[update] minimind-3

app.py

@@ -1,36 +1,56 @@
 import random
 import re
+import json
+import os
 from threading import Thread
 
 import torch
 import numpy as np
 import streamlit as st
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 
 st.set_page_config(page_title="MiniMind", initial_sidebar_state="collapsed")
 
 st.markdown("""
     <style>
-        /* 调整主容器边距，避免溢出 */
-        .stMainBlockContainer {
-            padding-top: 3rem !important;
-            padding-bottom: 0rem !important;
+        /* 添加操作按钮样式 */
+        .stButton button {
+            border-radius: 50% !important;  /* 改为圆形 */
+            width: 32px !important;         /* 固定宽度 */
+            height: 32px !important;        /* 固定高度 */
+            padding: 0 !important;          /* 移除内边距 */
+            background-color: transparent !important;
+            border: 1px solid #ddd !important;
+            display: flex !important;
+            align-items: center !important;
+            justify-content: center !important;
+            font-size: 14px !important;
+            color: #666 !important;         /* 更柔和的颜色 */
+            margin: 5px 10px 5px 0 !important;  /* 调整按钮间距 */
         }
-        
-        /* 调整应用容器，避免顶部内容被遮挡 */
-        .stApp {
-            overflow-y: auto !important;
+        .stButton button:hover {
+            border-color: #999 !important;
+            color: #333 !important;
+            background-color: #f5f5f5 !important;
+        }
+        .stMainBlockContainer > div:first-child {
+            margin-top: -50px !important;
+        }
+        .stApp > div:last-child {
+            margin-bottom: -35px !important;
         }
         
-        /* 操作按钮样式 */
+        /* 重置按钮基础样式 */
         .stButton > button {
+            all: unset !important;  /* 重置所有默认样式 */
             box-sizing: border-box !important;
             border-radius: 50% !important;
-            width: 24px !important;
-            height: 24px !important;
-            min-width: 24px !important;
-            min-height: 24px !important;
-            max-width: 24px !important;
-            max-height: 24px !important;
+            width: 18px !important;
+            height: 18px !important;
+            min-width: 18px !important;
+            min-height: 18px !important;
+            max-width: 18px !important;
+            max-height: 18px !important;
             padding: 0 !important;
             background-color: transparent !important;
             border: 1px solid #ddd !important;
@@ -41,54 +61,136 @@ st.markdown("""
             color: #888 !important;
             cursor: pointer !important;
             transition: all 0.2s ease !important;
-            margin: 2px !important;
-        }
-        
-        .stButton > button:hover {
-            border-color: #999 !important;
-            color: #333 !important;
-            background-color: #f5f5f5 !important;
-        }
-        
-        /* 确保聊天容器不溢出 */
-        .stChatMessage {
-            max-width: 100% !important;
-        }
-        
-        /* 侧边栏样式优化 */
-        section[data-testid="stSidebar"] {
-            overflow-y: auto !important;
+            margin: 0 2px !important;  /* 调整这里的 margin 值 */
         }
+
     </style>
 """, unsafe_allow_html=True)
 
