Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- README.md +169 -0
- added_tokens.json +28 -0
- chat_template.jinja +97 -0
- config.json +53 -0
- generation_config.json +14 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- quant_log.csv +253 -0
- quantize_config.json +21 -0
- special_tokens_map.json +25 -0
- tokenizer.json +3 -0
- tokenizer_config.json +241 -0
- vocab.json +0 -0
.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 +1,169 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- Qwen/Qwen3-4B
|
4 |
+
tags:
|
5 |
+
- text-generation-inference
|
6 |
+
- transformers
|
7 |
+
- qwen3
|
8 |
+
- ui-generation
|
9 |
+
- tailwind-css
|
10 |
+
- html
|
11 |
+
language:
|
12 |
+
- en
|
13 |
+
---
|
14 |
+
|
15 |
+
# UIGEN-T3 — Advanced UI Generation with Hybrid Reasoning
|
16 |
+
|
17 |
+
> Tesslate’s next-gen UI model, built for thoughtful design.
|
18 |
+
|
19 |
+
---
|
20 |
+
|
21 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/fqZE717ubrgSpAOHeMEeQ.png" alt="UIGEN-T3 UI Screenshot 1" width="500">
|
22 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/N5gfKRD-j9JAeMoGy7O3K.png" alt="UIGEN-T3 UI Screenshot 2" width="500">
|
23 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/PDGXycDkVsxFRxqHc6TKD.png" alt="UIGEN-T3 UI Screenshot 2" width="500">
|
24 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/Q4CHYYcDAN60NFjIPVQnH.png" alt="UIGEN-T3 UI Screenshot 3" width="500">
|
25 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/ePZoCA8lS4Y1KdkchrTlQ.png" alt="UIGEN-T3 UI Screenshot 4" width="500">
|
26 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/BU-Pk2moNsTOGuYF1XuRx.png" alt="UIGEN-T3 UI Screenshot 5" width="500">
|
27 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/gz5ub0lDpS-hhw1MB7e07.png" alt="UIGEN-T3 UI Screenshot 6" width="500">
|
28 |
+
|
29 |
+
## Demos
|
30 |
+
|
31 |
+
Explore New UI generations:
|
32 |
+
📂 [https://uigenoutput.tesslate.com](https://uigenoutput.tesslate.com)
|
33 |
+
|
34 |
+
---
|
35 |
+
|
36 |
+
**Join our Discord:** [https://discord.gg/GNbWAeJ4](https://discord.gg/GNbWAeJ4)
|
37 |
+
**Our Website:** [https://tesslate.com](https://tesslate.com)
|
38 |
+
|
39 |
+
## Quick Information
|
40 |
+
|
41 |
+
* **UI generation model** built on **Qwen3 architecture**
|
42 |
+
* Supports both **components** and **full web pages**
|
43 |
+
* **Hybrid reasoning system**: Use `/think` or `/no_think` modes
|
44 |
+
* Powered by **UIGenEval**, a first-of-its-kind benchmark for UI generation
|
45 |
+
* Released for **research, non-commercial use.** If you want to use it commercially, please contact us for a pilot program.
|
46 |
+
|
47 |
+
---
|
48 |
+
|
49 |
+
## Model Details
|
50 |
+
|
51 |
+
* **Base Model**: Qwen/Qwen3-4B
|
52 |
+
* **Reasoning Style**: Hybrid (`/think` and `/no_think`)
|
53 |
+
* **Tokenizer**: Qwen default, with design token headers
|
54 |
+
* **Output**: Components + Full pages (with `<html>`, `<head>`)
|
55 |
+
* **Images**: User-supplied or placehold.co – no images in the dataset due to licensing concerns.
|
56 |
+
* **License**: Research only (non-commercial). Contact us for enterprise use cases.
|
57 |
+
|
58 |
+
---
|
59 |
+
|
60 |
+
## Reasoning System
|
61 |
+
|
62 |
+
UIGEN-T3 was trained using a **pre/post reasoning model architecture**.
|
63 |
+
|
64 |
+
You can explicitly control the reasoning mode:
|
65 |
+
|
66 |
+
* `/think` → Enables guided reasoning with layout analysis and heuristics.
|
67 |
+
* `/no_think` → Faster, raw code generation.
|
68 |
+
|
69 |
+
Outputs also include **design tokens** at the top of each generation for easier site-wide customization.
|
70 |
+
|
71 |
+
---
|
72 |
+
|
73 |
+
## Inference Parameters
|
74 |
+
|
75 |
+
Please use 20k context length to get the best results if using reasoning.
|
76 |
+
|
77 |
+
| Parameter | Value |
|
78 |
+
| :---------- | :---- |
|
79 |
+
| Temperature | 0.6 |
|
80 |
+
| Top P | 0.95 |
|
81 |
+
| Top K | 20 |
|
82 |
+
| Max Tokens | 40k+ |
|
83 |
+
|
84 |
+
---
|
85 |
+
|
86 |
+
## Evaluation: UIGenEval Framework
|
87 |
+
|
88 |
+
**UIGenEval** is our internal evaluation suite, designed to **bridge the gap** between creative output and quality assurance.
