初始化项目，由ModelHub XC社区提供模型

Model: UNIVA-Bllossom/DeepSeek-llama3.1-Bllossom-8B Source: Original Platform
2026-05-15 19:46:42 +08:00
commit 4c79638106
12 changed files with 2618 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,134 @@
+---
+license: mit
+language:
+- ko
+- en
+base_model:
+- deepseek-ai/DeepSeek-R1-Distill-Llama-8B
+library_name: transformers
+---
+# DeepSeek-llama3.1-Bllossom-8B
+
+DeepSeek-Bllossom Series는 기존 DeepSeek-R1-Distill Series 모델의 language mixing, 다국어 성능 저하 문제를 해결하기 위해 추가로 학습된 모델입니다.
+
+DeepSeek-llama3.1-Bllossom-8B는 DeepSeek-R1-distill-Llama-8B 모델을 베이스로 구축된 모델로, 한국어 환경에서의 추론 성능 향상을 목표로 개발되었습니다.
+
+본 모델은 UNIVA와 Bllossom팀이 합작으로 제작한 첫 번째 모델입니다.
+
+<div align="center">
+
+| **Model** | **Base Model** | **Download** |
+| :------------: | :------------: | :------------: |
+| DeepSeek-qwen-Bllossom-1.5B  | [DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) | 공개예정  |
+| DeepSeek-qwen-Bllossom-7B  | [DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) | 공개예정  |
+| DeepSeek-llama3.1-Bllossom-8B  | [DeepSeek-R1-Distill-Llama-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B) | [🤗 HuggingFace](https://huggingface.co/UNIVA-Bllossom/DeepSeek-llama3.1-Bllossom-8B)   |
+| DeepSeek-qwen-Bllossom-14B   | [DeepSeek-R1-Distill-Qwen-14B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B) | 공개예정   |
+| DeepSeek-qwen-Bllossom-32B  | [DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B) | [🤗 HuggingFace](https://huggingface.co/UNIVA-Bllossom/DeepSeek-qwen-Bllossom-32B)  |
+| DeepSeek-llama3.3-Bllossom-70B  | [DeepSeek-R1-Distill-Llama-70B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B) | [🤗 HuggingFace](https://huggingface.co/UNIVA-Bllossom/DeepSeek-llama3.3-Bllossom-70B )   |
+
+</div>
+
+
+
+
+## 1. Introduction
+
+DeepSeek-llama3.1-Bllossom-8B은 DeepSeek-R1-distill-Llama-8B 모델을 베이스로 구축된 모델로, 기존 베이스 모델이 영어와 중국어 위주의 데이터로 학습된 한계를 극복하고자 개발되었습니다. 특히, 기존 DeepSeek-R1-distill-Llama-8B의 경우 한국어로 추론 시 모델 성능이 크게 하락하는 문제가 있었는데, DeepSeek-Bllossom은 이 문제를 해결하기 위해 내부 사고 과정은 영어로 수행하고 최종 사용자에게 제공되는 응답은 입력 언어에 따라 출력되도록 추가로 학습되었습니다. 이를 통해 한국어 환경에서의 추론 성능이 크게 개선되었습니다.
+
+학습에는 한국어, 영어 reasoning 데이터를 사용하였으며, 기존 DeepSeek-R1 모델 학습에 주로 사용된 STEM 분야 데이터 외에도 다양한 분야의 데이터가 포함되었습니다. 데이터셋 설계와 모델 학습 과정에서 DeepSeek-llama3.1-Bllossom-8B는 한국어 사용 환경에서 더 정확하고 신뢰할 수 있는 추론 결과를 제공하는 것을 주된 목표로 개발되었습니다.
+
+---
+
+## 2. Post-training
+
+DeepSeek-llama3.1-Bllossom-8B는 자체적으로 제작한 다양한 reasoning 데이터를 활용하여 post-training 과정을 진행하였습니다. 이 과정에서는 대규모 모델이 보유한 우수한 reasoning 능력과 한국어 처리 능력을 DeepSeek-R1-distill-Llama-8B 모델에 효과적으로 distillation하는 방법을 적용하였습니다. 이를 통해 기존 모델의 성능을 보완하고, 복합적인 추론 문제에 대해 더 정확하며 신뢰할 수 있는 응답을 생성할 수 있도록 최적화하였습니다.