-system_prompt = []
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
-
-def process_assistant_content(content):
-    if model_source == "API" and 'R1' not in api_model_name:
-        return content
-    if model_source != "API" and 'R1' not in MODEL_PATHS[selected_model][1]:
-        return content
+# 多语言文本
+LANG_TEXTS = {
+    'zh': {
+        'settings': '模型设定调整',
+        'history_rounds': '历史对话轮次',
+        'max_length': '最大生成长度',
+        'temperature': '温度',
+        'thinking': '思考',
+        'tools': '工具',
+        'language': '语言',
+        'send': '给 MiniMind 发送消息',
+        'disclaimer': 'AI 生成内容可能存在错误，请仔细核实',
+        'think_tip': '自适应思考，目前多轮对话或Tool Call共存时思考不稳定',
+        'tool_select': '工具选择（最多4个）',
+    },
+    'en': {
+        'settings': 'Model Settings',
+        'history_rounds': 'History Rounds',
+        'max_length': 'Max Length',
+        'temperature': 'Temperature',
+        'thinking': 'Thinking',
+        'tools': 'Tools',
+        'language': 'Language',
+        'send': 'Send a message to MiniMind',
+        'disclaimer': 'AI-generated content may be inaccurate, please verify',
+        'think_tip': 'Adaptive thinking; may be unstable with multi-turn or Tool Call',
+        'tool_select': 'Tool Selection (max 4)',
+    }
+}
+
+def get_text(key):
+    lang = st.session_state.get('lang', 'en')
+    return LANG_TEXTS.get(lang, {}).get(key, LANG_TEXTS['zh'].get(key, key))
+
+# 工具定义
+TOOLS = [
+    {"type": "function", "function": {"name": "calculate_math", "description": "计算数学表达式", "parameters": {"type": "object", "properties": {"expression": {"type": "string", "description": "数学表达式"}}, "required": ["expression"]}}},
+    {"type": "function", "function": {"name": "get_current_time", "description": "获取当前时间", "parameters": {"type": "object", "properties": {"timezone": {"type": "string", "default": "Asia/Shanghai"}}, "required": []}}},
+    {"type": "function", "function": {"name": "random_number", "description": "生成随机数", "parameters": {"type": "object", "properties": {"min": {"type": "integer"}, "max": {"type": "integer"}}, "required": ["min", "max"]}}},
+    {"type": "function", "function": {"name": "text_length", "description": "计算文本长度", "parameters": {"type": "object", "properties": {"text": {"type": "string"}}, "required": ["text"]}}},
+    {"type": "function", "function": {"name": "unit_converter", "description": "单位转换", "parameters": {"type": "object", "properties": {"value": {"type": "number"}, "from_unit": {"type": "string"}, "to_unit": {"type": "string"}}, "required": ["value", "from_unit", "to_unit"]}}},
+    {"type": "function", "function": {"name": "get_current_weather", "description": "获取天气", "parameters": {"type": "object", "properties": {"city": {"type": "string"}}, "required": ["city"]}}},
+    {"type": "function", "function": {"name": "get_exchange_rate", "description": "获取汇率", "parameters": {"type": "object", "properties": {"from_currency": {"type": "string"}, "to_currency": {"type": "string"}}, "required": ["from_currency", "to_currency"]}}},
+    {"type": "function", "function": {"name": "translate_text", "description": "翻译文本", "parameters": {"type": "object", "properties": {"text": {"type": "string"}, "target_lang": {"type": "string"}}, "required": ["text", "target_lang"]}}},
+]
+
+TOOL_SHORT_NAMES = {
+    'calculate_math': '数学', 'get_current_time': '时间', 'random_number': '随机',
+    'text_length': '字数', 'unit_converter': '单位', 'get_current_weather': '天气',
+    'get_exchange_rate': '汇率', 'translate_text': '翻译'
+}
+
+def execute_tool(tool_name, args):
+    import datetime
+    try:
+        if tool_name == 'calculate_math':
+            return {"result": eval(args.get('expression', '0'))}
+        elif tool_name == 'get_current_time':
+            tz = args.get('timezone', 'Asia/Shanghai')
+            return {"result": datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')}
+        elif tool_name == 'random_number':
+            return {"result": random.randint(args.get('min', 0), args.get('max', 100))}
+        elif tool_name == 'text_length':
+            return {"result": len(args.get('text', ''))}
+        elif tool_name == 'unit_converter':
+            return {"result": f"{args.get('value', 0)} {args.get('from_unit', '')} = ? {args.get('to_unit', '')}"}
+        elif tool_name == 'get_current_weather':
+            return {"result": f"{args.get('city', 'Unknown')}: 晴, 7~10°C"}
+        elif tool_name == 'get_exchange_rate':
+            return {"result": f"1 {args.get('from_currency', 'USD')} = 7.2 {args.get('to_currency', 'CNY')}"}
+        elif tool_name == 'translate_text':
+            return {"result": f"[翻译结果]: hello world"}
+        return {"result": "Unknown tool"}
+    except Exception as e:
+        return {"error": str(e)}
+
+
+def process_assistant_content(content, is_streaming=False):
+    # 处理tool_call标签，格式化显示
+    if '<tool_call>' in content:
+        def format_tool_call(match):
+            try:
+                tc = json.loads(match.group(1))
+                name = tc.get('name', 'unknown')
+                args = tc.get('arguments', {})
+                return f'<div style="background: rgba(80, 110, 150, 0.20); border: 1px solid rgba(140, 170, 210, 0.30); padding: 10px 12px; border-radius: 12px; margin: 6px 0;"><div style="font-size:12px;opacity:.75;display:block;margin:0 0 6px 0;line-height:1;">ToolCalling</div><div><b>{name}</b>: {json.dumps(args, ensure_ascii=False)}</div></div>'
+            except:
+                return match.group(0)
+        content = re.sub(r'<tool_call>(.*?)</tool_call>', format_tool_call, content, flags=re.DOTALL)
+    
+    # 流式生成且开启思考时，一开始就放到折叠里
+    if is_streaming and st.session_state.get('enable_thinking', False) and '</think>' not in content and '<think>' not in content:
+        m = re.search(r'(\n\n(?:我是|您好|你好)[^\n]*)', content)
+        if m and m.start(1) > 5:
+            i = m.start(1)
+            think_part = content[:i]
+            answer_part = content[i:]
+            return f'<details open style="border-left: 2px solid #666; padding-left: 12px; margin: 8px 0;"><summary style="cursor: pointer; color: #888;">已思考</summary><div style="color: #aaa; font-size: 0.95em; margin-top: 8px; max-height: 100px; overflow-y: auto;">{think_part.strip()}</div></details>{answer_part}'
+        elif len(content) > 5:
+            return f'<details open style="border-left: 2px solid #666; padding-left: 12px; margin: 8px 0;"><summary style="cursor: pointer; color: #888;">思考中...</summary><div style="color: #aaa; font-size: 0.95em; margin-top: 8px; max-height: 100px; overflow-y: auto; display: flex; flex-direction: column-reverse;"><div style="margin-bottom: auto;">{content.strip().replace(chr(10), "<br>")}</div></div></details>'
 
