commit e254a0fbb2a5046a9345e127ffd21fd54ed65b67
Author: ModelHub XC
Date: Wed Jun 17 05:00:14 2026 +0800
初始化项目,由ModelHub XC社区提供模型
Model: yulan-team/YuLan-Mini
Source: Original Platform
diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..53d7257
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,47 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
\ No newline at end of file
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..22c8fbf
--- /dev/null
+++ b/README.md
@@ -0,0 +1,387 @@
+---
+license: mit
+library_name: transformers
+pipeline_tag: text-generation
+datasets:
+- yulan-team/YuLan-Mini-Datasets
+- HuggingFaceFW/fineweb-edu
+- bigcode/the-stack-v2
+- mlfoundations/dclm-baseline-1.0
+- math-ai/AutoMathText
+- gair-prox/open-web-math-pro
+- RUC-AIBOX/long_form_thought_data_5k
+- internlm/Lean-Workbook
+- internlm/Lean-Github
+- deepseek-ai/DeepSeek-Prover-V1
+- ScalableMath/Lean-STaR-base
+- ScalableMath/Lean-STaR-plus
+- ScalableMath/Lean-CoT-base
+- ScalableMath/Lean-CoT-plus
+- opencsg/chinese-fineweb-edu
+- liwu/MNBVC
+- vikp/textbook_quality_programming
+- HuggingFaceTB/smollm-corpus
+- OpenCoder-LLM/opc-annealing-corpus
+- OpenCoder-LLM/opc-sft-stage1
+- OpenCoder-LLM/opc-sft-stage2
+- XinyaoHu/AMPS_mathematica
+- deepmind/math_dataset
+- mrfakename/basic-math-10m
+- microsoft/orca-math-word-problems-200k
+- AI-MO/NuminaMath-CoT
+- HuggingFaceTB/cosmopedia
+- MU-NLPC/Calc-ape210k
+- manu/project_gutenberg
+- storytracer/LoC-PD-Books
+- allenai/dolma
+language:
+- en
+- zh
+tags:
+- code
+- math
+arxiv: 2412.17743
+model-index:
+- name: YuLan-Mini
+ results:
+ - task:
+ type: text-generation
+ dataset:
+ type: openai_humaneval
+ name: HumanEval
+ metrics:
+ - name: pass@1
+ type: pass@1
+ value: 0.640
+ verified: false
+ - task:
+ type: text-generation
+ dataset:
+ type: mbpp
+ name: MBPP
+ metrics:
+ - name: pass@1
+ type: pass@1
+ value: 0.659
+ verified: false
+ - task:
+ type: text-generation
+ dataset:
+ type: math-500
+ name: MATH-500
+ metrics:
+ - name: maj@1
+ type: maj@1
+ value: 0.378
+ verified: false
+ - task:
+ type: text-generation
+ dataset:
+ type: gsm8k
+ name: GSM8K
+ metrics:
+ - name: maj@1
+ type: maj@1
+ value: 0.684
+ verified: false
+---
+
+# Important Notice: This is a pre-trained **base model** without instruction-following capabilities. The **SFT version** will be released within a few weeks.
+
+
+
+

+
YuLan-Mini: An Open Data-efficient Language Model
+

+

+

+

+
+
+YuLan-Mini is a lightweight language model with 2.4 billion parameters. It achieves performance comparable to industry-leading models trained on significantly more data, despite being pre-trained on only 1.08T tokens. The model excels particularly in the domains of **mathematics** and **code**. To facilitate reproducibility, we will open-source the relevant [pre-training resources](https://github.com/RUC-GSAI/YuLan-Mini/tree/main/pretrain).
+
+---
+
+## Model Downloads 🔗
+
+| Model | Context Length | SFT |
+|---------|----------------|-----|
+| [YuLan-Mini](https://huggingface.co/yulan-team/YuLan-Mini) (Recommended) | 28K | ❎ |
+| [YuLan-Mini-2.4B-4K](https://huggingface.co/yulan-team/YuLan-Mini-Intermediate-4K) | 4K | ❎ |
+| YuLan-Mini-Instruct | Comming soon | ✅ |
+
+---
+
+## Features 🌟
+
+
+

+
+
+Our pre-training methodology improves training efficiency through three key innovations:
+
+1. an elaborately designed **data pipeline** that combines data cleaning with data schedule strategies;
+2. a systematic **optimization method** that can effectively mitigate training instability;
+3. an effective **annealing approach** that integrate targeted data selection and long context training.