|
89 |
+
*(Learn more in our upcoming paper: "UIGenEval: Bridging the Evaluation Gap in AI-Driven UI Generation" - August, 2025)*
|
90 |
+
|
91 |
+
UIGenEval evaluates models across four pillars:
|
92 |
+
|
93 |
+
1. **Technical Quality** — Clean HTML, CSS structure, semantic accuracy.
|
94 |
+
2. **Prompt Adherence** — Feature completeness and fidelity to instructions.
|
95 |
+
3. **Interaction Behavior** — Dynamic logic hooks and functional interactivity.
|
96 |
+
4. **Responsive Design** — Multi-viewport performance via Lighthouse, Axe-core, and custom scripts.
|
97 |
+
|
98 |
+
This comprehensive framework directly informs our **GRPO reward functions** for the next release.
|
99 |
+
|
100 |
+
---
|
101 |
+
|
102 |
+
## Example Prompts to Try
|
103 |
+
|
104 |
+
* `make a google drive clone`
|
105 |
+
* `build a figma-style canvas with toolbar`
|
106 |
+
* `create a modern pricing page with three plans`
|
107 |
+
* `generate a mobile-first recipe sharing app layout`
|
108 |
+
|
109 |
+
---
|
110 |
+
|
111 |
+
## Use Cases
|
112 |
+
|
113 |
+
| Use Case | Description |
|
114 |
+
| :---------------------- | :-------------------------------------------------------------------------- |
|
115 |
+
| **Startup MVPs** | Quickly scaffold UIs from scratch with clean code. |
|
116 |
+
| **Design-to-Code Transfer** | Figma (coming soon) → Code generation. |
|
117 |
+
| **Component Libraries** | Build buttons, cards, navbars, and export at scale. |
|
118 |
+
| **Internal Tool Builders** | Create admin panels, dashboards, and layout templates. |
|
119 |
+
| **Rapid Client Prototypes** | Save time on mockups with production-ready HTML+Tailwind outputs. |
|
120 |
+
|
121 |
+
---
|
122 |
+
|
123 |
+
## Limitations
|
124 |
+
|
125 |
+
* No Bootstrap support (planned).
|
126 |
+
* Not suited for production use — **research-only license**.
|
127 |
+
* Responsive tuning varies across output complexity.
|
128 |
+
|
129 |
+
---
|
130 |
+
|
131 |
+
## Roadmap
|
132 |
+
|
133 |
+
| Milestone | Status |
|
134 |
+
| :-------------------------- | :----- |
|
135 |
+
| Launch Tesslate Designer | 2 days |
|
136 |
+
| Figma convert | |
|
137 |
+
| Bootstrap & JS logic | |
|
138 |
+
| GRPO fine-tuning | |
|
139 |
+
| 4B draft model release | Now |
|
140 |
+
|
141 |
+
---
|
142 |
+
|
143 |
+
## Technical Requirements
|
144 |
+
|
145 |
+
* **GPU**: ~4GB VRAM for 4B inference on GGUF.
|
146 |
+
* **Libraries**: `transformers`, `torch`, `peft`.
|
147 |
+
* Compatible with Hugging Face inference APIs and local generation pipelines.
|
148 |
+
|
149 |
+
---
|
150 |
+
|
151 |
+
## Community & Contribution
|
152 |
+
|
153 |
+
* **Join our Discord:** [https://discord.gg/GNbWAeJ4](https://discord.gg/GNbWAeJ4)
|
154 |
+
* Chat about AI, design, or model training.
|
155 |
+
* Want to contribute UIs or feedback? Let’s talk!
