Add files using upload-large-folder tool

LICENSE

@@ -0,0 +1,21 @@
+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.

README.md

@@ -0,0 +1,239 @@
+---
+license: mit
+library_name: transformers
+---
+# DeepSeek-R1
+<!-- markdownlint-disable first-line-h1 -->
+<!-- markdownlint-disable html -->
+<!-- markdownlint-disable no-duplicate-header -->
+
+<div align="center">
+  <img src="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/logo.svg?raw=true" width="60%" alt="DeepSeek-V3" />
+</div>
+<hr>
+<div align="center" style="line-height: 1;">
+  <a href="https://www.deepseek.com/" target="_blank" style="margin: 2px;">
+    <img alt="Homepage" src="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/badge.svg?raw=true" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+  <a href="https://chat.deepseek.com/" target="_blank" style="margin: 2px;">
+    <img alt="Chat" src="https://img.shields.io/badge/🤖%20Chat-DeepSeek%20R1-536af5?color=536af5&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+  <a href="https://huggingface.co/deepseek-ai" target="_blank" style="margin: 2px;">
+    <img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-DeepSeek%20AI-ffc107?color=ffc107&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+</div>
+
+<div align="center" style="line-height: 1;">
+  <a href="https://discord.gg/Tc7c45Zzu5" target="_blank" style="margin: 2px;">
+    <img alt="Discord" src="https://img.shields.io/badge/Discord-DeepSeek%20AI-7289da?logo=discord&logoColor=white&color=7289da" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+  <a href="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/qr.jpeg?raw=true" target="_blank" style="margin: 2px;">
+    <img alt="Wechat" src="https://img.shields.io/badge/WeChat-DeepSeek%20AI-brightgreen?logo=wechat&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+  <a href="https://twitter.com/deepseek_ai" target="_blank" style="margin: 2px;">
+    <img alt="Twitter Follow" src="https://img.shields.io/badge/Twitter-deepseek_ai-white?logo=x&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+</div>
+
+<div align="center" style="line-height: 1;">
+  <a href="https://github.com/deepseek-ai/DeepSeek-R1/blob/main/LICENSE" style="margin: 2px;">
+    <img alt="License" src="https://img.shields.io/badge/License-MIT-f5de53?&color=f5de53" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+</div>
+
+
+<p align="center">
+  <a href="https://github.com/deepseek-ai/DeepSeek-R1/blob/main/DeepSeek_R1.pdf"><b>Paper Link</b>👁️</a>
+</p>
+
+
+## 1. Introduction
+
+We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. 
+DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step, demonstrated remarkable performance on reasoning.
+With RL, DeepSeek-R1-Zero naturally emerged with numerous powerful and interesting reasoning behaviors.
+However, DeepSeek-R1-Zero encounters challenges such as endless repetition, poor readability, and language mixing. To address these issues and further enhance reasoning performance,
+we introduce DeepSeek-R1, which incorporates cold-start data before RL.
+DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks. 
+To support the research community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six dense models distilled from DeepSeek-R1 based on Llama and Qwen. DeepSeek-R1-Distill-Qwen-32B outperforms OpenAI-o1-mini across various benchmarks, achieving new state-of-the-art results for dense models.
+
+**NOTE: Before running DeepSeek-R1 series models locally, we kindly recommend reviewing the [Usage Recommendation](#usage-recommendations) section.**
+
+<p align="center">
+  <img width="80%" src="figures/benchmark.jpg">
+</p>
+
+## 2. Model Summary
+
+---
+
+**Post-Training: Large-Scale Reinforcement Learning on the Base Model**
+
+-  We directly apply reinforcement learning (RL) to the base model without relying on supervised fine-tuning (SFT) as a preliminary step. This approach allows the model to explore chain-of-thought (CoT) for solving complex problems, resulting in the development of DeepSeek-R1-Zero. DeepSeek-R1-Zero demonstrates capabilities such as self-verification, reflection, and generating long CoTs, marking a significant milestone for the research community. Notably, it is the first open research to validate that reasoning capabilities of LLMs can be incentivized purely through RL, without the need for SFT. This breakthrough paves the way for future advancements in this area.
+
+-   We introduce our pipeline to develop DeepSeek-R1. The pipeline incorporates two RL stages aimed at discovering improved reasoning patterns and aligning with human preferences, as well as two SFT stages that serve as the seed for the model's reasoning and non-reasoning capabilities.
+    We believe the pipeline will benefit the industry by creating better models. 
+
+---
+
+**Distillation: Smaller Models Can Be Powerful Too**
+
+-  We demonstrate that the reasoning patterns of larger models can be distilled into smaller models, resulting in better performance compared to the reasoning patterns discovered through RL on small models. The open source DeepSeek-R1, as well as its API, will benefit the research community to distill better smaller models in the future. 
+- Using the reasoning data generated by DeepSeek-R1, we fine-tuned several dense models that are widely used in the research community. The evaluation results demonstrate that the distilled smaller dense models perform exceptionally well on benchmarks. We open-source distilled 1.5B, 7B, 8B, 14B, 32B, and 70B checkpoints based on Qwen2.5 and Llama3 series to the community.
+
+## 3. Model Downloads
+
+### DeepSeek-R1 Models
+
+<div align="center">
+
+| **Model** | **#Total Params** | **#Activated Params** | **Context Length** | **Download** |
+| :------------: | :------------: | :------------: | :------------: | :------------: |
+| DeepSeek-R1-Zero | 671B | 37B | 128K   | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Zero)   |
+| DeepSeek-R1   | 671B | 37B |  128K   | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1)   |
+
+</div>
+
+DeepSeek-R1-Zero & DeepSeek-R1 are trained based on DeepSeek-V3-Base. 
