commit 372c5bc5faf70f637d3b6231d821d6494a313be7
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Sat Jul 25 08:41:10 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: Rakuten/RakutenAI-2.0-mini
    Source: Original Platform

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..a6344aa
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,35 @@
+*.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
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..39bc7a0
--- /dev/null
+++ b/README.md
@@ -0,0 +1,67 @@
+---
+license: apache-2.0
+language:
+- en
+- ja
+---
+
+# RakutenAI-2.0-mini
+## Model Description
+RakutenAI-2.0-mini is a lightweight Japanese language model trained from scratch using a transformer architecture, designed for efficient performance in resource-constrained environments. As a foundation model, it serves as the backbone for instruct models.
+
+*If you are looking for instruct model, check [RakutenAI-2.0-mini-instruct](https://huggingface.co/Rakuten/RakutenAI-2.0-mini-instruct)*.
+
+
+## Model Usage
+## Usage
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+model_path = "Rakuten/RakutenAI-2.0-mini"
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForCausalLM.from_pretrained(model_path, torch_dtype="auto", device_map="auto")
+model.eval()
+
+requests = [
+    "南硫黄島原生自然環境保全地域は、自然",
+    "The capybara is a giant cavy rodent",
+]
+
+for req in requests:
+    input_text = tokenizer(req, return_tensors="pt").to(device=model.device)
+    tokens = model.generate(
+        **input_text,
+        max_new_tokens=512,
+        do_sample=True,
+        pad_token_id=tokenizer.eos_token_id,
+    )
+    out = tokenizer.decode(tokens[0], skip_special_tokens=True)
+    print("INPUT:\n" + req)
+    print("OUTPUT:\n" + out)
+
+```
+
+## Model Details
+
+* **Developed by**: [Rakuten Group, Inc.](https://ai.rakuten.com/)
+* **Language(s)**: Japanese, English
+* **License**: This model is licensed under [Apache License, Version 2.0](https://www.apache.org/licenses/LICENSE-2.0).
+* **Model Architecture**: Transformer
+
+### Limitations and Bias
+
+The suite of RakutenAI-2.0 models is capable of generating human-like text on a wide range of topics. However, like all LLMs, they have limitations and can produce biased, inaccurate, or unsafe outputs. Please exercise caution and judgement while interacting with them.
+
+## Citation
+For citing our work on the suite of RakutenAI-2.0 models, please use: 
+
+```
+@misc{rakutengroup2025rakutenai2.0,
+  author = {Rakuten Group, Inc.},
+  title = {RakutenAI-2.0},
+  year = {2025},
+  publisher = {Hugging Face},
+  url = {https://huggingface.co/Rakuten},
+}
+
+```
+
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..52728db
--- /dev/null
+++ b/config.json
@@ -0,0 +1,28 @@
+{
+  "_flash_attn_2_enabled": true,
+  "_name_or_path": "Rakuten/RakutenAI-2.0-mini",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 100000.0,
+  "sliding_window": 8192,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "use_transformers_inputs": true,
+  "vocab_size": 48000
+}
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..b8e05e6
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.39.3"
+}
diff --git a/model.safetensors b/model.safetensors
new file mode 100644
index 0000000..f9b8104
--- /dev/null
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:100d404fe364bdb0fbab7989c75ff82141b20193cb2c3f42e43a69ce3b4ea625
+size 3069389424
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000..71d10fa
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/tokenizer.model b/tokenizer.model
new file mode 100644
index 0000000..47a92af
--- /dev/null
+++ b/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7978987401ef447724ded0544d048831954b7517a96555ce1593149e3678b6dc
+size 755169
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..52d5b11
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,48 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] | trim + ' ' %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = 'A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user\\'s questions. ' %}\n{%- endif %}\n\n{{- system_message }}\n{%- for message in messages %}\n    {%- if message['role'] == 'user' %}\n        {{- 'USER: ' + message['content'] | trim }}\n    {%- elif message['role'] == 'assistant' %}\n        {{- ' ASSISTANT: '  + message['content'] | trim + '</s>' }}\n    {%- endif %}\n{%- endfor %}\n\n{%- if add_generation_prompt %}\n    {{- ' ASSISTANT:' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}