Hugging Face's logo

sfsx
/
Z-Image-Engineer-V6

Text Generation
Transformers
Safetensors
English
qwen3
prompt-engineering
image-generation
z-image
z-image-turbo
text-encoder
comfyui
lm-studio
conversational
text-generation-inference
Model card Files
xet
 Community
sfsx BennyDaBall commited on
Commit
90bfe5c
·
0 Parent(s):

Duplicate from BennyDaBall/Z-Image-Engineer-V6

Browse files

Co-authored-by: BennyDaBall <BennyDaBall@users.noreply.huggingface.co>

Files changed (15) hide show
  1. .gitattributes +44 -0
  2. HASHES.sha256 +12 -0
  3. README.md +182 -0
  4. RELEASE_MANIFEST.json +108 -0
  5. V6_SYSTEM_PROMPT.md +11 -0
  6. chat_template.jinja +89 -0
  7. config.json +71 -0
  8. evidence/gallery_z_image_engineer_v6_simple_ab_with_rewrites_CONTACT.png +3 -0
  9. generation_config.json +10 -0
  10. model-00001-of-00003.safetensors +3 -0
  11. model-00002-of-00003.safetensors +3 -0
  12. model-00003-of-00003.safetensors +3 -0
  13. model.safetensors.index.json +406 -0
  14. tokenizer.json +3 -0
  15. tokenizer_config.json +30 -0
.gitattributes ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz 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
+ Z-Image-Engineer-V6-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Z-Image-Engineer-V6-F16.gguf filter=lfs diff=lfs merge=lfs -text
38
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ Z-Image-Engineer-V6-MXFP4.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Z-Image-Engineer-V6-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Z-Image-Engineer-V6-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Z-Image-Engineer-V6-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
43
+ evidence/gallery_z_image_engineer_v6_simple_ab_with_rewrites_CONTACT.png filter=lfs diff=lfs merge=lfs -text
44
+ Z-Image-Engineer-V6-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
HASHES.sha256 ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 51FA65C79BB57F058DC7EF8734884BD325FE9D45BB03A61BFEF59785D3BC2DA9 chat_template.jinja
2
+ FABBE298983E905E68B64645E76712189C07776F6D4124648B09C66FA8F6E9CB config.json
3
+ D8AD1C43FD8C76F1EBDAD11C85D494A474F9CFE9F83AF5F72F590AE3852315A2 evidence/gallery_z_image_engineer_v6_simple_ab_with_rewrites_CONTACT.png
4
+ 4667A99763A8A867921429B113A4BDC0E9942D878A51C95F673CCD12355C471D generation_config.json
5
+ 646973887378A236D3CF81292DE5CD631218B940EC0AECF03A16F57890572EFC model.safetensors.index.json
6
+ C4D12692AE5CEFA9B7E61C2A581062F6B4B06183165EB2BCEEE9E11F26B82308 model-00001-of-00003.safetensors
7
+ 93A4CAF2F35B815178DB5CE43C9FD5E06E3EF836F5CBEEE7C690961D95DA653B model-00002-of-00003.safetensors
8
+ 4B3EF3D52BCAD649213FD2035D94DF48CBF2FD670250EC1FD8E1748072ECDBF2 model-00003-of-00003.safetensors
9
+ AF0D74388A53EF4A9B37CF98B05922F1D5D3A888C1C6BBB95D883D89AC423760 README.md
10
+ BE75606093DB2094D7CD20F3C2F385C212750648BD6EA4FB2BF507A6A4C55506 tokenizer.json
11
+ 154E5FF1E7C152D964EDF30DA854EA62465C767719AC8E97E58BABF2D4FA9079 tokenizer_config.json
12
+ 34126E2486E389F28C11693C2E51641199FB5B53E3E7D6BFA75A6E967C11D3CF V6_SYSTEM_PROMPT.md
README.md ADDED
@@ -0,0 +1,182 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - en
5
+ base_model:
6
+ - Tongyi-MAI/Z-Image-Turbo
7
+ library_name: transformers
8
+ pipeline_tag: text-generation
9
+ tags:
10
+ - text-generation
11
+ - prompt-engineering
12
+ - image-generation
13
+ - z-image
14
+ - z-image-turbo
15
+ - qwen3
16
+ - text-encoder
17
+ - comfyui
18
+ - lm-studio
19
+ - conversational
20
+ ---
21
+
22
+ # Z-Image-Engineer V6 (4B)
23
+
24
+ **Follow me on X [@BennyDaBall_OG](https://x.com/BennyDaBall_OG) !**
25
+
26
+ ## Model Metadata
27
+
28
+ | Key | Value |
29
+ |---|---|
30
+ | **License** | Apache-2.0 |
31
+ | **Language** | English (`en`) |
32
+ | **Base Model** | `Tongyi-MAI/Z-Image-Turbo` |
33
+ | **Library** | `transformers` |
34
+ | **Pipeline Tag** | `text-generation` |
35
+ | **Format** | HF Safetensors |
36
+
37
+ ---
38
+
39
+ The **Z-Engineer** returns, fully rebuilt around the **SMART DoRA** training system for Z-Image Turbo.
