMiFKZUIF%2By3L%2F6YYjSpu134w2EaouEKPsNH4rlwWgI0JEzcE0Qjfl19NAVsJFR6JGCF5LovAzrId2%2B8LoD6BBT8OGQy2E2rCUaJXebhGALZC9z%2FwUhC18%2F0wc1UWsBFJ1klEOymWvKgCe%2F7CW999xxdAusCI0R99PMgP7IiJczFJY3qtEiLw8tOckw88uKs40FR4xXuWzvzjVD%2BwJnqTlVUKaYpS5Ul6ReCsdOeOmVveKgq%2Bh%2F%2FvveCiu7Zvmz2rFDhRq2tqw7GoJJP%2FJ0vRWFmyplqF1NBv0KmTJz7fumX1d889%2B8yTzzz73Ldfbtm6bdS48RNygDcx3Xu1NqPMUxdLS7uWlhar85RlJK9600VIOf6c0mWDpj391NNtBg0uyfFDSlEF8T%2Ft3eFyqjwTwPGNiKq9eq%2BtqiCeoxZVEcRW4mK%2Bvc%2F5%2Bk7bBSDZOJPfFfwHWkEMG%2B%2BfXChwHMdxHMdxHMdxHMdxHMdxHIeV4yiR%2FyOUS6tHfBxP88Vse74N%2F7mdt7PF%2FHT8EFakbYg0XupvMZ%2Fddt%2F%2Ber27zebFX%2BXSfpQfD%2BMLsX7iMp4fc460%2BfgiqbSD1jSCGH1WXAV1v32OhOm0O1Yh9aUR0sNUYnVyekjBEH9eL%2B2mIY2gilmGdWXvhTKQNnpvkDYrBJgjNluJTchtIDSnBY3TNgLMUEGvbL4Qvhco3WkPbOS%2FNAEGjMay1bsEMjyCJsewXVo5HoFuH5P2b7OsJh9a0har1mn3tmkElXTzPlU%2FUd2nDfnTKH53b%2FTN%2FI7TZp2l7X3QZNPlO6X9jb1pJwUa5J8SuyQ%2Fc2vTFjl0zu%2F8vfrH2O8obdx52jaFjmmZ7HAdQQeOVw1pwxF0StNskd0GWtvsUIfsBB3SNt3m%2FgUtva1402jEfCXm%2BUBLjWkHBZ2gJ3zxHcG51JhWdnQENc%2BYk3O2vz%2F6CEJrBqYcyi9o6E172hJaMjJn876BRjYG0k7QiqFJr7tRo7SdgbSsgBaMzRoe%2BlCbfzWTlkILxqZdj%2FPaaWM0Y%2BtBUwbnrT8%2BoaZPY2kLBc2Ynfi%2FgVo2BtNO0JDRPSf6PtTgm0y7pNCI2KNJewWVqZnZNAH1md93J4HKEsNpb1Abw85P%2FQ%2Bo6GNoOs2H%2BgZo2gQqWqBpA6iNY%2Fe7EVRyXNm%2FMR%2FP%2FotjBRWokCFtK6AOrh1AA6ggkBxpG6hFnImzzLUFKNv2uOec5Q9Qw3kO7N%2BgmT7LjB81asuU1hNQXSyRhyyAULClxVDdHh%2FI4YEzIMzY0vZQWZQhlyyFX6V8aasIqnoinwP86oB8nlBRfkM%2Btxx%2BIaZWpNGf03zkCH4xYk0r7PiuTljALz6R0wQqya%2FI6ZrTHy78acS%2FCSd5hB8dmdNGdlyDCQfiGmz7dVhtkddWWZvWU0D72CGv3Qf84O%2BFP40Wl8irLOAHBXtaDLQDoq0fgnPk9gTaHrnt4Qcz5Bba8T2OcBPwLUGnWXAnmGbILfP5Lm%2BELLX3WSp9v3q0IC0GytcDuT1O8K2TBWlLq58kEJfhOfJbACVEfhN7z20IlDPy2xM3WIymQBkiv57i%2ByZM6ANlh%2FymAr6hpshvB5QVoqW3q%2BKK%2FO5AkchvmMM38iHyk0ApkV%2Ffg294feRXugPoDiCr0n0GtiPdVbid%2BwvfB4op8svcN5F2%2Bu67cDvTV34aM0F%2B4Ss%2FDzzYcW4JSwse%2Byav%2FETa4t9ERhakBS%2F9q5wFaRH%2F6kDaNbf3d2EPXuAyvLd30UQItCdyO9i7bOf5EquzYnvTgpdeH8iflvlAUz3kZf8KVcs%2FBJ%2F2rl1cQxWFvUvhR8xpBVThDfnvAu28SR16UMkEOS3sfdQxgGri0tp%2Fk0Lac39l6T%2FKLbd2AfLVg4rW9t7rPy24BtOiFXJZRda%2BTL%2F6A1Wp0N7BBHu2tFBBZUGJPGRs7QPfMrB9cBExnIV7pM1ZQA0nrvFA9qYlUEc%2B5R9QZddYrymdxn%2Bey5O9g%2BUSqEf0rB3SJ7YMaT0BNRUMEywLa9NkDHWpdzRtYO9413cFtaUXw6NyL76VA4abj%2BL%2BMjys%2BcvaEdePJTQhxmhSKGqkhWjSWEAj0cXagfWpybRdBA0lpbktExJrN5oo36ApNUFTJqpm2gJNGShozOuhGT3P2rSzBy1EfSMbF%2FVTqC01lBZBK%2FHK2q2zisxA2iqGlhKpf%2FO2pGHaXXuafOPfGZKMLJeMO0MSaXNoTz1LvRtYPhXftqlE2lpBB9SayOQ6fgDqqTXtk07jzKSPH00dpL60tbJ9h%2Bb2%2BzODWt7tSKM34tZhlUBrSaYn7Q06Ffc1bKXfj6EDhQ1ptOhcP5OI7EXQibTXedo5gs55gxK7VE68ztImstu0gQcaqGSH%2BOjqHF8S1WXapcO03ZsCPaLxA7tRhhF0Kg1L7MZjHIE24os%2B05X%2B%2FL6ErWm7pQCd0ndJdxKN93cfNPDf763T5CwFzVTcK%2BnOXxrLXqE0pRXbtmmxAv3EaUp3%2Ftg4PQlL0x7TRIAZeXIusYnyfMo1p50apyU5mCOCcIV1rcJA2J9mivqzvpZYXXldR8pQWlQ77Y8CBnk8GFYLlcNBnJtNmwwlVlH%2Bl%2BYBG69Yn7Py98Ksty48lrQemXY2kEZRfvAMr5l84P97yOwaPgNfWZq2NpZG86JgPhlP%2B9ldlo9S3rP%2BdDyZB5FnRdqygzTHcRzHcRzHcRzHcRzHcZz%2FAbyvLkVmYcs9AAAAAElFTkSuQmCC&link=https%3A%2F%2Fwww.together.ai" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+</div>
+</div>