+
+
+---
+## Behchmarks 🌟
+
+| Models | Model Size | # Train Tokens | Context Length | MATH 500 | GSM 8K | Human Eval | MBPP | RACE Middle | RACE High | RULER |
+|:----------------|----------:|--------------:|--------------:|:--------|:------|:----------|:------|:-----------|:---------|:------|
+| MiniCPM | 2.6B | 1.06T | 4K | 15.00 | 53.83 | 50.00* | 47.31 | 56.61 | 44.27 | N/A |
+| Qwen-2 | 1.5B | 7T | 128K | 22.60 | 46.90* | 34.80* | 46.90* | 55.77 | 43.69 | 60.16 |
+| Qwen2.5 | 0.5B | 18T | 128K | 23.60 | 41.60* | 30.50* | 39.30* | 52.36 | 40.31 | 49.23 |
+| Qwen2.5 | 1.5B | 18T | 128K | **45.40** | **68.50\*** | 37.20* | 60.20* | **58.77** | 44.33 | 68.26 |
+| Gemma2 | 2.6B | 2T | 8K | 18.30* | 30.30* | 19.50* | 42.10* | - | - | N/A |
+| StableLM2 | 1.7B | 2T | 4K | - | 20.62 | 8.50* | 17.50 | 56.33 | **45.06** | N/A |
+| SmolLM2 | 1.7B | 11T | 8K | 11.80 | - | 23.35 | 45.00 | 55.77 | 43.06 | N/A |
+| Llama3.2 | 3.2B | 9T | 128K | 7.40 | - | 29.30 | 49.70 | 55.29 | 43.34 | **77.06** |
+| YuLan-Mini | 2.4B | 1.04T | 4K | 32.60 | 66.65 | 61.60 | **66.70** | 55.71 | 43.58 | N/A |
+| YuLan-Mini | 2.4B | 1.08T | 28K | 37.80 | 68.46 | **64.00** | 65.90| 57.18 | 44.57 | 51.48 |
+
+
+| Models | LAMBADA | MMLU | CMMLU | CEval | HellaSwag | WinoGrande | StoryCloze | ARC-e | ARC-c |
+|:----------------|:-------|:-----|:-----|:-----|:----------|:-----------|:-----------|:-----|:-----|
+| MiniCPM-2.6B | 61.91 | 53.37 | 48.97 | 48.24 | 67.92 | 65.74 | 78.51 | 55.51 | 43.86 |
+| Qwen2-1.5B | 64.68 | 55.90 | **70.76** | **71.94** | 66.11 | 66.14 | 77.60 | 62.21 | 42.92 |
+| Qwen2.5-0.5B | 52.00 | 47.50 | 52.17 | 54.27 | 50.54 | 55.88 | 71.67 | 56.10 | 39.51 |
+| Qwen2.5-1.5B | 62.12 | 60.71 | 67.82 | 69.05 | 67.18 | 64.48 | 76.80 | **71.51** | 53.41 |
+| Gemma2-2.6B | - | 52.20*| - | 28.00*| 74.60* | **71.50\*** | - | - | **55.70\***|
+| StableLM2-1.7B | 66.15 | 40.37 | 29.29 | 26.99 | 69.79 | 64.64 | 78.56 | 54.00 | 40.78 |
+| SmolLM2-1.7B | 67.42 | 51.91 | 33.46 | 35.10 | 72.96 | 67.40 | **79.32** | 44.82 | 35.49 |
+| Llama3.2-3B | **69.08** | **63.40** | 44.44 | 44.49 | **75.62** | 67.48 | 76.80 | 70.12 | 48.81 |
+| YuLan-Mini | 64.72 | 51.79 | 48.35 | 51.47 | 68.65 | 67.09 | 76.37 | 69.87 | 50.51 |
+| YuLan-Mini | 65.67 | 49.10 | 45.45 | 48.23 | 67.22 | 67.24 | 75.89 | 67.47 | 49.32 |
+
+
+---
+
+## Pre-Training Resources 🔧
+
+To enhance research transparency and reproducibility, we are open-sourcing relevant [pre-training resources](https://github.com/RUC-GSAI/YuLan-Mini/blob/main/pretrain):
+
+1. Pre-training and Evaluation Code
+
+The pre-training and evaluation code will be released in a future update.