|
156 |
+
|
157 |
+
---
|
158 |
+
|
159 |
+
## Citation
|
160 |
+
|
161 |
+
```bibtex
|
162 |
+
@misc{tesslate_UIGEN-T3,
|
163 |
+
title={UIGEN-T3: Hybrid Reasoning for Robust UI Generation on Qwen3},
|
164 |
+
author={Tesslate Team},
|
165 |
+
year={2025},
|
166 |
+
publisher={Tesslate},
|
167 |
+
note={Non-commercial Research License},
|
168 |
+
url={https://huggingface.co/tesslate/UIGEN-T3}
|
169 |
+
}
|
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 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 forward_message in messages %}
|
19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
20 |
+
{%- set message = messages[index] %}
|
21 |
+
{%- set tool_start = '<tool_response>' %}
|
22 |
+
{%- set tool_start_length = tool_start|length %}
|
23 |
+
{%- set start_of_message = message.content[:tool_start_length] %}
|
24 |
+
{%- set tool_end = '</tool_response>' %}
|
25 |
+
{%- set tool_end_length = tool_end|length %}
|
26 |
+
{%- set start_pos = (message.content|length) - tool_end_length %}
|
27 |
+
{%- if start_pos < 0 %}
|
28 |
+
{%- set start_pos = 0 %}
|
29 |
+
{%- endif %}
|
30 |
+
{%- set end_of_message = message.content[start_pos:] %}
|
31 |
+
{%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
|
32 |
+
{%- set ns.multi_step_tool = false %}
|
33 |
+
{%- set ns.last_query_index = index %}
|
34 |
+
{%- endif %}
|
35 |
+
{%- endfor %}
|
36 |
+
{%- for message in messages %}
|
37 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
38 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
39 |
+
{%- elif message.role == "assistant" %}
|
40 |
+
{%- set content = message.content %}
|
41 |
+
{%- set reasoning_content = '' %}
|
42 |
+
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
43 |
+
{%- set reasoning_content = message.reasoning_content %}
|
44 |
+
{%- else %}
|
45 |
+
{%- if '</think>' in message.content %}
|
46 |
+
{%- set content = (message.content.split('</think>')|last).lstrip('\n') %}
|
47 |
+
{%- set reasoning_content = (message.content.split('</think>')|first).rstrip('\n') %}
|
48 |
+
{%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\n') %}
|
49 |
+
{%- endif %}
|
50 |
+
{%- endif %}
|
51 |
+
{%- if loop.index0 > ns.last_query_index %}
|
52 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
53 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
54 |
+
{%- else %}
|
55 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
56 |
+
{%- endif %}
|
57 |
+
{%- else %}
|
58 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
59 |
+
{%- endif %}
|
60 |
+
{%- if message.tool_calls %}
|
61 |
+
{%- for tool_call in message.tool_calls %}
|
62 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
63 |
+
{{- '\n' }}
|
64 |
+
{%- endif %}
|
65 |
+
{%- if tool_call.function %}
|
66 |
+
{%- set tool_call = tool_call.function %}
|
67 |
+
{%- endif %}
|
68 |
+
{{- '<tool_call>\n{"name": "' }}
|
69 |
+
{{- tool_call.name }}
|
70 |
+
{{- '", "arguments": ' }}
|
71 |
+
{%- if tool_call.arguments is string %}
|
72 |
+
{{- tool_call.arguments }}
|
73 |
+
{%- else %}
|
74 |
+
{{- tool_call.arguments | tojson }}
|
75 |
+
{%- endif %}
|
76 |
+
{{- '}\n</tool_call>' }}
|
77 |
+
{%- endfor %}
|
78 |
+
{%- endif %}
|
79 |
+
{{- '<|im_end|>\n' }}
|
80 |
+
{%- elif message.role == "tool" %}
|
81 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
82 |
+
{{- '<|im_start|>user' }}
|
83 |
+
{%- endif %}
|
84 |
+