+For more details regarding the model architecture, please refer to [DeepSeek-V3](https://github.com/deepseek-ai/DeepSeek-V3) repository.
+
+### DeepSeek-R1-Distill Models
+
+<div align="center">
+
+| **Model** | **Base Model** | **Download** |
+| :------------: | :------------: | :------------: |
+| DeepSeek-R1-Distill-Qwen-1.5B  | [Qwen2.5-Math-1.5B](https://huggingface.co/Qwen/Qwen2.5-Math-1.5B) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B)   |
+| DeepSeek-R1-Distill-Qwen-7B  | [Qwen2.5-Math-7B](https://huggingface.co/Qwen/Qwen2.5-Math-7B) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B)   |
+| DeepSeek-R1-Distill-Llama-8B  | [Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B)   |
+| DeepSeek-R1-Distill-Qwen-14B   | [Qwen2.5-14B](https://huggingface.co/Qwen/Qwen2.5-14B) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B)   |
+|DeepSeek-R1-Distill-Qwen-32B  | [Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B)   |
+| DeepSeek-R1-Distill-Llama-70B  | [Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct) | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B)   |
+
+</div>
+
+DeepSeek-R1-Distill models are fine-tuned based on open-source models, using samples generated by DeepSeek-R1.
+We slightly change their configs and tokenizers. Please use our setting to run these models.
+
+## 4. Evaluation Results
+
+### DeepSeek-R1-Evaluation
+ For all our models, the maximum generation length is set to 32,768 tokens. For benchmarks requiring sampling, we use a temperature of $0.6$, a top-p value of $0.95$, and generate 64 responses per query to estimate pass@1.
+<div align="center">
+
+
+| Category | Benchmark (Metric) | Claude-3.5-Sonnet-1022 | GPT-4o 0513 | DeepSeek V3 | OpenAI o1-mini | OpenAI o1-1217 | DeepSeek R1 |
+|----------|-------------------|----------------------|------------|--------------|----------------|------------|--------------|
+| | Architecture | - | - | MoE | - | - | MoE |
+| | # Activated Params | - | - | 37B | - | - | 37B |
+| | # Total Params | - | - | 671B | - | - | 671B |
+| English | MMLU (Pass@1) | 88.3 | 87.2 | 88.5 | 85.2 | **91.8** | 90.8 |
+| | MMLU-Redux (EM) | 88.9 | 88.0 | 89.1 | 86.7 | - | **92.9** |
+| | MMLU-Pro (EM) | 78.0 | 72.6 | 75.9 | 80.3 | - | **84.0** |
+| | DROP (3-shot F1) | 88.3 | 83.7 | 91.6 | 83.9 | 90.2 | **92.2** |
+| | IF-Eval (Prompt Strict) | **86.5** | 84.3 | 86.1 | 84.8 | - | 83.3 |
+| | GPQA-Diamond (Pass@1) | 65.0 | 49.9 | 59.1 | 60.0 | **75.7** | 71.5 |
+| | SimpleQA (Correct) | 28.4 | 38.2 | 24.9 | 7.0 | **47.0** | 30.1 |
+| | FRAMES (Acc.) | 72.5 | 80.5 | 73.3 | 76.9 | - | **82.5** |
+| | AlpacaEval2.0 (LC-winrate) | 52.0 | 51.1 | 70.0 | 57.8 | - | **87.6** |
+| | ArenaHard (GPT-4-1106) | 85.2 | 80.4 | 85.5 | 92.0 | - | **92.3** |
+| Code | LiveCodeBench (Pass@1-COT) | 33.8 | 34.2 | - | 53.8 | 63.4 | **65.9** |
+| | Codeforces (Percentile) | 20.3 | 23.6 | 58.7 | 93.4 | **96.6** | 96.3 |
+| | Codeforces (Rating) | 717 | 759 | 1134 | 1820 | **2061** | 2029 |
+| | SWE Verified (Resolved) | **50.8** | 38.8 | 42.0 | 41.6 | 48.9 | 49.2 |
+| | Aider-Polyglot (Acc.) | 45.3 | 16.0 | 49.6 | 32.9 | **61.7** | 53.3 |
+| Math | AIME 2024 (Pass@1) | 16.0 | 9.3 | 39.2 | 63.6 | 79.2 | **79.8** |
+| | MATH-500 (Pass@1) | 78.3 | 74.6 | 90.2 | 90.0 | 96.4 | **97.3** |
+| | CNMO 2024 (Pass@1) | 13.1 | 10.8 | 43.2 | 67.6 | - | **78.8** |
+| Chinese | CLUEWSC (EM) | 85.4 | 87.9 | 90.9 | 89.9 | - | **92.8** |
+| | C-Eval (EM) | 76.7 | 76.0 | 86.5 | 68.9 | - | **91.8** |
+| | C-SimpleQA (Correct) | 55.4 | 58.7 | **68.0** | 40.3 | - | 63.7 |
+
+</div>
+
+
+### Distilled Model Evaluation
+
+
+<div align="center">
+
+| Model                                    | AIME 2024 pass@1 | AIME 2024 cons@64 | MATH-500 pass@1 | GPQA Diamond pass@1 | LiveCodeBench pass@1 | CodeForces rating |
+|------------------------------------------|------------------|-------------------|-----------------|----------------------|----------------------|-------------------|
+| GPT-4o-0513                          | 9.3              | 13.4              | 74.6            | 49.9                 | 32.9                 | 759               |
+| Claude-3.5-Sonnet-1022             | 16.0             | 26.7                 | 78.3            | 65.0                 | 38.9                 | 717               |
+| o1-mini                              | 63.6             | 80.0              | 90.0            | 60.0                 | 53.8                 | **1820**          |
+| QwQ-32B-Preview                              | 44.0             | 60.0                 | 90.6            | 54.5               | 41.9                 | 1316              |