+</div>
+
+## DeepCoder Overview
+DeepCoder-14B-Preview is a code reasoning LLM fine-tuned from DeepSeek-R1-Distilled-Qwen-14B using distributed reinforcement learning (RL) to scale up to long context lengths. The model achieves 60.6% Pass@1 accuracy on LiveCodeBench v5 (8/1/24-2/1/25), representing a 8% improvement over the base model (53%) and achieving similar performance to OpenAI's o3-mini with just 14B parameters.
+
+<div style="margin: 0 auto;">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/654037be97949fd2304aab7f/r3-vzkItOCrMf1qldW0Mj.png" style="width: 100%;" />
+</div>
+
+## Data
+Our training dataset consists of approximately 24K unique problem-tests pairs compiled from:
+- Taco-Verified
+- PrimeIntellect SYNTHETIC-1
+- LiveCodeBench v5 (5/1/23-7/31/24)
+
+## Training Recipe
+
+Our training recipe relies on an improved version of GRPO (GRPO+) and iterative context lengthening, introduced in DeepScaleR.
+
+### GRPO+
+
+We enhance the original GRPO algorithm with insights from DAPO to enable more stable training:
+
+- **Offline Difficulty Filtering:** DAPO employs online dynamic sampling, discarding both entirely correct and entirely incorrect samples on the fly. While this helps maintain a more stable effective batch size, it introduces significant runtime overhead due to rejection sampling. Instead, we perform offline difficulty filtering on a subset of coding problems to ensure the training dataset remains within a suitable difficulty range.
+- **No Entropy Loss:** We observed that including an entropy loss term often led to instability, with entropy growing exponentially and ultimately collapsing training. To mitigate this, we eliminate the entropy loss entirely.
+- **No KL Loss:** Eliminating KL loss prevents the LLM from staying within trust region of the original SFT model. This removal also obviates the need to compute log probabilities for the reference policy, thereby accelerating training.
+- **Overlong Filtering** **(from DAPO):** To preserve long-context reasoning, we mask the loss for truncated sequences. This technique enables DeepCoder to generalize to 64K-context inference despite being trained with a 32K context.
+- **Clip High (from DAPO):** By increasing the upper bound in GRPO/PPO’s surrogate loss, we encourage more exploration and more stable entropy.
+
+### Iterative Context Lengthening
+
+Our original `Deepscaler-1.5B-Preview` scaled long context training from 8K→16K→24K, achieving 33→38→43% on AIME respectively. Similarly, `Deepcoder-14B-Preview` is trained on 16K→32K, achieving 54→58% on LiveCodeBench (v5). `DeepCoder-14B-Preview` successfully generalizes to longer contexts when evaluated at 64K context, reaching 60.6%. 
+
+DeepCoder generalizes better to long contexts than the base distilled model, due to DAPO's overlong filtering. However, it's longer responses are often truncated when the max length is capped at 16K, which can lower its scores.
+
+| **Model** | **16K** | **32K** | **64K** |
+| --- | --- | --- | --- |