{{- '\n<tool_response>\n' }}
|
85 |
+
{{- message.content }}
|
86 |
+
{{- '\n</tool_response>' }}
|
87 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
88 |
+
{{- '<|im_end|>\n' }}
|
89 |
+
{%- endif %}
|
90 |
+
{%- endif %}
|
91 |
+
{%- endfor %}
|
92 |
+
{%- if add_generation_prompt %}
|
93 |
+
{{- '<|im_start|>assistant\n' }}
|
94 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
95 |
+
{{- '<think>\n\n</think>\n\n' }}
|
96 |
+
{%- endif %}
|
97 |
+
{%- endif %}
|
config.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": 2560,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 9728,
|
13 |
+
"max_position_embeddings": 40960,
|
14 |
+
"max_window_layers": 36,
|
15 |
+
"model_type": "qwen3",
|
16 |
+
"num_attention_heads": 32,
|
17 |
+
"num_hidden_layers": 36,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"pad_token_id": 151654,
|
20 |
+
"quantization_config": {
|
21 |
+
"bits": 4,
|
22 |
+
"checkpoint_format": "gptq",
|
23 |
+
"desc_act": true,
|
24 |
+
"group_size": 128,
|
25 |
+
"lm_head": false,
|
26 |
+
"meta": {
|
27 |
+
"damp_auto_increment": 0.0025,
|
28 |
+
"damp_percent": 0.01,
|
29 |
+
"mse": 0.0,
|
30 |
+
"quantizer": [
|
31 |
+
"gptqmodel:2.2.0"
|
32 |
+
],
|
33 |
+
"static_groups": false,
|
34 |
+
"true_sequential": true,
|
35 |
+
"uri": "https://github.com/modelcloud/gptqmodel"
|
36 |
+
},
|
37 |
+
"pack_dtype": "int32",
|
38 |
+
"quant_method": "gptq",
|
39 |
+
"sym": true
|
40 |
+
},
|
41 |
+
"rms_norm_eps": 1e-06,
|
42 |
+
"rope_scaling": null,
|
43 |
+
"rope_theta": 1000000,
|
44 |
+
"sliding_window": null,
|
45 |
+
"tie_word_embeddings": true,
|
46 |
+
"torch_dtype": "bfloat16",
|
47 |
+
"transformers_version": "4.52.4",
|
48 |
+
"unsloth_fixed": true,
|
49 |
+
"unsloth_version": "2025.6.1",
|
50 |
+
"use_cache": true,
|
51 |
+
"use_sliding_window": false,
|
52 |
+
"vocab_size": 151936
|
53 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 151643,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": [
|
5 |
+
151645,
|
6 |
+
151643
|
7 |
+
],
|
8 |
+
"max_length": 40960,
|
9 |
+
"pad_token_id": 151654,
|
10 |
+
"temperature": 0.6,
|
11 |
+
"top_k": 20,
|
12 |
+
"top_p": 0.95,
|
13 |
+
"transformers_version": "4.52.4"
|
14 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95f33d844f5500a35d0eddc28d69e77baabaeb1e400613f725cc1a9ddb86829e
|
3 |
+
size 2669888648
|
quant_log.csv
ADDED
@@ -0,0 +1,253 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
layer,module,loss,samples,damp,time
|
2 |
+
0,self_attn.k_proj,0.00123873,0.01000,0.856
|
3 |
+
0,self_attn.v_proj,0.00110737,0.01000,0.542
|
4 |
+
0,self_attn.q_proj,0.00448249,0.01000,0.546
|
5 |
+
0,self_attn.o_proj,0.00289857,0.01000,0.907
|
6 |
+
0,mlp.up_proj,0.23524620,0.01000,0.612
|
7 |
+
0,mlp.gate_proj,0.26896679,0.01000,0.584
|
8 |
+
0,mlp.down_proj,0.02773039,0.01000,2.354
|
9 |
+
1,self_attn.k_proj,0.00187088,0.01000,0.570
|
10 |
+
1,self_attn.v_proj,0.00191912,0.01000,0.554
|
11 |
+
1,self_attn.q_proj,0.00693994,0.01000,0.561
|
12 |
+
1,self_attn.o_proj,0.00380677,0.01000,0.929
|
13 |
+
1,mlp.up_proj,2.75171781,0.01000,0.592
|
14 |
+
1,mlp.gate_proj,6.11283016,0.01000,0.572
|
15 |
+
1,mlp.down_proj,0.03118854,0.01000,2.615
|
16 |
+
2,self_attn.k_proj,0.00615210,0.01000,0.621
|
17 |
+
2,self_attn.v_proj,0.00591036,0.01000,0.587
|
18 |
+
2,self_attn.q_proj,0.02148693,0.01000,0.593
|
19 |
+
2,self_attn.o_proj,0.00486573,0.01000,0.994