+| DeepSeek-R1-Distill-Qwen-1.5B       | 28.9             | 52.7              | 83.9            | 33.8                 | 16.9                 | 954               |
+| DeepSeek-R1-Distill-Qwen-7B          | 55.5             | 83.3              | 92.8            | 49.1                 | 37.6                 | 1189              |
+| DeepSeek-R1-Distill-Qwen-14B         | 69.7             | 80.0              | 93.9            | 59.1                 | 53.1                 | 1481              |
+| DeepSeek-R1-Distill-Qwen-32B        | **72.6**         | 83.3              | 94.3            | 62.1                 | 57.2                 | 1691              |
+| DeepSeek-R1-Distill-Llama-8B         | 50.4             | 80.0              | 89.1            | 49.0                 | 39.6                 | 1205              |
+| DeepSeek-R1-Distill-Llama-70B        | 70.0             | **86.7**          | **94.5**        | **65.2**             | **57.5**             | 1633              |
+
+</div>
+
+
+## 5. Chat Website & API Platform
+You can chat with DeepSeek-R1 on DeepSeek's official website: [chat.deepseek.com](https://chat.deepseek.com), and switch on the button "DeepThink"
+
+We also provide OpenAI-Compatible API at DeepSeek Platform: [platform.deepseek.com](https://platform.deepseek.com/)
+
+## 6. How to Run Locally
+
+### DeepSeek-R1 Models
+
+Please visit [DeepSeek-V3](https://github.com/deepseek-ai/DeepSeek-V3) repo for more information about running DeepSeek-R1 locally.
+
+**NOTE: Hugging Face's Transformers has not been directly supported yet.**
+
+### DeepSeek-R1-Distill Models
+
+DeepSeek-R1-Distill models can be utilized in the same manner as Qwen or Llama models.
+
+For instance, you can easily start a service using [vLLM](https://github.com/vllm-project/vllm):
+
+```shell
+vllm serve deepseek-ai/DeepSeek-R1-Distill-Qwen-32B --tensor-parallel-size 2 --max-model-len 32768 --enforce-eager
+```
+
+You can also easily start a service using [SGLang](https://github.com/sgl-project/sglang)
+
+```bash
+python3 -m sglang.launch_server --model deepseek-ai/DeepSeek-R1-Distill-Qwen-32B --trust-remote-code --tp 2
+```
+
+### Usage Recommendations
+
+**We recommend adhering to the following configurations when utilizing the DeepSeek-R1 series models, including benchmarking, to achieve the expected performance:**
+
+1. Set the temperature within the range of 0.5-0.7 (0.6 is recommended) to prevent endless repetitions or incoherent outputs.
+2. **Avoid adding a system prompt; all instructions should be contained within the user prompt.**
+3. 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{}."
+4. When evaluating model performance, it is recommended to conduct multiple tests and average the results.
+
+Additionally, we have observed that the DeepSeek-R1 series models tend to bypass thinking pattern (i.e., outputting "\<think\>\n\n\</think\>") when responding to certain queries, which can adversely affect the model's performance.
+**To ensure that the model engages in thorough reasoning, we recommend enforcing the model to initiate its response with "\<think\>\n" at the beginning of every output.**
+
+## 7. License
+This code repository and the model weights are licensed under the [MIT License](https://github.com/deepseek-ai/DeepSeek-R1/blob/main/LICENSE).
+DeepSeek-R1 series support commercial use, allow for any modifications and derivative works, including, but not limited to, distillation for training other LLMs. Please note that:
+- DeepSeek-R1-Distill-Qwen-1.5B, DeepSeek-R1-Distill-Qwen-7B, DeepSeek-R1-Distill-Qwen-14B and DeepSeek-R1-Distill-Qwen-32B are derived from [Qwen-2.5 series](https://github.com/QwenLM/Qwen2.5), which are originally licensed under [Apache 2.0 License](https://huggingface.co/Qwen/Qwen2.5-1.5B/blob/main/LICENSE), and now finetuned with 800k samples curated with DeepSeek-R1.
+- DeepSeek-R1-Distill-Llama-8B is derived from Llama3.1-8B-Base and is originally licensed under [llama3.1 license](https://huggingface.co/meta-llama/Llama-3.1-8B/blob/main/LICENSE).
+- DeepSeek-R1-Distill-Llama-70B is derived from Llama3.3-70B-Instruct and is originally licensed under [llama3.3 license](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct/blob/main/LICENSE).
+
+## 8. Citation
+```
+@misc{deepseekai2025deepseekr1incentivizingreasoningcapability,
+      title={DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning}, 
+      author={DeepSeek-AI},
+      year={2025},
+      eprint={2501.12948},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2501.12948}, 
+}
+
+```
+
+## 9. Contact
+If you have any questions, please raise an issue or contact us at [[email protected]]([email protected]).