+
+---
+
+## 3. inference
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+model = AutoModelForCausalLM.from_pretrained(
+    "UNIVA-Bllossom/DeepSeek-llama3.1-Bllossom-8B",
+    torch_dtype="auto",
+    device_map="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained("UNIVA-Bllossom/DeepSeek-llama3.3-Bllossom-70B")
+
+system='''
+You are a highly capable assistant. For every user question, follow these instructions exactly:
+	1.	First, think through the problem step-by-step in English. Enclose all of your internal reasoning between <think> and </think> tags. This chain-of-thought should detail your reasoning process.
+	2.	After the closing </think> tag, provide your final answer.
+	3.	Do not include any additional text or commentary outside of this format.
+	4.	Your output should strictly follow this structure:
+
+<think>
+[Your detailed step-by-step reasoning in English]
+</think>
+[Your final answer]
+'''
+
+text="철수, 영희, 민수가 3회의 게임에서 점수를 받았습니다. 영희의 점수는 민수의 점수의 두 배이며, 민수의 점수는 철수의 4배입니다. 철수가 10점을 받았다면 이 3명의 평균 점수를 계산하세요."
+chat = [
+    {"role": "system", "content": system},
+    {"role": "user", "content": text}
+]
+
+prompt=tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
+model_inputs = tokenizer(
+    prompt,
+    return_tensors="pt",
+    add_special_tokens=True
+)
+
+if "token_type_ids" in model_inputs:
+    del model_inputs["token_type_ids"]
+
+model_inputs = {k: v.to(model.device) for k, v in model_inputs.items()}
+
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=8192,
+)
+
+```
+
+## 4. 모델 응답 비교
+
+| 입력 (Prompt) | DeepSeek-R1-distill-Llama-70B | DeepSeek-llama3.3-Bllossom-70B |
+| ------------- | ----------------------------- | -------------------------- |
+| **Alice, Bob, Charlie가 3회의 게임에서 점수를 받았습니다.<br>Alice의 점수는 Bob의 점수의 두 배이며, Bob의 점수는 Charlie의 4배입니다.<br>Charlie가 10점을 받았다면 이 3명의 평균 점수를 계산하세요.** |<br>Charlie의 점수는 10점입니다.<br>Bob의 점수는 Charlie의 4배이므로, Bob의 점수는 <br>$$<br>4 \\times 10 = 40<br>$$<br>점입니다.<br>Alice의 점수는 Bob의 점수의 두 배이므로, Alice의 점수는 <br>$$<br>2 \\times 40 = 80<br>$$<br>점입니다.<br>세人的 총 점수는 <br>$$<br>10 + 40 + 80 = 130<br>$$<br>점입니다.<br>평균 점수는 <br>$$<br>\\frac{130}{3} \\approx 43.33$점입니다.<br>$$<br>\\boxed{43.33}<br>$$<br>Charlie의 점수는 10점입니다. | <br>Charlie의 점수는 10점으로 주어졌습니다. Bob의 점수는 Charlie의 점수의 4배이며, 이는 다음과 같이 계산됩니다:<br>$$<br>4 \times 10 = 40<br>$$<br>Alice의 점수는 Bob의 점수의 두 배이며, 이는 다음과 같습니다:<br>$$<br>2 \times 40 = 80<br>$$<br>세 사람의 총 점수는 다음과 같습니다:<br>$$<br>10 + 40 + 80 = 130<br>$$<br>이 세 사람의 평균 점수는 총 점수를 사람 수로 나누어 계산됩니다:<br>$$<br>\frac{130}{3}<br>$$<br>따라서, 이 세 사람의 평균 점수는 <br>$$<br>\boxed{\dfrac{130}{3}}<br>$$<br>입니다. |