     if '<think>' in content and '</think>' in content:
-        content = re.sub(r'(<think>)(.*?)(</think>)',
-                         r'<details style="font-style: italic; background: rgba(222, 222, 222, 0.5); padding: 10px; border-radius: 10px;"><summary style="font-weight:bold;">推理内容（展开）</summary>\2</details>',
-                         content,
-                         flags=re.DOTALL)
+        def format_think(match):
+            think_content = match.group(2)
+            if think_content.replace('\n', '').strip():  # 不是全换行
+                return f'<details open style="border-left: 2px solid #666; padding-left: 12px; margin: 8px 0;"><summary style="cursor: pointer; color: #888;">已思考</summary><div style="color: #aaa; font-size: 0.95em; margin-top: 8px; max-height: 100px; overflow-y: auto;">{think_content.strip()}</div></details>'
+            return ''
+        content = re.sub(r'(<think>)(.*?)(</think>)', format_think, content, flags=re.DOTALL)
 
     if '<think>' in content and '</think>' not in content:
-        content = re.sub(r'<think>(.*?)$',
-                         r'<details open style="font-style: italic; background: rgba(222, 222, 222, 0.5); padding: 10px; border-radius: 10px;"><summary style="font-weight:bold;">推理中...</summary>\1</details>',
-                         content,
-                         flags=re.DOTALL)
+        def format_think_in_progress(match):
+            tc = match.group(1)
+            return f'<details open style="border-left: 2px solid #666; padding-left: 12px; margin: 8px 0;"><summary style="cursor: pointer; color: #888;">思考中...</summary><div style="color: #aaa; font-size: 0.95em; margin-top: 8px; max-height: 100px; overflow-y: auto; display: flex; flex-direction: column-reverse;"><div style="margin-bottom: auto;">{tc.strip().replace(chr(10), "<br>")}</div></div></details>'
+        content = re.sub(r'<think>(.*?)$', format_think_in_progress, content, flags=re.DOTALL)
 
     if '<think>' not in content and '</think>' in content:
-        content = re.sub(r'(.*?)</think>',
-                         r'<details style="font-style: italic; background: rgba(222, 222, 222, 0.5); padding: 10px; border-radius: 10px;"><summary style="font-weight:bold;">推理内容（展开）</summary>\1</details>',
-                         content,
-                         flags=re.DOTALL)
+        def format_think_no_start(match):
+            think_content = match.group(1)
+            if think_content.replace('\n', '').strip():
+                return f'<details open style="border-left: 2px solid #666; padding-left: 12px; margin: 8px 0;"><summary style="cursor: pointer; color: #888;">已思考</summary><div style="color: #aaa; font-size: 0.95em; margin-top: 8px; max-height: 100px; overflow-y: auto;">{think_content.strip()}</div></details>'
+            return ''
+        content = re.sub(r'(.*?)</think>', format_think_no_start, content, flags=re.DOTALL)
 
     return content
 
@@ -116,17 +218,10 @@ def init_chat_messages():
     if "messages" in st.session_state:
         for i, message in enumerate(st.session_state.messages):
             if message["role"] == "assistant":
-                with st.chat_message("assistant", avatar=image_url):
-                    st.markdown(process_assistant_content(message["content"]), unsafe_allow_html=True)
-                    if st.button("🗑", key=f"delete_{i}"):
-                        st.session_state.messages.pop(i)
-                        st.session_state.messages.pop(i - 1)
-                        st.session_state.chat_messages.pop(i)
-                        st.session_state.chat_messages.pop(i - 1)
-                        st.rerun()
+                st.markdown(process_assistant_content(message["content"]), unsafe_allow_html=True)
             else:
                 st.markdown(
-                    f'<div style="display: flex; justify-content: flex-end;"><div style="display: inline-block; margin: 10px 0; padding: 8px 12px 8px 12px;  background-color: #ddd; border-radius: 10px; color: black;">{message["content"]}</div></div>',
+                    f'<div style="display: flex; justify-content: flex-end;"><div style="display: inline-block; margin: 10px 0; padding: 8px 12px 8px 12px; background-color: #3d4450; border-radius: 22px; color: white;">{message["content"]}</div></div>',
                     unsafe_allow_html=True)
 
     else:
@@ -135,56 +230,70 @@ def init_chat_messages():
 
     return st.session_state.messages
 
-
 def regenerate_answer(index):
     st.session_state.messages.pop()
     st.session_state.chat_messages.pop()
     st.rerun()
 