+
+
+
+
+2. Intermediate Stage Checkpoints
+The intermediate stage checkpoints are released in YuLan-Mini.
+
+
+
+
+ | Stage |
+ Curriculum Phase |
+ 4K Context |
+ 28K Context |
+ Optimizer |
+ Inference Architecture |
+ LAMBADA Acc |
+ GSM8K Acc |
+ HumanEval pass@1 |
+
+
+
+
+ | Stable |
+ 5 |
+ YuLan-Mini-Phase5 |
+ |
+ |
+ yulanmini |
+ 53.85 |
+ 3.41 |
+ 12.26 |
+
+
+ | Stable |
+ 10 |
+ YuLan-Mini-Phase10 |
+ |
+ |
+ yulanmini |
+ 55.00 |
+ 9.57 |
+ 15.95 |
+
+
+ | Stable |
+ 15 |
+ YuLan-Mini-Phase15 |
+ |
+ |
+ yulanmini |
+ 55.81 |
+ 13.81 |
+ 16.99 |
+
+
+ | Stable |
+ 20 |
+ YuLan-Mini-Phase20 |
+ |
+ ✅ |
+ yulanmini |
+ 55.81 |
+ 21.39 |
+ 20.79 |
+
+
+ | Stable |
+ 25 (1T tokens) |
+ YuLan-Mini-Before-Annealing |
+ |
+ ✅ |
+ yulanmini |
+ 55.67 |
+ 29.94 |
+ 34.06 |
+
+
+ |
+ |
+ |
+ |
+ |
+ |
+ |
+ |
+ |
+
+
+ | Annealing |
+ 26 |
+ YuLan-Mini-4K |
+ |
+ |
+ llama* |
+ 64.72 |
+ 66.65 |
+ 61.60 |
+
+
+ | Annealing |
+ 27 |
+ |
+ YuLan-Mini |
+ |
+ llama* |
+ 65.67 |
+ 68.46 |
+ 64.00 |
+
+
+
+
+\*: For easier inference and deployment, we merged the re-parameterized added parameters and scaling factors into the final released models ([**YuLan-Mini**](https://huggingface.co/yulan-team/YuLan-Mini) and **YuLan-Mini-Intermediate-4K**), enabling it to run on the Llama architecture. However, these parameters are still retained in the intermediate checkpoints from the training process.
+
+
+
+3. Optimizer States Before Annealing
+
+YuLan-Mini-Before-Annealing
+
+
+
+4. The Used Open-Source Datasets
+
+Used-Datasets-List
+
+
+
+5. Data Distribution for every phase
+
+
+
+

+
+
+
+
+
+6. Synthetic Data
+
+Data cleaning and synthesis pipeline:
+
+

+
+
+The synthetic data we are using is released in YuLan-Mini-Datasets
+
+
+
+
+### What you can do with these pre-training resources
+
+1. **Pre-train** your own LLM. You can use [our data](https://huggingface.co/yulan-team/YuLan-Mini-Datasets) and curriculum to train a model that's just as powerful as YuLan-Mini.
+2. Perform your own **learning rate annealing**. During the annealing phase, YuLan-Mini's learning ability is at its peak. You can resume training from [the checkpoint before annealing](https://huggingface.co/yulan-team/YuLan-Mini-Before-Annealing) and use your own dataset for learning rate annealing.
+3. **Fine-tune** the Instruct version of the LLM. You can use the [YuLan-Mini](https://huggingface.co/yulan-team/YuLan-Mini) base model to train your own Instruct version.
+4. **Training dynamics** research. You can use YuLan-Mini's [intermediate checkpoints](https://huggingface.co/collections/yulan-team/yulan-mini-676d214b24376739b00d95f3) to explore internal changes during the pre-training process.
+5. **Synthesize** your own data. You can use YuLan-Mini's [data pipeline](https://github.com/RUC-GSAI/YuLan-Mini) to clean and generate your own dataset.