config.json

@@ -0,0 +1,61 @@
+{
+  "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,
+  "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
+}

configuration_deepseek.py

@@ -0,0 +1,210 @@
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+logger = logging.get_logger(__name__)
+
+DEEPSEEK_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
+class DeepseekV3Config(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`DeepseekV3Model`]. It is used to instantiate an DeepSeek
+    model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
+    defaults will yield a similar configuration to that of the DeepSeek-V3.
+
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
+    documentation from [`PretrainedConfig`] for more information.
+
+
+    Args:
+        vocab_size (`int`, *optional*, defaults to 129280):
+            Vocabulary size of the Deep model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`DeepseekV3Model`]
+        hidden_size (`int`, *optional*, defaults to 4096):
+            Dimension of the hidden representations.
+        intermediate_size (`int`, *optional*, defaults to 11008):
+            Dimension of the MLP representations.
+        moe_intermediate_size (`int`, *optional*, defaults to 1407):
+            Dimension of the MoE representations.
+        num_hidden_layers (`int`, *optional*, defaults to 32):
+            Number of hidden layers in the Transformer decoder.
+        num_nextn_predict_layers (`int`, *optional*, defaults to 1):
+            Number of nextn predict layers in the DeepSeekV3 Model.
+        num_attention_heads (`int`, *optional*, defaults to 32):
+            Number of attention heads for each attention layer in the Transformer decoder.
+        n_shared_experts (`int`, *optional*, defaults to None):
+            Number of shared experts, None means dense model.
+        n_routed_experts (`int`, *optional*, defaults to None):
+            Number of routed experts, None means dense model.
+        routed_scaling_factor (`float`, *optional*, defaults to 1.0):
+            Scaling factor or routed experts.
+        topk_method (`str`, *optional*, defaults to `gready`):
+            Topk method used in routed gate.
+        n_group (`int`, *optional*, defaults to None):
+            Number of groups for routed experts.
+        topk_group (`int`, *optional*, defaults to None):
+            Number of selected groups for each token(for each token, ensuring the selected experts is only within `topk_group` groups).
+        num_experts_per_tok (`int`, *optional*, defaults to None):
+            Number of selected experts, None means dense model.
+        moe_layer_freq (`int`, *optional*, defaults to 1):
+            The frequency of the MoE layer: one expert layer for every `moe_layer_freq - 1` dense layers.
+        first_k_dense_replace (`int`, *optional*, defaults to 0):
+            Number of dense layers in shallow layers(embed->dense->dense->...->dense->moe->moe...->lm_head).
+                                                            \--k dense layers--/
+        norm_topk_prob (`bool`, *optional*, defaults to False):
+            Whether to normalize the weights of the routed experts.
+        scoring_func (`str`, *optional*, defaults to 'softmax'):
+            Method of computing expert weights.
+        aux_loss_alpha (`float`, *optional*, defaults to 0.001):
+            Auxiliary loss weight coefficient.
+        seq_aux = (`bool`, *optional*, defaults to True):
+            Whether to compute the auxiliary loss for each individual sample.
+        num_key_value_heads (`int`, *optional*):
+            This is the number of key_value heads that should be used to implement Grouped Query Attention. If
+            `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
+            `num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
+            converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
+            by meanpooling all the original heads within that group. For more details checkout [this
+            paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
+            `num_attention_heads`.
+        hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
+            The non-linear activation function (function or string) in the decoder.
+        max_position_embeddings (`int`, *optional*, defaults to 2048):
+            The maximum sequence length that this model might ever be used with.
+        initializer_range (`float`, *optional*, defaults to 0.02):
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+        rms_norm_eps (`float`, *optional*, defaults to 1e-06):
+            The epsilon used by the rms normalization layers.
+        use_cache (`bool`, *optional*, defaults to `True`):
+            Whether or not the model should return the last key/values attentions (not used by all models). Only
+            relevant if `config.is_decoder=True`.
+        pad_token_id (`int`, *optional*):
+            Padding token id.
+        bos_token_id (`int`, *optional*, defaults to 1):
+            Beginning of stream token id.
+        eos_token_id (`int`, *optional*, defaults to 2):
+            End of stream token id.
+        pretraining_tp (`int`, *optional*, defaults to 1):
+            Experimental feature. Tensor parallelism rank used during pretraining. Please refer to [this
+            document](https://huggingface.co/docs/transformers/parallelism) to understand more about it. This value is
+            necessary to ensure exact reproducibility of the pretraining results. Please refer to [this
+            issue](https://github.com/pytorch/pytorch/issues/76232).
+        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
+            Whether to tie weight embeddings
+        rope_theta (`float`, *optional*, defaults to 10000.0):
+            The base period of the RoPE embeddings.
+        rope_scaling (`Dict`, *optional*):
+            Dictionary containing the scaling configuration for the RoPE embeddings. Currently supports two scaling
+            strategies: linear and dynamic. Their scaling factor must be a float greater than 1. The expected format is
+            `{"type": strategy name, "factor": scaling factor}`. When using this flag, don't update
+            `max_position_embeddings` to the expected new maximum.
+        attention_bias (`bool`, defaults to `False`, *optional*, defaults to `False`):
+            Whether to use a bias in the query, key, value and output projection layers during self-attention.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for the attention probabilities.
+
+    ```python
+    >>> from transformers import DeepseekV3Model, DeepseekV3Config
+
+    >>> # Initializing a Deepseek-V3 style configuration
+    >>> configuration = DeepseekV3Config()
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "deepseek_v3"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        vocab_size=129280,
+        hidden_size=7168,
+        intermediate_size=18432,
+        moe_intermediate_size = 2048,
+        num_hidden_layers=61,
+        num_nextn_predict_layers=1,
+        num_attention_heads=128,
+        num_key_value_heads=128,
+        n_shared_experts = 1,
+        n_routed_experts = 256,
+        ep_size = 1,
+        routed_scaling_factor = 2.5,
+        kv_lora_rank = 512,
+        q_lora_rank = 1536,
+        qk_rope_head_dim = 64,
+        v_head_dim = 128,
+        qk_nope_head_dim = 128,
+        topk_method = 'noaux_tc',
+        n_group = 8,
+        topk_group = 4,
+        num_experts_per_tok = 8,
+        moe_layer_freq = 1,
+        first_k_dense_replace = 3,
+        norm_topk_prob = True,
+        scoring_func = 'sigmoid',
+        aux_loss_alpha = 0.001,
+        seq_aux = True,
+        hidden_act="silu",
+        max_position_embeddings=4096,
+        initializer_range=0.02,
+        rms_norm_eps=1e-6,
+        use_cache=True,
+        pad_token_id=None,
+        bos_token_id=0,
+        eos_token_id=1,
+        pretraining_tp=1,
+        tie_word_embeddings=False,
+        rope_theta=10000.0,
+        rope_scaling=None,
+        attention_bias=False,
+        attention_dropout=0.0,
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.max_position_embeddings = max_position_embeddings
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.moe_intermediate_size = moe_intermediate_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_nextn_predict_layers = num_nextn_predict_layers
+        self.num_attention_heads = num_attention_heads
+        self.n_shared_experts = n_shared_experts
+        self.n_routed_experts = n_routed_experts
+        self.ep_size = ep_size
+        self.routed_scaling_factor = routed_scaling_factor
+        self.kv_lora_rank = kv_lora_rank
+        self.q_lora_rank = q_lora_rank
+        self.qk_rope_head_dim = qk_rope_head_dim
+        self.v_head_dim = v_head_dim
+        self.qk_nope_head_dim = qk_nope_head_dim
+        self.topk_method = topk_method
+        self.n_group = n_group
+        self.topk_group = topk_group
+        self.num_experts_per_tok = num_experts_per_tok
+        self.moe_layer_freq = moe_layer_freq
+        self.first_k_dense_replace = first_k_dense_replace
+        self.norm_topk_prob = norm_topk_prob
+        self.scoring_func = scoring_func
+        self.aux_loss_alpha = aux_loss_alpha
+        self.seq_aux = seq_aux
+        # for backward compatibility
+        if num_key_value_heads is None:
+            num_key_value_heads = num_attention_heads
+
+        self.num_key_value_heads = num_key_value_heads
+        self.hidden_act = hidden_act
+        self.initializer_range = initializer_range
+        self.rms_norm_eps = rms_norm_eps
+        self.pretraining_tp = pretraining_tp
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.rope_scaling = rope_scaling
+        self.attention_bias = attention_bias
+        self.attention_dropout = attention_dropout
+
+        super().__init__(
+            pad_token_id=pad_token_id,
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "do_sample": true,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.39.3"
+}

inference/bf16_cast_channel_int8.py

@@ -0,0 +1,95 @@
+import os
+import json
+from argparse import ArgumentParser
+from glob import glob
+from tqdm import tqdm
+
+import torch
+from safetensors.torch import load_file, save_file
+from huggingface_hub import snapshot_download
+
+def weight_quant(tensor: torch.Tensor):
+    assert tensor.dim() == 2
+    qmax = 127.0
+    abs_max = torch.abs(tensor).max(dim=1, keepdim=True)[0]  # [rows, 1]
+    scale = abs_max / qmax  # [rows, 1]
+    assert scale.shape == (tensor.shape[0], 1)
+    quantized = torch.round(tensor / scale)
+    quantized = torch.clamp(quantized, -qmax, qmax)
+    return quantized.to(torch.int8), scale.to(torch.float32)
+
+def main(bf16_path, int8_path, model_name="deepseek-ai/DeepSeek-R1"):
+    torch.set_default_dtype(torch.bfloat16)
+    os.makedirs(int8_path, exist_ok=True)
+    model_index_file = os.path.join(int8_path, "model.safetensors.index.json")
+    config_file = os.path.join(int8_path, "config.json")
+
+    if not os.path.exists(model_index_file) or not os.path.exists(config_file):
+        snapshot_download(
+            repo_id=model_name,
+            ignore_patterns=["*.safetensors"],
+            local_dir=int8_path,
+            local_dir_use_symlinks=False
+        )
+        print(f"model index file and config file downloaded to {int8_path}")
+
+        # modify config.json and save it
+        config = json.load(open(config_file))
+        # delete quantization_config
+        config.pop("quantization_config", None)
+        with open(config_file, "w", encoding="utf-8") as f:
+            json.dump(config, f, indent=2, ensure_ascii=False, sort_keys=True)
+        print(f"config.json modified and saved to {config_file}")
+
+    with open(model_index_file, "r") as f:
+        model_index = json.load(f)
+    weight_map = model_index["weight_map"]
+    scale_count = len([key for key in weight_map.keys() if key.endswith("_scale_inv")])
+    
+    safetensor_files = list(glob(os.path.join(bf16_path, "*.safetensors")))
+    safetensor_files.sort()
+    quant_count = 0
+    new_weight_map = {}
+    for safetensor_file in tqdm(safetensor_files):
+        file_name = os.path.basename(safetensor_file)
+        state_dict = load_file(safetensor_file, device="cuda")
+        new_state_dict = {}
+        for weight_name, weight in state_dict.items():
+            scale_inv_name = f"{weight_name}_scale_inv"
+            if scale_inv_name in weight_map:
+                assert weight.element_size() == 2
+                quant_count += 1
+                int8_weight, scale_inv = weight_quant(weight)
+                new_state_dict[weight_name] = int8_weight
+                new_scale_name = scale_inv_name.replace("_scale_inv", "_scale")
+                new_state_dict[new_scale_name] = scale_inv
+
+                new_weight_map[weight_name] = file_name
+                new_weight_map[new_scale_name] = file_name
+            else:
+                new_state_dict[weight_name] = weight
+                new_weight_map[weight_name] = file_name
+        new_safetensor_file = os.path.join(int8_path, file_name)
+        save_file(new_state_dict, new_safetensor_file)
+    assert quant_count == scale_count
+    print(f"{quant_count} weights are quantized.")