+| **DeepCoder-14B-Preview** | 45.6 | 57.9 | 60.6 |
+| **DeepSeek-R1-Distill-Qwen-14B** | 50.2 | 53.0 | 53.0 |
+
+A more detailed description of the training recipe can be found in our [blog post](https://pretty-radio-b75.notion.site/DeepCoder-A-Fully-Open-Source-14B-Coder-at-O3-mini-Level-1cf81902c14680b3bee5eb349a512a51).
+
+## Evaluation
+
+We evaluate `Deepcoder-14B-Preview` on various coding benchmarks, including LiveCodeBench (LCBv5), Codeforces, and HumanEval+. 
+
+| **Model** | LCB (v5)(8/1/24-2/1/25) | Codeforces Rating | Codeforces Percentile | HumanEval+ |
+| --- | --- | --- | --- | --- |
+| **DeepCoder-14B-Preview (ours)** | ***60.6*** | ***1936*** | ***95.3*** | ***92.6*** |
+| **DeepSeek-R1-Distill-Qwen-14B** | 53.0 | 1791 | 92.7 | 92.0 |
+| **O1-2024-12-17 (Low)** | 59.5 | **1991** | **96.1** | 90.8 |
+| **O3-Mini-2025-1-31 (Low)** | **60.9** | 1918 | 94.9 | 92.6 |
+| **O1-Preview** | 42.7 | 1658 | 88.5 | 89 |
+| **Deepseek-R1** | 62.8 | 1948 | 95.4 | 92.6 |
+| **Llama-4-Behemoth** | 49.4 | - | - | - |
+
+## Serving DeepCoder
+Our model can be served using popular high-performance inference systems:
+- vLLM
+- Hugging Face Text Generation Inference (TGI)
+- SGLang
+- TensorRT-LLM
+
+All these systems support the OpenAI Chat Completions API format.
+
+### Usage Recommendations
+Our usage recommendations are similar to those of R1 and R1 Distill series:
+1. Avoid adding a system prompt; all instructions should be contained within the user prompt.
+2. `temperature = 0.6`
+3. `top_p = 0.95`
+4. This model performs best with `max_tokens` set to at least `64000` 
+
+## License
+This project is released under the MIT License, reflecting our commitment to open and accessible AI development.
+We believe in democratizing AI technology by making our work freely available for anyone to use, modify, and build upon.
+This permissive license ensures that researchers, developers, and enthusiasts worldwide can leverage and extend our work without restrictions, fostering innovation and collaboration in the AI community.
+
+## Acknowledgement
+- Our training experiments are powered by our heavily modified fork of [Verl](https://github.com/agentica-project/verl), an open-source post-training library.
+- Our model is trained on top of [`DeepSeek-R1-Distill-Qwen-14B`](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B).
+- Our work is done as part of  [Berkeley Sky Computing Lab](https://skycomputing.berkeley.edu/) and [Berkeley AI Research](https://bair.berkeley.edu/).
+
+## Citation 
+```bibtex
+@misc{deepcoder2025,
+  title={DeepCoder: A Fully Open-Source 14B Coder at O3-mini Level},
+  author={Michael Luo, Sijun Tan, Roy Huang, Ameen Patel, Alpay Ariyak, Qingyang Wu, Xiaoxiang Shi, Rachel Xin, Colin Cai, Maurice Weber, Ce Zhang, Li Erran Li, Raluca Ada Popa, Ion Stoica},
+  howpublished={\url{https://pretty-radio-b75.notion.site/DeepCoder-A-Fully-Open-Source-14B-Coder-at-O3-mini-Level-1cf81902c14680b3bee5eb349a512a51}},
+  note={Notion Blog},
+  year={2025}
+}
+```

