Add files using upload-large-folder tool

README.md

@@ -4,32 +4,153 @@ base_model:
 - deepseek-ai/DeepSeek-R1
 license: mit
 ---
+# Model Overview
 
-Results from running `vllm serve RedHatAI/DeepSeek-R1-NVFP4-FP8-BLOCK --tensor-parallel-size=4` on 4 B200s, with `python vllm/tests/evals/gsm8k/gsm8k_eval.py --port 8000`:
+## Description:
+The NVIDIA DeepSeek R1 FP4 model is the quantized version of the DeepSeek AI's DeepSeek R1 model, which is an auto-regressive language model that uses an optimized transformer architecture. For more information, please check [here](https://huggingface.co/deepseek-ai/DeepSeek-R1). The NVIDIA DeepSeek R1 FP4 model is quantized with [TensorRT Model Optimizer](https://github.com/NVIDIA/TensorRT-Model-Optimizer).
 
+This model is ready for commercial/non-commercial use.  <br>
+
+## Third-Party Community Consideration
+This model is not owned or developed by NVIDIA. This model has been developed and built to a third-party’s requirements for this application and use case; see link to Non-NVIDIA [(DeepSeek R1) Model Card](https://huggingface.co/deepseek-ai/DeepSeek-R1).
+
+### License/Terms of Use:
+[MIT](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/mit.md)
+
+
+## Model Architecture:
+**Architecture Type:** Transformers  <br>
+**Network Architecture:** DeepSeek R1 <br>
+
+## Input:
+**Input Type(s):** Text <br>
+**Input Format(s):** String <br>
+**Input Parameters:** One Dimensional(1D): Sequences <br>
+**Other Properties Related to Input:** Context length up to 128K <br>
+
+## Output:
+**Output Type(s):** Text <br>
+**Output Format:** String <br>
+**Output Parameters:** 1D: Sequences <br>
+**Other Properties Related to Output:** N/A <br>
+
+## Software Integration:
+**Supported Runtime Engine(s):** <br>
+* TensorRT-LLM <br>
+
+**Supported Hardware Microarchitecture Compatibility:** <br>
+* NVIDIA Blackwell <br>
+
+**Preferred Operating System(s):** <br>
+* Linux <br>
+
+## Model Version(s):
+The model is quantized with nvidia-modelopt **v0.23.0**  <br>
+
+## Datasets:
+* Calibration Dataset: [cnn_dailymail](https://huggingface.co/datasets/abisee/cnn_dailymail) <br>
+** Data collection method: Automated. <br>
+** Labeling method: Unknown. <br>
+* Evaluation Dataset: [MMLU](https://github.com/hendrycks/test)  <br>
+** Data collection method: Unknown. <br>
+** Labeling method: N/A. <br>
+
+
+## Inference:
+**Engine:** TensorRT-LLM <br>
+**Test Hardware:** B200 <br>
+
+## Post Training Quantization
+This model was obtained by quantizing the weights and activations of DeepSeek R1 to FP4 data type, ready for inference with TensorRT-LLM. Only the weights and activations of the linear operators within transformers blocks are quantized. This optimization reduces the number of bits per parameter from 8 to 4, reducing the disk size and GPU memory requirements by approximately 1.6x.
+
+## Usage
+
+### Deploy with TensorRT-LLM
+
+To deploy the quantized FP4 checkpoint with [TensorRT-LLM](https://github.com/NVIDIA/TensorRT-LLM) LLM API, follow the sample codes below (you need 8xB200 GPU and TensorRT LLM built from source with the latest main branch):
+
+* LLM API sample usage:
 ```
-Running GSM8K evaluation: 1319 questions, 5-shot
-Evaluating: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1319/1319 [01:49<00:00, 12.09it/s]
-
-Results:
-Accuracy: 0.952
-Invalid responses: 0.000
-Total latency: 109.097 s
-Questions per second: 12.090
-Total output tokens: 124914
-Output tokens per second: 1144.985
-```
+from tensorrt_llm import SamplingParams
+from tensorrt_llm._torch import LLM
+
+def main():
+
+    prompts = [
+        "Hello, my name is",
+        "The president of the United States is",
+        "The capital of France is",
+        "The future of AI is",
+    ]
+    sampling_params = SamplingParams(max_tokens=32)
+
+    llm = LLM(model="nvidia/DeepSeek-R1-FP4", tensor_parallel_size=8, enable_attention_dp=True)
+
+    outputs = llm.generate(prompts, sampling_params)
+
+    # Print the outputs.
+    for output in outputs:
+        prompt = output.prompt
+        generated_text = output.outputs[0].text
+        print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
+
+
+# The entry point of the program need to be protected for spawning processes.
+if __name__ == '__main__':
+    main()
 
-Compare to results with `nvidia/DeepSeek-R1-NVFP4`
 ```
-Running GSM8K evaluation: 1319 questions, 5-shot
-Evaluating: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████��███████| 1319/1319 [01:52<00:00, 11.74it/s]
-
-Results:
-Accuracy: 0.954
-Invalid responses: 0.000
-Total latency: 112.357 s
-Questions per second: 11.739
-Total output tokens: 128126
-Output tokens per second: 1140.344
-```
+
+### Evaluation
+The accuracy benchmark results are presented in the table below:
+<table>
+  <tr>
+   <td><strong>Precision</strong>
+   </td>
+   <td><strong>MMLU</strong>
+   </td>
+   <td><strong>GSM8K</strong>
+   </td>
+   <td><strong>AIME2024</strong>
+   </td>
+   <td><strong>GPQA Diamond</strong>
+   </td>
+   <td><strong>MATH-500</strong>
+   </td>
+  </tr>
+  <tr>
+   <td>FP8
+   </td>
+   <td>90.8
+   </td>
+   <td>96.3
+   </td>
+   <td>80.0
+   </td>
+   <td>69.7
+   </td>
+   <td>95.4
+   </td>
+  </tr>
+  <tr>
+   <td>FP4
+   </td>
+   <td>90.7
+   </td>
+   <td>96.1
+   </td>
+   <td>80.0
+   </td>
+   <td>69.2
+   </td>
+   <td>94.2
+   </td>
+  </tr>
+  <tr>
+</table>
+
+## Ethical Considerations
+
+NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications.  When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.
+
+Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).

