stelterlab commited on
Commit
af524a5
·
verified ·
1 Parent(s): 1f18aec

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 +1,458 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - Tesslate/UIGEN-X-32B-0727
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
+ AWQ quantization: done by stelterlab in INT4 GEMM with AutoAWQ by casper-hansen (https://github.com/casper-hansen/AutoAWQ/)
21
+
22
+ Original Weights by Tesslate AI. Original Model Card follows:
23
+
24
+
25
+ # UIGEN-X-32B-0727 Reasoning Only UI Generation Model
26
+
27
+
28
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/-C7uzKoh8rxQKj_x1QpbB.png)
29
+
30
+ > 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.
31
+
32
+
33
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/WxPvegx82dFLiWpgLLfIS.png)
34
+
35
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/sd4TlO0yZ7-xM7lWwDShi.png)
36
+
37
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/YhS0eaOuAJx-JjyiFMO0-.png)
38
+
39
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/VkkkoSeCzqlFzMxIPDQfC.png)
40
+
41
+ **Live Examples**: [https://uigenoutput.tesslate.com](https://uigenoutput.tesslate.com)
42
+ **Discord Community**: [https://discord.gg/EcCpcTv93U](https://discord.gg/EcCpcTv93U)
43
+ **Website**: [https://tesslate.com](https://tesslate.com)
44
+
45
+ ---
46
+
47
+ ## Model Architecture
48
+
49
+ UIGEN-X-32B-0727 implements **Reasoning Only** from the Qwen3 family - combining systematic planning with direct implementation. The model follows a structured thinking process:
50
+
51
+ 1. **Problem Analysis** — Understanding requirements and constraints
52
+ 2. **Architecture Planning** — Component structure and technology decisions
53
+ 3. **Design System Definition** — Color schemes, typography, and styling approach
54
+ 4. **Implementation Strategy** — Step-by-step code generation with reasoning
55
+
56
+ This hybrid approach enables both thoughtful planning and efficient code generation, making it suitable for complex UI development tasks.
57
+
58
+ ---
59
+
60
+ ## Complete Technology Coverage
61
+
62
+ UIGEN-X-32B-0727 supports **26 major categories** spanning **frameworks and libraries** across **7 platforms**:
63
+
64
+ ### Web Frameworks
65
+ - **React**: Next.js, Remix, Gatsby, Create React App, Vite
66
+ - **Vue**: Nuxt.js, Quasar, Gridsome
67
+ - **Angular**: Angular CLI, Ionic Angular
68
+ - **Svelte**: SvelteKit, Astro
69
+ - **Modern**: Solid.js, Qwik, Alpine.js
70
+ - **Static**: Astro, 11ty, Jekyll, Hugo
71
+
72
+ ### Styling Systems
73
+ - **Utility-First**: Tailwind CSS, UnoCSS, Windi CSS
74
+ - **CSS-in-JS**: Styled Components, Emotion, Stitches
75
+ - **Component Systems**: Material-UI, Chakra UI, Mantine
76
+ - **Traditional**: Bootstrap, Bulma, Foundation
77
+ - **Design Systems**: Carbon Design, IBM Design Language
78
+ - **Framework-Specific**: Angular Material, Vuetify, Quasar
79
+
80
+ ### UI Component Libraries
81
+ - **React**: shadcn/ui, Material-UI, Ant Design, Chakra UI, Mantine, PrimeReact, Headless UI, NextUI, DaisyUI
82
+ - **Vue**: Vuetify, PrimeVue, Quasar, Element Plus, Naive UI
83
+ - **Angular**: Angular Material, PrimeNG, ng-bootstrap, Clarity Design
84
+ - **Svelte**: Svelte Material UI, Carbon Components Svelte
85
+ - **Headless**: Radix UI, Reach UI, Ariakit, React Aria
86
+
87
+ ### State Management
88
+ - **React**: Redux Toolkit, Zustand, Jotai, Valtio, Context API
89
+ - **Vue**: Pinia, Vuex, Composables
90
+ - **Angular**: NgRx, Akita, Services
91
+ - **Universal**: MobX, XState, Recoil
92
+
93
+ ### Animation Libraries
94
+ - **React**: Framer Motion, React Spring, React Transition Group
95
+ - **Vue**: Vue Transition, Vueuse Motion
96
+ - **Universal**: GSAP, Lottie, CSS Animations, Web Animations API
97
+ - **Mobile**: React Native Reanimated, Expo Animations
98
+
99
+ ### Icon Systems
100
+ Lucide, Heroicons, Material Icons, Font Awesome, Ant Design Icons, Bootstrap Icons, Ionicons, Tabler Icons, Feather, Phosphor, React Icons, Vue Icons
101
+
102
+ ---
103
+
104
+ ## Platform Support
105
+
106
+ ### Web Development
107
+ Complete coverage of modern web development from simple HTML/CSS to complex enterprise applications.