+
+---
+
+## Quick Start 💻
+
+Below is a simple example for inference using Huggingface:
+
+**Huggingface Inference Example**
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+# Load model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained("yulan-team/YuLan-Mini")
+model = AutoModelForCausalLM.from_pretrained("yulan-team/YuLan-Mini", torch_dtype=torch.bfloat16)
+
+# Input text
+input_text = "Renmin University of China is"
+inputs = tokenizer(input_text, return_tensors="pt")
+
+# Completion
+output = model.generate(inputs["input_ids"], max_new_tokens=100)
+print(tokenizer.decode(output[0], skip_special_tokens=True))
+```
+
+**vLLM Serve Example**
+```bash
+vllm serve yulan-team/YuLan-Mini --dtype bfloat16
+```
+
+**SGLang Serve Example**
+```bash
+python -m sglang.launch_server --model-path yulan-team/YuLan-Mini --port 30000 --host 0.0.0.0
+```
+
+---
+
+## The Team
+
+YuLan-Mini is developed and maintained by [AI Box, Renmin University of China](http://aibox.ruc.edu.cn/).
+
+## License
+
+- The code in this repository is released under the [MIT License](./LICENSE).
+- Policies regarding the use of model weights, intermediate optimizer states, and training data will be announced in future updates.
+- Limitations: Despite our efforts to mitigate safety concerns and encourage the generation of ethical and lawful text, the probabilistic nature of language models may still lead to unexpected outputs. For instance, responses might contain bias, discrimination, or other harmful content. Please refrain from disseminating such content. We are not liable for any consequences arising from the spread of harmful information.
+
+## Citation
+
+If you find YuLan-Mini helpful for your research or development, please cite [our technical report](https://arxiv.org/abs/2412.17743):
+
+```
+@misc{hu2024yulanmini,
+ title={YuLan-Mini: An Open Data-efficient Language Model},
+ author={Yiwen Hu and Huatong Song and Jia Deng and Jiapeng Wang and Jie Chen and Kun Zhou and Yutao Zhu and Jinhao Jiang and Zican Dong and Wayne Xin Zhao and Ji-Rong Wen},
+ year={2024},
+ eprint={2412.17743},
+ archivePrefix={arXiv},
+ primaryClass={cs.CL},
+ url={https://arxiv.org/abs/2412.17743},
+}
+```
diff --git a/assets/YuLan-logo.jpg b/assets/YuLan-logo.jpg
new file mode 100644
index 0000000..b8ba741
Binary files /dev/null and b/assets/YuLan-logo.jpg differ
diff --git a/assets/data-pipeline.png b/assets/data-pipeline.png
new file mode 100644
index 0000000..49c3eb9
Binary files /dev/null and b/assets/data-pipeline.png differ
diff --git a/assets/data-preview.png b/assets/data-preview.png
new file mode 100644
index 0000000..1e25384
Binary files /dev/null and b/assets/data-preview.png differ
diff --git a/assets/data_distribution_for_every_phase.png b/assets/data_distribution_for_every_phase.png
new file mode 100644
index 0000000..5277fe7
Binary files /dev/null and b/assets/data_distribution_for_every_phase.png differ