 
-def delete_conversation(index):
-    st.session_state.messages.pop(index)
-    st.session_state.messages.pop(index - 1)
-    st.session_state.chat_messages.pop(index)
-    st.session_state.chat_messages.pop(index - 1)
+# 动态扫描模型目录
+script_dir = os.path.dirname(os.path.abspath(__file__))
+MODEL_PATHS = {}
+for d in sorted(os.listdir(script_dir), reverse=True):
+    full_path = os.path.join(script_dir, d)
+    if os.path.isdir(full_path) and not d.startswith('.') and not d.startswith('_'):
+        if any(f.endswith(('.bin', '.safetensors', '.pt')) or os.path.exists(os.path.join(full_path, 'model.safetensors.index.json')) for f in os.listdir(full_path) if os.path.isfile(os.path.join(full_path, f))):
+            MODEL_PATHS[d] = [d, d]
+if not MODEL_PATHS:
+    MODEL_PATHS = {"No models found": ["", "No models"]}
+
+# 模型选择
+selected_model = st.sidebar.selectbox('Model', list(MODEL_PATHS.keys()), index=0, accept_new_options=False)
+model_path = MODEL_PATHS[selected_model][0]
+slogan = f"我是 {MODEL_PATHS[selected_model][1]}，有什么可以帮你的？" if st.session_state.get('lang', 'en') == 'zh' else f"I am {MODEL_PATHS[selected_model][1]}, how can I help you?"
+
+st.sidebar.markdown('<hr style="margin: 12px 0 16px 0;">', unsafe_allow_html=True)
+
+# 语言选择
+lang_options = {'中文': 'zh', 'English': 'en'}
+current_lang = st.session_state.get('lang', 'en')
+lang_index = 0 if current_lang == 'zh' else 1
+lang_label = st.sidebar.radio('Language / 语言', list(lang_options.keys()), index=lang_index, horizontal=True)
+if lang_options[lang_label] != current_lang:
+    st.session_state.lang = lang_options[lang_label]
     st.rerun()
 
+st.sidebar.markdown('<hr style="margin: 12px 0 16px 0;">', unsafe_allow_html=True)
 
-st.sidebar.title("模型设定调整")
-
-# st.sidebar.text("训练数据偏差，增加上下文记忆时\n多轮对话（较单轮）容易出现能力衰减")
-st.session_state.history_chat_num = st.sidebar.slider("Number of Historical Dialogues", 0, 6, 0, step=2)
-# st.session_state.history_chat_num = 0
-st.session_state.max_new_tokens = st.sidebar.slider("Max Sequence Length", 256, 8192, 8192, step=1)
-st.session_state.temperature = st.sidebar.slider("Temperature", 0.6, 1.2, 0.85, step=0.01)
+# 参数设置
+st.session_state.history_chat_num = st.sidebar.slider(get_text('history_rounds'), 0, 8, 0, step=2)
+st.session_state.max_new_tokens = st.sidebar.slider(get_text('max_length'), 256, 8192, 8192, step=1)
+st.session_state.temperature = st.sidebar.slider(get_text('temperature'), 0.6, 1.2, 0.90, step=0.01)
 
-model_source = st.sidebar.radio("选择模型来源", ["本地模型", "API"], index=0)
-
-if model_source == "API":
-    api_url = st.sidebar.text_input("API URL", value="http://127.0.0.1:8000/v1")
-    api_model_id = st.sidebar.text_input("Model ID", value="minimind")
-    api_model_name = st.sidebar.text_input("Model Name", value="MiniMind2")
-    api_key = st.sidebar.text_input("API Key", value="none", type="password")
-    slogan = f"Hi, I'm {api_model_name}"
-else:
-    MODEL_PATHS = {
-        "MiniMind2 (0.1B)": ["./MiniMind2", "MiniMind2"],
-        "MiniMind2-R1 (0.1B)": ["./MiniMind2-R1", "MiniMind2-R1"]
-    }
+st.sidebar.markdown('<hr style="margin: 12px 0 16px 0;">', unsafe_allow_html=True)
 
