model card and ckpt

.gitattributes

@@ -33,5 +33,3 @@ 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
-model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
-tokenizer.json filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -1,9 +0,0 @@
-MIT License
-Copyright (c) 2025 Nvidia
-Copyright (c) 2023 DeepSeek
-
-Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

README.md

@@ -1,231 +1,184 @@
----
-pipeline_tag: text-generation
-base_model:
-- deepseek-ai/DeepSeek-R1-0528
-license: mit
-library_name: Model Optimizer
-tags:
-- nvidia
-- ModelOpt
-- DeepSeekR1
-- quantized
-- FP4
----
-# Model Overview
-
-## Description:
-The NVIDIA DeepSeek-R1-0528-FP4 model is the quantized version of the DeepSeek AI's DeepSeek R1 0528 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-R1-0528). 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-R1-0528).
-
-### 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:** 1D (One Dimensional): Sequences <br>
-**Other Properties Related to Input:** DeepSeek recommends adhering to the following configurations when utilizing the DeepSeek-R1 series models, including benchmarking, to achieve the expected performance: \
-
-- Set the temperature within the range of 0.5-0.7 (0.6 is recommended) to prevent endless repetitions or incoherent outputs.
-- Avoid adding a system prompt; all instructions should be contained within the user prompt.
-- For mathematical problems, it is advisable to include a directive in your prompt such as: "Please reason step by step, and put your final answer within \boxed{}."
-- When evaluating model performance, it is recommended to conduct multiple tests and average the results. <br>
-
-## Output:
-**Output Type(s):** Text <br>
-**Output Format:** String <br>
-**Output Parameters:** 1D (One Dimensional): Sequences <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 **v0.31.0**  <br>
-
-## Training Dataset: <br>
-** Data Collection Method by dataset: Hybrid: Human, Automated <br>
-** Labeling Method by dataset: Hybrid: Human, Automated <br>
-
-## Testing Dataset: <br>
-** Data Collection Method by dataset: Hybrid: Human, Automated <br>
-** Labeling Method by dataset: Hybrid: Human, Automated <br>
-
-## Evaluation Dataset: <br>
-** Data Collection Method by dataset: Hybrid: Human, Automated <br>
-** Labeling Method by dataset: Hybrid: Human, Automated <br>
-
-## Calibration Datasets:
-* Calibration Dataset: [cnn_dailymail](https://huggingface.co/datasets/abisee/cnn_dailymail) <br>
-** Data collection method: Automated. <br>
-** Labeling method: Undisclosed. <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 transformer 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:
-```
-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-R1-0528-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()
-
-```
-
-
-#### Minimum Latency Server Deployment
-
-If you want to deploy your endpoint to minimize response latency for a single-concurrency or low-concurrency use case, follow the instructions below.
-
-**Step 1: Create configuration file (`args.yaml`)**
-
-```yaml
-moe_backend: TRTLLM
-use_cuda_graph: true
-speculative_config:
-  decoding_type: MTP
-  num_nextn_predict_layers: 3
-  use_relaxed_acceptance_for_thinking: true
-  relaxed_topk: 10
-  relaxed_delta: 0.6
-```
-
-**Step 2: Start the TensorRT-LLM server**
-
-```bash
-trtllm-serve nvidia/DeepSeek-R1-0528-FP4 \
-  --host 0.0.0.0 \
-  --port 8000 \
-  --backend pytorch \
-  --max_batch_size 4 \
-  --tp_size 8 \
-  --ep_size 2 \
-  --max_num_tokens 32768 \
-  --trust_remote_code \
-  --extra_llm_api_options args.yaml \
-  --kv_cache_free_gpu_memory_fraction 0.75
-```
-
-**Step 3: Send an example query**
-
-```bash
-curl localhost:8000/v1/chat/completions \
-  -H "Content-Type: application/json" \
-  -d '{
-    "model": "nvidia/DeepSeek-R1-0528-FP4",
-    "messages": [{"role": "user", "content": "Why is NVIDIA a great company?"}],
-    "max_tokens": 1024
-  }'
-```
-
-### Evaluation
-The accuracy benchmark results are presented in the table below:
-<table>
-  <tr>
-   <td><strong>Precision</strong>
-   </td>
-   <td><strong>MMLU Pro</strong>
-   </td>
-   <td><strong>GPQA Diamond</strong>
-   </td>
-   <td><strong>LiveCodeBench</strong>
-   </td>
-   <td><strong>SCICODE</strong>
-   </td>
-   <td><strong>MATH-500</strong>
-   </td>
-   <td><strong>AIME 2024</strong>
-   </td>
-  </tr>
-  <tr>