40
+
41
+ Yes, we jump from V4 to V6. Unlike the usual guy math, this one actually brought the extra two inches.
42
+
43
+ **Z-Image-Engineer V6** is a fine-tuned 4B Qwen text encoder (`Tongyi-MAI/Z-Image-Turbo`) optimized for dual-role performance: a local prompt-enhancement model and a merged HF text encoder for Z-Image workflows. The [ComfyUI-Z-Engineer](https://github.com/BennyDaBall930/ComfyUI-Z-Engineer) node runs both roles fully inside ComfyUI from this release.
44
+
45
+ ![Z-Image-Engineer V6 simple A/B with rewrites](evidence/gallery_z_image_engineer_v6_simple_ab_with_rewrites_CONTACT.png)
46
+
47
+ ---
48
+
49
+ ## What is Z-Image-Engineer V6?
50
+
51
+ V6 transforms minimal seed prompts into rich, highly structured visual narratives. It adds explicit scene composition, lighting direction, material texture, and depth separation while stripping out empty prompt sludge like *"8k, masterpiece, trending on ArtStation."*
52
+
53
+ It can also be used directly as a Z-Image text encoder. This repo contains the merged HF safetensors. The GGUF quantized release lives in the companion repo: [Z-Image-Engineer-V6-GGUF](https://huggingface.co/BennyDaBall/Z-Image-Engineer-V6-GGUF).
54
+
55
+ ### Key Use Cases
56
+
57
+ - **Prompt Enhancement:** Upgrade simple concepts into descriptive, high-fidelity visual prompts locally.
58
+ - **Text Encoder Swap:** Replace the stock Z-Image Qwen text encoder to generate different conditioning from the same seed.
59
+ - **Hybrid Mode:** Use V6 to rewrite your prompt, then use V6 again to encode it. It writes the scene and drives the image model.
60
+ - **Private Local Workflow:** Built for LM Studio, ComfyUI, and `llama.cpp`. No API logs, no external telemetry.
61
+
62
+ ---
63
+
64
+ ## Under the Hood: SMART DoRA
65
+
66
+ V4 pioneered SMART training. V6 adapts that system into a **Weight-Decomposed Low-Rank Adaptation (DoRA)** framework.
67
+
68
+ DoRA provides surgical adapter updates by decoupling directional and magnitude adjustments. SMART adds auxiliary pressure so the model does not collapse into repetitive prompt loops or superficial sentence patterns.