|
20 |
+
2,mlp.up_proj,7.16873598,0.01000,0.638
|
21 |
+
2,mlp.gate_proj,9.03812218,0.01000,0.616
|
22 |
+
2,mlp.down_proj,0.02829662,0.01000,2.787
|
23 |
+
3,self_attn.k_proj,0.01034767,0.01000,0.628
|
24 |
+
3,self_attn.v_proj,0.01046178,0.01000,0.601
|
25 |
+
3,self_attn.q_proj,0.03955096,0.01000,0.611
|
26 |
+
3,self_attn.o_proj,0.00826392,0.01000,1.005
|
27 |
+
3,mlp.up_proj,5.60811424,0.01000,0.639
|
28 |
+
3,mlp.gate_proj,10.94514084,0.01000,0.619
|
29 |
+
3,mlp.down_proj,0.08294636,0.01000,2.597
|
30 |
+
4,self_attn.k_proj,0.02284316,0.01000,0.622
|
31 |
+
4,self_attn.v_proj,0.02291789,0.01000,0.601
|
32 |
+
4,self_attn.q_proj,0.08206808,0.01000,0.603
|
33 |
+
4,self_attn.o_proj,0.01434520,0.01000,1.016
|
34 |
+
4,mlp.up_proj,4.82861996,0.01000,0.634
|
35 |
+
4,mlp.gate_proj,12.29374027,0.01000,0.613
|
36 |
+
4,mlp.down_proj,0.14373066,0.01000,2.543
|
37 |
+
5,self_attn.k_proj,0.02268875,0.01000,0.617
|
38 |
+
5,self_attn.v_proj,0.02433329,0.01000,0.597
|
39 |
+
5,self_attn.q_proj,0.08635324,0.01000,0.597
|
40 |
+
5,self_attn.o_proj,0.02219364,0.01000,0.999
|
41 |
+
5,mlp.up_proj,2.56769133,0.01000,0.630
|
42 |
+
5,mlp.gate_proj,5.16079426,0.01000,0.610
|
43 |
+
5,mlp.down_proj,0.22544172,0.01000,2.538
|
44 |
+
6,self_attn.k_proj,0.04727184,0.01000,0.619
|
45 |
+
6,self_attn.v_proj,0.05417306,0.01000,0.604
|
46 |
+
6,self_attn.q_proj,0.19562775,0.01000,0.601
|
47 |
+
6,self_attn.o_proj,0.06651908,0.01000,0.994
|
48 |
+
6,mlp.up_proj,3.43282795,0.01000,0.625
|
49 |
+
6,mlp.gate_proj,5.75655413,0.01000,0.607
|
50 |
+
6,mlp.down_proj,29.82526207,0.01000,2.542
|
51 |
+
7,self_attn.k_proj,0.10091165,0.01000,0.613
|
52 |
+
7,self_attn.v_proj,0.10057791,0.01000,0.598
|
53 |
+
7,self_attn.q_proj,0.37546265,0.01000,0.603
|
54 |
+
7,self_attn.o_proj,0.06946541,0.01000,0.989
|
55 |
+
7,mlp.up_proj,4.19534111,0.01000,0.630
|
56 |
+
7,mlp.gate_proj,6.64188242,0.01000,0.612
|
57 |
+
7,mlp.down_proj,0.37315902,0.01000,2.578
|
58 |
+
8,self_attn.k_proj,0.16401398,0.01000,0.630
|
59 |
+
8,self_attn.v_proj,0.17864552,0.01000,0.610
|
60 |
+
8,self_attn.q_proj,0.61840451,0.01000,0.615
|
61 |
+
8,self_attn.o_proj,0.11465244,0.01000,0.990
|
62 |
+
8,mlp.up_proj,4.47200966,0.01000,0.631
|
63 |
+
8,mlp.gate_proj,5.44155025,0.01000,0.614
|
64 |
+
8,mlp.down_proj,0.57710153,0.01000,2.459
|
65 |
+
9,self_attn.k_proj,0.22350451,0.01000,0.632
|
66 |
+
9,self_attn.v_proj,0.21595715,0.01000,0.612
|
67 |
+
9,self_attn.q_proj,0.78851616,0.01000,0.618
|
68 |
+
9,self_attn.o_proj,0.12789759,0.01000,0.993
|
69 |
+
9,mlp.up_proj,5.82484818,0.01000,0.630
|
70 |
+
9,mlp.gate_proj,8.97248840,0.01000,0.611
|
71 |
+
9,mlp.down_proj,0.65336919,0.01000,2.546
|
72 |
+
10,self_attn.k_proj,0.34492105,0.01000,0.616
|
73 |
+
10,self_attn.v_proj,0.40373421,0.01000,0.600
|
74 |
+
10,self_attn.q_proj,1.29320168,0.01000,0.607
|
75 |
+
10,self_attn.o_proj,0.18604402,0.01000,0.989
|
76 |
+
10,mlp.up_proj,5.45041943,0.01000,0.624
|
77 |
+
10,mlp.gate_proj,7.72248268,0.01000,0.611
|
78 |
+
10,mlp.down_proj,0.64600360,0.01000,2.489
|
79 |
+
11,self_attn.k_proj,0.18291125,0.01000,0.612
|
80 |
+
11,self_attn.v_proj,0.19269162,0.01000,0.598
|
81 |
+
11,self_attn.q_proj,0.65538025,0.01000,0.599
|
82 |
+
11,self_attn.o_proj,0.13604632,0.01000,0.987
|
83 |
+
11,mlp.up_proj,5.37614202,0.01000,0.627
|
84 |
+
11,mlp.gate_proj,6.76691675,0.01000,0.610
|
85 |
+