108
+
109
+ ### Mobile Development
110
+ - **React Native**: Expo, CLI, with navigation and state management
111
+ - **Flutter**: Cross-platform mobile with Material and Cupertino designs
112
+ - **Ionic**: Angular, React, and Vue-based hybrid applications
113
+
114
+ ### Desktop Applications
115
+ - **Electron**: Cross-platform desktop apps (Slack, VSCode-style)
116
+ - **Tauri**: Rust-based lightweight desktop applications
117
+ - **Flutter Desktop**: Native desktop performance
118
+
119
+ ### Python Applications
120
+ - **Web UI**: Streamlit, Gradio, Flask, FastAPI
121
+ - **Desktop GUI**: Tkinter, PyQt5/6, Kivy, wxPython, Dear PyGui
122
+
123
+ ### Development Tools
124
+ Build tools, bundlers, testing frameworks, and development environments.
125
+
126
+ ---
127
+
128
+ ## Programming Language Support
129
+
130
+ **26 Languages and Approaches**:
131
+ JavaScript, TypeScript, Python, Dart, HTML5, CSS3, SCSS, SASS, Less, PostCSS, CSS Modules, Styled Components, JSX, TSX, Vue SFC, Svelte Components, Angular Templates, Tailwind, PHP
132
+
133
+ ---
134
+
135
+ ## Visual Style System
136
+
137
+ UIGEN-X-32B-0727 includes **21 distinct visual style categories** that can be applied to any framework:
138
+
139
+ ### Modern Design Styles
140
+ - **Glassmorphism**: Frosted glass effects with blur and transparency
141
+ - **Neumorphism**: Soft, extruded design elements
142
+ - **Material Design**: Google's design system principles
143
+ - **Fluent Design**: Microsoft's design language
144
+
145
+ ### Traditional & Classic
146
+ - **Skeuomorphism**: Real-world object representations
147
+ - **Swiss Design**: Clean typography and grid systems
148
+ - **Bauhaus**: Functional, geometric design principles
149
+
150
+ ### Contemporary Trends
151
+ - **Brutalism**: Bold, raw, unconventional layouts
152
+ - **Anti-Design**: Intentionally imperfect, organic aesthetics
153
+ - **Minimalism**: Essential elements only, generous whitespace
154
+
155
+ ### Thematic Styles
156
+ - **Cyberpunk**: Neon colors, glitch effects, futuristic elements
157
+ - **Dark Mode**: High contrast, reduced eye strain
158
+ - **Retro-Futurism**: 80s/90s inspired futuristic design
159
+ - **Geocities/90s Web**: Nostalgic early web aesthetics
160
+
161
+ ### Experimental
162
+ - **Maximalism**: Rich, layered, abundant visual elements
163
+ - **Madness/Experimental**: Unconventional, boundary-pushing designs
164
+ - **Abstract Shapes**: Geometric, non-representational elements
165
+
166
+ ---
167
+
168
+ ## Prompt Structure Guide
169
+
170
+ ### Basic Structure
171
+ To achieve the best results, use this prompting structure below:
172
+ ```
173
+ [Action] + [UI Type] + [Framework Stack] + [Specific Features] + [Optional: Style]
174
+ ```
175
+
176
+ ### Examples
177
+
178
+ **Simple Component**:
179
+ ```
180
+ Create a navigation bar using React + Tailwind CSS with logo, menu items, and mobile hamburger menu
181
+ ```
182
+
183
+ **Complex Application**:
184
+ ```
185
+ Build a complete e-commerce dashboard using Next.js + TypeScript + Tailwind CSS + shadcn/ui with:
186
+ - Product management (CRUD operations)
187
+ - Order tracking with status updates
188
+ - Customer analytics with charts
189
+ - Responsive design for mobile/desktop
190
+ - Dark mode toggle
191
+ Style: Use a clean, modern glassmorphism aesthetic
192
+ ```
193
+
194
+ **Framework-Specific**:
195
+ ```
196
+ Design an Angular Material admin panel with:
197
+ - Sidenav with expandable menu items
198
+ - Data tables with sorting and filtering
199
+ - Form validation with reactive forms
200
+ - Charts using ng2-charts
201
+ - SCSS custom theming
202
+ ```
203
+
204
+ ### Advanced Prompt Techniques
205
+
206
+ **Multi-Page Applications**:
207
+ ```
208
+ Create a complete SaaS application using Vue 3 + Nuxt 3 + Tailwind CSS + Pinia:
209
+
210
+ Pages needed:
211
+ 1. Landing page with hero, features, pricing
212
+ 2. Dashboard with metrics and quick actions
213
+ 3. Settings page with user preferences
214
+ 4. Billing page with subscription management
215
+
216
+ Include: Navigation between pages, state management, responsive design
217
+ Style: Professional, modern with subtle animations
218
+ ```
219
+
220
+ **Style Mixing**:
221
+ ```
222
+ Build a portfolio website using Svelte + SvelteKit + Tailwind CSS combining:
223
+ - Minimalist layout principles
224
+ - Cyberpunk color scheme (neon accents)
225
+ - Smooth animations for page transitions
226
+ - Typography-driven content sections
227
+ ```
228
+
229
+ ---
230
+
231
+ ## Tool Calling & Agentic Usage
232
+
233
+ UIGEN-X-32B-0727 supports **function calling** for dynamic asset integration and enhanced development workflows.
234
+
235
+ ### Image Integration with Unsplash
236
+
237
+ Register tools for dynamic image fetching:
238
+
239
+ ```json
240
+ {
241
+ "type": "function",
242
+ "function": {
243
+ "name": "fetch_unsplash_image",
244
+ "description": "Fetch high-quality images from Unsplash for UI mockups",
245
+ "parameters": {
246
+ "type": "object",
247
+ "properties": {
248
+ "query": {
249
+ "type": "string",
250
+ "description": "Search term for image (e.g., 'modern office', 'technology', 'nature')"
251
+ },
252
+ "orientation": {
253
+ "type": "string",
254
+ "enum": ["landscape", "portrait", "squarish"],
255
+ "description": "Image orientation"
256
+ },
257
+ "size": {
258
+ "type": "string",
259
+ "enum": ["small", "regular", "full"],
260
+ "description": "Image size"
261
+ }
262
+ },
263
+ "required": ["query"]
264
+ }
265
+ }
266
+ }
267
+ ```
268
+
269
+ ### Content Generation Tools
270
+
271
+ ```json
272
+ {
273
+ "type": "function",
274
+ "function": {
275
+ "name": "generate_content",
276
+ "description": "Generate realistic content for UI components",
277
+ "parameters": {
278
+ "type": "object",
279
+ "properties": {
280
+ "type": {
281
+ "type": "string",
282
+ "enum": ["user_profiles", "product_data", "blog_posts", "testimonials"],
283
+ "description": "Type of content to generate"
284
+ },
285
+ "count": {
286
+ "type": "integer",
287
+ "description": "Number of items to generate"
288
+ },
289
+ "theme": {
290
+ "type": "string",
291
+ "description": "Content theme or industry"
292
+ }
293
+ },
294
+ "required": ["type", "count"]
295
+ }
296
+ }
297
+ }
298
+ ```
299
+
300
+ ### Complete Agentic Workflow Example
301
+
302
+ ```python
303
+ # 1. Plan the application
304
+ response = model.chat([
305
+ {"role": "user", "content": "Plan a complete travel booking website using React + Next.js + Tailwind CSS + shadcn/ui"}
306
+ ], tools=[fetch_unsplash_image, generate_content])
307
+
308
+ # 2. The model will reason through the requirements and call tools:
309
+ # - fetch_unsplash_image(query="travel destinations", orientation="landscape")
310
+ # - generate_content(type="destinations", count=10, theme="popular travel")
311
+ # - fetch_unsplash_image(query="hotel rooms", orientation="landscape")
312
+
313
+ # 3. Generate complete implementation with real assets
314