diff --git a/assets/main.png b/assets/main.png
new file mode 100644
index 0000000..5cd9b9a
Binary files /dev/null and b/assets/main.png differ
diff --git a/assets/training-stability.png b/assets/training-stability.png
new file mode 100644
index 0000000..e6d0be7
Binary files /dev/null and b/assets/training-stability.png differ
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..5c6c3d6
--- /dev/null
+++ b/config.json
@@ -0,0 +1,31 @@
+{
+ "_name_or_path": "/home/huyiwen/miniyulan-ckpts/miniyulan-2B-s25d-decay80-1sqrt-long-28k-qkln-final-stage2-resume-27_20241213_051741/YuLan-Mini-2.4B-bfloat16",
+ "architectures": [
+ "LlamaForCausalLM"
+ ],
+ "attention_bias": true,
+ "attention_dropout": 0.0,
+ "bos_token_id": 1,
+ "eos_token_id": 2,
+ "head_dim": 64,
+ "hidden_act": "silu",
+ "hidden_size": 1920,
+ "initializer_range": 5e-05,
+ "intermediate_size": 4800,
+ "max_position_embeddings": 28723,
+ "mlp_bias": false,
+ "model_type": "llama",
+ "num_attention_heads": 30,
+ "num_hidden_layers": 56,
+ "num_key_value_heads": 6,
+ "pad_token_id": 102,
+ "pretraining_tp": 1,
+ "rms_norm_eps": 1e-06,
+ "rope_scaling": null,
+ "rope_theta": 490000.0,
+ "tie_word_embeddings": false,
+ "torch_dtype": "bfloat16",
+ "transformers_version": "4.47.1",
+ "use_cache": true,
+ "vocab_size": 99000
+}
diff --git a/configuration.json b/configuration.json
new file mode 100644
index 0000000..262fd55
--- /dev/null
+++ b/configuration.json
@@ -0,0 +1 @@
+{"framework":"Pytorch","task":"chatbot"}
\ No newline at end of file
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..064a29c
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,6 @@
+{
+ "_from_model_config": true,
+ "bos_token_id": 1,
+ "eos_token_id": 2,
+ "transformers_version": "4.47.1"
+}
diff --git a/model.safetensors b/model.safetensors
new file mode 100644
index 0000000..4289669
--- /dev/null
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b8cd6aa5571fa57d75255dcc627d0279a640335424797f75c9660918f94623e
+size 4848833776
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000..a782b2f
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+ "bos_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "unk_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000..43a5fc9
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,607639 @@
+{
+ "version": "1.0",
+ "truncation": null,
+ "padding": null,
+ "added_tokens": [
+ {
+ "id": 0,
+ "content": "",
+ "single_word": false,
+ "lstrip": false,
+ "rstrip": false,
+ "normalized": false,
+ "special": true
+ },
+ {
+ "id": 1,
+ "content": "",
+ "single_word": false,
+ "lstrip": false,
+ "rstrip": false,
+ "normalized": false,
+ "special": true
+ },
+ {
+ "id": 2,
+ "content": "",
+ "single_word": false,
+ "lstrip": false,
+ "rstrip": false,
+ "normalized": false,
+ "special": true
+ },
+ {
+ "id": 102,
+ "content": "",
+ "single_word": false,
+ "lstrip": false,
+ "rstrip": false,
+ "normalized": false,
+ "special": true