-    selected_model = st.sidebar.selectbox('Models', list(MODEL_PATHS.keys()), index=0)  # 默认选择 MiniMind2
-    model_path = MODEL_PATHS[selected_model][0]
-    slogan = f"Hi, I'm {MODEL_PATHS[selected_model][1]}"
+# 功能开关
+st.session_state.enable_thinking = st.sidebar.checkbox(get_text('thinking'), value=False, help=get_text('think_tip'))
+st.session_state.selected_tools = []
+with st.sidebar.expander(get_text('tools')):
+    st.caption(get_text('tool_select'))
+    selected_count = sum(1 for tool in TOOLS if st.session_state.get(f"tool_{tool['function']['name']}", False))
+    for tool in TOOLS:
+        name = tool['function']['name']
+        short_name = TOOL_SHORT_NAMES.get(name, name)
+        checked = st.checkbox(short_name, key=f"tool_{name}", disabled=(selected_count >= 4 and not st.session_state.get(f"tool_{name}", False)))
+        if checked and len(st.session_state.selected_tools) < 4:
+            st.session_state.selected_tools.append(name)
 
 image_url = "https://www.modelscope.cn/api/v1/studio/gongjy/MiniMind/repo?Revision=master&FilePath=images%2Flogo2.png&View=true"
 
 st.markdown(
     f'<div style="display: flex; flex-direction: column; align-items: center; text-align: center; margin: 0; padding: 0;">'
     '<div style="font-style: italic; font-weight: 900; margin: 0; padding-top: 4px; display: flex; align-items: center; justify-content: center; flex-wrap: wrap; width: 100%;">'
-    f'<img src="{image_url}" style="width: 45px; height: 45px; "> '
+    f'<img src="{image_url}" style="width: 40px; height: 40px; "> '
     f'<span style="font-size: 26px; margin-left: 10px;">{slogan}</span>'
     '</div>'
-    '<span style="color: #bbb; font-style: italic; margin-top: 6px; margin-bottom: 10px;">内容完全由AI生成，请务必仔细甄别<br>Content AI-generated, please discern with care</span>'
+    f'<span style="color: #bbb; font-style: italic; margin-top: 6px; margin-bottom: 10px;">{get_text("disclaimer")}</span>'
     '</div>',
     unsafe_allow_html=True
 )
@@ -201,10 +310,7 @@ def setup_seed(seed):
 
 
 def main():
-    if model_source == "本地模型":
-        model, tokenizer = load_model_tokenizer(model_path)
-    else:
-        model, tokenizer = None, None
+    model, tokenizer = load_model_tokenizer(model_path)
 
     if "messages" not in st.session_state:
         st.session_state.messages = []
@@ -214,18 +320,13 @@ def main():
 
     for i, message in enumerate(messages):
         if message["role"] == "assistant":
-            with st.chat_message("assistant", avatar=image_url):
-                st.markdown(process_assistant_content(message["content"]), unsafe_allow_html=True)
-                if st.button("×", key=f"delete_{i}"):
-                    st.session_state.messages = st.session_state.messages[:i - 1]
-                    st.session_state.chat_messages = st.session_state.chat_messages[:i - 1]
-                    st.rerun()
+            st.markdown(process_assistant_content(message["content"]), unsafe_allow_html=True)
         else:
             st.markdown(
-                f'<div style="display: flex; justify-content: flex-end;"><div style="display: inline-block; margin: 10px 0; padding: 8px 12px 8px 12px;  background-color: gray; border-radius: 10px; color:white; ">{message["content"]}</div></div>',
+                f'<div style="display: flex; justify-content: flex-end;"><div style="display: inline-block; margin: 10px 0; padding: 8px 12px 8px 12px; background-color: #3d4450; border-radius: 22px; color: white;">{message["content"]}</div></div>',
                 unsafe_allow_html=True)
 
-    prompt = st.chat_input(key="input", placeholder="给 MiniMind 发送消息")
+    prompt = st.chat_input(key="input", placeholder=get_text('send'))
 
     if hasattr(st.session_state, 'regenerate') and st.session_state.regenerate:
         prompt = st.session_state.last_user_message
@@ -236,89 +337,84 @@ def main():
 
     if prompt:
         st.markdown(
-            f'<div style="display: flex; justify-content: flex-end;"><div style="display: inline-block; margin: 10px 0; padding: 8px 12px 8px 12px;  background-color: gray; border-radius: 10px; color:white; ">{prompt}</div></div>',
+            f'<div style="display: flex; justify-content: flex-end;"><div style="display: inline-block; margin: 10px 0; padding: 8px 12px 8px 12px; background-color: #3d4450; border-radius: 22px; color: white;">{prompt}</div></div>',
             unsafe_allow_html=True)
         messages.append({"role": "user", "content": prompt[-st.session_state.max_new_tokens:]})
         st.session_state.chat_messages.append({"role": "user", "content": prompt[-st.session_state.max_new_tokens:]})
 