+ final_response = model.chat([
315
+ {"role": "user", "content": "Now implement the complete website with the fetched images and content"}
316
+ ])
317
+ ```
318
+
319
+ ### Tool Integration Patterns
320
+
321
+ **Dynamic Asset Loading**:
322
+ - Fetch relevant images during UI generation
323
+ - Generate realistic content for components
324
+ - Create cohesive color palettes from images
325
+ - Optimize assets for web performance
326
+
327
+ **Multi-Step Development**:
328
+ - Plan application architecture
329
+ - Generate individual components
330
+ - Integrate components into pages
331
+ - Apply consistent styling and theming
332
+ - Test responsive behavior
333
+
334
+ **Content-Aware Design**:
335
+ - Adapt layouts based on content types
336
+ - Optimize typography for readability
337
+ - Create responsive image galleries
338
+ - Generate accessible alt text
339
+
340
+ ---
341
+
342
+ ## Inference Configuration
343
+
344
+ ### Optimal Parameters
345
+ ```python
346
+ {
347
+ "temperature": 0.6, # Balanced creativity and consistency (make it lower if quantized!!!!)
348
+ "top_p": 0.9, # Nucleus sampling for quality
349
+ "top_k": 40, # Vocabulary restriction
350
+ "max_tokens": 25000, # Full component generation
351
+ "repetition_penalty": 1.1, # Avoid repetitive patterns
352
+ }
353
+ ```
354
+
355
+ ---
356
+
357
+ ## Use Cases & Applications
358
+
359
+ ### Rapid Prototyping
360
+ - Quick mockups for client presentations
361
+ - A/B testing different design approaches
362
+ - Concept validation with interactive prototypes
363
+
364
+ ### Production Development
365
+ - Component library creation
366
+ - Design system implementation
367
+ - Template and boilerplate generation
368
+
369
+ ### Educational & Learning
370
+ - Teaching modern web development
371
+ - Framework comparison and evaluation
372
+ - Best practices demonstration
373
+
374
+ ### Enterprise Solutions
375
+ - Dashboard and admin panel generation
376
+ - Internal tool development
377
+ - Legacy system modernization
378
+
379
+ ---
380
+
381
+ ## Technical Requirements
382
+
383
+ ### Hardware
384
+ - **GPU**: 8GB+ VRAM recommended (RTX 3080/4070 or equivalent)
385
+ - **RAM**: 16GB system memory minimum
386
+ - **Storage**: 20GB for model weights and cache
387
+
388
+ ### Software
389
+ - **Python**: 3.8+ with transformers, torch, unsloth
390
+ - **Node.js**: For running generated JavaScript/TypeScript code
391
+ - **Browser**: Modern browser for testing generated UIs
392
+
393
+ ### Integration
394
+ - Compatible with HuggingFace transformers
395
+ - Supports GGML/GGUF quantization
396
+ - Works with text-generation-webui
397
+ - API-ready for production deployment
398
+
399
+ ---
400
+
401
+ ## Limitations & Considerations
402
+
403
+ - **Token Usage**: Reasoning process increases token consumption
404
+ - **Complex Logic**: Focuses on UI structure rather than business logic
405
+ - **Real-time Features**: Generated code requires backend integration
406
+ - **Testing**: Output may need manual testing and refinement
407
+ - **Accessibility**: While ARIA-aware, manual a11y testing recommended
408
+
409
+ ---
410
+
411
+ ## Community & Support
412
+
413
+ **Discord**: [https://discord.gg/EcCpcTv93U](https://discord.gg/EcCpcTv93U)
414
+ **Website**: [https://tesslate.com](https://tesslate.com)
415
+ **Examples**: [https://uigenoutput.tesslate.com](https://uigenoutput.tesslate.com)
416
+
417
+ Join our community to share creations, get help, and contribute to the ecosystem.