+ },
+ {
+ "id": 103,
+ "content": "",
+ "single_word": false,
+ "lstrip": false,
+ "rstrip": false,
+ "normalized": false,
+ "special": true
+ },
+ {
+ "id": 104,
+ "content": "<|start_header_id|>",
+ "single_word": false,
+ "lstrip": false,
+ "rstrip": false,
+ "normalized": false,
+ "special": true
+ },
+ {
+ "id": 105,
+ "content": "<|end_header_id|>",
+ "single_word": false,
+ "lstrip": false,
+ "rstrip": false,
+ "normalized": false,
+ "special": true
+ },
+ {
+ "id": 106,
+ "content": "<|eot_id|>",
+ "single_word": false,
+ "lstrip": false,
+ "rstrip": false,
+ "normalized": false,
+ "special": true
+ }
+ ],
+ "normalizer": {
+ "type": "Sequence",
+ "normalizers": [
+ {
+ "type": "Prepend",
+ "prepend": "▁"
+ },
+ {
+ "type": "Replace",
+ "pattern": {
+ "String": " "
+ },
+ "content": "▁"
+ },
+ {
+ "type": "Replace",
+ "pattern": {
+ "String": " "
+ },
+ "content": "▁"
+ }
+ ]
+ },
+ "pre_tokenizer": null,
+ "post_processor": {
+ "type": "TemplateProcessing",
+ "single": [
+ {
+ "SpecialToken": {
+ "id": "",
+ "type_id": 0
+ }
+ },
+ {
+ "Sequence": {
+ "id": "A",
+ "type_id": 0
+ }
+ }
+ ],
+ "pair": [
+ {
+ "SpecialToken": {
+ "id": "",
+ "type_id": 0
+ }
+ },
+ {
+ "Sequence": {
+ "id": "A",
+ "type_id": 0
+ }
+ },
+ {
+ "SpecialToken": {
+ "id": "",
+ "type_id": 1
+ }
+ },
+ {
+ "Sequence": {
+ "id": "B",
+ "type_id": 1
+ }
+ }
+ ],
+ "special_tokens": {
+ "": {
+ "id": "",
+ "ids": [
+ 1
+ ],
+ "tokens": [
+ ""
+ ]
+ }
+ }
+ },
+ "decoder": {
+ "type": "Sequence",
+ "decoders": [
+ {
+ "type": "Replace",
+ "pattern": {
+ "String": "▁"
+ },
+ "content": " "
+ },
+ {
+ "type": "ByteFallback"
+ },
+ {
+ "type": "Fuse"
+ },
+ {
+ "type": "Strip",
+ "content": " ",
+ "start": 1,
+ "stop": 0
+ }
+ ]
+ },
+ "model": {
+ "type": "BPE",
+ "dropout": null,
+ "unk_token": "",
+ "continuing_subword_prefix": null,
+ "end_of_word_suffix": null,
+ "fuse_unk": true,
+ "byte_fallback": true,
+ "ignore_merges": false,
+ "vocab": {
+ "": 0,
+ "": 1,
+ "": 2,
+ "": 3,
+ "": 4,
+ "\n": 5,
+ "\t": 6,
+ "
": 7,
+ "
": 8,
+ "": 9,
+ "": 10,
+ "": 11,
+ "
": 12,
+ "": 13,
+ " | | ": 14,
+ "": 15,
+ "": 16,
+ "": 17,
+ "": 18,
+ "": 21,
+ "": 22,
+ "
": 23,
+ "": 24,
+ "": 25,
+ "": 26,
+ "": 27,
+ "": 28,
+ "": 29,
+ "": 30,
+ "": 31,
+ "": 32,
+ "
": 33,
+ "
": 34,
+ "
": 35,
+ "": 36,
+ "": 37,
+ "": 38,
+ "
": 39,
+ "": 40,
+ "": 41,
+ "
": 42,
+ "": 43,
+ "
": 44,
+ "
": 45,
+ "": 46,
+ "": 47,
+ "
": 48,
+ "": 49,
+ "": 50,
+ "": 51,
+ "0": 52,
+ "1": 53,
+ "2": 54,
+ "3": 55,
+ "4": 56,
+ "5": 57,
+ "6": 58,
+ "7": 59,
+ "8": 60,
+ "9": 61,
+ "+": 62,
+ "-": 63,
+ "=": 64,
+ ",": 65,
+ "。": 66,
+ "!": 67,
+ "?": 68,
+ "、": 69,
+ ":": 70,
+ "¥": 71,
+ ".": 72,
+ "!": 73,
+ "?": 74,
+ "...": 75,
+ "。。。": 76,
+ "。。。。。。": 77,
+ "《": 78,
+ "》": 79,
+ "【": 80,
+ "】": 81,
+ "『": 82,
+ "』": 83,
+ "```": 84,
+ "": 86,
+ "---": 87,
+ "": 88,
+ ";": 89,
+ ".": 90,
+ "=": 91,
+ "<": 92,
+ ">": 93,