-        with st.chat_message("assistant", avatar=image_url):
-            placeholder = st.empty()
+        placeholder = st.empty()
+
+        random_seed = random.randint(0, 2 ** 32 - 1)
+        setup_seed(random_seed)
+
+        tools = [t for t in TOOLS if t['function']['name'] in st.session_state.get('selected_tools', [])] or None
+        sys_prompt = [] if tools else [{"role": "system", "content": "你是MiniMind，一个乐于助人、知识渊博的AI助手。请用完整且友好的方式回答用户问题。"}]
+        st.session_state.chat_messages = sys_prompt + st.session_state.chat_messages[-(st.session_state.history_chat_num + 1):]
+        template_kwargs = {"tokenize": False, "add_generation_prompt": True}
+        if st.session_state.get('enable_thinking', False):
+            template_kwargs["open_thinking"] = True
+        if tools:
+            template_kwargs["tools"] = tools
+        new_prompt = tokenizer.apply_chat_template(st.session_state.chat_messages, **template_kwargs)
+
+        inputs = tokenizer(new_prompt, return_tensors="pt", truncation=True).to(device)
+
+        streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
+        generation_kwargs = {
+            "input_ids": inputs.input_ids,
+            "max_length": inputs.input_ids.shape[1] + st.session_state.max_new_tokens,
+            "num_return_sequences": 1,
+            "do_sample": True,
+            "attention_mask": inputs.attention_mask,
+            "pad_token_id": tokenizer.pad_token_id,
+            "eos_token_id": tokenizer.eos_token_id,
+            "temperature": st.session_state.temperature,
+            "top_p": 0.85,
+            "streamer": streamer,
+        }
 
-            if model_source == "API":
-                try:
-                    from openai import OpenAI
-
-                    client = OpenAI(
-                        api_key=api_key,
-                        base_url=api_url
-                    )
-                    history_num = st.session_state.history_chat_num + 1  # +1 是为了包含当前的用户消息
-                    conversation_history = system_prompt + st.session_state.chat_messages[-history_num:]
-                    answer = ""
-                    response = client.chat.completions.create(
-                        model=api_model_id,
-                        messages=conversation_history,
-                        stream=True,
-                        temperature=st.session_state.temperature
-                    )
-
-                    for chunk in response:
-                        content = chunk.choices[0].delta.content or ""
-                        answer += content
-                        placeholder.markdown(process_assistant_content(answer), unsafe_allow_html=True)
-
-                except Exception as e:
-                    answer = f"API调用出错: {str(e)}"
-                    placeholder.markdown(answer, unsafe_allow_html=True)
-            else:
-                random_seed = random.randint(0, 2 ** 32 - 1)
-                setup_seed(random_seed)
-
-                st.session_state.chat_messages = system_prompt + st.session_state.chat_messages[
-                                                                 -(st.session_state.history_chat_num + 1):]
-                new_prompt = tokenizer.apply_chat_template(
-                    st.session_state.chat_messages,
-                    tokenize=False,
-                    add_generation_prompt=True
-                )
-
-                inputs = tokenizer(
-                    new_prompt,
-                    return_tensors="pt",
-                    truncation=True
-                ).to(device)
-
-                streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
-                generation_kwargs = {
-                    "input_ids": inputs.input_ids,
-                    "max_length": inputs.input_ids.shape[1] + st.session_state.max_new_tokens,
-                    "num_return_sequences": 1,
-                    "do_sample": True,
-                    "attention_mask": inputs.attention_mask,
-                    "pad_token_id": tokenizer.pad_token_id,
-                    "eos_token_id": tokenizer.eos_token_id,
-                    "temperature": st.session_state.temperature,
-                    "top_p": 0.85,
-                    "streamer": streamer,
-                }
-
-                Thread(target=model.generate, kwargs=generation_kwargs).start()
-
-                answer = ""
-                for new_text in streamer:
-                    answer += new_text
-                    placeholder.markdown(process_assistant_content(answer), unsafe_allow_html=True)
-
-            messages.append({"role": "assistant", "content": answer})
+        Thread(target=model.generate, kwargs=generation_kwargs).start()
+
+        answer = ""
+        for new_text in streamer:
+            answer += new_text
+            placeholder.markdown(process_assistant_content(answer, is_streaming=True), unsafe_allow_html=True)
+
+        full_answer = answer
+        for _ in range(16):
+            tool_calls = re.findall(r'<tool_call>(.*?)</tool_call>', answer, re.DOTALL)
+            if not tool_calls:
+                break
             st.session_state.chat_messages.append({"role": "assistant", "content": answer})
-            with st.empty():
-                if st.button("×", key=f"delete_{len(messages) - 1}"):
-                    st.session_state.messages = st.session_state.messages[:-2]
-                    st.session_state.chat_messages = st.session_state.chat_messages[:-2]
-                    st.rerun()
+            tool_results = []
+            for tc_str in tool_calls:
+                try:
+                    tc = json.loads(tc_str.strip())
+                    result = execute_tool(tc.get('name', ''), tc.get('arguments', {}))
+                    st.session_state.chat_messages.append({"role": "tool", "content": json.dumps(result, ensure_ascii=False)})
+                    tool_results.append(f'<div style="background: rgba(90, 130, 110, 0.20); border: 1px solid rgba(150, 200, 170, 0.30); padding: 10px 12px; border-radius: 12px; margin: 6px 0;"><div style="font-size:12px;opacity:.75;display:block;margin:0 0 6px 0;line-height:1;">ToolCalled</div><div><b>{tc.get("name", "")}</b>: {json.dumps(result, ensure_ascii=False)}</div></div>')
+                except:
+                    pass
+            full_answer += "\n" + "\n".join(tool_results) + "\n"
+            placeholder.markdown(process_assistant_content(full_answer, is_streaming=True), unsafe_allow_html=True)
+            new_prompt = tokenizer.apply_chat_template(st.session_state.chat_messages, **template_kwargs)
+            inputs = tokenizer(new_prompt, return_tensors="pt", truncation=True).to(device)
+            streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
+            generation_kwargs["input_ids"] = inputs.input_ids
+            generation_kwargs["attention_mask"] = inputs.attention_mask
+            generation_kwargs["max_length"] = inputs.input_ids.shape[1] + st.session_state.max_new_tokens
+            generation_kwargs["streamer"] = streamer
+            Thread(target=model.generate, kwargs=generation_kwargs).start()
+            answer = ""
+            for new_text in streamer:
+                answer += new_text
+                placeholder.markdown(process_assistant_content(full_answer + answer, is_streaming=True), unsafe_allow_html=True)
+            full_answer += answer
+        answer = full_answer
+
+        messages.append({"role": "assistant", "content": answer})
+        st.session_state.chat_messages.append({"role": "assistant", "content": answer})
 