-   <td>FP8 (AA Ref)
-   </td>
-   <td>85
-   </td>
-   <td>81
-   </td>
-   <td>77
-   </td>
-   <td>40
-   </td>
-   <td>98
-   </td>
-   <td>89
-   </td>
-  </tr>
-  <tr>
-   <td>FP4
-   </td>
-   <td>84.2
-   </td>
-   <td>80.0
-   </td>
-   <td>76.3
-   </td>
-   <td>40.1
-   </td>
-   <td>98.1
-   </td>
-   <td>91.3
-   </td>
-  </tr>
-  <tr>
-</table>
-
-## Model Limitations:
-The base model was trained on data that contains toxic language and societal biases originally crawled from the internet. Therefore, the model may amplify those biases and return toxic responses especially when prompted with toxic prompts. The model may generate answers that may be inaccurate, omit key information, or include irrelevant or redundant text producing socially unacceptable or undesirable text, even if the prompt itself does not include anything explicitly offensive.
-
-## 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/).
-
+---
+pipeline_tag: text-generation
+base_model:
+- deepseek-ai/DeepSeek-R1-0528
+license: mit
+library_name: Model Optimizer
+tags:
+- nvidia
+- ModelOpt
+- DeepSeekR1
+- quantized
+- FP4
+---
+# Model Overview
+
+## 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-R1-0528). 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-R1-0528).
+
+### 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:** 1D (One Dimensional): Sequences <br>
+**Other Properties Related to Input:** DeepSeek recommends adhering to the following configurations when utilizing the DeepSeek-R1 series models, including benchmarking, to achieve the expected performance: \
+
+- Set the temperature within the range of 0.5-0.7 (0.6 is recommended) to prevent endless repetitions or incoherent outputs.
+- Avoid adding a system prompt; all instructions should be contained within the user prompt.
+- For mathematical problems, it is advisable to include a directive in your prompt such as: "Please reason step by step, and put your final answer within \boxed{}."
+- When evaluating model performance, it is recommended to conduct multiple tests and average the results. <br>
+
+## Output:
+**Output Type(s):** Text <br>
+**Output Format:** String <br>
+**Output Parameters:** 1D (One Dimensional): Sequences <br>
+
+## Software Integration:
+**Supported Runtime Engine(s):** <br>
+* Tensor(RT)-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 **v0.3123.0**  <br>
+
+## Training Dataset: <br>
+** Data Collection Method by dataset: Hybrid: Human, Automated <br>
+** Labeling Method by dataset: Hybrid: Human, Automated <br>
+
+## Testing Dataset: <br>
+** Data Collection Method by dataset: Hybrid: Human, Automated <br>
+** Labeling Method by dataset: Hybrid: Human, Automated <br>
+
+## Evaluation Dataset: <br>
+** Data Collection Method by dataset: Hybrid: Human, Automated <br>
+** Labeling Method by dataset: Hybrid: Human, Automated <br>
+
+## Calibration 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:** Tensor(RT)-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:
+```
+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-R1-0528-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()
+
+```
+
+### Evaluation
+The accuracy benchmark results are presented in the table below:
+<table>
+  <tr>
+   <td><strong>Precision</strong>
+   </td>
+   <td><strong>MMLU-Pro</strong>
+   </td>
+   <td><strong>GPQA Diamond</strong>
+   </td>
+   <td><strong>HLE</strong>
+   </td>
+   <td><strong>LiveCodeBench</strong>
+   </td>
+   <td><strong>AIME2024</strong>
+   </td>
+  </tr>
+  <tr>
+   <td>FP8
+   </td>
+   <td>85.0
+   </td>
+   <td>81.0
+   </td>
+   <td>17.7
+   </td>
+   <td>73.3
+   </td>
+   <td>91.4
+   </td>
+  </tr>
+  <tr>
+   <td>FP4
+   </td>
+   <td>X
+   </td>
+   <td>X
+   </td>
+   <td>X
+   </td>
+   <td>X
+   </td>
+   <td>X
+   </td>
+  </tr>
+  <tr>
+</table>
+
+## Model Limitations:
+The base model was trained on data that contains toxic language and societal biases originally crawled from the internet. Therefore, the model may amplify those biases and return toxic responses especially when prompted with toxic prompts. The model may generate answers that may be inaccurate, omit key information, or include irrelevant or redundant text producing socially unacceptable or undesirable text, even if the prompt itself does not include anything explicitly offensive.
+
+## 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