+
+    # modify model.safetensors.index.json
+    with open(model_index_file, "r") as f:
+        model_index = json.load(f)
+    model_index["weight_map"] = new_weight_map
+    with open(model_index_file, "w", encoding="utf-8") as f:
+        json.dump(model_index, f, indent=2, ensure_ascii=False, sort_keys=True)
+    print(f"model.safetensors.index.json modified and saved to {model_index_file}")
+        
+
+if __name__ == "__main__":
+    parser = ArgumentParser()
+    parser.add_argument("--input-bf16-hf-path", type=str, required=True)
+    parser.add_argument("--output-int8-hf-path", type=str, required=True)
+    parser.add_argument("--model-name", type=str, default="deepseek-ai/DeepSeek-R1")
+
+    args = parser.parse_args()
+    main(args.input_bf16_hf_path, args.output_int8_hf_path, args.model_name)
+    print("done")
+    

inference/kernel.py

@@ -0,0 +1,136 @@
+from typing import Tuple
+
+import torch
+import triton
+import triton.language as tl
+from triton import Config
+
+@triton.jit
+def act_quant_kernel(x_ptr, y_ptr, s_ptr, BLOCK_SIZE: tl.constexpr):
+    pid = tl.program_id(axis=0)
+    offs = pid * BLOCK_SIZE + tl.arange(0, BLOCK_SIZE)
+    x = tl.load(x_ptr + offs).to(tl.float32)
+    s = tl.max(tl.abs(x)) / 448.
+    y = x / s
+    y = y.to(y_ptr.dtype.element_ty)
+    tl.store(y_ptr + offs, y)
+    tl.store(s_ptr + pid, s)
+
+
+def act_quant(x: torch.Tensor, block_size: int = 128) -> Tuple[torch.Tensor, torch.Tensor]:
+    assert x.is_contiguous()
+    assert x.size(-1) % block_size == 0
+    y = torch.empty_like(x, dtype=torch.float8_e4m3fn)
+    s = x.new_empty(*x.size()[:-1], x.size(-1) // block_size, dtype=torch.float32)
+    grid = lambda meta: (triton.cdiv(x.numel(), meta['BLOCK_SIZE']), )
+    act_quant_kernel[grid](x, y, s, BLOCK_SIZE=block_size)
+    return y, s
+
+
+@triton.jit
+def weight_dequant_kernel(x_ptr, s_ptr, y_ptr, M, N, BLOCK_SIZE: tl.constexpr):
+    pid_m = tl.program_id(axis=0)
+    pid_n = tl.program_id(axis=1)
+    n = tl.cdiv(N, BLOCK_SIZE)
+    offs_m = pid_m * BLOCK_SIZE + tl.arange(0, BLOCK_SIZE)
+    offs_n = pid_n * BLOCK_SIZE + tl.arange(0, BLOCK_SIZE)
+    offs = offs_m[:, None] * N + offs_n[None, :]
+    mask = (offs_m[:, None] < M) & (offs_n[None, :] < N)
+    x = tl.load(x_ptr + offs, mask=mask).to(tl.float32)
+    s = tl.load(s_ptr + pid_m * n + pid_n)
+    y = x * s
+    tl.store(y_ptr + offs, y, mask=mask)
+
+
+def weight_dequant(x: torch.Tensor, s: torch.Tensor, block_size: int = 128) -> torch.Tensor:
+    assert x.is_contiguous() and s.is_contiguous()
+    assert x.dim() == 2 and s.dim() == 2
+    M, N = x.size()
+    y = torch.empty_like(x, dtype=torch.get_default_dtype())
+    grid = lambda meta: (triton.cdiv(M, meta['BLOCK_SIZE']), triton.cdiv(N, meta['BLOCK_SIZE']))
+    weight_dequant_kernel[grid](x, s, y, M, N, BLOCK_SIZE=block_size)
+    return y
+
+
+@triton.jit
+def weight_quant_kernel(x_ptr, y_ptr, s_ptr, M, N, BLOCK_SIZE: tl.constexpr):
+    pid_m = tl.program_id(axis=0)
+    pid_n = tl.program_id(axis=1)
+    n = tl.cdiv(N, BLOCK_SIZE)
+    offs_m = pid_m * BLOCK_SIZE + tl.arange(0, BLOCK_SIZE)
+    offs_n = pid_n * BLOCK_SIZE + tl.arange(0, BLOCK_SIZE)
+    offs = offs_m[:, None] * N + offs_n[None, :]
+    mask = (offs_m[:, None] < M) & (offs_n[None, :] < N)
+    x = tl.load(x_ptr + offs, mask=mask).to(tl.float32)
+    s = tl.max(tl.abs(x)) / 127.#int8
+    y = x / s
+    y = y.to(y_ptr.dtype.element_ty)
+    tl.store(y_ptr + offs, y, mask=mask)
+    tl.store(s_ptr + pid_m * n + pid_n, s)
+
+# quant to block int8
+def weight_quant(x: torch.Tensor, block_size: int = 128) -> Tuple[torch.Tensor, torch.Tensor]:
+    assert x.is_contiguous()
+    assert x.dim() == 2
+    M, N = x.size()
+    y = torch.empty_like(x, dtype=torch.int8)
+    sM, sN = torch.tensor(1.0*M/block_size).ceil().int(), torch.tensor(1.0*N/block_size).ceil().int()
+    s = x.new_empty(sM, sN, dtype=torch.float32)
+    grid = lambda meta: (triton.cdiv(M, meta['BLOCK_SIZE']), triton.cdiv(N, meta['BLOCK_SIZE']))
+    weight_quant_kernel[grid](x, y, s, M, N, BLOCK_SIZE=block_size)
+    return y, s
+
+
+fp8_gemm_configs = [
+    Config({'BLOCK_SIZE_M': block_m, 'BLOCK_SIZE_N': block_n, 'BLOCK_SIZE_K': 128}, num_stages=num_stages, num_warps=8)
+    for block_m in [16, 32, 64] for block_n in [32, 64, 128] for num_stages in [3, 4, 5, 6]