11,mlp.down_proj,0.62111914,0.01000,2.522
|
86 |
+
12,self_attn.k_proj,0.21477230,0.01000,0.623
|
87 |
+
12,self_attn.v_proj,0.22783864,0.01000,0.604
|
88 |
+
12,self_attn.q_proj,0.77636456,0.01000,0.609
|
89 |
+
12,self_attn.o_proj,0.15855847,0.01000,1.018
|
90 |
+
12,mlp.up_proj,5.45675278,0.01000,0.630
|
91 |
+
12,mlp.gate_proj,6.25355577,0.01000,0.611
|
92 |
+
12,mlp.down_proj,0.60615569,0.01000,2.550
|
93 |
+
13,self_attn.k_proj,0.15745580,0.01000,0.616
|
94 |
+
13,self_attn.v_proj,0.15657398,0.01000,0.597
|
95 |
+
13,self_attn.q_proj,0.60514981,0.01000,0.600
|
96 |
+
13,self_attn.o_proj,0.10628274,0.01000,0.990
|
97 |
+
13,mlp.up_proj,5.61672163,0.01000,0.628
|
98 |
+
13,mlp.gate_proj,5.87201500,0.01000,0.612
|
99 |
+
13,mlp.down_proj,0.67708504,0.01000,2.538
|
100 |
+
14,self_attn.k_proj,0.27187395,0.01000,0.619
|
101 |
+
14,self_attn.v_proj,0.28658593,0.01000,0.600
|
102 |
+
14,self_attn.q_proj,1.01191640,0.01000,0.610
|
103 |
+
14,self_attn.o_proj,0.22648007,0.01000,0.990
|
104 |
+
14,mlp.up_proj,5.57868195,0.01000,0.644
|
105 |
+
14,mlp.gate_proj,5.84806681,0.01000,0.629
|
106 |
+
14,mlp.down_proj,0.62482631,0.01000,2.595
|
107 |
+
15,self_attn.k_proj,0.27123177,0.01000,0.619
|
108 |
+
15,self_attn.v_proj,0.26198697,0.01000,0.598
|
109 |
+
15,self_attn.q_proj,1.01776075,0.01000,0.603
|
110 |
+
15,self_attn.o_proj,0.16403264,0.01000,1.015
|
111 |
+
15,mlp.up_proj,5.26691723,0.01000,0.630
|
112 |
+
15,mlp.gate_proj,5.33374262,0.01000,0.611
|
113 |
+
15,mlp.down_proj,0.66066480,0.01000,2.523
|
114 |
+
16,self_attn.k_proj,0.46768245,0.01000,0.618
|
115 |
+
16,self_attn.v_proj,0.53261256,0.01000,0.597
|
116 |
+
16,self_attn.q_proj,1.89557815,0.01000,0.601
|
117 |
+
16,self_attn.o_proj,0.22165260,0.01000,0.993
|
118 |
+
16,mlp.up_proj,6.08415842,0.01000,0.628
|
119 |
+
16,mlp.gate_proj,6.49113941,0.01000,0.610
|
120 |
+
16,mlp.down_proj,1.85670257,0.01000,2.518
|
121 |
+
17,self_attn.k_proj,0.42134002,0.01000,0.632
|
122 |
+
17,self_attn.v_proj,0.48449194,0.01000,0.613
|
123 |
+
17,self_attn.q_proj,1.87889564,0.01000,0.615
|
124 |
+
17,self_attn.o_proj,0.25283197,0.01000,0.984
|
125 |
+
17,mlp.up_proj,6.02301502,0.01000,0.627
|
126 |
+
17,mlp.gate_proj,6.27272224,0.01000,0.610
|
127 |
+
17,mlp.down_proj,1.09825277,0.01000,2.525
|
128 |
+
18,self_attn.k_proj,0.51484811,0.01000,0.615
|
129 |
+
18,self_attn.v_proj,0.56935638,0.01000,0.597
|
130 |
+
18,self_attn.q_proj,2.12831020,0.01000,0.599
|
131 |
+
18,self_attn.o_proj,0.26237524,0.01000,0.990
|
132 |
+
18,mlp.up_proj,7.09830236,0.01000,0.625
|
133 |
+
18,mlp.gate_proj,7.31005383,0.01000,0.610
|
134 |
+
18,mlp.down_proj,1.12803757,0.01000,2.514
|
135 |
+
19,self_attn.k_proj,1.02484667,0.01000,0.618
|
136 |
+
19,self_attn.v_proj,1.06308436,0.01000,0.602
|
137 |
+
19,self_attn.q_proj,4.28408527,0.01000,0.600
|
138 |
+
19,self_attn.o_proj,0.41635871,0.01000,0.978
|
139 |
+
19,mlp.up_proj,8.21070194,0.01000,0.602
|
140 |
+
19,mlp.gate_proj,8.41306496,0.01000,0.606
|
141 |
+
19,mlp.down_proj,1.33759713,0.01000,2.568
|
142 |
+
20,self_attn.k_proj,0.85735595,0.01000,0.614
|
143 |
+
20,self_attn.v_proj,0.95374173,0.01000,0.596
|
144 |
+
20,self_attn.q_proj,4.03840733,0.01000,0.607
|
145 |
+
20,self_attn.o_proj,0.43925771,0.01000,0.989
|
146 |
+
20,mlp.up_proj,9.09930897,0.01000,0.627
|
147 |
+
20,mlp.gate_proj,9.20165539,0.01000,0.605
|
148 |
+
20,mlp.down_proj,1.49482775,0.01000,2.507