@@ -34,6 +34,15 @@
   "q_lora_rank": 1536,
   "qk_nope_head_dim": 128,
   "qk_rope_head_dim": 64,
+  "quantization_config": {
+    "activation_scheme": "dynamic",
+    "fmt": "e4m3",
+    "quant_method": "fp8",
+    "weight_block_size": [
+      128,
+      128
+    ]
+  },
   "rms_norm_eps": 1e-06,
   "rope_scaling": {
     "beta_fast": 32,

configuration_deepseek.py

@@ -1,42 +1,3 @@
-# Adapted from https://huggingface.co/deepseek-ai/DeepSeek-R1-0528/blob/main/configuration_deepseek.py
-# MIT License
-
-# Copyright (c) 2023 DeepSeek
-
-# Permission is hereby granted, free of charge, to any person obtaining a copy
-# of this software and associated documentation files (the "Software"), to deal
-# in the Software without restriction, including without limitation the rights
-# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-# copies of the Software, and to permit persons to whom the Software is
-# furnished to do so, subject to the following conditions:
-
-# The above copyright notice and this permission notice shall be included in all
-# copies or substantial portions of the Software.
-
-# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-# SOFTWARE.
-
-# SPDX-FileCopyrightText: Copyright (c) 2023-2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
-# SPDX-License-Identifier: Apache-2.0
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-
 from transformers.configuration_utils import PretrainedConfig
 from transformers.utils import logging
 

hf_quant_config.json

@@ -1,7 +1,7 @@
 {
     "producer": {
         "name": "modelopt",
-        "version": "0.31.0"
+        "version": "0.30.1.dev58+gbf8bcafc6.d20250529"
     },
     "quantization": {
         "quant_algo": "NVFP4",
@@ -71,8 +71,7 @@
             "model.layers.60.self_attn*",
             "model.layers.7.self_attn*",
             "model.layers.8.self_attn*",
-            "model.layers.9.self_attn*",
-            "model.layers.61*"
+            "model.layers.9.self_attn*"
         ]
     }
 }

model-00001-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbf04b49f4cdb3c2cb139d84e9701089cff14d08b95b969379aa5b57a63a9242
-size 4832128352
+oid sha256:69f66612649ef39a54c958aee7ab95ad6dcd690c52886f22011a599184df66a8
+size 4832127568

model-00004-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca5f80f8d62248366271495d0a9a95953dd5fb06237231a3f8465207d475edd9
-size 2690159456
+oid sha256:f0039648c9461ae4b8a9bd1efba9518b453ac12cc89b392f152d799950a3ae17
+size 2690159256

model-00006-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bb8873103ba89dd16efad52e7846abe7a0ee40af47d4739f3503a82160b1001
-size 2727779136
+oid sha256:bcde09e04afbaf2018feefbc54350d960b560d4ed3b2e04b0a177605285cbaa3
+size 2727778936

model-00009-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f0274233de53fe22c50262c36d6154579af3cc29b83d3b2d601761b0475c810
-size 2690159840
+oid sha256:c4fddcdc66a39c8d572b7ab799c2b9041e9f4921c6bb2de2dbcc71ceade1c110
+size 2690159640

model-00013-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc6ed60abb1be1223979884405aad63f35e5eec42c28b73773bd19f834c90065
-size 2690130224
+oid sha256:7b7be8ce09917e5e08b88fc7ad5901b545d280e2e9d02162568b426bb6888f42
+size 2690130024

model-00015-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afbdb1f5da08dc38ecaf900ae8866e4687a3ec9e2b21b16d0cba7fa3d529b74a
-size 2690159904
+oid sha256:a966910f03d23623906864a3b07a67a6acb783192b378175d74738e821bca307
+size 2690159704

model-00018-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca0e49de986c19b866bf2c330ca91f8c0a092ee56e19ce832267f375174cc496
-size 2690159520
+oid sha256:558f96a63196f303c62da85151dfa8d080fdc44e69a985533158b8ce390f9082
+size 2690159320

model-00021-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4929c6acd11fa3f87465aef13e5ce7e3d24c83a1babac6d1c99c0201bba7985b
-size 2690160248
+oid sha256:a168b5c767494472f373656539a48abaeaeb1f45262f3ab3d607ee7418767212
+size 2690160048

model-00023-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f861d34dfd9299c043ba0c351505bef3a107d8f95ea8a46ceda8a3ebf6f2625
-size 2690161056
+oid sha256:992ddc04bdcd10549949fa0c17dbb9fc02d944ba6489251f73e67715a555052c
+size 2690160856

model-00026-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d181f80f2aaf9cb7bdf68e421b950d64a583a52420ce5fd0d3b411ed33c3ea66
-size 2690160688
+oid sha256:5505979629cbb9fbd0e02675526ae476d63b56e7839e9569a191e94160aa5e8f
+size 2690160480

model-00029-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecf62e772486af899afb440540803550480343b66e5dc096e1e4a8dea6a44154
-size 2690160304
+oid sha256:59a6ebae0d72537d1d58ee3e01254388d42798362d6cd66bbc1d9c1dab5cadb6
+size 2690160104

model-00031-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70e471763de9f5ad8b12cc26be6f44d48c8ebcbb7f1c4a57f4eaabf112f7f57f
-size 2690161096
+oid sha256:7a2f8473930712f9a654f2e6c1a89103cba04bc4b62f1100b191f19783271747
+size 2690160896

model-00035-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3898dfd91f59bec65c82ae04b707575501e32f43d2f1dfb26174912f01d0fd5
-size 2690131360
+oid sha256:63a2df1ce7bf96c7419cc1e7d98959dfe28106b8c258d3192ccfa9dc637f905a
+size 2690131152

model-00037-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77afb4330256683ef7962bf43cae8762f80fb0edf889be55073f421c3ad24930
-size 2690161032
+oid sha256:a31847366fe7a829f5aeba504d859b82416fe339c59842060b932d9174019948
+size 2690160832

model-00040-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54bee64d4e307768da9a6bf437e00eec91e3a4986a2358d2d5eb41d915f4dd0e
-size 2690160656
+oid sha256:900a430029d5b16783d10b2e7d94490cb92c74241f9c9fe99e2bb8022ae537ac
+size 2690160448

model-00043-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bad155fdce361b40b328edbe35e3995cf6e149e1f798eba415db58ff998880fb
-size 2690160264
+oid sha256:72080a68818ac0960460f21ed4850cee022cc0af00b7778a10f6dc095ec46461
+size 2690160064

model-00045-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:215c3ee090030d9f6a12cac238e1cdc14c1bf7d33a45eb5a84114986a65e988c
-size 2690161056
+oid sha256:71a19d75f923f56e2140219e3ef326042948004140873d4b94360fd77c13e597
+size 2690160856

model-00048-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:171a534fa7797a90cfcfc5b340a25013359750ef37f637b89d7ce5665b13d191
-size 2690160688
+oid sha256:86f47ab2daa219706de56cacbda917b9d79b2539f35850ea67b8e1e514b28315
+size 2690160480

model-00051-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e07cadc4d02a7783e0ea6edfeeff88bbcf02b78679ad4efe32592c54d154208
-size 2690160304
+oid sha256:2d11349318b977a53ff7513aac566dfbd4232f058e328f83179972d3504bb083
+size 2690160104

model-00053-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96fa3cc110f476e1414000da8431ddac767c694143a20f07cfb14de62bdbe419
-size 2690161096
+oid sha256:3ca68cdf2376332059feca8cc03a5c1912e8cc25c614d27e8c85df39281a5055
+size 2690160896

model-00057-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ec5916a49938b634be79548cbe6944660fdcacbdb255a6393932fd404e796ee
-size 2690131360
+oid sha256:d13ab8cdf7743fdd81894f591ac23e3ca3e69a16235f5320a3535b2972e42b0c
+size 2690131152

model-00059-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0eb7d1c45c8444dbcfc152b44280357543fc1b798f9dc38cd7cb555204f55d99
-size 2690161032
+oid sha256:bff3c0da0cdf666cbb63fa717268537e394f7b4faf61f124cf4b71305e18c54c
+size 2690160832

model-00062-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14ac6babc7b5ec03944a0253aa3276d114e07e36221d797fca50292ab4f371da
-size 2690160656
+oid sha256:944db79ae743a5ac9720ab043e5e98ab20665866d95b786c57b5fa8028893d4b
+size 2690160448

model-00065-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5341f93faa5c992d684f234c3a479aab87eb3b4576b1f978eb119476131a8ef2
-size 2690160264
+oid sha256:41185edfe9c1c78328fc700cee93ecdc9783d547cbdcb46276c4e7d2be80961f
+size 2690160064

model-00067-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ec23f22dcae3d5d883dc925ce70d463a6c9bba3c1f9b5150d447ccfee451e77
-size 2690161056
+oid sha256:ccc70a20cb14579863f232de99d7af9732d061679272a0b826c392bd5ab1205f
+size 2690160856

model-00070-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f7ee508718627657ef87966a885a9956f3734674cb988fcb0bbb9e22de005d1
-size 2690160688
+oid sha256:9a6c2dfa545adc2ef06feceb62c795cb2585580c36f25708ce1d083eae8b77d4
+size 2690160480

model-00073-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b53bc434459993f27ce202bd913640f64129c6d91cea6445fddaf6869ea3e618
-size 2690160304
+oid sha256:24af6569c4d847d2954c77de3e24082b9c7a66334f1f81a8728d0c3bbe417853
+size 2690160104

model-00075-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0eac1ff5b435996ca17677429909307081eced38c7aa8543f54569e509a18b7c
-size 2690161096
+oid sha256:a3d2c9d9d1794ee7a0d4fee0ef1eb3321ab3d4ad991352c3bfe8fe78fccd2f46
+size 2690160896

model-00079-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2cbd1c7ac0762ae69a453fdca414ff3b41d6a831e36f33a0e365eeb3a4f7796
-size 2690131360
+oid sha256:3b585eb7094c691ef787970fa0ae2d3c427a03595215ffe70c7a4cbacdf3e18b
+size 2690131152

model-00081-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f1bf3ae7b459e3471ead763cacddaf77b030c1bd153ae7c6c330fbe9309a75a
-size 2690161032
+oid sha256:2190fefe1a93f6cf09f04b879cb8dba094f3b3afa4d47e25121326e1b8646f02
+size 2690160832