+]
+
+@triton.autotune(configs=fp8_gemm_configs, key=['N', 'K'])
+@triton.jit
+def fp8_gemm_kernel(a_ptr, b_ptr, c_ptr,
+                    a_s_ptr, b_s_ptr,
+                    M, N: tl.constexpr, K: tl.constexpr,
+                    BLOCK_SIZE_M: tl.constexpr,
+                    BLOCK_SIZE_N: tl.constexpr,
+                    BLOCK_SIZE_K: tl.constexpr):
+    pid_m = tl.program_id(axis=0)
+    pid_n = tl.program_id(axis=1)
+    k = tl.cdiv(K, BLOCK_SIZE_K)
+    offs_m = (pid_m * BLOCK_SIZE_M + tl.arange(0, BLOCK_SIZE_M)) % M
+    offs_n = (pid_n * BLOCK_SIZE_N + tl.arange(0, BLOCK_SIZE_N)) % N
+    offs_k = tl.arange(0, BLOCK_SIZE_K)
+    a_ptrs = a_ptr + offs_m[:, None] * K + offs_k[None, :]
+    b_ptrs = b_ptr + offs_n[None, :] * K + offs_k[:, None]
+    a_s_ptrs = a_s_ptr + offs_m * k
+    b_s_ptrs = b_s_ptr + (offs_n // BLOCK_SIZE_K) * k
+
+    accumulator = tl.zeros((BLOCK_SIZE_M, BLOCK_SIZE_N), dtype=tl.float32)
+    for i in range(k):
+        a = tl.load(a_ptrs, mask=offs_k[None, :] < K - i * BLOCK_SIZE_K, other=0.0)
+        b = tl.load(b_ptrs, mask=offs_k[:, None] < K - i * BLOCK_SIZE_K, other=0.0)
+        a_s = tl.load(a_s_ptrs)
+        b_s = tl.load(b_s_ptrs)
+        accumulator += tl.dot(a, b) * a_s[:, None] * b_s[None, :]
+        a_ptrs += BLOCK_SIZE_K
+        b_ptrs += BLOCK_SIZE_K
+        a_s_ptrs += 1
+        b_s_ptrs += 1
+    c = accumulator.to(c_ptr.dtype.element_ty)
+    offs_m = pid_m * BLOCK_SIZE_M + tl.arange(0, BLOCK_SIZE_M)
+    offs_n = pid_n * BLOCK_SIZE_N + tl.arange(0, BLOCK_SIZE_N)
+    c_ptrs = c_ptr + offs_m[:, None] * N + offs_n[None, :]
+    mask = (offs_m[:, None] < M) & (offs_n[None, :] < N)
+    tl.store(c_ptrs, c, mask=mask)
+
+
+def fp8_gemm(a: torch.Tensor, a_s: torch.Tensor, b: torch.Tensor, b_s: torch.Tensor):
+    assert a.is_contiguous() and b.is_contiguous()
+    assert a_s.is_contiguous() and b_s.is_contiguous()
+    K = a.size(-1)
+    M = a.numel() // K
+    N = b.size(0)
+    c = a.new_empty(*a.size()[:-1], N, dtype=torch.get_default_dtype())
+    grid = lambda META: (triton.cdiv(M, META['BLOCK_SIZE_M']), triton.cdiv(N, META['BLOCK_SIZE_N']))
+    fp8_gemm_kernel[grid](a, b, c, a_s, b_s, M, N, K)
+    return c

model-00001-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef3d88cf1e73ba0e44802173f9bc60a578e320b79c80373ed9ab467377d3d772
+size 5236369040

model-00002-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:277c11384b925bc7652a98134b1d68f505d53a1635abbe9bfa8b01d811b8a491
+size 4305737040

model-00003-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6a815fe689d3eb14ae9414ed230d812f45c1d9c38fe15a4461e82e301cf2bb2
+size 4305737448

model-00004-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9284af3d323dbdc7141af71f7336c2f7ca67eeb7e54f0149d6cc6a6ad5f880c6
+size 4305761544

model-00005-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d670c22cabc3f3b69a04f92699f7ffdb602c4a4a332cf9118eefaa28cc04eaa
+size 4305737224

model-00006-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b903c0a69d6284d8001a7ad72a5dd7a558140d795692c249b1fb56330ab05b4
+size 4375574176

model-00007-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03667366eacf64046970c05294e2171f8343120c9f7fe83507fde10dd85c8e6e
+size 4309387600

model-00009-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7152b5c650d6adebe13b6f68e4d182535358dc44629cede514ba6ad3858abbe0
+size 4305761736

model-00010-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dbc77a021e7c0299df3f7b3ed414155af5fca1742f2373af9968f34437bec09
+size 4305737032

model-00011-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a55e03e8c5a7368345b235d20b5006f44195a27ae3200b4e6db36375e4f9e05
+size 4305737448

model-00012-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f51f32f5bf75fe53880b93016a94408c2626239e850228d1125e36050dceff3
+size 1322608064

model-00013-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:838eaee61e21b5109c4c469ed953f2894032719bb455f012bfe420635472d7c6
+size 4305732480

model-00014-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51752907be40b93818fa69fd20a976b672afe9346631cc6f7049ef0559f8d9aa
+size 4305737400

model-00015-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19d6da768e75ff7b22d3a74f6e442fefa4926244bf627f218b9d2442333ed0c8
+size 4305761768

model-00016-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdc10437b7b8e42c8c73ccd7a09928ad9b7a8dd5d7f03de09814af35e77ebc9a
+size 4305737008

model-00017-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81314e223ab55baeacb7f147ad4a6685b07b82936ef454e9683e457740d3f585
+size 4305716968

model-00019-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7986c4c7674e8d4e9177e3a0791af9bfbf698fcd8f3456ecbef03329815c7ab
+size 4305716712

model-00020-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0268ccee978a221951350cc1e26b1b55682cecafc7165f5efd9ba9006390b16f
+size 4305737456

model-00021-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:581755da204ebfd20b2819aa957ec7d036125a5716e6f114cb3e6a44fe1973e8
+size 4305761936

model-00022-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39d03d2500d8672eb14c46e3a62af72a796deadd2c4d080580679ff4b14625c7
+size 4305737976

model-00023-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19f81a27ac3a69534bf9d5aa39e65280cd398af747de2ccb00dbef3be5499131
+size 4305762360

model-00026-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:831b6add17f7ddb62d55fd9a95551afe5be881f2c692e01004fea39cd6890d73
+size 4305762168

model-00029-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cb1244f84384eb3a2360f92184392411afd152645f708704a4938e1c028f67a
+size 4305782464

model-00030-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17c3c0b970e82f2ec9438d3cf08064c6f3ea127ea2ebce7c970b617c7cd8ed44
+size 4305717472

model-00031-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06f0ed9040ecb4a4ecb8585bf1ab0f59b11dc3e6a23e2b2f9b3c5c24f42c9822
+size 4305782864

model-00032-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e016a3c73eb6132eae5cb8b8da53731655e0ccd50befee8272a6f9439800b1c7
+size 4305717080

model-00033-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0764e8d2690cd938100933087699e219ea7fd6339ed38a25890910d4ed872a7a
+size 4305738048

model-00034-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:227a4ac45a97716ce59380dba0bd29040ed02021dff6ed9878c68590fb45b456
+size 1748779624

model-00035-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b15c237b61c9c59c2799c7939156d7d8ee87d219988ac2b44395e1d645bcd6b
+size 4305733056

model-00037-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0b2e8738aa549b96a3a41fc83ef5bcd973d4fa47c9de31b2d487ee544e20c72
+size 4305762344

model-00038-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b33277d423c67a62b0cc5a4d7d07c3a855f666e3291cdd497dd208a5e899b2c9
+size 4305737592

model-00039-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ccb350d98b7bc6b4312188927ae344c199a2b48278bd0b83443676eca3173ea
+size 4305717552

model-00040-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9409c38307db9adf25364abe8938563200a94ad00a98cefb67f246b234c8513d
+size 4305782640

model-00041-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:960e508b1a691476882b7f47fa20ec705b1850ac1546e4a26033a561c925b4d6
+size 4305717304

model-00042-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cb39dc86cbba28307393407816e20b053a5e61d9fa80ab43fb2db378583bb3a
+size 4305738048

model-00043-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f40870f7a995013ec48e7ab949a914801d0377e2b449e2dec1d29a60a999a34c
+size 4305761960

model-00045-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfd272252d354788fed1896b74f2c8fc0f8cb451e6f217467240f9b16bf14339
+size 4305762360

model-00046-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07ad34a51ba6605a83f6d0f164d7e4b503f9dd3d549a2577a395175ac885829b
+size 4305737584

model-00047-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:940176847c29e872eaa78257d8dd9f47cd481b38cbb49ef4fd2058558360c784
+size 4305738040

model-00048-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e40de3791a213a24f82e7a2f3de520899c86888c022152bc16fef6569c7db0e7
+size 4305762168

model-00049-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e53a5cc9aeed9d754de147d07a35e89362cd8322a09b8f6c1562d7d2cb31e2b
+size 4305737768

model-00050-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e3bd58a24a44fa81e9dc7350ef7f18358644df5e169a3f8b781ff298dd239f4
+size 4305717552

model-00051-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:001537af8037b19b5f4fa89769d9999e7b144da634188a07cffad4ba83df459e
+size 4305782464