+| **소수가 무한하다는 사실을 3가지 방법으로 증명하시오.** | <br>以下是用三种方法证明素数无限的详细步骤：<br>### 方法一：欧几里得的反证法<br>1. **假设**：假设素数是有限的，且所有素数为 $ p_1, p_2, p_3, \\ldots, p_n $。<br>2. **构造数**：构造一个新数 $ N = (p_1 \\times p_2 \\times p_3 \\times \\ldots \\times p_n) + 1 $。<br>3. **分析N的性质**：<br>   - 如果N是素数，则N不在原假设的素数列表中，与假设矛盾。<br>   - 如果N是合数，则存在某个素数 $ p $ 整除N。但由于N除以任何 $ p_i $ 都余1，故 $ p $ 不在原列表中，同样矛盾。<br>4. **结论**：因此，素数必须是无限的。<br>### 方法二：费马数的性质<br>1. **定义**：费马数形如 $ F_k = 2^{2^k} + 1 $，其中 $ k $ 为非负整数。<br>2. **假设**：假设素数是有限的，且所有素数为 $ p_1, p_2, \\ldots, p_n $。<br>3. **构造费马数**：对于每个 $ k $，构造 $ F_k $。如果 $ F_k $ 是素数，则不在原列表中；如果是合数，其素因数不在原列表中。<br>4. **结论**：因此，素数必须是无限的。<br>### 方法三：欧拉函数与素数无限性<br>1. **欧拉函数**：欧拉函数 $ \\phi(n) $ 表示小于 $ n $ 且与 $ n $ 互质的数的个数。<br>2. **假设**：假设素数有限，记为 $ p_1, p_2, \\ldots, p_n $。<br>3. **构造数**：考虑形如 $ N = p_1^{k_1} p_2^{k_2} \\ldots p_n^{k_n} $ 的数，其欧拉函数为 $ \\phi(N) = N \\prod_{i=1}^{n} \\left(1 - \\frac{1}{p_i}\\right) $。<br>4. **分析**：如果素数有限，$ \\prod_{p \\text{素数}} \\left(1 - \\frac{1}{p}\\right) $ 收敛，但实际上该积发散，导致矛盾。<br>5. **结论**：因此，素数必须是无限的。<br>这三种方法各自从不同的角度证明了素数的无限性，展示了数论中素数无限性的深刻性。 | <br>소수가 무한하다는 것을 3가지 방법으로 증명하기 위해, 우리는 다음과 같은 접근 방식을 사용할 수 있습니다:<br>1. **유클리드의 모순 증명**:<br>   - **가정**: 소수는 유한한 개수 $ p_1, p_2, \\dots, p_n $이라고 가정합니다.<br>   - **구성**: $ P = p_1 \\times p_2 \\times \\dots \\times p_n + 1 $으로 정의합니다.<br>   - **결론**: $ P $가 소수이면, 그것은 목록에 없는 새로운 소수입니다. 만약 $ P $가 합성수이면, 그것은 목록에 없는 소수를 포함해야 합니다. 두 경우 모두 가정에 모순됩니다. 따라서, 소수는 무한합니다.<br>2. **팩토리얼 접근법**:<br>   - **가정**: 소수는 유한한 개수 $ p_1, p_2, \\dots, p_n $이라고 가정합니다.<br>   - **구성**: $ n! + 1 $을 고려하십시오, 여기서 $ n $은 가장 큰 소수입니다.<br>   - **결론**: $ n! $은 모든 $ p_i $로 나누어 떨어지므로, $ n! + 1 $은 $ p_i $ 중 어느 것도 포함하지 않습니다. 만약 $ n! + 1 $이 소수이면, 그것은 $ n $보다 큰 새로운 소수입니다. 만약 $ n! + 1 $이 합성수이면, 그것은 $ n $보다 큰 소수를 포함해야 합니다. 두 경우 모두 가정에 모순됩니다. 따라서, 소수는 무한합니다.<br>3. **오일러의 제타 함수 증명**:<br>   - **개념**: 오일러는 제타 함수 $ \\zeta(s) = \\sum_{k=1}^\\infty \\frac{1}{k^s} $가 소수에 대한 곱으로 표현될 수 있음을 보였습니다: $ \\zeta(s) = \\prod_{p \\text{ 소수}} \\frac{1}{1 - \\frac{1}{p^s}} $.<br>   - **결론**: 만약 소수가 유한하면, 곱은 유한해야 할 것입니다. 그러나 $ s $가 1보다 큰 값을 향해 접근할 때, $ \\zeta(s) $는 무한대로 발산합니다. 이것은 곱이 발산해야 함을 요구하며, 따라서 소수는 무한해야 합니다.<br>각 방법은 소수가 무한하다는 것을 확증하며, 서로 다른 수학적 원칙에 기반을 둡니다. 유클리드의 증명은 모순을 사용합니다, 팩토리얼 접근법은 간단한 수론을 사용하며, 오일러의 증명은 해석적 수론의 도구를 사용합니다. 세 방법 모두 소수 무한성에 대한 이해를 강화합니다. |
+
+## 5. Benchmark
+- dtype을 float16으로 추론을 진행하였습니다.
+- max_tokens: 32786
+- temperature: 0.7
+- 평가 방식: 각 벤치마크를 3회 반복 실행한 후 평균 점수를 산출하였습니다.
+- _en 벤치마크: 원본 벤치마크 질문을 그대로 사용하였습니다.
+- _ko 벤치마크: 원본 벤치마크 질문을 한국어로 고품질 번역하여 사용하였습니다.
+  
+| Model                                 | AIME24_ko | AIME24_en | MATH500_ko | MATH500_en |
+|---------------------------------------|-----------|-----------|------------|------------|
+| DeepSeek-R1-Distill-Llama-8B          | 25.56     | 46.67     | 63.40      | 88.87      |
+| DeepSeek-llama3.1-Bllossom-8B         | 36.67     | 40.00     | 78.07      | 87.80      |
+| DeepSeek-R1-Distill-Llama-70B         | 58.89     | 70.00     | 88.53      | 93.73      |
+| DeepSeek-llama3.3-Bllossom-70B        | 62.22     | 65.56     | 88.40      | 93.33      |
+
+## 6. License
+
+This code repository and the model weights are licensed under the MIT License.
+DeepSeek-Bllossom 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-Llama-8B** is derived from Llama3.1-8B-Instruct and is originally licensed under llama3.1 license.
+- **DeepSeek-llama3.1-Bllossom-8B** is derived from DeepSeek-R1-Distill-Llama-8B and is originally licensed under llama3.1 license.
+
+## 7. Contributor
+- **UNIVA AI Team** ([UNIVA](https://univa.co.kr), Main contributor)
+- 최창수 (서울과학기술대학교, [MLP연구실](https://sites.google.com/view/aailab) 석사과정)
+- **임경태** (KAIST, [MLP연구실](https://sites.google.com/view/aailab) 교수)
+
+## 8. Contact
+If you have any questions, please raise an issue or contact us at [frodobaggins@univa.co.kr](frodobaggins@univa.co.kr) or [ktlim@seoultech.ac.kr](ktlim@seoultech.ac.kr).
--- a/config.json
+++ b/config.json
@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "/home/raid/models/24UNSPC_Tulkun_v3.0.4/",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.48.3",
+  "use_cache": false,
+  "vocab_size": 128256
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.48.3"
+}
--- a/model-00001-of-00004.safetensors
+++ b/model-00001-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:939bc0a77e349a9896e2374abcb481ed147b042c49dc0b527339d967f01a2fd1
+size 4976698592
--- a/model-00002-of-00004.safetensors
+++ b/model-00002-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9eca7f9936d35bc42c01038d26ff89bd26fab8b79a093c6aa19deb66ec851e5
+size 4999802616
--- a/model-00003-of-00004.safetensors
+++ b/model-00003-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0d23c52ce9197c04995fc64682e120e4ec47bbe0cf03c6d7c576b7efa3f2058
+size 4915916080
--- a/model-00004-of-00004.safetensors
+++ b/model-00004-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e318aacfeffb95c600b62f1d9a224f9ada79f365b7746d5449363e0d81abc64
+size 1168138808
--- a/model.safetensors.index.json
+++ b/model.safetensors.index.json
@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d91915040cfac999d8c55f4b5bc6e67367c065e3a7a4e4b9438ce1f256addd86
+size 17209530
--- a/tokenizer_config.json
+++ b/tokenizer_config.json