Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+logo.png filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

Modelfile

@@ -0,0 +1,14 @@
+# ollama modelfile auto-generated by llamafactory
+
+FROM .
+
+TEMPLATE """<bos>{{ if .System }}{{ .System }}
+
+{{ end }}{{ range .Messages }}{{ if eq .Role "user" }}<start_of_turn>user
+{{ .Content }}<end_of_turn>
+<start_of_turn>model
+{{ else if eq .Role "assistant" }}{{ .Content }}<end_of_turn>
+{{ end }}{{ end }}"""
+
+PARAMETER stop "<end_of_turn>"
+PARAMETER num_ctx 4096

README.md

@@ -1,3 +1,125 @@
----
-license: apache-2.0
----
+---
+library_name: transformers
+license: apache-2.0
+license_link: https://huggingface.co/google/gemma-3-270m-it/blob/main/LICENSE
+pipeline_tag: text-generation
+base_model:
+- google/gemma-3-270m-it
+---
+
+# 小熠（Yee）AI 数据安全专家
+
+![Logo](logo.png)
+
+> 由 [广州熠数信息技术有限公司](https://shining-data.com) 开发，基于大语言模型技术构建的数据安全智能助手。
+---
+
+## 🔍 核心特点
+
+- **基于 Gemma-3-270M-IT 微调**
+  - 使用 Google 最新一代轻量级大语言模型 Gemma-3，具备优秀的推理能力和指令跟随能力。
+  - 模型参数精简，推理速度快，资源消耗低，适合资源受限环境部署。
+
+- **高效推理机制**
+  - 针对数据安全场景优化，在保证准确性的同时提供快速响应。
+  - 支持流式输出，提升用户体验。
+
+- **高兼容性**
+  - 支持主流部署方式：本地运行、Docker 容器、Kubernetes 集群、SaaS API 接口等。
+  - 兼容 HuggingFace Transformers、vLLM、Ollama 等推理框架。
+
+---
+
+## 📊 性能特点
+
+Yee-270m 基于 Gemma-3-270M-IT 微调，在保持轻量级特性的同时，针对数据安全领域任务进行了专门优化：
+
+- 模型参数量：2.7亿，部署资源需求低
+- 支持上下文长度：8K tokens
+- 推理速度快，响应延迟低
+- 针对中文数据安全场景优化
+
+---
+
+## 📦 快速开始
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+# 加载 tokenizer 和模型
+tokenizer = AutoTokenizer.from_pretrained("sds-ai/Yee-270m")
+model = AutoModelForCausalLM.from_pretrained(
+    "sds-ai/Yee-270m",
+    torch_dtype="auto",
+    device_map="auto"
+)
+
+# 输入提示
+prompt = "请帮我检查这份数据是否包含敏感字段？"
+
+# 应用聊天模板
+messages = [{"role": "user", "content": prompt}]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+
+# 编码输入
+inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+# 生成响应
+response_ids = model.generate(**inputs, max_new_tokens=1024)
+response = tokenizer.decode(response_ids[0][len(inputs.input_ids[0]):], skip_special_tokens=True)
+
+print("小熠：\n", response)
+```
+
+---
+
+## 🛠️ 部署方式
+
+你可以通过以下任意一种方式部署小熠：
+
+### 使用 Transformers 直接加载
+```python
+from transformers import pipeline
+
+pipe = pipeline("text-generation", model="sds-ai/Yee-270m")
+response = pipe("数据安全最佳实践有哪些？")
+```
+
+### 使用 vLLM 启动服务
+```bash
+vllm serve sds-ai/Yee-270m
+```
+
+### 使用 Ollama / LMStudio
+Gemma-3 已被主流本地化 LLM 工具广泛支持，详情请参考官方文档。
+
+---
+
+## 📚 最佳实践建议
+
+为获得最佳性能，请遵循以下推荐设置：
+
+| 参数 | 推荐值 | 说明 |
+|------|--------|------|
+| 温度 | 0.6 | 平衡创造性和一致性 |
+| TopP | 0.9 | 核采样参数 |
+| Max Length | 2048 | 最大生成长度 |
+
+- 输出长度建议设为 **1024 tokens**，复杂任务可适当增加。
+- 在多轮对话中，建议保留完整的对话历史以获得最佳效果。
+
+---
+
+## 📞 联系我们
+
+了解更多关于小熠的信息，请访问 [熠数信息官网](https://shining-data.com)
+
+---
+
+## 🌟 致谢
+
+感谢 Google 开源 Gemma-3 模型，为小熠提供了高效的语言理解和生成能力基础。

chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}

config.json

@@ -0,0 +1,54 @@
+{
+  "_sliding_window_pattern": 6,
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 640,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_local_base_freq": 10000.0,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 512,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.0.dev0",
+  "use_bidirectional_attention": false,
+  "use_cache": true,
+  "vocab_size": 262144
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "4.55.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:421f80b5110955a40ea570f3f391484c191d3c9478d03f717da1834a531b2c68
+size 536223056

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<end_of_turn>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568