config.json

@@ -40,6 +40,7 @@
         "config_groups": {
             "config_group_0": {
                 "targets": [
+                    "re:.*self_attn.(kv_a_proj_with_mqa|q_a_proj)$",
                     "re:.*self_attn.(o_proj|q_b_proj).*"
                 ],
                 "weights": {
@@ -56,7 +57,7 @@
                     "actorder": null,
                     "scale_dtype": null,
                     "zp_dtype": null,
-                    "observer": "static_minmax",
+                    "observer": "memoryless_minmax",
                     "observer_kwargs": {}
                 },
                 "input_activations": {
@@ -91,7 +92,7 @@
                     "actorder": null,
                     "scale_dtype": "torch.float8_e4m3fn",
                     "zp_dtype": null,
-                    "observer": "static_minmax",
+                    "observer": "memoryless_minmax",
                     "observer_kwargs": {}
                 },
                 "input_activations": {
@@ -118,7 +119,7 @@
         "quantization_status": "compressed",
         "global_compression_ratio": null,
         "ignore": [
-            "re:.*self_attn.(kv_a_proj_with_mqa|kv_b_proj|q_a_proj)$"
+            "re:.*self_attn.kv_b_proj$"
         ]
     },
     "rms_norm_eps": 1e-06,

model-00001-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c577c1f8f9039f367a10f952371d685462562194dd8bcf413428b38dd13f4916
-size 4747304092
+oid sha256:ddbdea3126f86461cc6e0a754a81d4e9cada1a5a1166d55dc27f8c64b381e572
+size 4686754212

model-00003-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37bae77e9794030d439280a70fc4418869137614a5404f7e43577d7e2f4e4e75
-size 5210583888
+oid sha256:d7808defe3cbfd53f03684edfee441788cf164155bbe04df9ddbade63a29eb8c
+size 5195435688

model-00005-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7144aa9a8c550b60cee4d8c2aef27374ac587470823684bb9666096a3bcd6284
-size 5210598400
+oid sha256:2624a747e615f7021e5a867c5552dcc3265bbc600c5b3f3a2c8c19f17d16e572
+size 5195450192

model-00007-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efe393d136e827b35a1eff9878d1eb1c66db2f4166418a45869243f36d369691
-size 5210598856
+oid sha256:ce98120048c5cde10600ad47d7206c2d8d3b648f75c14674f9a230e288a7f284
+size 5195450648

model-00008-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0baafdbe7d4aeaded563fe4b0eef3e6e66dacefe972fa477c11930b700b290d
-size 5210569368
+oid sha256:4e204042e014a7eaaad90be918cf5d469a32033c6468c2bf0d4aa36e4bd8a4c6
+size 5195421160

model-00009-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9ec7c6811d2c482bd77c4128f74782f5ec941e16e072f740b947488598597a0
-size 5210598160
+oid sha256:6c0811581fa31ab8fc38243eb05f48675edff40e119f39e40b9d0f2f794d216c
+size 5195449952

model-00013-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf9e4834a74d8344a10a095329582843d6173cd663fef17118ac4915b8f74d3a
-size 5210571728
+oid sha256:460cfb80f78286973006b2ab1a09697016ee56ed9bf8d524f9967d2061406b70
+size 5195423520

model-00014-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:553ccfd57d0d093d16f4b8bde805a16b5e60c0cb3200b13c10bf6e8aac092aa5
-size 5210600712
+oid sha256:649b47a429c4d5672bc1a8fc311763180d1cde7be745d1e0f44c29f443c0d927
+size 5195452512

model-00015-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a11d0b87f06a1962bc808e1dc1f47b9fc83f97f3332c2e50c64d696f262197c0
-size 5210600728
+oid sha256:7074a7eecaf8c113a3299c3909e6dbdc5bfc3453a647c6e0c529b40620fd3cc9
+size 5195452528

model-00017-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0ecb572a8ed62d65d7e9864bb933d412f3e71b3893ac141c7cfd5045dbcc0ac
-size 5210586800
+oid sha256:67af704ba8869984abe9a086e81d1eea7ddf9cfd8a76c94e717ce7014a29b38b
+size 5195438600

model-00018-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cb5bad119fcfe28183208add8b7975041d633c6149cc0157682cd81a50864d7
-size 5210586120
+oid sha256:1f02c36d8965ab020a1c7891ee5bf8d6409df0d009a3f4f2f55735828cf51a68
+size 5195437920

model-00019-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f793316e80367c6702fd3208be83e6a020cc47a8be83fee9fb03682cae471ca5
-size 5210600736
+oid sha256:04835f5e0a306f964ea8d42cd247c64c11478ec34bd49397e47a5e9ed32f7e88
+size 5195452528

model-00020-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a38165ff3220725f456f9775cdd53a462ba503e31b7f5c71b6403d7da4455ba
-size 5148980796
+oid sha256:c0548af8e6f0e9af0929480b2a9c5814384f5b6cc5fa3b767c0f4935ea8b8081
+size 5144840964

model-00021-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b83e35861c1dcc15ed0db840acc736c99c95943438871ab164cd7f0ac3459902
-size 5094080624
+oid sha256:3553b92ea19659ee6228bd00acc2b89be46da7d1df89427e183fe0aa0137c497
+size 5067924360

model-00024-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:502b718fb358b10aed72e3852a22eb13f9255c5530d0d66861cf5ba425674add
-size 5210600712
+oid sha256:cac149e544ffd32b1142021f06d2a3b21fd0dbe104465a08d77c688fbaa3de2d
+size 5195452504

model-00025-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bb05d262f58434ed53d19b87f5d404090bf46a24ebfc98f5f8bca0cf81994c8
-size 5210600984
+oid sha256:6b475679e93e22dcb48fed7c2e66004c9ad33d436964aa570bf68424dde5d08a
+size 5195452776

model-00027-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:012b5473570f76fde57596a142a45a0f11504ae22238bd85319f92ac49505be8
-size 5210586536
+oid sha256:095cb6550dc2352de9175807bdf77ddad67e56adcb9117d1584869073e4840cc
+size 5195438328

model-00028-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e72abc9f9a3fb530b7e0f94b08b7c89a393c5730061e7426a20697fade6edec
-size 5210586120
+oid sha256:4d4342eb40e2e84f244b40e027f94426a8f35f433797b2b5a49a3072e87a7693
+size 5195437920

model-00029-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a30ac8b1afa9b920c53f488660eff7870a9ac66aefc4d16e580d93997746550
-size 5210600984
+oid sha256:cce00297a42ffab3b1e056a7f368c12dfb279837142087e3571f0fc51f9f53f5
+size 5195452776

model-00032-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1540a5594d1b931fcc62d576750719cf02db33b2337db3470a03746dcb2a1961
-size 5206914204
+oid sha256:77dbe478f57c6c2db58e42bf1509ae0759188b3a0ada53388379e7a0fc7a46a2
+size 5191765988

model-00033-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5731e61c36494d02d468d70a7ed1c244eb6b821afbf1cd6e18c4f1c61db4dcf
-size 5210586120
+oid sha256:42d258270b07b56532df9919a05d83651dca5dd4c222ef38ef26470e6fc88aaa
+size 5195437920

model-00034-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dab5fcebc49b46e58963501164212bed091ed15ab899b0057c376527f2f8b484
-size 5210600712
+oid sha256:5b265435e10625fc707ef554d489b41aa4c9bb17c627ac703183cb7f0e7efe3f
+size 5195452512

model-00037-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a88290928247e75f29a7af41cb722d5741cd85adf7764cc4afdc2ad19ec77f62
-size 5210586368
+oid sha256:ddbc893603b8e0106391d81f199b08d270ca44ea22eff36e93b9423ad820f062
+size 5195438168

model-00038-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43801398ed20fb8bb94eb1a7b8ffd75aa09a95c407a253405fab9d853841dc19
-size 5210586120
+oid sha256:768d501abeebe39a4d23d0686099afce58d3a1af58d99d855372259f4aef72e3
+size 5195437920

model-00042-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0a68c91d1e4be1e42d27c609cd38be8ae6769af91b8022c8e275621628f28c6
-size 5210571856
+oid sha256:3446ff0423431ab1b23626f2e2979e40b42033c775ca34fad5e86a75a864fefb
+size 5195423648

model-00044-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dd013f867ca92af05a8619e11deddf0eeea8130d680505624568a9905ddca5f
-size 5210600712
+oid sha256:1f542759b658a83f5dce1d105c9833c6a941c9ea4e5a2890514817f912dddfab
+size 5195452512

model-00045-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3c59c2f007f79796204f89282f735ecfee822c67901c8b81f83ee9337c9a468
-size 5210601272
+oid sha256:2a2d73a155ec921a581f5aad47f1b666ac06b53ce467bf14f8b22c4e22294ffd
+size 5195453064

model-00047-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:079e31b088d7881605cda369c7cd3131443740899e051536ccc591d58d0a8afe
-size 5210586216
+oid sha256:430116dd6133aae72982dca9c7a908bafa1f4a074909e762d23fb61430ae694b
+size 5195438008

model-00051-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6820b57b4e50972a8dd8d1198efb54c17a44e9e1567dbe1c16761aee27c771e1
-size 5210601296
+oid sha256:03e15561ddb96416cdf7ac89c485dd03f3c21ca40605d79d2e0e1f346a159bdd
+size 5195453096

model-00052-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c0b212edf1d350fda896e43581343c8604c827d2ae9b0726b0052824b7e65f6
-size 5210571688
+oid sha256:194dc3792fcf180b2c1e045516377a71793e4913c47bb3247c9c181ce6da2761
+size 5195423480

model-00054-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24136263254bd6b9b79239c02263ffc760ba4602a0898490ae45d5cf270e3338
-size 5210600624
+oid sha256:f4694717aed6ff3863601c42cd0f6a119c5c618bafd6f37d7d14cd83e661a22d
+size 5195452416

model-00055-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9c9442436b8f42c58099db37411c7e3552b548e7c440069709ec7993540d96c
-size 5210601344
+oid sha256:c32299c8946b40736880ddc38493e13036031db45925991808217eb1f1e0a8f6
+size 5195453144

model-00062-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b186ce6995b7989b774c929b62d486f5f250d578a1e003f225b39809e59ef9e6
-size 5210586120
+oid sha256:460492a615d3cc8190d8177f8547b9c15f4c03a1b790beba354a9aa7bb7d0e48
+size 5195437912

model-00066-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8264d594762ed8db1c7bc88fe872abbc130eb53b3f42c56202ee24ae121cd05b
-size 5211504456
+oid sha256:827796efeb138b3067767208e53c9d18fede0a596e0087bb33fe38521ff735fa
+size 5196356232

model-00067-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0af3bcf994ed93fd29a5a1a476f161e4c9d65a938ea2a70a2b8cf18915b71c5
-size 5210586120
+oid sha256:72e37cc621f024f11829e9dfdb5209c1fabf602192e837eaa1e4765c60c7aba9
+size 5195437912

model-00068-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:272c51491b7a9c1b70796bd6f7e4831cacda185b9e10472f519409689eb17365
-size 5210600944
+oid sha256:59b75afede2bdb54d46f49785394ae78b99d14ccb5e8be12ea5bfd74f07bc889
+size 5195452744

model-00070-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1e30db5c5c9a00692000704543814e138015b70d0f50670e4e8709b11d42402
-size 5165247420
+oid sha256:5bb89dcb1e6204fea6007a5320b4ff32cb2c3b0aef50e6440f3e832dd3cce5c0
+size 5145971364

model-00072-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f11222b0fc6542f8af8223ab8580f4c3ae3b2261ee60c8dc7d78fdc4ee76298
-size 5211504000
+oid sha256:4a92f4dcf7447a0ba7ce60904ed1d357d56fa7d5da35f4adb58857db1a1cb47c
+size 5196355784

model-00079-of-00080.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88452f6262014b9e6037430abf81719d3ef6f13f5d8f76f7754c8679deda0445
-size 3640686792
+oid sha256:4b1c6a025aa30517a685976e247f9d9baa66d1212c1e57b09c3b9c441cbcdab2
+size 3640685920

model.safetensors.index.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:752ecdc83164e3bfd02f906dcd790c6e3fdbc9dcf0e7b88d3ab78d8b9cd331f2
-size 18089328
+oid sha256:1f514dfcbf619648c797394c851bc00df043f37ccc71b2766a2220bfe08ecb46
+size 17246002

old_config.json

@@ -0,0 +1,115 @@
+{
+    "architectures": [
+        "DeepseekV3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "auto_map": {
+        "AutoConfig": "configuration_deepseek.DeepseekV3Config",
+        "AutoModel": "modeling_deepseek.DeepseekV3Model",
+        "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
+    },
+    "aux_loss_alpha": 0.001,
+    "bos_token_id": 0,
+    "eos_token_id": 1,
+    "ep_size": 1,
+    "first_k_dense_replace": 3,
+    "hidden_act": "silu",
+    "hidden_size": 7168,
+    "initializer_range": 0.02,
+    "intermediate_size": 18432,
+    "kv_lora_rank": 512,
+    "max_position_embeddings": 163840,
+    "model_type": "deepseek_v3",
+    "moe_intermediate_size": 2048,
+    "moe_layer_freq": 1,
+    "n_group": 8,
+    "n_routed_experts": 256,
+    "n_shared_experts": 1,
+    "norm_topk_prob": true,
+    "num_attention_heads": 128,
+    "num_experts_per_tok": 8,
+    "num_hidden_layers": 61,
+    "num_key_value_heads": 128,
+    "num_nextn_predict_layers": 1,
+    "pretraining_tp": 1,
+    "q_lora_rank": 1536,
+    "qk_nope_head_dim": 128,
+    "qk_rope_head_dim": 64,
+    "quantization_config": {
+        "config_groups": {
+            "config_group_0": {
+                "format": "float-quantized",
+                "input_activations": {
+                    "actorder": null,
+                    "block_structure": null,
+                    "dynamic": true,
+                    "group_size": 128,
+                    "num_bits": 8,
+                    "observer": null,
+                    "observer_kwargs": {},
+                    "scale_dtype": null,
+                    "strategy": "group",
+                    "symmetric": true,
+                    "type": "float",
+                    "zp_dtype": null
+                },
+                "output_activations": null,
+                "targets": [
+                    "re:.*self_attn.(kv_a_proj_with_mqa|q_a_proj)$",
+                    "re:.*self_attn.(o_proj|q_b_proj).*"
+                ],
+                "weights": {
+                    "actorder": null,
+                    "block_structure": [
+                        128,
+                        128
+                    ],
+                    "dynamic": false,
+                    "group_size": null,
+                    "num_bits": 8,
+                    "observer": "memoryless_minmax",
+                    "observer_kwargs": {},
+                    "scale_dtype": null,
+                    "strategy": "block",
+                    "symmetric": true,
+                    "type": "float",
+                    "zp_dtype": null
+                }
+            }
+        },
+        "format": "float-quantized",
+        "global_compression_ratio": null,
+        "ignore": [
+            "re:.*self_attn.kv_b_proj$"
+        ],
+        "kv_cache_scheme": null,
+        "quant_method": "compressed-tensors",
+        "quantization_status": "compressed",
+        "sparsity_config": {},
+        "transform_config": {},
+        "version": "0.13.1.dev47+gcfc24ef"
+    },
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+        "beta_fast": 32,
+        "beta_slow": 1,
+        "factor": 40,
+        "mscale": 1.0,
+        "mscale_all_dim": 1.0,
+        "original_max_position_embeddings": 4096,
+        "type": "yarn"
+    },
+    "rope_theta": 10000,
+    "routed_scaling_factor": 2.5,
+    "scoring_func": "sigmoid",
+    "seq_aux": true,
+    "tie_word_embeddings": false,
+    "topk_group": 4,
+    "topk_method": "noaux_tc",
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.46.3",
+    "use_cache": true,
+    "v_head_dim": 128,
+    "vocab_size": 129280
+}