|
149 |
+
21,self_attn.k_proj,1.11751676,0.01000,0.616
|
150 |
+
21,self_attn.v_proj,1.31520808,0.01000,0.592
|
151 |
+
21,self_attn.q_proj,5.02755117,0.01000,0.604
|
152 |
+
21,self_attn.o_proj,0.43767923,0.01000,0.982
|
153 |
+
21,mlp.up_proj,10.56902695,0.01000,0.626
|
154 |
+
21,mlp.gate_proj,10.65886497,0.01000,0.610
|
155 |
+
21,mlp.down_proj,1.87661600,0.01000,2.510
|
156 |
+
22,self_attn.k_proj,2.37679768,0.01000,0.631
|
157 |
+
22,self_attn.v_proj,2.52294540,0.01000,0.613
|
158 |
+
22,self_attn.q_proj,9.91435432,0.01000,0.615
|
159 |
+
22,self_attn.o_proj,0.91688001,0.01000,1.010
|
160 |
+
22,mlp.up_proj,11.67081738,0.01000,0.639
|
161 |
+
22,mlp.gate_proj,12.07019424,0.01000,0.619
|
162 |
+
22,mlp.down_proj,2.71307826,0.01000,2.545
|
163 |
+
23,self_attn.k_proj,2.16365004,0.01000,0.618
|
164 |
+
23,self_attn.v_proj,2.64794898,0.01000,0.594
|
165 |
+
23,self_attn.q_proj,9.86817551,0.01000,0.596
|
166 |
+
23,self_attn.o_proj,1.23303890,0.01000,0.930
|
167 |
+
23,mlp.up_proj,13.13149452,0.01000,0.585
|
168 |
+
23,mlp.gate_proj,14.33207798,0.01000,0.569
|
169 |
+
23,mlp.down_proj,3.33734727,0.01000,2.384
|
170 |
+
24,self_attn.k_proj,3.32925725,0.01000,0.575
|
171 |
+
24,self_attn.v_proj,4.27226925,0.01000,0.555
|
172 |
+
24,self_attn.q_proj,14.87903214,0.01000,0.560
|
173 |
+
24,self_attn.o_proj,1.51258278,0.01000,0.949
|
174 |
+
24,mlp.up_proj,14.38549519,0.01000,0.593
|
175 |
+
24,mlp.gate_proj,16.04924965,0.01000,0.568
|
176 |
+
24,mlp.down_proj,3.88327122,0.01000,2.349
|
177 |
+
25,self_attn.k_proj,2.62339449,0.01000,0.574
|
178 |
+
25,self_attn.v_proj,3.02613497,0.01000,0.554
|
179 |
+
25,self_attn.q_proj,10.85767365,0.01000,0.558
|
180 |
+
25,self_attn.o_proj,0.78760964,0.01000,0.919
|
181 |
+
25,mlp.up_proj,15.94119358,0.01000,0.586
|
182 |
+
25,mlp.gate_proj,18.02243233,0.01000,0.568
|
183 |
+
25,mlp.down_proj,4.66944599,0.01000,2.348
|
184 |
+
26,self_attn.k_proj,3.96194148,0.01000,0.573
|
185 |
+
26,self_attn.v_proj,4.70262814,0.01000,0.555
|
186 |
+
26,self_attn.q_proj,17.04475403,0.01000,0.558
|
187 |
+
26,self_attn.o_proj,0.96386701,0.01000,0.931
|
188 |
+
26,mlp.up_proj,18.74828529,0.01000,0.587
|
189 |
+
26,mlp.gate_proj,20.73773575,0.01000,0.568
|
190 |
+
26,mlp.down_proj,5.22521782,0.01000,2.367
|
191 |
+
27,self_attn.k_proj,4.54148579,0.01000,0.575
|
192 |
+
27,self_attn.v_proj,5.86671495,0.01000,0.555
|
193 |
+
27,self_attn.q_proj,20.36342239,0.01000,0.567
|
194 |
+
27,self_attn.o_proj,1.05593729,0.01000,0.919
|
195 |
+
27,mlp.up_proj,21.33163071,0.01000,0.585
|
196 |
+
27,mlp.gate_proj,22.83546638,0.01000,0.567
|
197 |
+
27,mlp.down_proj,7.34728432,0.01000,2.376
|
198 |
+
28,self_attn.k_proj,5.29708862,0.01000,0.574
|
199 |
+
28,self_attn.v_proj,5.96206570,0.01000,0.554
|
200 |
+
28,self_attn.q_proj,21.48520851,0.01000,0.558
|
201 |
+
28,self_attn.o_proj,1.62529755,0.01000,0.921
|
202 |
+
28,mlp.up_proj,24.72805405,0.01000,0.585
|
203 |
+
28,mlp.gate_proj,25.50748444,0.01000,0.568
|
204 |
+
28,mlp.down_proj,10.48237228,0.01000,2.343
|
205 |
+
29,self_attn.k_proj,11.26534748,0.01000,0.560
|
206 |
+
29,self_attn.v_proj,15.88263798,0.01000,0.540
|
207 |
+
29,self_attn.q_proj,47.37147903,0.01000,0.569
|
208 |
+
29,self_attn.o_proj,1.92915714,0.01000,0.905
|
209 |
+
29,mlp.up_proj,29.49695587,0.01000,0.573
|
210 |
+
29,mlp.gate_proj,29.21311378,0.01000,0.554
|
211 |
+
29,mlp.down_proj,11.22981453,0.01000,2.349
|
212 |
+
30,self_attn.k_proj,14.48636055,0.01000,0.573
|
213 |
+
30,self_attn.v_proj,18.10686111,0.01000,0.554
|
214 |
+
30,self_attn.q_proj,57.71099091,0.01000,0.558
|
215 |
+
30,self_attn.o_proj,2.68425775,0.01000,0.918
|
216 |
+
30,mlp.up_proj,31.87129784,0.01000,0.585
|
217 |
+
30,mlp.gate_proj,30.56179810,0.01000,0.567
|
218 |
+
30,mlp.down_proj,14.61885548,0.01000,2.356
|
219 |
+
31,self_attn.k_proj,18.70092583,0.01000,0.578
|
220 |
+
31,self_attn.v_proj,26.29804993,0.01000,0.557
|
221 |
+
31,self_attn.q_proj,69.95246887,0.01000,0.561
|
222 |
+
31,self_attn.o_proj,3.12106752,0.01000,0.938
|
223 |
+
31,mlp.up_proj,33.03866959,0.01000,0.570
|
224 |
+
31,mlp.gate_proj,30.24897766,0.01000,0.573
|
225 |
+
31,mlp.down_proj,18.80881119,0.01000,2.312
|
226 |
+
32,self_attn.k_proj,24.38664246,0.01000,0.558
|
227 |
+
32,self_attn.v_proj,37.72523117,0.01000,0.539
|
228 |
+
32,self_attn.q_proj,99.24736023,0.01000,0.544
|
229 |
+
32,self_attn.o_proj,4.29221535,0.01000,0.898
|
230 |
+
32,mlp.up_proj,34.54088974,0.01000,0.571
|
231 |
+
32,mlp.gate_proj,30.91791344,0.01000,0.553
|
232 |
+
32,mlp.down_proj,24.25460434,0.01000,2.292
|
233 |
+
33,self_attn.k_proj,42.03315735,0.01000,0.586
|
234 |
+
33,self_attn.v_proj,84.53782654,0.01000,0.540
|
235 |
+
33,self_attn.q_proj,194.52450562,0.01000,0.544
|
236 |
+
33,self_attn.o_proj,8.65462017,0.01000,0.936
|
237 |
+
33,mlp.up_proj,37.32664490,0.01000,0.572
|
238 |
+
33,mlp.gate_proj,32.82886505,0.01000,0.554
|
239 |
+
33,mlp.down_proj,31.24522400,0.01000,2.353
|
240 |
+
34,self_attn.k_proj,37.48818207,0.01000,0.576
|
241 |
+
34,self_attn.v_proj,62.39939880,0.01000,0.554
|
242 |
+
34,self_attn.q_proj,165.71405029,0.01000,0.558
|
243 |
+
34,self_attn.o_proj,12.69763660,0.01000,0.925
|
244 |
+
34,mlp.up_proj,41.41612244,0.01000,0.589
|
245 |
+
34,mlp.gate_proj,38.91174316,0.01000,0.570
|
246 |
+
34,mlp.down_proj,43.10342407,0.01000,2.365
|
247 |
+
35,self_attn.k_proj,22.99954224,0.01000,0.573
|
248 |
+
35,self_attn.v_proj,29.88472366,0.01000,0.555
|
249 |
+
35,self_attn.q_proj,88.38960266,0.01000,0.557
|
250 |
+
35,self_attn.o_proj,12.08172131,0.01000,0.949
|
251 |
+
35,mlp.up_proj,59.13071442,0.01000,0.585
|
252 |
+
35,mlp.gate_proj,57.53834534,0.01000,0.573
|
253 |
+
35,mlp.down_proj,102.49040222,0.01000,2.351
|
quantize_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bits": 4,
|
3 |
+
"group_size": 128,
|
4 |
+
"desc_act": true,
|
5 |
+
"sym": true,
|
6 |
+
"lm_head": false,
|
7 |
+
"quant_method": "gptq",
|
8 |
+
"checkpoint_format": "gptq",
|
9 |
+
"pack_dtype": "int32",
|
10 |
+
"meta": {
|
11 |
+
"quantizer": [
|
12 |
+
"gptqmodel:2.2.0"
|
13 |
+
],
|
14 |
+
"uri": "https://github.com/modelcloud/gptqmodel",
|
15 |
+
"damp_percent": 0.01,
|
16 |
+
"damp_auto_increment": 0.0025,
|
17 |
+
"static_groups": false,
|
18 |
+
"true_sequential": true,
|
19 |
+
"mse": 0.0
|
20 |
+
}
|
21 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<|vision_pad|>"
|
25 |
+
}
|
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 +1,241 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": 40960,
|
235 |
+
"pad_token": "<|vision_pad|>",
|
236 |
+
"padding_side": "right",
|
237 |
+
"split_special_tokens": false,
|
238 |
+
"tokenizer_class": "Qwen2TokenizerFast",
|
239 |
+
"unk_token": null,
|
240 |
+
"_commit_hash": null
|
241 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|