model-00084-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f43e8dbbfbdbf808a11d8c42668aed50855b668e0f3c1a3cbd007e6b03652e78
-size 2690160656
+oid sha256:c4ede132e8f8513f762f3f65863457703ec8b6c54be5acd6e37b24595a4bb1f1
+size 2690160448

model-00087-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9eb75ba7b09bffab0a4d45fe739ab339db47352c227ca0ee15beed80cc1e7da5
-size 2690160264
+oid sha256:5e891a2a8a345d52c92f004066963c7390c9dc278a59fe27fa129bebc12834cf
+size 2690160064

model-00089-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cde75047119b80d9bb27333d9d52340b56c5c3879cb326f7418dd589dfd73d8
-size 2690161056
+oid sha256:be8bd46bc4560f7a975c32548d0ee502d331b33b0189140792280be1a7592ab7
+size 2690160856

model-00092-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1c78001c5e2ac6ae5a8212e87440091dd56142c0f8829da3c463e0f717725bb
-size 2690160688
+oid sha256:e18566aea8bc3d34cd0937d1469e3f64e0cb2783dbffb766d461122edc9cf52f
+size 2690160480

model-00095-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76c031439199fdba5c01bc8ad571a0f8655c3ce1a04bb466338c25ca5256cd6c
-size 2690160304
+oid sha256:39abbe929f0a73aaa822696eaf889906d00b3ba0aff9a5dc7de77a927b4eaeb8
+size 2690160104

model-00097-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ceebab7ff4022aaa21e15ff05e6a3ebd4a334e10049bf721d3e2519b98514737
-size 2690161096
+oid sha256:ce5c0a2e5d41fbe1501c22cea88c8494bb5dec07a521395f5e6015bc59a28b6e
+size 2690160896

model-00101-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d99c26d1874005fee504b44ac96c496a496ff25cb87ff755832e926541a48492
-size 2690131360
+oid sha256:b86d1435e4e39919062771696279dfb097374f4d48dae1d931ed21f2b3ec2cfc
+size 2690131152

model-00103-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:babcf9affea89d453f2023379a34b32d0ecc4f9b2787255c0fcb8889cabc093a
-size 2690161032
+oid sha256:c870af132544963d16515899b257b097cc5fadcc8e79be6b2f0e29f08a275efd
+size 2690160832

model-00106-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9a5527aede2cb7f292671d86f2864d6fc843396466d16f60e74743d7fc0a6ee
-size 2690160656
+oid sha256:a3f3a911cffe28d2935faec268d3e90bf9889a346b18227bdc18580e9b17d534
+size 2690160448

model-00109-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb9ac1d529250b0524bd86864725144d45d5e91c70e77375ff0bf30434633250
-size 2690160264
+oid sha256:ef0b1f87d84b84665fc271ea843ab906f7382fbb5944d678fe2e5e425a4bde63
+size 2690160064

model-00111-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ada750ccc74bcc4c283332ce7ca573c74254ed61931737b1d739e9b633d0e78
-size 2690161056
+oid sha256:69e156f4f325de69dc852b53bb448a3ac1e428518140291a0965d0bc6f823001
+size 2690160856

model-00114-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12fa6385c3932d28de5300199e53aadacc8a0d3638d03c42f5cbac71f2d8574b
-size 2690160688
+oid sha256:062f5666f7d8d560df9973a6ea72ad64ac8fc72b8eec9160db9eb5c71572f380
+size 2690160480

model-00117-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dc24b7fcbc6517c62222ca7da18bc664d5f1da5e2efcc8bcb8d5fd590652b78
-size 2690160304
+oid sha256:b4b8b4a2dcf942e86946904a999202bf4458f87cbe517c4c10d4f6e2657cf0af
+size 2690160104

model-00119-of-000163.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dae3a9aceb361372feef019635c17a1bda7c826dba8cacbcb3881ea7de2139db
-size 2690161096
+oid sha256:34af4a17310b76ac7814c8fe58feaa1cf8552473b7ef11441ed7a050b1dd6b03
+size 2690160896