+ "-": 94,
+ "+": 95,
+ "%": 96,
+ "‼": 97,
+ "㊣": 98,
+ "/": 99,
+ "|": 100,
+ "": 101,
+ "": 102,
+ "": 103,
+ "<|start_header_id|>": 104,
+ "<|end_header_id|>": 105,
+ "<|eot_id|>": 106,
+ "": 107,
+ "": 108,
+ "": 109,
+ "": 110,
+ "": 111,
+ "": 112,
+ "": 113,
+ "": 114,
+ "": 115,
+ "": 116,
+ "": 117,
+ "": 118,
+ "": 119,
+ "": 120,
+ "": 121,
+ "": 122,
+ "": 123,
+ "": 124,
+ "": 125,
+ "": 126,
+ "": 127,
+ "": 128,
+ "": 129,
+ "": 130,
+ "": 131,
+ "": 132,
+ "": 133,
+ "": 134,
+ "": 135,
+ "": 136,
+ "": 137,
+ "": 138,
+ "": 139,
+ "": 140,
+ "": 141,
+ "": 142,
+ "": 143,
+ "": 144,
+ "": 145,
+ "": 146,
+ "": 147,
+ "": 148,
+ "": 149,
+ "": 150,
+ "": 151,
+ "": 152,
+ "": 153,
+ "": 154,
+ "": 155,
+ "": 156,
+ "": 157,
+ "": 158,
+ "": 159,
+ "": 160,
+ "": 161,
+ "": 162,
+ "": 163,
+ "": 164,
+ "": 165,
+ "": 166,
+ "": 167,
+ "": 168,
+ "": 169,
+ "": 170,
+ "": 171,
+ "": 172,
+ "": 173,
+ "": 174,
+ "": 175,
+ "": 176,
+ "": 177,
+ "": 178,
+ "": 179,
+ "": 180,
+ "": 181,
+ "": 182,
+ "": 183,
+ "": 184,
+ "": 185,
+ "": 186,
+ "": 187,
+ "": 188,
+ "": 189,
+ "": 190,
+ "": 191,
+ "": 192,
+ "": 193,
+ "": 194,
+ "": 195,
+ "": 196,
+ "": 197,
+ "": 198,
+ "": 199,
+ "": 200,
+ "": 201,
+ "": 202,
+ "": 203,
+ "": 204,
+ "": 205,
+ "": 206,
+ "": 207,
+ "": 208,
+ "": 209,
+ "": 210,
+ "": 211,
+ "": 212,
+ "": 213,
+ "": 214,
+ "": 215,
+ "": 216,
+ "": 217,
+ "": 218,
+ "": 219,
+ "": 220,
+ "": 221,
+ "": 222,
+ "": 223,
+ "": 224,
+ "": 225,
+ "": 226,
+ "": 227,
+ "": 228,
+ "": 229,
+ "": 230,
+ "": 231,
+ "": 232,
+ "": 233,
+ "": 234,
+ "": 235,
+ "": 236,
+ "": 237,
+ "": 238,
+ "": 239,
+ "": 240,
+ "": 241,
+ "": 242,
+ "": 243,
+ "": 244,
+ "": 245,
+ "": 246,
+ "": 247,
+ "": 248,
+ "": 249,
+ "": 250,
+ "": 251,
+ "": 252,
+ "": 253,
+ "": 254,
+ "": 255,
+ "": 256,
+ "": 257,
+ "": 258,
+ "": 259,
+ "": 260,
+ "": 261,
+ "": 262,
+ "": 263,
+ "": 264,
+ "": 265,
+ "": 266,
+ "": 267,
+ "": 268,
+ "": 269,
+ "": 270,
+ "": 271,
+ "": 272,
+ "": 273,
+ "": 274,
+ "": 275,
+ "": 276,
+ "": 277,
+ "": 278,
+ "": 279,
+ "": 280,
+ "": 281,
+ "": 282,
+ "": 283,
+ "": 284,
+ "": 285,
+ "": 286,
+ "": 287,
+ "": 288,
+ "": 289,
+ "": 290,
+ "": 291,
+ "": 292,
+ "": 293,
+ "": 294,
+ "": 295,
+ "": 296,
+ "": 297,
+ "": 298,
+ "": 299,
+ "": 300,
+ "": 301,
+ "": 302,
+ "": 303,
+ "": 304,
+ "": 305,
+ "": 306,
+ "": 307,
+ "": 308,
+ "": 309,
+ "": 310,
+ "": 311,
+ "": 312,
+ "": 313,
+ "": 314,
+ "": 315,
+ "": 316,
+ "": 317,
+ "": 318,
+ "": 319,
+ "": 320,
+ "": 321,
+ "": 322,
+ "": 323,
+ "": 324,
+ "": 325,
+ "": 326,
+ "": 327,
+ "": 328,
+ "": 329,
+ "": 330,
+ "": 331,
+ "": 332,
+ "": 333,
+ "": 334,
+ "": 335,
+ "": 336,
+ "": 337,
+ "": 338,
+ "": 339,
+ "": 340,
+ "": 341,
+ "": 342,
+ "": 343,
+ "": 344,
+ "": 345,
+ "": 346,
+ "": 347,
+ "": 348,
+ "": 349,
+ "": 350,
+ "": 351,
+ "": 352,
+ "": 353,
+ "": 354,
+ "": 355,
+ "": 356,
+ "