 
 if __name__ == "__main__":
-    from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
-
-    main()
+    main()

minimind-3-moe/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if true %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if open_thinking is defined and open_thinking is true %}
+        {{- '<think>\n' }}
+    {%- else %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

minimind-3-moe/config.json

@@ -0,0 +1,35 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "decoder_sparse_step": 1,
+  "dtype": "float16",
+  "head_dim": 96,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 2432,
+  "max_position_embeddings": 32768,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_moe",
+  "moe_intermediate_size": 2432,
+  "norm_topk_prob": true,
+  "num_attention_heads": 8,
+  "num_experts": 4,
+  "num_experts_per_tok": 1,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 4,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 6400
+}

minimind-3-moe/generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.57.6"
+}

minimind-3-moe/minimind.modelfile

@@ -0,0 +1,68 @@
+FROM ./Minimind-3-Moe-4x64M-F16.gguf
+
+SYSTEM "你的名字叫MiniMind，你是一个乐于助人、知识渊博的AI助手。请用完整且友好的方式回答用户问题，当被问到名字时请回答MiniMind。"
+
+
+TEMPLATE """{{- if .Tools }}<|im_start|>system
+{{ if .System }}{{ .System }}
+
+{{ end }}# Tools
+
+You may call one or more functions to assist with the user query.
+
+You are provided with function signatures within <tools></tools> XML tags:
+<tools>
+{{- range .Tools }}
+{"type": "function", "function": {{ .Function }}}
+{{- end }}
+</tools>
+
+For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
+<tool_call>
+{"name": <function-name>, "arguments": <args-json-object>}
+</tool_call><|im_end|>
+{{ else if .System }}<|im_start|>system
+{{ .System }}<|im_end|>
+{{ end }}
+{{- range $i, $_ := .Messages }}
+{{- $last := eq (len (slice $.Messages $i)) 1 -}}
+{{- if eq .Role "user" }}<|im_start|>user
+{{ .Content }}<|im_end|>
+{{ else if eq .Role "assistant" }}<|im_start|>assistant
+<think>
+{{ .Thinking }}
+</think>
+
+{{ .Content }}
+{{- if .ToolCalls }}
+{{- range .ToolCalls }}
+<tool_call>
+{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}}
+</tool_call>
+{{- end }}
+{{- end }}
+{{- if not $last }}<|im_end|>
+{{ end }}
+{{- else if eq .Role "tool" }}<|im_start|>user
+<tool_response>
+{{ .Content }}
+</tool_response><|im_end|>
+{{ end }}
+{{- if and (ne .Role "assistant") $last }}<|im_start|>assistant
+{{ if and $.IsThinkSet $.Think -}}
+<think>
+{{ else -}}
+<think>
+
+</think>
+
+{{ end -}}
+{{ end }}
+{{- end }}"""
+
+PARAMETER repeat_penalty 1
+PARAMETER stop "<|im_start|>"
+PARAMETER stop "<|im_end|>"
+PARAMETER temperature 0.9
+PARAMETER top_p 0.9
+PARAMETER num_ctx 8192

minimind-3-moe/special_tokens_map.json

@@ -0,0 +1,52 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>",
+    "<|audio_start|>",
+    "<|audio_end|>",
+    "<|audio_pad|>",
+    "<tts_pad>",
+    "<tts_text_bos>",
+    "<tts_text_eod>",
+    "<tts_text_bos_single>"
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