69
+
70
+ | Regularizer | What it Does | Why it Matters |
71
+ |---|---|---|
72
+ | **Entropic** | Broadens output probability diversity. | Reduces repetitive loops and generic vocabulary. |
73
+ | **Holographic** | Enforces structured, depth-wise feature logic. | Improves foreground/background hierarchy. |
74
+ | **Topological** | Stabilizes coherent latent trajectories. | Keeps prompts flowing naturally instead of stalling out. |
75
+ | **Manifold** | Regulates overall weight distributions. | Keeps model behavior stable under high-pressure refinement. |
76
+
77
+ ### The Refinement Pipeline
78
+
79
+ V6 was not a simple one-and-done training run. The final architecture is a blended composite:
80
+
81
+ 1. **Base Pass:** Master-corpus SMART DoRA training on the native Z-Image Turbo text encoder.
82
+ 2. **Retention Pass:** Preservation pressure for numbers, color accuracy, text signage, named objects, actions, and spatial tracking.
83
+ 3. **SceneClean SFT32:** Supervised refinement to restore the cinematic V4/base-V6 voice.
84
+ 4. **AntiRepeat Binary24:** Binary anti-repeat refinement to reduce loops, abrupt fragments, and bad endings.
85
+ 5. **Final Blend:** A 25% style-restoration / 75% anti-repeat DoRA adapter blend, balancing vivid descriptions with tighter syntax.
86
+
87
+ ---
88
+
89
+ ## Quick Start
90
+
91
+ ### LM Studio: Prompt Enhancement
92
+
93
+ Use this merged HF release directly where supported, or download a GGUF quant from [Z-Image-Engineer-V6-GGUF](https://huggingface.co/BennyDaBall/Z-Image-Engineer-V6-GGUF) for LM Studio. No complex system prompt is required.
94
+
95
+ ```text
96
+ Enhance this image prompt for Z-Image Turbo: a unicorn
97
+ ```
98
+
99
+ The comparison examples were generated from direct LM Studio user requests like this, with no separate system prompt. `V6_SYSTEM_PROMPT.md` is included only as an optional preset for people who want a stricter prompt-only chat setup.
100
+
101
+ ### ComfyUI: Text Encoder + Local Prompt Enhancer
102
+
103
+ Use the [ComfyUI-Z-Engineer](https://github.com/BennyDaBall930/ComfyUI-Z-Engineer) custom node (v2.0+). It loads this repo's sharded safetensors release directly and runs V6 as both the Z-Image text encoder and an in-ComfyUI prompt enhancer - no LM Studio or external server required.
104
+
105
+ 1. Download this repo into `ComfyUI/models/text_encoders/Z-Image-Engineer-V6/` (the three `model-0000X-of-00003.safetensors` shards plus `model.safetensors.index.json`).
106
+ 2. Add **Z-Engineer CLIP Loader (Safetensors / Shards)** and pick `Z-Image-Engineer-V6/` from the dropdown.
107
+ 3. Wire `clip` into your Z-Image **CLIP Text Encode** - V6 replaces the stock Qwen text encoder.
108
+ 4. Optional: add **Z-Engineer Prompt Enhancer (Local)** with the same `clip` to rewrite seed prompts in-process; the enhanced prompt is previewed right on the node.
109
+
110
+ A ready-made workflow ships with the node repo: `example_workflows/z_image_turbo_z_engineer.json`.
111
+
112
+ Prefer smaller files? Use a quant from [Z-Image-Engineer-V6-GGUF](https://huggingface.co/BennyDaBall/Z-Image-Engineer-V6-GGUF) with the node's **Z-Engineer CLIP Loader (GGUF)** instead.
113
+
114
+ ### Verified Image Settings
115
+
116
+ ```text
117
+ UNET: z_image_turbo_bf16.safetensors
118
+ VAE: ae.safetensors
119
+ Text Encoder: Z-Image-Engineer-V6 (this repo's sharded safetensors, or a GGUF quant)
120
+ Resolution: 1024x1024
121
+ Steps: 8
122
+ CFG: 1.0
123
+ Sampler: res_multistep
124
+ Scheduler: simple
125
+ Shift: 3.0
126
+ ```
127
+
128
+ ---
129
+
130
+ ## Training Specifics
131
+
132
+ | Parameter | Specification |
133
+ |---|---|
134
+ | **Base Text Encoder** | `Tongyi-MAI/Z-Image-Turbo/text_encoder` |
135
+ | **Tokenizer** | `Tongyi-MAI/Z-Image-Turbo/tokenizer` |
136
+ | **Method** | SMART DoRA / PEFT Adapter Training |
137
+ | **Rank / Alpha / Dropout** | 64 / 64 / 0.03 |
138
+ | **Target Modules** | `q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`, `down_proj`, `up_proj` |
139
+ | **Refinement Stack** | Supervised Style SFT + Binary Anti-Repeat |
140
+ | **Final Packaging** | Merged HF safetensors |
141
+
142
+ ---
143
+
144
+ ## GGUF Quantization Ladder
145
+
146
+ The quantized release is separate on purpose:
147
+
148
+ [BennyDaBall/Z-Image-Engineer-V6-GGUF](https://huggingface.co/BennyDaBall/Z-Image-Engineer-V6-GGUF)
149
+
150
+ That repo contains the full GGUF ladder: F16, Q8_0, Q6_K, Q5_K_M, Q4_K_M, Q3_K_M, and MXFP4.
151
+
152
+ ---
153
+
154
+ ## Verification & Proof
155
+
156
+ The bundled comparison image is:
157
+
158
+ ```text
159
+ evidence/gallery_z_image_engineer_v6_simple_ab_with_rewrites_CONTACT.png
160
+ ```
161
+
162
+ It compares foundational prompts across four isolated control paths:
163
+
164
+ 1. Stock Encoder + Raw Prompt
165
+ 2. V6 Encoder + Raw Prompt
166
+ 3. Stock Encoder + V6 LM Studio Rewrite
167
+ 4. V6 Encoder + V6 LM Studio Rewrite
168
+
169
+ ---
170
+
171
+ ## Disclaimer & Acknowledgements
172
+
173
+ This model is a prompt engineer and text encoder. Diffusion is still diffusion; structural expansion improves compositional adherence, but it does not mathematically guarantee a perfect seed every single time. Use creative judgment locally.
174
+
175
+ - **Tongyi-MAI** for the Z-Image Turbo ecosystem.
176
+ - **Qwen** for the adaptable text encoder backbone.
177
+ - The open-source maintainers behind **LM Studio**, **ComfyUI**, **llama.cpp**, **PEFT**, and **Transformers**.
178
+ - My local power utility provider, for sustaining the research grid.
179
+
180
+ **Built & trained locally with care by BennyDaBall.**
181
+
182
+ **Follow me on X [@BennyDaBall_OG](https://x.com/BennyDaBall_OG) !**
RELEASE_MANIFEST.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "status": "upload_ready_user_approved",
3
+ "public_model_name": "Z-Image-Engineer-V6",
4
+ "repo_id": "BennyDaBall/Z-Image-Engineer-V6",
5
+ "package_kind": "merged_hf_safetensors",
6
+ "base_model": "Tongyi-MAI/Z-Image-Turbo/text_encoder",
7
+ "tokenizer": "Tongyi-MAI/Z-Image-Turbo/tokenizer",
8
+ "files": [
9
+ {
10
+ "path": "chat_template.jinja",
11
+ "size_bytes": 4256,
12
+ "size_gib": 0,
13
+ "sha256": "51FA65C79BB57F058DC7EF8734884BD325FE9D45BB03A61BFEF59785D3BC2DA9",
14
+ "last_write_time": "2026-06-05T13:35:46"
15
+ },
16
+ {
17
+ "path": "config.json",
18
+ "size_bytes": 1662,
19
+ "size_gib": 0,
20
+ "sha256": "FABBE298983E905E68B64645E76712189C07776F6D4124648B09C66FA8F6E9CB",
21
+ "last_write_time": "2026-06-05T13:35:41"
22
+ },
23
+ {
24
+ "path": "evidence/gallery_z_image_engineer_v6_simple_ab_with_rewrites_CONTACT.png",
25
+ "size_bytes": 6174098,
26
+ "size_gib": 0.006,
27
+ "sha256": "D8AD1C43FD8C76F1EBDAD11C85D494A474F9CFE9F83AF5F72F590AE3852315A2",
28
+ "last_write_time": "2026-06-05T23:31:26"
29
+ },
30
+ {
31
+ "path": "generation_config.json",
32
+ "size_bytes": 199,
33
+ "size_gib": 0,
34
+ "sha256": "4667A99763A8A867921429B113A4BDC0E9942D878A51C95F673CCD12355C471D",
35
+ "last_write_time": "2026-06-05T13:35:46"
36
+ },
37
+ {
38
+ "path": "model.safetensors.index.json",
39
+ "size_bytes": 33261,
40
+ "size_gib": 0,
41
+ "sha256": "646973887378A236D3CF81292DE5CD631218B940EC0AECF03A16F57890572EFC",
42
+ "last_write_time": "2026-06-05T13:35:46"
43
+ },
44
+ {
45
+ "path": "model-00001-of-00003.safetensors",
46
+ "size_bytes": 3981503976,
47
+ "size_gib": 3.708,
48
+ "sha256": "C4D12692AE5CEFA9B7E61C2A581062F6B4B06183165EB2BCEEE9E11F26B82308",
49
+ "last_write_time": "2026-06-05T13:35:43"
50
+ },
51
+ {
52
+ "path": "model-00002-of-00003.safetensors",
53
+ "size_bytes": 3961229704,
54
+ "size_gib": 3.689,
55
+ "sha256": "93A4CAF2F35B815178DB5CE43C9FD5E06E3EF836F5CBEEE7C690961D95DA653B",
56
+ "last_write_time": "2026-06-05T13:35:46"
57
+ },
58
+ {
59
+ "path": "model-00003-of-00003.safetensors",
60
+ "size_bytes": 102247928,
61
+ "size_gib": 0.095,
62
+ "sha256": "4B3EF3D52BCAD649213FD2035D94DF48CBF2FD670250EC1FD8E1748072ECDBF2",
63
+ "last_write_time": "2026-06-05T13:35:46"
64
+ },
65
+ {
66
+ "path": "README.md",
67
+ "size_bytes": 6895,
68
+ "size_gib": 0,
69
+ "sha256": "AF0D74388A53EF4A9B37CF98B05922F1D5D3A888C1C6BBB95D883D89AC423760",
70
+ "last_write_time": "2026-06-06T01:54:57"
71
+ },
72
+ {
73
+ "path": "tokenizer.json",
74
+ "size_bytes": 11422650,
75
+ "size_gib": 0.011,
76
+ "sha256": "BE75606093DB2094D7CD20F3C2F385C212750648BD6EA4FB2BF507A6A4C55506",
77
+ "last_write_time": "2026-06-05T13:35:46"
78
+ },
79
+ {
80
+ "path": "tokenizer_config.json",
81
+ "size_bytes": 724,
82
+ "size_gib": 0,
83
+ "sha256": "154E5FF1E7C152D964EDF30DA854EA62465C767719AC8E97E58BABF2D4FA9079",
84
+ "last_write_time": "2026-06-05T13:35:46"
85
+ },
86
+ {
87
+ "path": "V6_SYSTEM_PROMPT.md",
88
+ "size_bytes": 1617,
89
+ "size_gib": 0,
90
+ "sha256": "34126E2486E389F28C11693C2E51641199FB5B53E3E7D6BFA75A6E967C11D3CF",
91
+ "last_write_time": "2026-05-30T07:33:27"
92
+ }
93
+ ],
94
+ "ggufs": [
95
+
96
+ ],
97
+ "evidence": [
98
+ {
99
+ "path": "evidence/gallery_z_image_engineer_v6_simple_ab_with_rewrites_CONTACT.png",
100
+ "size_bytes": 6174098,
101
+ "size_gib": 0.006,
102
+ "sha256": "D8AD1C43FD8C76F1EBDAD11C85D494A474F9CFE9F83AF5F72F590AE3852315A2",
103
+ "last_write_time": "2026-06-05T23:31:26"
104
+ }
105
+ ],
106
+ "generated_at_local": "2026-06-06T01:55:59",
107
+ "upload_approved_by_user": true
108
+ }
V6_SYSTEM_PROMPT.md ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Z-Image-Engineer V6 System Prompt
2
+
3
+ Base model: `Tongyi-MAI/Z-Image-Turbo/text_encoder`
4
+
5
+ Tokenizer: `Tongyi-MAI/Z-Image-Turbo/tokenizer`
6
+
7
+ Output contract: one prompt-only paragraph.
8
+
9
+ ```text
10
+ You are Z-Image-Engineer V6, a prompt-only cinematography and visual-language specialist for the Tongyi-MAI Z-Image-Turbo Qwen text encoder. Convert the user's seed into one polished natural-language image prompt that the text encoder can bind cleanly to the diffusion model. Preserve every explicit subject, object, relationship, count, name, written word, action, style request, composition constraint, and safety constraint from the seed. Use positive constraints: describe what must appear and how it should look, instead of writing negative-prompt fragments. Keep compact constraint phrases contiguous when possible, such as written text, counts, colors, named objects, and spatial terms; do not hide them by inserting extra adjectives inside the phrase. Build the prompt around semantic cinematography: clear visual hierarchy, foreground/midground/background relationships, lens and depth cues, lighting direction and quality, material texture, color palette, atmosphere, era, medium, and controlled style language. Prefer coherent sentences over tag soup, keyword stacks, markdown, analysis, or meta commentary. Never include camera body brands, prompt labels, alternatives, apologies, reasoning traces, assistant chatter, or negative prompt sections. Aim for roughly 180-250 words unless the user explicitly asks for a shorter or longer prompt. Return only the final image prompt as one self-contained paragraph.
11
+ ```
chat_template.jinja ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 message.content is string 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.content is string %}
27
+ {%- set content = message.content %}
28
+ {%- else %}
29
+ {%- set content = '' %}
30
+ {%- endif %}
31
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
32
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
33
+ {%- elif message.role == "assistant" %}
34
+ {%- set reasoning_content = '' %}
35
+ {%- if message.reasoning_content is string %}
36
+ {%- set reasoning_content = message.reasoning_content %}
37
+ {%- else %}
38
+ {%- if '</think>' in content %}
39
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
40
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
41
+ {%- endif %}
42
+ {%- endif %}
43
+ {%- if loop.index0 > ns.last_query_index %}
44
+ {%- if loop.last or (not loop.last and reasoning_content) %}
45
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
46
+ {%- else %}
47
+ {{- '<|im_start|>' + message.role + '\n' + content }}
48
+ {%- endif %}
49
+ {%- else %}
50
+ {{- '<|im_start|>' + message.role + '\n' + content }}
51
+ {%- endif %}
52
+ {%- if message.tool_calls %}
53
+ {%- for tool_call in message.tool_calls %}
54
+ {%- if (loop.first and content) or (not loop.first) %}
55
+ {{- '\n' }}
56
+ {%- endif %}
57
+ {%- if tool_call.function %}
58
+ {%- set tool_call = tool_call.function %}
59
+ {%- endif %}
60
+ {{- '<tool_call>\n{"name": "' }}
61
+ {{- tool_call.name }}
62
+ {{- '", "arguments": ' }}
63
+ {%- if tool_call.arguments is string %}
64
+ {{- tool_call.arguments }}
65
+ {%- else %}
66
+ {{- tool_call.arguments | tojson }}
67
+ {%- endif %}
68
+ {{- '}\n</tool_call>' }}
69
+ {%- endfor %}
70
+ {%- endif %}
71
+ {{- '<|im_end|>\n' }}
72
+ {%- elif message.role == "tool" %}
73
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
74
+ {{- '<|im_start|>user' }}
75
+ {%- endif %}
76
+ {{- '\n<tool_response>\n' }}
77
+ {{- content }}
78
+ {{- '\n</tool_response>' }}
79
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
80
+ {{- '<|im_end|>\n' }}
81
+ {%- endif %}
82
+ {%- endif %}
83
+ {%- endfor %}
84
+ {%- if add_generation_prompt %}
85
+ {{- '<|im_start|>assistant\n' }}
86
+ {%- if enable_thinking is defined and enable_thinking is false %}
87
+ {{- '<think>\n\n</think>\n\n' }}
88
+ {%- endif %}
89
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "dtype": "float16",
9
+ "eos_token_id": 151645,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2560,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 9728,
15
+ "layer_types": [
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
+ ],
53
+ "max_position_embeddings": 40960,
54
+ "max_window_layers": 36,
55
+ "model_type": "qwen3",
56
+ "num_attention_heads": 32,
57
+ "num_hidden_layers": 36,
58
+ "num_key_value_heads": 8,
59
+ "pad_token_id": null,
60
+ "rms_norm_eps": 1e-06,
61
+ "rope_parameters": {
62
+ "rope_theta": 1000000,
63
+ "rope_type": "default"
64
+ },
65
+ "sliding_window": null,
66
+ "tie_word_embeddings": true,
67
+ "transformers_version": "5.7.0",
68
+ "use_cache": true,
69
+ "use_sliding_window": false,
70
+ "vocab_size": 151936
71
+ }
evidence/gallery_z_image_engineer_v6_simple_ab_with_rewrites_CONTACT.png ADDED

Git LFS Details

  • SHA256: d8ad1c43fd8c76f1ebdad11c85d494a474f9cfe9f83af5f72f590ae3852315a2
  • Pointer size: 132 Bytes
  • Size of remote file: 6.17 MB
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": 151645,
4
+ "max_new_tokens": 320,
5
+ "pad_token_id": 151643,
6
+ "temperature": 0.2,
7
+ "top_k": 40,
8
+ "top_p": 0.9,
9
+ "transformers_version": "5.7.0"
10
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4d12692ae5cefa9b7e61c2a581062f6b4b06183165eb2bceee9e11f26b82308
3
+ size 3981503976
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93a4caf2f35b815178db5ce43c9fd5e06e3ef836f5cbeee7c690961d95da653b
3
+ size 3961229704
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b3ef3d52bcad649213fd2035d94df48cbf2fd670250ec1fd8e1748072ecdbf2
3
+ size 102247928
model.safetensors.index.json ADDED
@@ -0,0 +1,406 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 4022468096,
4
+ "total_size": 8044936192
5
+ },
6
+ "weight_map": {
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
27
+ "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
28
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
30
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
31
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
32
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
33
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
34
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
35
+ "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
36
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
37
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
38
+ "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
39
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
40
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
41
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
42
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
43
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
44
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
45
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
46
+ "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
47
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
48
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
49
+ "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
50
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
51
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
52
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
53
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
54
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
55
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
56
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
57
+ "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
58
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
59
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
60
+ "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
61
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
62
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
63
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
64
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
65
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
66
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
67
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
68
+ "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
69
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
70
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
71
+ "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
72
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
73
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
74
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
75
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
76
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
77
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
78
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
79
+ "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
80
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
81
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
82
+ "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
83
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
84
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
85
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors",
86
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
87
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
88
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
89
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
90
+ "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
91
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
92
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
93
+ "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
94
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
117
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
118
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
119
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
120
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
121
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
122
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
123
+ "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
124
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
125
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
126
+ "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
129
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
136
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
138
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
139
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
140
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
141
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
142
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
143
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
144
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
145
+ "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
146
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
147
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
148
+ "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
149
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
150
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
151
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
152
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
153
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
154
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
155
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
156
+ "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
157
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
158
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
159
+ "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
160
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
161
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
162
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
163
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
164
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
165
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
166
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
167
+ "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
168
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
169
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
170
+ "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
171
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
172
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
173
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
174
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
175
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
176
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
177
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
178
+ "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
179
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
180
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
181
+ "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
182
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
183
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
184
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
185
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
186
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
187
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
188
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
189
+ "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
190
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
191
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
192
+ "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
193
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
194
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
195
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
196
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
197
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
198
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
199
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
200
+ "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
201
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
202
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
203
+ "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
204
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
205
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
206
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
207
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
208
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
209
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
210
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
211
+ "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
212
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
213
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
214
+ "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
215
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
216
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
217
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
218
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
219
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
220
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
221
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
222
+ "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
223
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
224
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
225
+ "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
226
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
227
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
228
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
229
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
230
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
231
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
232
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
233
+ "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
234
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
235
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
236
+ "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
237
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
238
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
239
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
240
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
241
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
242
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
243
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
244
+ "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
245
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
246
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
247
+ "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
248
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
249
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
250
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
251
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
252
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
253
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
254
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
255
+ "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
256
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
257
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
258
+ "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
259
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
260
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
261
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
262
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
263
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
264
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
265
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
266
+ "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
267
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
268
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
269
+ "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
271
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
272
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
273
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
274
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
275
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
276
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
277
+ "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
278
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
279
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
280
+ "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
281
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
282
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
283
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors",
284
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
285
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
286
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
287
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
288
+ "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
289
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
290
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
291
+ "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
292
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
293
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
294
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors",
295
+ "model.layers.32.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
296
+ "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
297
+ "model.layers.32.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
298
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
299
+ "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
300
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
301
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
302
+ "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
303
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
304
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
305
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors",
306
+ "model.layers.33.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
307
+ "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
308
+ "model.layers.33.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
309
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
310
+ "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
311
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
312
+ "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
313
+ "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
314
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
315
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
316
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors",
317
+ "model.layers.34.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
318
+ "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
319
+ "model.layers.34.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
320
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
321
+ "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
322
+ "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
323
+ "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
324
+ "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
325
+ "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
326
+ "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
327
+ "model.layers.35.input_layernorm.weight": "model-00002-of-00003.safetensors",
328
+ "model.layers.35.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
329
+ "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
330
+ "model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
331
+ "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
332
+ "model.layers.35.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
333
+ "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
334
+ "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
335
+ "model.layers.35.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
336
+ "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
337
+ "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
338
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
339
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
340
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
341
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
342
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
343
+ "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
344
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
345
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
346
+ "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
347
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
348
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
349
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
350
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
351
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
352
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
353
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
354
+ "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
355
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
356
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
357
+ "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
358
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
359
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
360
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
361
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
362
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
363
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
364
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
365
+ "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
366
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
367
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
368
+ "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
369
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
370
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
371
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
372
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
373
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
374
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
375
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
376
+ "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
377
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
378
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
379
+ "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
380
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
381
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
382
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
383
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
384
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
385
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
386
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
387
+ "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
388
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
389
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
390
+ "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
391
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
392
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
393
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
394
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
395
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
396
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
397
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
398
+ "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
399
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
400
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
401
+ "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
402
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
403
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
404
+ "model.norm.weight": "model-00003-of-00003.safetensors"
405
+ }
406
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
3
+ size 11422650
tokenizer_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|im_start|>",
10
+ "<|im_end|>",
11
+ "<|object_ref_start|>",
12
+ "<|object_ref_end|>",
13
+ "<|box_start|>",
14
+ "<|box_end|>",
15
+ "<|quad_start|>",
16
+ "<|quad_end|>",
17
+ "<|vision_start|>",
18
+ "<|vision_end|>",
19
+ "<|vision_pad|>",
20
+ "<|image_pad|>",
21
+ "<|video_pad|>"
22
+ ],
23
+ "is_local": false,
24
+ "local_files_only": false,
25
+ "model_max_length": 131072,
26
+ "pad_token": "<|endoftext|>",
27
+ "split_special_tokens": false,
28
+ "tokenizer_class": "Qwen2Tokenizer",
29
+ "unk_token": null
30
+ }