config.json

@@ -0,0 +1,41 @@
+{
+    "_name_or_path": "agentica-org/DeepCoder-14B-Preview",
+    "architectures": [
+        "Qwen2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 151646,
+    "eos_token_id": 151643,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 13824,
+    "max_position_embeddings": 131072,
+    "max_window_layers": 48,
+    "model_type": "qwen2",
+    "num_attention_heads": 40,
+    "num_hidden_layers": 48,
+    "num_key_value_heads": 8,
+    "pad_token_id": 151643,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "float32",
+    "transformers_version": "4.47.1",
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 152064,
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.2.6",
+        "bits": 6.5,
+        "head_bits": 8,
+        "calibration": {
+            "rows": 115,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151646,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "max_tokens":64000,
+  "transformers_version": "4.47.1"
+}

model.safetensors.index.json

@@ -0,0 +1,586 @@
+{
+  "metadata": {
+    "total_size": 59080134656
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00012-of-00012.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00012.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00012.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00012.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00006-of-00012.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00006-of-00012.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00006-of-00012.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00006-of-00012.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00006-of-00012.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00006-of-00012.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00006-of-00012.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00006-of-00012.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00006-of-00012.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00006-of-00012.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00006-of-00012.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00006-of-00012.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00008-of-00012.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00008-of-00012.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00008-of-00012.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00012.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00012.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00012.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00008-of-00012.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00008-of-00012.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00008-of-00012.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00008-of-00012.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00008-of-00012.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00008-of-00012.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00008-of-00012.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00008-of-00012.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00008-of-00012.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00010-of-00012.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00010-of-00012.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00010-of-00012.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00010-of-00012.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00010-of-00012.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00010-of-00012.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00010-of-00012.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00010-of-00012.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00010-of-00012.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00010-of-00012.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00010-of-00012.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00010-of-00012.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00012-of-00012.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00012-of-00012.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00012-of-00012.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00012-of-00012.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00012-of-00012.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00012-of-00012.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00012-of-00012.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00012.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00012.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00012.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "model.norm.weight": "model-00012-of-00012.safetensors"
+  }
+}

output-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:550790e9a7a31dfbd2a380b231d1752d982031aa8e1e15d34f7b1f85eaca32b0
+size 8584693748

output-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46f93dda9f535ee9f16bfc0a43f785605a12aa54892fdac59f3cc8a841298ff6
+size 4484844024

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778

tokenizer_config.json

@@ -0,0 +1,195 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin��>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}