minimind-3-moe/tokenizer_config.json

@@ -0,0 +1,335 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<|audio_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<|audio_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<|audio_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<tts_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<tts_text_bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "19": {
+      "content": "<tts_text_eod>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "20": {
+      "content": "<tts_text_bos_single>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "21": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "22": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "23": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "24": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "25": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "26": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "<|buffer1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "<|buffer2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "<|buffer3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "<|buffer4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31": {
+      "content": "<|buffer5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "<|buffer6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "<|buffer7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "34": {
+      "content": "<|buffer8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "<|buffer9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>",
+    "<|audio_start|>",
+    "<|audio_end|>",
+    "<|audio_pad|>",
+    "<tts_pad>",
+    "<tts_text_bos>",
+    "<tts_text_eod>",
+    "<tts_text_bos_single>"
+  ],
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "image_token": "<|image_pad|>",
+  "legacy": true,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<|endoftext|>",
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

minimind-3/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if true %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if open_thinking is defined and open_thinking is true %}
+        {{- '<think>\n' }}
+    {%- else %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

minimind-3/config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "float16",
+  "head_dim": 96,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 2432,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 6400
+}

minimind-3/generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.57.6"
+}

minimind-3/minimind.modelfile

@@ -0,0 +1,68 @@
+FROM ./minimind-64M-3-F16.gguf
+
+SYSTEM "你的名字叫MiniMind，你是一个乐于助人、知识渊博的AI助手。请用完整且友好的方式回答用户问题，当被问到名字时请回答MiniMind。"
+
+
+TEMPLATE """{{- if .Tools }}<|im_start|>system
+{{ if .System }}{{ .System }}
+
+{{ end }}# Tools
+
+You may call one or more functions to assist with the user query.
+
+You are provided with function signatures within <tools></tools> XML tags:
+<tools>
+{{- range .Tools }}
+{"type": "function", "function": {{ .Function }}}
+{{- end }}
+</tools>
+
+For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
+<tool_call>
+{"name": <function-name>, "arguments": <args-json-object>}
+</tool_call><|im_end|>
+{{ else if .System }}<|im_start|>system
+{{ .System }}<|im_end|>
+{{ end }}
+{{- range $i, $_ := .Messages }}
+{{- $last := eq (len (slice $.Messages $i)) 1 -}}
+{{- if eq .Role "user" }}<|im_start|>user
+{{ .Content }}<|im_end|>
+{{ else if eq .Role "assistant" }}<|im_start|>assistant
+<think>
+{{ .Thinking }}
+</think>
+
+{{ .Content }}
+{{- if .ToolCalls }}
+{{- range .ToolCalls }}
+<tool_call>
+{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}}
+</tool_call>
+{{- end }}
+{{- end }}
+{{- if not $last }}<|im_end|>
+{{ end }}
+{{- else if eq .Role "tool" }}<|im_start|>user
+<tool_response>
+{{ .Content }}
+</tool_response><|im_end|>
+{{ end }}
+{{- if and (ne .Role "assistant") $last }}<|im_start|>assistant
+{{ if and $.IsThinkSet $.Think -}}
+<think>
+{{ else -}}
+<think>
+
+</think>
+
+{{ end -}}
+{{ end }}
+{{- end }}"""
+
+PARAMETER repeat_penalty 1
+PARAMETER stop "<|im_start|>"
+PARAMETER stop "<|im_end|>"
+PARAMETER temperature 0.9
+PARAMETER top_p 0.9
+PARAMETER num_ctx 8192

minimind-3/special_tokens_map.json

@@ -0,0 +1,52 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>",
+    "<|audio_start|>",
+    "<|audio_end|>",
+    "<|audio_pad|>",
+    "<tts_pad>",
+    "<tts_text_bos>",
+    "<tts_text_eod>",
+    "<tts_text_bos_single>"
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

minimind-3/tokenizer_config.json

@@ -0,0 +1,335 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<|audio_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<|audio_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<|audio_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<tts_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<tts_text_bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "19": {
+      "content": "<tts_text_eod>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "20": {
+      "content": "<tts_text_bos_single>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "21": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "22": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "23": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "24": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "25": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "26": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "<|buffer1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "<|buffer2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "<|buffer3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "<|buffer4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31": {
+      "content": "<|buffer5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "<|buffer6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "<|buffer7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "34": {
+      "content": "<|buffer8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "<|buffer9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>",
+    "<|audio_start|>",
+    "<|audio_end|>",
+    "<|audio_pad|>",
+    "<tts_pad>",
+    "<tts_text_bos>",
+    "<tts_text_eod>",
+    "<tts_text_bos_single>"
+  ],
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "image_token": "<|image_pad|>",
+  "legacy": true,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<|endoftext|>",
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}