418
+
419
+ ---
420
+
421
+ ## Citation
422
+
423
+ ```bibtex
424
+ @misc{tesslate_uigen_x_2025,
425
+ title={UIGEN-X-32B-0727: Reasoning Only UI Generation with Qwen3},
426
+ author={Tesslate Team},
427
+ year={2025},
428
+ publisher={Tesslate},
429
+ url={https://huggingface.co/tesslate/UIGEN-X-32B-0727}
430
+ }
431
+ ```
432
+
433
+ ---
434
+
435
+
436
+
437
+
438
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/ZhW150gEhg0lkXoSjkiiU.png" alt="UI Screenshot 1" width="400">
439
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/NdxVu6Zv6beigOYjbKCl1.png" alt="UI Screenshot 2" width="400">
440
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/RX8po_paCIxrrcTvZ3xfA.png" alt="UI Screenshot 3" width="400">
441
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/DBssA7zan39uxy9HQOo5N.png" alt="UI Screenshot 4" width="400">
442
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/ttljEdBcYh1tkmyrCUQku.png" alt="UI Screenshot 5" width="400">
443
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/duLxNQAuqv1FPVlsmQsWr.png" alt="UI Screenshot 6" width="400">
444
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/ja2nhpNrvucf_zwCARXxa.png" alt="UI Screenshot 7" width="400">
445
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/ca0f_8U9HQdaSVAejpzPn.png" alt="UI Screenshot 8" width="400">
446
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/gzZF2CiOjyEbPAPRYSV-N.png" alt="UI Screenshot 9" width="400">
447
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/y8wB78PffUUoVLzw3al2R.png" alt="UI Screenshot 10" width="400">
448
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/M12dGr0xArAIF7gANSC5T.png" alt="UI Screenshot 11" width="400">
449
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/t7r7cYlUwmI1QQf3fxO7o.png" alt="UI Screenshot 12" width="400">
450
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/-uCIIJqTrrY9xkJHKCEqC.png" alt="UI Screenshot 13" width="400">
451
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/eqT3IUWaPtoNQb-IWQNuy.png" alt="UI Screenshot 14" width="400">
452
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/RhbGMcxCNlMIXRLEacUGi.png" alt="UI Screenshot 15" width="400">
453
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/FWhs43BKkXku12MwiW0v9.png" alt="UI Screenshot 16" width="400">
454
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/67db34a5e7f1d129b294e2af/ILHx-xcn18cyDLX5a63xV.png" alt="UIGEN-X UI Screenshot 1" width="400">
455
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/67db34a5e7f1d129b294e2af/A-zKo1J4HYftjiOjq_GB4.png" alt="UIGEN-X UI Screenshot 2" width="400">
456
+
457
+
458
+ *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
+ }
config.json ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "quantization_config": {
86
+ "bits": 4,
87
+ "group_size": 128,
88
+ "modules_to_not_convert": null,
89
+ "quant_method": "awq",
90
+ "version": "gemm",
91
+ "zero_point": true
92
+ },
93
+ "rms_norm_eps": 1e-06,
94
+ "rope_scaling": null,
95
+ "rope_theta": 1000000,
96
+ "sliding_window": null,
97
+ "tie_word_embeddings": false,
98
+ "torch_dtype": "bfloat16",
99
+ "transformers_version": "4.51.3",
100
+ "use_cache": false,
101
+ "use_sliding_window": false,
102
+ "vocab_size": 151936
103
+ }
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": "4.51.3"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d133d8422d1be8840f680b6678d304fd6282005e629a5b1da1ffd046f29fcb0
3
+ size 4966384592
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fa26787fed22a477276efc27ec6e033e6a67b8687e7f31895f09cae7de3cb08
3
+ size 4998722976
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09ba80bab65dd45279e89856763ca6d09014558c2a760e31f5694316fd0a2e8e
3
+ size 4949671016
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6eadb1ec20aebbd454369dc3ced7ad1521eee8a66864782ba43e1469eb0660f0
3
+ size 4410702712
model.safetensors.index.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 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# 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>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- else %}\n {{- '<think>\\n\\n' }}\n {%- endif %}\n{%- endif %}\n",
231
+ "clean_up_tokenization_spaces": false,
232
+ "eos_token": "<|im_end|>",
233
+ "errors": "replace",
234
+ "extra_special_tokens": {},
235
+ "model_max_length": 131072,
236
+ "pad_token": "<|endoftext|>",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "unk_token": null
240
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff