ArtusDev commited on
Commit
81a1f57
·
verified ·
1 Parent(s): 981dc8d

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,455 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - Qwen/Qwen3-32B
4
+ tags:
5
+ - text-generation-inference
6
+ - transformers
7
+ - qwen3
8
+ - ui-generation
9
+ - tailwind-css
10
+ - html
11
+ - reasoning
12
+ - step-by-step-generation
13
+ - hybrid-thinking
14
+ - tool-calling
15
+ license: apache-2.0
16
+ language:
17
+ - en
18
+ ---
19
+
20
+
21
+
22
+ # UIGEN-X-32B-0727 Reasoning Only UI Generation Model
23
+
24
+
25
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/-C7uzKoh8rxQKj_x1QpbB.png)
26
+
27
+ > Tesslate's Reasoning Only UI generation model built on Qwen3-32B architecture. Trained to systematically plan, architect, and implement complete user interfaces across modern development stacks.
28
+
29
+
30
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/WxPvegx82dFLiWpgLLfIS.png)
31
+
32
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/sd4TlO0yZ7-xM7lWwDShi.png)
33
+
34
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/YhS0eaOuAJx-JjyiFMO0-.png)
35
+
36
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/VkkkoSeCzqlFzMxIPDQfC.png)
37
+
38
+ **Live Examples**: [https://uigenoutput.tesslate.com](https://uigenoutput.tesslate.com)
39
+ **Discord Community**: [https://discord.gg/EcCpcTv93U](https://discord.gg/EcCpcTv93U)
40
+ **Website**: [https://tesslate.com](https://tesslate.com)
41
+
42
+ ---
43
+
44
+ ## Model Architecture
45
+
46
+ UIGEN-X-32B-0727 implements **Reasoning Only** from the Qwen3 family - combining systematic planning with direct implementation. The model follows a structured thinking process:
47
+
48
+ 1. **Problem Analysis** — Understanding requirements and constraints
49
+ 2. **Architecture Planning** — Component structure and technology decisions
50
+ 3. **Design System Definition** — Color schemes, typography, and styling approach
51
+ 4. **Implementation Strategy** — Step-by-step code generation with reasoning
52
+
53
+ This hybrid approach enables both thoughtful planning and efficient code generation, making it suitable for complex UI development tasks.
54
+
55
+ ---
56
+
57
+ ## Complete Technology Coverage
58
+
59
+ UIGEN-X-32B-0727 supports **26 major categories** spanning **frameworks and libraries** across **7 platforms**:
60
+
61
+ ### Web Frameworks
62
+ - **React**: Next.js, Remix, Gatsby, Create React App, Vite
63
+ - **Vue**: Nuxt.js, Quasar, Gridsome
64
+ - **Angular**: Angular CLI, Ionic Angular
65
+ - **Svelte**: SvelteKit, Astro
66
+ - **Modern**: Solid.js, Qwik, Alpine.js
67
+ - **Static**: Astro, 11ty, Jekyll, Hugo
68
+
69
+ ### Styling Systems
70
+ - **Utility-First**: Tailwind CSS, UnoCSS, Windi CSS
71
+ - **CSS-in-JS**: Styled Components, Emotion, Stitches
72
+ - **Component Systems**: Material-UI, Chakra UI, Mantine
73
+ - **Traditional**: Bootstrap, Bulma, Foundation
74
+ - **Design Systems**: Carbon Design, IBM Design Language
75
+ - **Framework-Specific**: Angular Material, Vuetify, Quasar
76
+
77
+ ### UI Component Libraries
78
+ - **React**: shadcn/ui, Material-UI, Ant Design, Chakra UI, Mantine, PrimeReact, Headless UI, NextUI, DaisyUI
79
+ - **Vue**: Vuetify, PrimeVue, Quasar, Element Plus, Naive UI
80
+ - **Angular**: Angular Material, PrimeNG, ng-bootstrap, Clarity Design
81
+ - **Svelte**: Svelte Material UI, Carbon Components Svelte
82
+ - **Headless**: Radix UI, Reach UI, Ariakit, React Aria
83
+
84
+ ### State Management
85
+ - **React**: Redux Toolkit, Zustand, Jotai, Valtio, Context API
86
+ - **Vue**: Pinia, Vuex, Composables
87
+ - **Angular**: NgRx, Akita, Services
88
+ - **Universal**: MobX, XState, Recoil
89
+
90
+ ### Animation Libraries
91
+ - **React**: Framer Motion, React Spring, React Transition Group
92
+ - **Vue**: Vue Transition, Vueuse Motion
93
+ - **Universal**: GSAP, Lottie, CSS Animations, Web Animations API
94
+ - **Mobile**: React Native Reanimated, Expo Animations
95
+
96
+ ### Icon Systems
97
+ Lucide, Heroicons, Material Icons, Font Awesome, Ant Design Icons, Bootstrap Icons, Ionicons, Tabler Icons, Feather, Phosphor, React Icons, Vue Icons
98
+
99
+ ---
100
+
101
+ ## Platform Support
102
+
103
+ ### Web Development
104
+ Complete coverage of modern web development from simple HTML/CSS to complex enterprise applications.
105
+
106
+ ### Mobile Development
107
+ - **React Native**: Expo, CLI, with navigation and state management
108
+ - **Flutter**: Cross-platform mobile with Material and Cupertino designs
109
+ - **Ionic**: Angular, React, and Vue-based hybrid applications
110
+
111
+ ### Desktop Applications
112
+ - **Electron**: Cross-platform desktop apps (Slack, VSCode-style)
113
+ - **Tauri**: Rust-based lightweight desktop applications
114
+ - **Flutter Desktop**: Native desktop performance
115
+
116
+ ### Python Applications
117
+ - **Web UI**: Streamlit, Gradio, Flask, FastAPI
118
+ - **Desktop GUI**: Tkinter, PyQt5/6, Kivy, wxPython, Dear PyGui
119
+
120
+ ### Development Tools
121
+ Build tools, bundlers, testing frameworks, and development environments.
122
+
123
+ ---
124
+
125
+ ## Programming Language Support
126
+
127
+ **26 Languages and Approaches**:
128
+ JavaScript, TypeScript, Python, Dart, HTML5, CSS3, SCSS, SASS, Less, PostCSS, CSS Modules, Styled Components, JSX, TSX, Vue SFC, Svelte Components, Angular Templates, Tailwind, PHP
129
+
130
+ ---
131
+
132
+ ## Visual Style System
133
+
134
+ UIGEN-X-32B-0727 includes **21 distinct visual style categories** that can be applied to any framework:
135
+
136
+ ### Modern Design Styles
137
+ - **Glassmorphism**: Frosted glass effects with blur and transparency
138
+ - **Neumorphism**: Soft, extruded design elements
139
+ - **Material Design**: Google's design system principles
140
+ - **Fluent Design**: Microsoft's design language
141
+
142
+ ### Traditional & Classic
143
+ - **Skeuomorphism**: Real-world object representations
144
+ - **Swiss Design**: Clean typography and grid systems
145
+ - **Bauhaus**: Functional, geometric design principles
146
+
147
+ ### Contemporary Trends
148
+ - **Brutalism**: Bold, raw, unconventional layouts
149
+ - **Anti-Design**: Intentionally imperfect, organic aesthetics
150
+ - **Minimalism**: Essential elements only, generous whitespace
151
+
152
+ ### Thematic Styles
153
+ - **Cyberpunk**: Neon colors, glitch effects, futuristic elements
154
+ - **Dark Mode**: High contrast, reduced eye strain
155
+ - **Retro-Futurism**: 80s/90s inspired futuristic design
156
+ - **Geocities/90s Web**: Nostalgic early web aesthetics
157
+
158
+ ### Experimental
159
+ - **Maximalism**: Rich, layered, abundant visual elements
160
+ - **Madness/Experimental**: Unconventional, boundary-pushing designs
161
+ - **Abstract Shapes**: Geometric, non-representational elements
162
+
163
+ ---
164
+
165
+ ## Prompt Structure Guide
166
+
167
+ ### Basic Structure
168
+ To achieve the best results, use this prompting structure below:
169
+ ```
170
+ [Action] + [UI Type] + [Framework Stack] + [Specific Features] + [Optional: Style]
171
+ ```
172
+
173
+ ### Examples
174
+
175
+ **Simple Component**:
176
+ ```
177
+ Create a navigation bar using React + Tailwind CSS with logo, menu items, and mobile hamburger menu
178
+ ```
179
+
180
+ **Complex Application**:
181
+ ```
182
+ Build a complete e-commerce dashboard using Next.js + TypeScript + Tailwind CSS + shadcn/ui with:
183
+ - Product management (CRUD operations)
184
+ - Order tracking with status updates
185
+ - Customer analytics with charts
186
+ - Responsive design for mobile/desktop
187
+ - Dark mode toggle
188
+ Style: Use a clean, modern glassmorphism aesthetic
189
+ ```
190
+
191
+ **Framework-Specific**:
192
+ ```
193
+ Design an Angular Material admin panel with:
194
+ - Sidenav with expandable menu items
195
+ - Data tables with sorting and filtering
196
+ - Form validation with reactive forms
197
+ - Charts using ng2-charts
198
+ - SCSS custom theming
199
+ ```
200
+
201
+ ### Advanced Prompt Techniques
202
+
203
+ **Multi-Page Applications**:
204
+ ```
205
+ Create a complete SaaS application using Vue 3 + Nuxt 3 + Tailwind CSS + Pinia:
206
+
207
+ Pages needed:
208
+ 1. Landing page with hero, features, pricing
209
+ 2. Dashboard with metrics and quick actions
210
+ 3. Settings page with user preferences
211
+ 4. Billing page with subscription management
212
+
213
+ Include: Navigation between pages, state management, responsive design
214
+ Style: Professional, modern with subtle animations
215
+ ```
216
+
217
+ **Style Mixing**:
218
+ ```
219
+ Build a portfolio website using Svelte + SvelteKit + Tailwind CSS combining:
220
+ - Minimalist layout principles
221
+ - Cyberpunk color scheme (neon accents)
222
+ - Smooth animations for page transitions
223
+ - Typography-driven content sections
224
+ ```
225
+
226
+ ---
227
+
228
+ ## Tool Calling & Agentic Usage
229
+
230
+ UIGEN-X-32B-0727 supports **function calling** for dynamic asset integration and enhanced development workflows.
231
+
232
+ ### Image Integration with Unsplash
233
+
234
+ Register tools for dynamic image fetching:
235
+
236
+ ```json
237
+ {
238
+ "type": "function",
239
+ "function": {
240
+ "name": "fetch_unsplash_image",
241
+ "description": "Fetch high-quality images from Unsplash for UI mockups",
242
+ "parameters": {
243
+ "type": "object",
244
+ "properties": {
245
+ "query": {
246
+ "type": "string",
247
+ "description": "Search term for image (e.g., 'modern office', 'technology', 'nature')"
248
+ },
249
+ "orientation": {
250
+ "type": "string",
251
+ "enum": ["landscape", "portrait", "squarish"],
252
+ "description": "Image orientation"
253
+ },
254
+ "size": {
255
+ "type": "string",
256
+ "enum": ["small", "regular", "full"],
257
+ "description": "Image size"
258
+ }
259
+ },
260
+ "required": ["query"]
261
+ }
262
+ }
263
+ }
264
+ ```
265
+
266
+ ### Content Generation Tools
267
+
268
+ ```json
269
+ {
270
+ "type": "function",
271
+ "function": {
272
+ "name": "generate_content",
273
+ "description": "Generate realistic content for UI components",
274
+ "parameters": {
275
+ "type": "object",
276
+ "properties": {
277
+ "type": {
278
+ "type": "string",
279
+ "enum": ["user_profiles", "product_data", "blog_posts", "testimonials"],
280
+ "description": "Type of content to generate"
281
+ },
282
+ "count": {
283
+ "type": "integer",
284
+ "description": "Number of items to generate"
285
+ },
286
+ "theme": {
287
+ "type": "string",
288
+ "description": "Content theme or industry"
289
+ }
290
+ },
291
+ "required": ["type", "count"]
292
+ }
293
+ }
294
+ }
295
+ ```
296
+
297
+ ### Complete Agentic Workflow Example
298
+
299
+ ```python
300
+ # 1. Plan the application
301
+ response = model.chat([
302
+ {"role": "user", "content": "Plan a complete travel booking website using React + Next.js + Tailwind CSS + shadcn/ui"}
303
+ ], tools=[fetch_unsplash_image, generate_content])
304
+
305
+ # 2. The model will reason through the requirements and call tools:
306
+ # - fetch_unsplash_image(query="travel destinations", orientation="landscape")
307
+ # - generate_content(type="destinations", count=10, theme="popular travel")
308
+ # - fetch_unsplash_image(query="hotel rooms", orientation="landscape")
309
+
310
+ # 3. Generate complete implementation with real assets
311
+ final_response = model.chat([
312
+ {"role": "user", "content": "Now implement the complete website with the fetched images and content"}
313
+ ])
314
+ ```
315
+
316
+ ### Tool Integration Patterns
317
+
318
+ **Dynamic Asset Loading**:
319
+ - Fetch relevant images during UI generation
320
+ - Generate realistic content for components
321
+ - Create cohesive color palettes from images
322
+ - Optimize assets for web performance
323
+
324
+ **Multi-Step Development**:
325
+ - Plan application architecture
326
+ - Generate individual components
327
+ - Integrate components into pages
328
+ - Apply consistent styling and theming
329
+ - Test responsive behavior
330
+
331
+ **Content-Aware Design**:
332
+ - Adapt layouts based on content types
333
+ - Optimize typography for readability
334
+ - Create responsive image galleries
335
+ - Generate accessible alt text
336
+
337
+ ---
338
+
339
+ ## Inference Configuration
340
+
341
+ ### Optimal Parameters
342
+ ```python
343
+ {
344
+ "temperature": 0.6, # Balanced creativity and consistency (make it lower if quantized!!!!)
345
+ "top_p": 0.9, # Nucleus sampling for quality
346
+ "top_k": 40, # Vocabulary restriction
347
+ "max_tokens": 25000, # Full component generation
348
+ "repetition_penalty": 1.1, # Avoid repetitive patterns
349
+ }
350
+ ```
351
+
352
+ ---
353
+
354
+ ## Use Cases & Applications
355
+
356
+ ### Rapid Prototyping
357
+ - Quick mockups for client presentations
358
+ - A/B testing different design approaches
359
+ - Concept validation with interactive prototypes
360
+
361
+ ### Production Development
362
+ - Component library creation
363
+ - Design system implementation
364
+ - Template and boilerplate generation
365
+
366
+ ### Educational & Learning
367
+ - Teaching modern web development
368
+ - Framework comparison and evaluation
369
+ - Best practices demonstration
370
+
371
+ ### Enterprise Solutions
372
+ - Dashboard and admin panel generation
373
+ - Internal tool development
374
+ - Legacy system modernization
375
+
376
+ ---
377
+
378
+ ## Technical Requirements
379
+
380
+ ### Hardware
381
+ - **GPU**: 8GB+ VRAM recommended (RTX 3080/4070 or equivalent)
382
+ - **RAM**: 16GB system memory minimum
383
+ - **Storage**: 20GB for model weights and cache
384
+
385
+ ### Software
386
+ - **Python**: 3.8+ with transformers, torch, unsloth
387
+ - **Node.js**: For running generated JavaScript/TypeScript code
388
+ - **Browser**: Modern browser for testing generated UIs
389
+
390
+ ### Integration
391
+ - Compatible with HuggingFace transformers
392
+ - Supports GGML/GGUF quantization
393
+ - Works with text-generation-webui
394
+ - API-ready for production deployment
395
+
396
+ ---
397
+
398
+ ## Limitations & Considerations
399
+
400
+ - **Token Usage**: Reasoning process increases token consumption
401
+ - **Complex Logic**: Focuses on UI structure rather than business logic
402
+ - **Real-time Features**: Generated code requires backend integration
403
+ - **Testing**: Output may need manual testing and refinement
404
+ - **Accessibility**: While ARIA-aware, manual a11y testing recommended
405
+
406
+ ---
407
+
408
+ ## Community & Support
409
+
410
+ **Discord**: [https://discord.gg/EcCpcTv93U](https://discord.gg/EcCpcTv93U)
411
+ **Website**: [https://tesslate.com](https://tesslate.com)
412
+ **Examples**: [https://uigenoutput.tesslate.com](https://uigenoutput.tesslate.com)
413
+
414
+ Join our community to share creations, get help, and contribute to the ecosystem.
415
+
416
+ ---
417
+
418
+ ## Citation
419
+
420
+ ```bibtex
421
+ @misc{tesslate_uigen_x_2025,
422
+ title={UIGEN-X-32B-0727: Reasoning Only UI Generation with Qwen3},
423
+ author={Tesslate Team},
424
+ year={2025},
425
+ publisher={Tesslate},
426
+ url={https://huggingface.co/tesslate/UIGEN-X-32B-0727}
427
+ }
428
+ ```
429
+
430
+ ---
431
+
432
+
433
+
434
+
435
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/ZhW150gEhg0lkXoSjkiiU.png" alt="UI Screenshot 1" width="400">
436
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/NdxVu6Zv6beigOYjbKCl1.png" alt="UI Screenshot 2" width="400">
437
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/RX8po_paCIxrrcTvZ3xfA.png" alt="UI Screenshot 3" width="400">
438
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/DBssA7zan39uxy9HQOo5N.png" alt="UI Screenshot 4" width="400">
439
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/ttljEdBcYh1tkmyrCUQku.png" alt="UI Screenshot 5" width="400">
440
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/duLxNQAuqv1FPVlsmQsWr.png" alt="UI Screenshot 6" width="400">
441
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/ja2nhpNrvucf_zwCARXxa.png" alt="UI Screenshot 7" width="400">
442
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/ca0f_8U9HQdaSVAejpzPn.png" alt="UI Screenshot 8" width="400">
443
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/gzZF2CiOjyEbPAPRYSV-N.png" alt="UI Screenshot 9" width="400">
444
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/y8wB78PffUUoVLzw3al2R.png" alt="UI Screenshot 10" width="400">
445
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/M12dGr0xArAIF7gANSC5T.png" alt="UI Screenshot 11" width="400">
446
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/t7r7cYlUwmI1QQf3fxO7o.png" alt="UI Screenshot 12" width="400">
447
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/-uCIIJqTrrY9xkJHKCEqC.png" alt="UI Screenshot 13" width="400">
448
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/eqT3IUWaPtoNQb-IWQNuy.png" alt="UI Screenshot 14" width="400">
449
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/RhbGMcxCNlMIXRLEacUGi.png" alt="UI Screenshot 15" width="400">
450
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/FWhs43BKkXku12MwiW0v9.png" alt="UI Screenshot 16" width="400">
451
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/67db34a5e7f1d129b294e2af/ILHx-xcn18cyDLX5a63xV.png" alt="UIGEN-X UI Screenshot 1" width="400">
452
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/67db34a5e7f1d129b294e2af/A-zKo1J4HYftjiOjq_GB4.png" alt="UIGEN-X UI Screenshot 2" width="400">
453
+
454
+
455
+ *Built with Reasoning Only capabilities from Qwen3, UIGEN-X-32B-0727 represents a comprehensive approach to AI-driven UI development across the entire modern web development ecosystem.*
added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
chat_template.jinja ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# 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>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\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" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
27
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
28
+ {%- elif message.role == "assistant" %}
29
+ {%- set content = message.content %}
30
+ {%- set reasoning_content = '' %}
31
+ {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
32
+ {%- set reasoning_content = message.reasoning_content %}
33
+ {%- else %}
34
+ {%- if '</think>' in message.content %}
35
+ {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
36
+ {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
37
+ {%- endif %}
38
+ {%- endif %}
39
+ {%- if loop.index0 > ns.last_query_index %}
40
+ {%- if loop.last or (not loop.last and reasoning_content) %}
41
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
42
+ {%- else %}
43
+ {{- '<|im_start|>' + message.role + '\n' + content }}
44
+ {%- endif %}
45
+ {%- else %}
46
+ {{- '<|im_start|>' + message.role + '\n' + content }}
47
+ {%- endif %}
48
+ {%- if message.tool_calls %}
49
+ {%- for tool_call in message.tool_calls %}
50
+ {%- if (loop.first and content) or (not loop.first) %}
51
+ {{- '\n' }}
52
+ {%- endif %}
53
+ {%- if tool_call.function %}
54
+ {%- set tool_call = tool_call.function %}
55
+ {%- endif %}
56
+ {{- '<tool_call>\n{"name": "' }}
57
+ {{- tool_call.name }}
58
+ {{- '", "arguments": ' }}
59
+ {%- if tool_call.arguments is string %}
60
+ {{- tool_call.arguments }}
61
+ {%- else %}
62
+ {{- tool_call.arguments | tojson }}
63
+ {%- endif %}
64
+ {{- '}\n</tool_call>' }}
65
+ {%- endfor %}
66
+ {%- endif %}
67
+ {{- '<|im_end|>\n' }}
68
+ {%- elif message.role == "tool" %}
69
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
70
+ {{- '<|im_start|>user' }}
71
+ {%- endif %}
72
+ {{- '\n<tool_response>\n' }}
73
+ {{- message.content }}
74
+ {{- '\n</tool_response>' }}
75
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
76
+ {{- '<|im_end|>\n' }}
77
+ {%- endif %}
78
+ {%- endif %}
79
+ {%- endfor %}
80
+ {%- if add_generation_prompt %}
81
+ {{- '<|im_start|>assistant\n' }}
82
+ {%- if enable_thinking is defined and enable_thinking is false %}
83
+ {{- '<think>\n\n</think>\n\n' }}
84
+ {%- else %}
85
+ {{- '<think>\n\n' }}
86
+ {%- endif %}
87
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "eos_token_id": 151645,
8
+ "head_dim": 128,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 25600,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention",
65
+ "full_attention",
66
+ "full_attention",
67
+ "full_attention",
68
+ "full_attention",
69
+ "full_attention",
70
+ "full_attention",
71
+ "full_attention",
72
+ "full_attention",
73
+ "full_attention",
74
+ "full_attention",
75
+ "full_attention",
76
+ "full_attention",
77
+ "full_attention"
78
+ ],
79
+ "max_position_embeddings": 40960,
80
+ "max_window_layers": 64,
81
+ "model_type": "qwen3",
82
+ "num_attention_heads": 64,
83
+ "num_hidden_layers": 64,
84
+ "num_key_value_heads": 8,
85
+ "rms_norm_eps": 1e-06,
86
+ "rope_scaling": null,
87
+ "rope_theta": 1000000,
88
+ "sliding_window": null,
89
+ "tie_word_embeddings": false,
90
+ "torch_dtype": "bfloat16",
91
+ "transformers_version": "4.53.2",
92
+ "use_cache": false,
93
+ "use_sliding_window": false,
94
+ "vocab_size": 151936,
95
+ "quantization_config": {
96
+ "quant_method": "exl3",
97
+ "version": "0.0.5",
98
+ "bits": 5.0,
99
+ "head_bits": 6,
100
+ "calibration": {
101
+ "rows": 100,
102
+ "cols": 2048
103
+ },
104
+ "out_scales": "auto"
105
+ }
106
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.6,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.53.2"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46543383e560fcdd06ff348d076d9740fcd32362bc48faffe727a52d58b3977c
3
+ size 8571475832
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bd159670b732b3f4d4bacae8ec46409670772cc7fbd9ab4d9b94afc3430c2fb
3
+ size 8540789736
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6cb3fd874977f9106d74349199d8e759158954a9caa2ed0f7b353db4b4e6f73
3
+ size 4549125568
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
quantization_config.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
tokenizer_config.json ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 131072,
235
+ "pad_token": "<|endoftext|>",
236
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null
239
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff