Commit ·
131433a
0
Parent(s):
Duplicate from crownelius/Crow-9B-Opus-4.6-Distill-Heretic_Qwen3.5
Browse filesCo-authored-by: Shane <crownelius@users.noreply.huggingface.co>
- .gitattributes +41 -0
- Qwen3.5-9B-heretic-v2.BF16-mmproj.gguf +3 -0
- Qwen3.5-9B-heretic-v2.F16.gguf +3 -0
- Qwen3.5-9B-heretic-v2.Q4_K_M.gguf +3 -0
- Qwen3.5-9B-heretic-v2.Q5_K_M.gguf +3 -0
- Qwen3.5-9B-heretic-v2.Q8_0.gguf +3 -0
- README.md +223 -0
- banner.png +0 -0
- chat_template.jinja +154 -0
- config.json +112 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +768 -0
- processor_config.json +63 -0
- tokenizer.json +3 -0
- tokenizer_config.json +34 -0
.gitattributes
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
Qwen3.5-9B-heretic-v2.F16.gguf filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
Qwen3.5-9B-heretic-v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
Qwen3.5-9B-heretic-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
Qwen3.5-9B-heretic-v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
Qwen3.5-9B-heretic-v2.BF16-mmproj.gguf filter=lfs diff=lfs merge=lfs -text
|
Qwen3.5-9B-heretic-v2.BF16-mmproj.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce02ff3e11d9294561402067a0cdb4ef8d16d5f56d458205af03177d9992156d
|
| 3 |
+
size 921704576
|
Qwen3.5-9B-heretic-v2.F16.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72c1a716660d99e51c4763161e98001d039141912af227235617115441c95222
|
| 3 |
+
size 17920696832
|
Qwen3.5-9B-heretic-v2.Q4_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7e71023c6dd43a6aad9ca2c66aee487dcf20db301dedbdbe3d0075a51daf43a
|
| 3 |
+
size 5627044352
|
Qwen3.5-9B-heretic-v2.Q5_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:302c490de6438a701edd94aa517ad0bf698e686f81419f2df0fed4a79067a752
|
| 3 |
+
size 6522003968
|
Qwen3.5-9B-heretic-v2.Q8_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97691e870e785731676a2e4ee6f936a1d9858271385ce2414b0592c36dd2e787
|
| 3 |
+
size 9527501312
|
README.md
ADDED
|
@@ -0,0 +1,223 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
datasets:
|
| 3 |
+
- crownelius/Creative_Writing_ShareGPT_Enhanced
|
| 4 |
+
- microsoft/rStar-Coder
|
| 5 |
+
- peteromallet/dataclaw-peteromallet
|
| 6 |
+
- crownelius/Opus-4.6-Reasoning-3300x
|
| 7 |
+
- openbmb/UltraData-Math
|
| 8 |
+
- Unreleased/Dataset
|
| 9 |
+
base_model:
|
| 10 |
+
- trohrbaugh/Qwen3.5-9B-heretic-v2
|
| 11 |
+
tags:
|
| 12 |
+
- agent
|
| 13 |
+
license: apache-2.0
|
| 14 |
+
language:
|
| 15 |
+
- en
|
| 16 |
+
- zh
|
| 17 |
+
- ru
|
| 18 |
+
- es
|
| 19 |
+
- fr
|
| 20 |
+
- it
|
| 21 |
+
- ja
|
| 22 |
+
- ko
|
| 23 |
+
- af
|
| 24 |
+
- de
|
| 25 |
+
- ar
|
| 26 |
+
- tr
|
| 27 |
+
- is
|
| 28 |
+
- pl
|
| 29 |
+
- sw
|
| 30 |
+
- sv
|
| 31 |
+
- nl
|
| 32 |
+
- he
|
| 33 |
+
- id
|
| 34 |
+
- uk
|
| 35 |
+
- fa
|
| 36 |
+
- pa
|
| 37 |
+
- pt
|
| 38 |
+
- ms
|
| 39 |
+
- fi
|
| 40 |
+
- el
|
| 41 |
+
---
|
| 42 |
+
[<img src="https://huggingface.co/crownelius/Crow-9B-Opus-4.6-Distill-Heretic_Qwen3.5/resolve/main/banner.png" width="350"/>](https://ko-fi.com/abcuo)
|
| 43 |
+
CROW HAS REACHED THE FIRST PAGE OF HUGGINGFACE TRENDING MODELS! THANK YOU SO MUCH!!! NUMBER 15 IN THE WORLD!!!
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
# 🪶 CROW-9B
|
| 47 |
+
> **Flagship Intelligence. Featherweight Footprint.**
|
| 48 |
+
> *Meticulously distilled from Claude Opus 4.6 into a highly efficient Qwen 3.5 architecture.*
|
| 49 |
+
|
| 50 |
+
---
|
| 51 |
+
|
| 52 |
+
**`Architecture:`** `Qwen 3.5` | **`Parameters:`** `9 Billion` | **`Teacher Model:`** `Claude Opus 4.6` | **`Type:`** `Distilled LLM`
|
| 53 |
+
|
| 54 |
+
---
|
| 55 |
+
|
| 56 |
+
### 🌟 Model Highlights
|
| 57 |
+
* **Distilled Excellence:** Captures the deep reasoning, nuanced formatting, and instruction-following capabilities of Claude Opus 4.6.
|
| 58 |
+
* **Highly Agile:** At just 9B parameters, Crow runs efficiently on consumer-grade GPUs and edge devices without sacrificing contextual depth.
|
| 59 |
+
* **Qwen 3.5 Backbone:** Inherits robust multilingual support, a massive context window, and structural stability.
|
| 60 |
+
|
| 61 |
+
--- Generating this model was expensive. You can support this one and future models by tipping. https://ko-fi.com/abcuo
|
| 62 |
+
|
| 63 |
+
## Available Model files:
|
| 64 |
+
- `Qwen3.5-9B-heretic-v2.F16.gguf`
|
| 65 |
+
- `Qwen3.5-9B-heretic-v2.Q8_0.gguf`
|
| 66 |
+
- `Qwen3.5-9B-heretic-v2.Q5_K_M.gguf`
|
| 67 |
+
- `Qwen3.5-9B-heretic-v2.Q4_K_M.gguf`
|
| 68 |
+
- `Qwen3.5-9B-heretic-v2.BF16-mmproj.gguf`
|
| 69 |
+
|
| 70 |
+
## User Guide
|
| 71 |
+
|
| 72 |
+
### Recommended System Prompt
|
| 73 |
+
|
| 74 |
+
Default system prompt:
|
| 75 |
+
|
| 76 |
+
```text
|
| 77 |
+
You are Crow, a precise and capable assistant for reasoning, writing, coding, and long-form dialogue.
|
| 78 |
+
|
| 79 |
+
Behavior rules:
|
| 80 |
+
- Answer the user's actual request directly.
|
| 81 |
+
- Be accurate, complete, and structured.
|
| 82 |
+
- Think before answering, but do not get stuck in repetitive loops or meta-commentary.
|
| 83 |
+
- If the request is ambiguous or incomplete, state what is missing and make the smallest reasonable assumption needed to continue.
|
| 84 |
+
- If the user wants creative writing, preserve tone, continuity, and character consistency.
|
| 85 |
+
- If the user wants analysis or technical help, prefer concrete steps, examples, and decisions over fluff.
|
| 86 |
+
- Finish with a usable answer, not just planning.
|
| 87 |
+
```
|
| 88 |
+
|
| 89 |
+
Shorter fallback system prompt:
|
| 90 |
+
|
| 91 |
+
```text
|
| 92 |
+
You are Crow. Give direct, useful answers. Keep reasoning concise. Do not loop, do not repeat yourself, and do not pad. If context is missing, say what is missing in one sentence and continue with the best reasonable assumption.
|
| 93 |
+
```
|
| 94 |
+
|
| 95 |
+
### Install & Dependencies
|
| 96 |
+
|
| 97 |
+
#### LM Studio
|
| 98 |
+
|
| 99 |
+
1. Install LM Studio from `https://lmstudio.ai/`.
|
| 100 |
+
2. Download one of the GGUF files from the Files tab for this repo.
|
| 101 |
+
3. Pick a quant based on your hardware:
|
| 102 |
+
- `Q4_K_M`: lowest memory use
|
| 103 |
+
- `Q5_K_M`: best default for most users
|
| 104 |
+
- `Q8_0`: stronger quality, higher memory use
|
| 105 |
+
- `F16`: best quality, highest memory use
|
| 106 |
+
4. Load the GGUF in LM Studio.
|
| 107 |
+
5. If you need image support in a compatible GGUF runtime, also download the paired `mmproj` file.
|
| 108 |
+
|
| 109 |
+
Dependencies:
|
| 110 |
+
|
| 111 |
+
- A current LM Studio build
|
| 112 |
+
- Enough disk space for the model and cache
|
| 113 |
+
- Enough RAM / VRAM for your selected quant
|
| 114 |
+
- Current GPU drivers if you want GPU offload
|
| 115 |
+
|
| 116 |
+
#### Ollama
|
| 117 |
+
|
| 118 |
+
1. Install Ollama from `https://docs.ollama.com/quickstart`.
|
| 119 |
+
2. Download a Crow 9B GGUF from this repo.
|
| 120 |
+
3. Place the GGUF in its own folder.
|
| 121 |
+
4. Create a `Modelfile`.
|
| 122 |
+
5. Build the model with `ollama create`.
|
| 123 |
+
|
| 124 |
+
Dependencies:
|
| 125 |
+
|
| 126 |
+
- A current Ollama release
|
| 127 |
+
- Enough disk space for the GGUF and Ollama model store
|
| 128 |
+
- Enough RAM / VRAM for your selected quant
|
| 129 |
+
- Current GPU drivers if you want GPU acceleration
|
| 130 |
+
|
| 131 |
+
### Good LM Studio Settings
|
| 132 |
+
|
| 133 |
+
Recommended starting points:
|
| 134 |
+
|
| 135 |
+
| Use case | Temperature | Top P | Top K | Repeat penalty | Context | Max tokens |
|
| 136 |
+
|---|---:|---:|---:|---:|---:|---:|
|
| 137 |
+
| General / reasoning | 0.6 | 0.95 | 20 | 1.05 | 16384 | 4096 |
|
| 138 |
+
| Creative writing / roleplay | 0.8 | 0.95 | 40 | 1.02 | 16384-32768 | 4096-8192 |
|
| 139 |
+
|
| 140 |
+
Notes:
|
| 141 |
+
|
| 142 |
+
- Start with `Q5_K_M` unless you have a reason to use a different quant.
|
| 143 |
+
- Lower temperature if you see rambling or unstable reasoning.
|
| 144 |
+
- Do not max out context by default. Larger contexts cost more memory and can make long chats less stable on weaker hardware.
|
| 145 |
+
|
| 146 |
+
### Good Ollama Settings
|
| 147 |
+
|
| 148 |
+
Example `Modelfile`:
|
| 149 |
+
|
| 150 |
+
```text
|
| 151 |
+
FROM ./Qwen3.5-9B-heretic-v2.Q5_K_M.gguf
|
| 152 |
+
|
| 153 |
+
PARAMETER num_ctx 16384
|
| 154 |
+
PARAMETER temperature 0.6
|
| 155 |
+
PARAMETER top_p 0.95
|
| 156 |
+
PARAMETER top_k 20
|
| 157 |
+
PARAMETER repeat_penalty 1.05
|
| 158 |
+
PARAMETER repeat_last_n 256
|
| 159 |
+
|
| 160 |
+
SYSTEM """
|
| 161 |
+
You are Crow, a precise and capable assistant for reasoning, writing, coding, and long-form dialogue.
|
| 162 |
+
Answer directly, stay coherent, avoid repetitive thinking loops, and finish with a complete answer.
|
| 163 |
+
If context is missing, identify the gap briefly and continue with the best reasonable assumption.
|
| 164 |
+
"""
|
| 165 |
+
```
|
| 166 |
+
|
| 167 |
+
Build and run:
|
| 168 |
+
|
| 169 |
+
```bash
|
| 170 |
+
ollama create crow-9b -f Modelfile
|
| 171 |
+
ollama run crow-9b
|
| 172 |
+
```
|
| 173 |
+
|
| 174 |
+
For more creative outputs, raise `temperature` to `0.8`, raise `top_k` to `40`, and reduce `repeat_penalty` slightly to `1.02`.
|
| 175 |
+
|
| 176 |
+
### If You Hit a Thinking Loop
|
| 177 |
+
|
| 178 |
+
If the model starts looping inside `<think>` tags, repeating analysis, or stalling:
|
| 179 |
+
|
| 180 |
+
1. Stop generation.
|
| 181 |
+
2. Retry with a lower temperature, ideally `0.4` to `0.6`.
|
| 182 |
+
3. Increase repeat penalty slightly, for example from `1.05` to `1.08`.
|
| 183 |
+
4. Add an instruction like:
|
| 184 |
+
|
| 185 |
+
```text
|
| 186 |
+
Answer directly. Keep reasoning brief. Do not repeat analysis. Give the final answer.
|
| 187 |
+
```
|
| 188 |
+
|
| 189 |
+
5. Start a fresh chat if the current conversation has become unstable.
|
| 190 |
+
6. If the problem happens mostly on lower quants, move up to `Q8_0` or `F16`.
|
| 191 |
+
|
| 192 |
+
### If the Prompt Is Incomplete or the Output Cuts Off
|
| 193 |
+
|
| 194 |
+
If the prompt is incomplete or malformed:
|
| 195 |
+
|
| 196 |
+
1. Clean it before sending it.
|
| 197 |
+
2. Remove broken tags, clipped instructions, or half-finished bullets.
|
| 198 |
+
3. If only partial context is available, prepend:
|
| 199 |
+
|
| 200 |
+
```text
|
| 201 |
+
If context is missing, state your assumptions briefly and continue with the most likely intended task.
|
| 202 |
+
```
|
| 203 |
+
|
| 204 |
+
If the output cuts off:
|
| 205 |
+
|
| 206 |
+
1. Increase max tokens.
|
| 207 |
+
2. Ask:
|
| 208 |
+
|
| 209 |
+
```text
|
| 210 |
+
Continue from the last complete sentence. Do not restart or summarize. Continue exactly where you stopped.
|
| 211 |
+
```
|
| 212 |
+
|
| 213 |
+
3. If it still restarts instead of continuing, begin a fresh chat and resend the prompt with the desired output format stated more explicitly.
|
| 214 |
+
|
| 215 |
+
### Prompting Tips
|
| 216 |
+
|
| 217 |
+
- State the exact deliverable: list, table, code, rewrite, draft, critique, or decision.
|
| 218 |
+
- For coding, specify language, runtime, and expected input/output.
|
| 219 |
+
- For creative writing, specify tone, genre, constraints, and point of view up front.
|
| 220 |
+
- For high-control tasks, say whether you want concise output, full reasoning, or final answer only.
|
| 221 |
+
|
| 222 |
+
This was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth)
|
| 223 |
+
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
banner.png
ADDED
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set image_count = namespace(value=0) %}
|
| 2 |
+
{%- set video_count = namespace(value=0) %}
|
| 3 |
+
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 4 |
+
{%- if content is string %}
|
| 5 |
+
{{- content }}
|
| 6 |
+
{%- elif content is iterable and content is not mapping %}
|
| 7 |
+
{%- for item in content %}
|
| 8 |
+
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
+
{%- if is_system_content %}
|
| 10 |
+
{{- raise_exception('System message cannot contain images.') }}
|
| 11 |
+
{%- endif %}
|
| 12 |
+
{%- if do_vision_count %}
|
| 13 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{%- if add_vision_id %}
|
| 16 |
+
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 19 |
+
{%- elif 'video' in item or item.type == 'video' %}
|
| 20 |
+
{%- if is_system_content %}
|
| 21 |
+
{{- raise_exception('System message cannot contain videos.') }}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if do_vision_count %}
|
| 24 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
{%- if add_vision_id %}
|
| 27 |
+
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 30 |
+
{%- elif 'text' in item %}
|
| 31 |
+
{{- item.text }}
|
| 32 |
+
{%- else %}
|
| 33 |
+
{{- raise_exception('Unexpected item type in content.') }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endfor %}
|
| 36 |
+
{%- elif content is none or content is undefined %}
|
| 37 |
+
{{- '' }}
|
| 38 |
+
{%- else %}
|
| 39 |
+
{{- raise_exception('Unexpected content type.') }}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endmacro %}
|
| 42 |
+
{%- if not messages %}
|
| 43 |
+
{{- raise_exception('No messages provided.') }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- if tools and tools is iterable and tools is not mapping %}
|
| 46 |
+
{{- '<|im_start|>system\n' }}
|
| 47 |
+
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 48 |
+
{%- for tool in tools %}
|
| 49 |
+
{{- "\n" }}
|
| 50 |
+
{{- tool | tojson }}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{{- "\n</tools>" }}
|
| 53 |
+
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 54 |
+
{%- if messages[0].role == 'system' %}
|
| 55 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 56 |
+
{%- if content %}
|
| 57 |
+
{{- '\n\n' + content }}
|
| 58 |
+
{%- endif %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<|im_end|>\n' }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{%- if messages[0].role == 'system' %}
|
| 63 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 64 |
+
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
|
| 65 |
+
{%- endif %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 68 |
+
{%- for message in messages[::-1] %}
|
| 69 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 70 |
+
{%- if ns.multi_step_tool and message.role == "user" %}
|
| 71 |
+
{%- set content = render_content(message.content, false)|trim %}
|
| 72 |
+
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
|
| 73 |
+
{%- set ns.multi_step_tool = false %}
|
| 74 |
+
{%- set ns.last_query_index = index %}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{%- endif %}
|
| 77 |
+
{%- endfor %}
|
| 78 |
+
{%- if ns.multi_step_tool %}
|
| 79 |
+
{{- raise_exception('No user query found in messages.') }}
|
| 80 |
+
{%- endif %}
|
| 81 |
+
{%- for message in messages %}
|
| 82 |
+
{%- set content = render_content(message.content, true)|trim %}
|
| 83 |
+
{%- if message.role == "system" %}
|
| 84 |
+
{%- if not loop.first %}
|
| 85 |
+
{{- raise_exception('System message must be at the beginning.') }}
|
| 86 |
+
{%- endif %}
|
| 87 |
+
{%- elif message.role == "user" %}
|
| 88 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 89 |
+
{%- elif message.role == "assistant" %}
|
| 90 |
+
{%- set reasoning_content = '' %}
|
| 91 |
+
{%- if message.reasoning_content is string %}
|
| 92 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 93 |
+
{%- else %}
|
| 94 |
+
{%- if '</think>' in content %}
|
| 95 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 96 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 97 |
+
{%- endif %}
|
| 98 |
+
{%- endif %}
|
| 99 |
+
{%- set reasoning_content = reasoning_content|trim %}
|
| 100 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 101 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 102 |
+
{%- else %}
|
| 103 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 104 |
+
{%- endif %}
|
| 105 |
+
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 106 |
+
{%- for tool_call in message.tool_calls %}
|
| 107 |
+
{%- if tool_call.function is defined %}
|
| 108 |
+
{%- set tool_call = tool_call.function %}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- if loop.first %}
|
| 111 |
+
{%- if content|trim %}
|
| 112 |
+
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 113 |
+
{%- else %}
|
| 114 |
+
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- else %}
|
| 117 |
+
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 118 |
+
{%- endif %}
|
| 119 |
+
{%- if tool_call.arguments is defined %}
|
| 120 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 121 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 122 |
+
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 123 |
+
{{- args_value }}
|
| 124 |
+
{{- '\n</parameter>\n' }}
|
| 125 |
+
{%- endfor %}
|
| 126 |
+
{%- endif %}
|
| 127 |
+
{{- '</function>\n</tool_call>' }}
|
| 128 |
+
{%- endfor %}
|
| 129 |
+
{%- endif %}
|
| 130 |
+
{{- '<|im_end|>\n' }}
|
| 131 |
+
{%- elif message.role == "tool" %}
|
| 132 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 133 |
+
{{- '<|im_start|>user' }}
|
| 134 |
+
{%- endif %}
|
| 135 |
+
{{- '\n<tool_response>\n' }}
|
| 136 |
+
{{- content }}
|
| 137 |
+
{{- '\n</tool_response>' }}
|
| 138 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 139 |
+
{{- '<|im_end|>\n' }}
|
| 140 |
+
{%- elif loop.last %}
|
| 141 |
+
{{- '<|im_end|>\n' }}
|
| 142 |
+
{%- endif %}
|
| 143 |
+
{%- else %}
|
| 144 |
+
{{- raise_exception('Unexpected message role.') }}
|
| 145 |
+
{%- endif %}
|
| 146 |
+
{%- endfor %}
|
| 147 |
+
{%- if add_generation_prompt %}
|
| 148 |
+
{{- '<|im_start|>assistant\n' }}
|
| 149 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 150 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 151 |
+
{%- else %}
|
| 152 |
+
{{- '<think>\n' }}
|
| 153 |
+
{%- endif %}
|
| 154 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"torch_dtype": "bfloat16",
|
| 6 |
+
"eos_token_id": 248046,
|
| 7 |
+
"image_token_id": 248056,
|
| 8 |
+
"model_type": "qwen3_5",
|
| 9 |
+
"pad_token_id": 248044,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"attention_bias": false,
|
| 12 |
+
"attention_dropout": 0.0,
|
| 13 |
+
"attn_output_gate": true,
|
| 14 |
+
"bos_token_id": null,
|
| 15 |
+
"torch_dtype": "bfloat16",
|
| 16 |
+
"eos_token_id": 248044,
|
| 17 |
+
"full_attention_interval": 4,
|
| 18 |
+
"head_dim": 256,
|
| 19 |
+
"hidden_act": "silu",
|
| 20 |
+
"hidden_size": 4096,
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 12288,
|
| 23 |
+
"layer_types": [
|
| 24 |
+
"linear_attention",
|
| 25 |
+
"linear_attention",
|
| 26 |
+
"linear_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"linear_attention",
|
| 29 |
+
"linear_attention",
|
| 30 |
+
"linear_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"linear_attention",
|
| 33 |
+
"linear_attention",
|
| 34 |
+
"linear_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"linear_attention",
|
| 37 |
+
"linear_attention",
|
| 38 |
+
"linear_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"linear_attention",
|
| 41 |
+
"linear_attention",
|
| 42 |
+
"linear_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"linear_attention",
|
| 45 |
+
"linear_attention",
|
| 46 |
+
"linear_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"linear_attention",
|
| 49 |
+
"linear_attention",
|
| 50 |
+
"linear_attention",
|
| 51 |
+
"full_attention",
|
| 52 |
+
"linear_attention",
|
| 53 |
+
"linear_attention",
|
| 54 |
+
"linear_attention",
|
| 55 |
+
"full_attention"
|
| 56 |
+
],
|
| 57 |
+
"linear_conv_kernel_dim": 4,
|
| 58 |
+
"linear_key_head_dim": 128,
|
| 59 |
+
"linear_num_key_heads": 16,
|
| 60 |
+
"linear_num_value_heads": 32,
|
| 61 |
+
"linear_value_head_dim": 128,
|
| 62 |
+
"mamba_ssm_dtype": "float32",
|
| 63 |
+
"max_position_embeddings": 262144,
|
| 64 |
+
"mlp_only_layers": [],
|
| 65 |
+
"model_type": "qwen3_5_text",
|
| 66 |
+
"mtp_num_hidden_layers": 1,
|
| 67 |
+
"mtp_use_dedicated_embeddings": false,
|
| 68 |
+
"num_attention_heads": 16,
|
| 69 |
+
"num_hidden_layers": 32,
|
| 70 |
+
"num_key_value_heads": 4,
|
| 71 |
+
"pad_token_id": null,
|
| 72 |
+
"partial_rotary_factor": 0.25,
|
| 73 |
+
"rms_norm_eps": 1e-06,
|
| 74 |
+
"rope_parameters": {
|
| 75 |
+
"mrope_interleaved": true,
|
| 76 |
+
"mrope_section": [
|
| 77 |
+
11,
|
| 78 |
+
11,
|
| 79 |
+
10
|
| 80 |
+
],
|
| 81 |
+
"partial_rotary_factor": 0.25,
|
| 82 |
+
"rope_theta": 10000000,
|
| 83 |
+
"rope_type": "default"
|
| 84 |
+
},
|
| 85 |
+
"tie_word_embeddings": false,
|
| 86 |
+
"use_cache": true,
|
| 87 |
+
"vocab_size": 248320
|
| 88 |
+
},
|
| 89 |
+
"tie_word_embeddings": false,
|
| 90 |
+
"unsloth_version": "2026.2.1",
|
| 91 |
+
"use_cache": false,
|
| 92 |
+
"video_token_id": 248057,
|
| 93 |
+
"vision_config": {
|
| 94 |
+
"deepstack_visual_indexes": [],
|
| 95 |
+
"depth": 27,
|
| 96 |
+
"torch_dtype": "bfloat16",
|
| 97 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 98 |
+
"hidden_size": 1152,
|
| 99 |
+
"in_channels": 3,
|
| 100 |
+
"initializer_range": 0.02,
|
| 101 |
+
"intermediate_size": 4304,
|
| 102 |
+
"model_type": "qwen3_5",
|
| 103 |
+
"num_heads": 16,
|
| 104 |
+
"num_position_embeddings": 2304,
|
| 105 |
+
"out_hidden_size": 4096,
|
| 106 |
+
"patch_size": 16,
|
| 107 |
+
"spatial_merge_size": 2,
|
| 108 |
+
"temporal_patch_size": 2
|
| 109 |
+
},
|
| 110 |
+
"vision_end_token_id": 248054,
|
| 111 |
+
"vision_start_token_id": 248053
|
| 112 |
+
}
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6193b1a1239bbfa2fd5624867d092b7a9aeeafe9896d10c19cabd1c9d1f2d1f0
|
| 3 |
+
size 9930464136
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39bb73a52f816d7f8aaac973c2d3e168be5f2976e27d1e8fa324c2b46371d488
|
| 3 |
+
size 8889257096
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,768 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 9409813744,
|
| 4 |
+
"total_size": 18819627488
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.language_model.layers.0.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.language_model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.language_model.layers.0.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.language_model.layers.0.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.language_model.layers.1.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.language_model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.language_model.layers.1.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.language_model.layers.1.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.language_model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.language_model.layers.10.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.language_model.layers.10.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.language_model.layers.10.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.language_model.layers.10.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.language_model.layers.10.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.language_model.layers.12.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.language_model.layers.12.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.language_model.layers.12.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.language_model.layers.12.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.language_model.layers.12.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.language_model.layers.13.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.language_model.layers.13.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.language_model.layers.13.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.language_model.layers.13.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.language_model.layers.13.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 88 |
+
"model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 89 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 90 |
+
"model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 91 |
+
"model.language_model.layers.14.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 92 |
+
"model.language_model.layers.14.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 93 |
+
"model.language_model.layers.14.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 94 |
+
"model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 95 |
+
"model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 96 |
+
"model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 97 |
+
"model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 98 |
+
"model.language_model.layers.14.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 99 |
+
"model.language_model.layers.14.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 100 |
+
"model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 101 |
+
"model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 102 |
+
"model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 103 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 104 |
+
"model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 105 |
+
"model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 106 |
+
"model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 107 |
+
"model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 108 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 109 |
+
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 110 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 111 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 112 |
+
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 113 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 114 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 115 |
+
"model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 116 |
+
"model.language_model.layers.16.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 117 |
+
"model.language_model.layers.16.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 118 |
+
"model.language_model.layers.16.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 119 |
+
"model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 120 |
+
"model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 121 |
+
"model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 122 |
+
"model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 123 |
+
"model.language_model.layers.16.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 124 |
+
"model.language_model.layers.16.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 125 |
+
"model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 126 |
+
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 127 |
+
"model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 128 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 129 |
+
"model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 130 |
+
"model.language_model.layers.17.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 131 |
+
"model.language_model.layers.17.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 132 |
+
"model.language_model.layers.17.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 133 |
+
"model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 134 |
+
"model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 135 |
+
"model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 136 |
+
"model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 137 |
+
"model.language_model.layers.17.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 138 |
+
"model.language_model.layers.17.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 139 |
+
"model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 140 |
+
"model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 141 |
+
"model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 142 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 143 |
+
"model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 144 |
+
"model.language_model.layers.18.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 145 |
+
"model.language_model.layers.18.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 146 |
+
"model.language_model.layers.18.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 147 |
+
"model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 148 |
+
"model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 149 |
+
"model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 150 |
+
"model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 151 |
+
"model.language_model.layers.18.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 152 |
+
"model.language_model.layers.18.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 153 |
+
"model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 154 |
+
"model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 155 |
+
"model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 156 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 157 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 158 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 159 |
+
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 160 |
+
"model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 161 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 162 |
+
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 163 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 165 |
+
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 167 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 168 |
+
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 169 |
+
"model.language_model.layers.2.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 170 |
+
"model.language_model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.language_model.layers.2.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 172 |
+
"model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 173 |
+
"model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 174 |
+
"model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 175 |
+
"model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.language_model.layers.2.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 177 |
+
"model.language_model.layers.2.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 178 |
+
"model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 179 |
+
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 181 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 182 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 183 |
+
"model.language_model.layers.20.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 184 |
+
"model.language_model.layers.20.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 185 |
+
"model.language_model.layers.20.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 186 |
+
"model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 187 |
+
"model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.language_model.layers.20.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"model.language_model.layers.20.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 197 |
+
"model.language_model.layers.21.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 198 |
+
"model.language_model.layers.21.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 199 |
+
"model.language_model.layers.21.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 200 |
+
"model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 203 |
+
"model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"model.language_model.layers.21.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 205 |
+
"model.language_model.layers.21.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 206 |
+
"model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 207 |
+
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 209 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 211 |
+
"model.language_model.layers.22.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 212 |
+
"model.language_model.layers.22.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 213 |
+
"model.language_model.layers.22.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 214 |
+
"model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 215 |
+
"model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 217 |
+
"model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 218 |
+
"model.language_model.layers.22.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 219 |
+
"model.language_model.layers.22.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 221 |
+
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 223 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 225 |
+
"model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 229 |
+
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 230 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 233 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 235 |
+
"model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"model.language_model.layers.24.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 237 |
+
"model.language_model.layers.24.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.language_model.layers.24.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 239 |
+
"model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 243 |
+
"model.language_model.layers.24.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 244 |
+
"model.language_model.layers.24.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 245 |
+
"model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 246 |
+
"model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 247 |
+
"model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 250 |
+
"model.language_model.layers.25.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 251 |
+
"model.language_model.layers.25.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 252 |
+
"model.language_model.layers.25.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 253 |
+
"model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 254 |
+
"model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 256 |
+
"model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 257 |
+
"model.language_model.layers.25.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 258 |
+
"model.language_model.layers.25.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 259 |
+
"model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 260 |
+
"model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 261 |
+
"model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 262 |
+
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 263 |
+
"model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 264 |
+
"model.language_model.layers.26.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 265 |
+
"model.language_model.layers.26.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 266 |
+
"model.language_model.layers.26.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 267 |
+
"model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 268 |
+
"model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 269 |
+
"model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 270 |
+
"model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 271 |
+
"model.language_model.layers.26.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 272 |
+
"model.language_model.layers.26.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 273 |
+
"model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 274 |
+
"model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 275 |
+
"model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 276 |
+
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 277 |
+
"model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 278 |
+
"model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 279 |
+
"model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 280 |
+
"model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 281 |
+
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 282 |
+
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 283 |
+
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 284 |
+
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 285 |
+
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 286 |
+
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 287 |
+
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 288 |
+
"model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 289 |
+
"model.language_model.layers.28.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 290 |
+
"model.language_model.layers.28.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 291 |
+
"model.language_model.layers.28.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 292 |
+
"model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 293 |
+
"model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 294 |
+
"model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 295 |
+
"model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 296 |
+
"model.language_model.layers.28.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 297 |
+
"model.language_model.layers.28.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 298 |
+
"model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 299 |
+
"model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 300 |
+
"model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 301 |
+
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 302 |
+
"model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 303 |
+
"model.language_model.layers.29.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 304 |
+
"model.language_model.layers.29.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 305 |
+
"model.language_model.layers.29.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 306 |
+
"model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 307 |
+
"model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 308 |
+
"model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 309 |
+
"model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 310 |
+
"model.language_model.layers.29.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 311 |
+
"model.language_model.layers.29.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 312 |
+
"model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 313 |
+
"model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 314 |
+
"model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 315 |
+
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 316 |
+
"model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 317 |
+
"model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 318 |
+
"model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 319 |
+
"model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 320 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 322 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 323 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 324 |
+
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 325 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 326 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 327 |
+
"model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 328 |
+
"model.language_model.layers.30.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 329 |
+
"model.language_model.layers.30.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 330 |
+
"model.language_model.layers.30.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 331 |
+
"model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 332 |
+
"model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 333 |
+
"model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 334 |
+
"model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 335 |
+
"model.language_model.layers.30.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 336 |
+
"model.language_model.layers.30.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 337 |
+
"model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 338 |
+
"model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 339 |
+
"model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 340 |
+
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 341 |
+
"model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 342 |
+
"model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 343 |
+
"model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 344 |
+
"model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 345 |
+
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 346 |
+
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 347 |
+
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 348 |
+
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 349 |
+
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 350 |
+
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 351 |
+
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 352 |
+
"model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 353 |
+
"model.language_model.layers.4.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 354 |
+
"model.language_model.layers.4.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 355 |
+
"model.language_model.layers.4.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 356 |
+
"model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"model.language_model.layers.4.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"model.language_model.layers.4.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 363 |
+
"model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 365 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 366 |
+
"model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 367 |
+
"model.language_model.layers.5.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 368 |
+
"model.language_model.layers.5.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.language_model.layers.5.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 372 |
+
"model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"model.language_model.layers.5.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.language_model.layers.5.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.language_model.layers.6.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.language_model.layers.6.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.language_model.layers.6.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 385 |
+
"model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.language_model.layers.6.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.language_model.layers.6.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 405 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 406 |
+
"model.language_model.layers.8.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 407 |
+
"model.language_model.layers.8.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 408 |
+
"model.language_model.layers.8.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 409 |
+
"model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 410 |
+
"model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 411 |
+
"model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 412 |
+
"model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 413 |
+
"model.language_model.layers.8.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 414 |
+
"model.language_model.layers.8.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 415 |
+
"model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 416 |
+
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 417 |
+
"model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 418 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 419 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 420 |
+
"model.language_model.layers.9.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 421 |
+
"model.language_model.layers.9.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 422 |
+
"model.language_model.layers.9.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 423 |
+
"model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 424 |
+
"model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 425 |
+
"model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 426 |
+
"model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 427 |
+
"model.language_model.layers.9.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 428 |
+
"model.language_model.layers.9.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 429 |
+
"model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 430 |
+
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 431 |
+
"model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 432 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 433 |
+
"model.language_model.norm.weight": "model-00002-of-00002.safetensors",
|
| 434 |
+
"model.visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 435 |
+
"model.visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 436 |
+
"model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 437 |
+
"model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 438 |
+
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 439 |
+
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 440 |
+
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 441 |
+
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 442 |
+
"model.visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors",
|
| 443 |
+
"model.visual.blocks.0.norm1.weight": "model-00002-of-00002.safetensors",
|
| 444 |
+
"model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors",
|
| 445 |
+
"model.visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors",
|
| 446 |
+
"model.visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 447 |
+
"model.visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 448 |
+
"model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 449 |
+
"model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 450 |
+
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 451 |
+
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 452 |
+
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 453 |
+
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 454 |
+
"model.visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors",
|
| 455 |
+
"model.visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors",
|
| 456 |
+
"model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors",
|
| 457 |
+
"model.visual.blocks.1.norm2.weight": "model-00002-of-00002.safetensors",
|
| 458 |
+
"model.visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 459 |
+
"model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 460 |
+
"model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 461 |
+
"model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 462 |
+
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 463 |
+
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 464 |
+
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 465 |
+
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 466 |
+
"model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
|
| 467 |
+
"model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
|
| 468 |
+
"model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors",
|
| 469 |
+
"model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors",
|
| 470 |
+
"model.visual.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 471 |
+
"model.visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 472 |
+
"model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 473 |
+
"model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 474 |
+
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 475 |
+
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 476 |
+
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 477 |
+
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 478 |
+
"model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors",
|
| 479 |
+
"model.visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors",
|
| 480 |
+
"model.visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors",
|
| 481 |
+
"model.visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors",
|
| 482 |
+
"model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 483 |
+
"model.visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 484 |
+
"model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 485 |
+
"model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 486 |
+
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 487 |
+
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 488 |
+
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 489 |
+
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 490 |
+
"model.visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors",
|
| 491 |
+
"model.visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors",
|
| 492 |
+
"model.visual.blocks.12.norm2.bias": "model-00002-of-00002.safetensors",
|
| 493 |
+
"model.visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors",
|
| 494 |
+
"model.visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 495 |
+
"model.visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 496 |
+
"model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 497 |
+
"model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 498 |
+
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 499 |
+
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 500 |
+
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 501 |
+
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 502 |
+
"model.visual.blocks.13.norm1.bias": "model-00002-of-00002.safetensors",
|
| 503 |
+
"model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors",
|
| 504 |
+
"model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors",
|
| 505 |
+
"model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors",
|
| 506 |
+
"model.visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 507 |
+
"model.visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 508 |
+
"model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 509 |
+
"model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 510 |
+
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 511 |
+
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 512 |
+
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 513 |
+
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 514 |
+
"model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors",
|
| 515 |
+
"model.visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors",
|
| 516 |
+
"model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors",
|
| 517 |
+
"model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors",
|
| 518 |
+
"model.visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 519 |
+
"model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 520 |
+
"model.visual.blocks.15.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 521 |
+
"model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 522 |
+
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 523 |
+
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 524 |
+
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 525 |
+
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 526 |
+
"model.visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors",
|
| 527 |
+
"model.visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors",
|
| 528 |
+
"model.visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors",
|
| 529 |
+
"model.visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors",
|
| 530 |
+
"model.visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 531 |
+
"model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 532 |
+
"model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 533 |
+
"model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 534 |
+
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 535 |
+
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 536 |
+
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 537 |
+
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 538 |
+
"model.visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors",
|
| 539 |
+
"model.visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors",
|
| 540 |
+
"model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors",
|
| 541 |
+
"model.visual.blocks.16.norm2.weight": "model-00002-of-00002.safetensors",
|
| 542 |
+
"model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 543 |
+
"model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 544 |
+
"model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 545 |
+
"model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 546 |
+
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 547 |
+
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 548 |
+
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 549 |
+
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 550 |
+
"model.visual.blocks.17.norm1.bias": "model-00002-of-00002.safetensors",
|
| 551 |
+
"model.visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors",
|
| 552 |
+
"model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
|
| 553 |
+
"model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors",
|
| 554 |
+
"model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 555 |
+
"model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 556 |
+
"model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 557 |
+
"model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 558 |
+
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 559 |
+
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 560 |
+
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 561 |
+
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 562 |
+
"model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors",
|
| 563 |
+
"model.visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors",
|
| 564 |
+
"model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
|
| 565 |
+
"model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors",
|
| 566 |
+
"model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 567 |
+
"model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 568 |
+
"model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 569 |
+
"model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 570 |
+
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 571 |
+
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 572 |
+
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 573 |
+
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 574 |
+
"model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors",
|
| 575 |
+
"model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
|
| 576 |
+
"model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
|
| 577 |
+
"model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors",
|
| 578 |
+
"model.visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 579 |
+
"model.visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 580 |
+
"model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 581 |
+
"model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 582 |
+
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 583 |
+
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 584 |
+
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 585 |
+
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 586 |
+
"model.visual.blocks.2.norm1.bias": "model-00002-of-00002.safetensors",
|
| 587 |
+
"model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
|
| 588 |
+
"model.visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors",
|
| 589 |
+
"model.visual.blocks.2.norm2.weight": "model-00002-of-00002.safetensors",
|
| 590 |
+
"model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 591 |
+
"model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 592 |
+
"model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 593 |
+
"model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 594 |
+
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 595 |
+
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 596 |
+
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 597 |
+
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 598 |
+
"model.visual.blocks.20.norm1.bias": "model-00002-of-00002.safetensors",
|
| 599 |
+
"model.visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
|
| 600 |
+
"model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors",
|
| 601 |
+
"model.visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors",
|
| 602 |
+
"model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 603 |
+
"model.visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 604 |
+
"model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 605 |
+
"model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 606 |
+
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 607 |
+
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 608 |
+
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 609 |
+
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 610 |
+
"model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors",
|
| 611 |
+
"model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
|
| 612 |
+
"model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors",
|
| 613 |
+
"model.visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors",
|
| 614 |
+
"model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 615 |
+
"model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 616 |
+
"model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 617 |
+
"model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 618 |
+
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 619 |
+
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 620 |
+
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 621 |
+
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 622 |
+
"model.visual.blocks.22.norm1.bias": "model-00002-of-00002.safetensors",
|
| 623 |
+
"model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
|
| 624 |
+
"model.visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors",
|
| 625 |
+
"model.visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors",
|
| 626 |
+
"model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 627 |
+
"model.visual.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 628 |
+
"model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 629 |
+
"model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 630 |
+
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 631 |
+
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 632 |
+
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 633 |
+
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 634 |
+
"model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors",
|
| 635 |
+
"model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
|
| 636 |
+
"model.visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors",
|
| 637 |
+
"model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
|
| 638 |
+
"model.visual.blocks.24.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 639 |
+
"model.visual.blocks.24.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 640 |
+
"model.visual.blocks.24.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 641 |
+
"model.visual.blocks.24.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 642 |
+
"model.visual.blocks.24.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 643 |
+
"model.visual.blocks.24.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 644 |
+
"model.visual.blocks.24.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 645 |
+
"model.visual.blocks.24.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 646 |
+
"model.visual.blocks.24.norm1.bias": "model-00002-of-00002.safetensors",
|
| 647 |
+
"model.visual.blocks.24.norm1.weight": "model-00002-of-00002.safetensors",
|
| 648 |
+
"model.visual.blocks.24.norm2.bias": "model-00002-of-00002.safetensors",
|
| 649 |
+
"model.visual.blocks.24.norm2.weight": "model-00002-of-00002.safetensors",
|
| 650 |
+
"model.visual.blocks.25.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 651 |
+
"model.visual.blocks.25.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 652 |
+
"model.visual.blocks.25.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 653 |
+
"model.visual.blocks.25.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 654 |
+
"model.visual.blocks.25.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 655 |
+
"model.visual.blocks.25.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 656 |
+
"model.visual.blocks.25.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 657 |
+
"model.visual.blocks.25.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 658 |
+
"model.visual.blocks.25.norm1.bias": "model-00002-of-00002.safetensors",
|
| 659 |
+
"model.visual.blocks.25.norm1.weight": "model-00002-of-00002.safetensors",
|
| 660 |
+
"model.visual.blocks.25.norm2.bias": "model-00002-of-00002.safetensors",
|
| 661 |
+
"model.visual.blocks.25.norm2.weight": "model-00002-of-00002.safetensors",
|
| 662 |
+
"model.visual.blocks.26.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 663 |
+
"model.visual.blocks.26.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 664 |
+
"model.visual.blocks.26.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 665 |
+
"model.visual.blocks.26.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 666 |
+
"model.visual.blocks.26.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 667 |
+
"model.visual.blocks.26.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 668 |
+
"model.visual.blocks.26.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 669 |
+
"model.visual.blocks.26.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 670 |
+
"model.visual.blocks.26.norm1.bias": "model-00002-of-00002.safetensors",
|
| 671 |
+
"model.visual.blocks.26.norm1.weight": "model-00002-of-00002.safetensors",
|
| 672 |
+
"model.visual.blocks.26.norm2.bias": "model-00002-of-00002.safetensors",
|
| 673 |
+
"model.visual.blocks.26.norm2.weight": "model-00002-of-00002.safetensors",
|
| 674 |
+
"model.visual.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 675 |
+
"model.visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 676 |
+
"model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 677 |
+
"model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 678 |
+
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 679 |
+
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 680 |
+
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 681 |
+
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 682 |
+
"model.visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors",
|
| 683 |
+
"model.visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors",
|
| 684 |
+
"model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors",
|
| 685 |
+
"model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors",
|
| 686 |
+
"model.visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 687 |
+
"model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 688 |
+
"model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 689 |
+
"model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 690 |
+
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 691 |
+
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 692 |
+
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 693 |
+
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 694 |
+
"model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors",
|
| 695 |
+
"model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors",
|
| 696 |
+
"model.visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors",
|
| 697 |
+
"model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors",
|
| 698 |
+
"model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 699 |
+
"model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 700 |
+
"model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 701 |
+
"model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 702 |
+
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 703 |
+
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 704 |
+
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 705 |
+
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 706 |
+
"model.visual.blocks.5.norm1.bias": "model-00002-of-00002.safetensors",
|
| 707 |
+
"model.visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors",
|
| 708 |
+
"model.visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors",
|
| 709 |
+
"model.visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors",
|
| 710 |
+
"model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 711 |
+
"model.visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 712 |
+
"model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 713 |
+
"model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 714 |
+
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 715 |
+
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 716 |
+
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 717 |
+
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 718 |
+
"model.visual.blocks.6.norm1.bias": "model-00002-of-00002.safetensors",
|
| 719 |
+
"model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
|
| 720 |
+
"model.visual.blocks.6.norm2.bias": "model-00002-of-00002.safetensors",
|
| 721 |
+
"model.visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors",
|
| 722 |
+
"model.visual.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 723 |
+
"model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 724 |
+
"model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 725 |
+
"model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 726 |
+
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 727 |
+
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 728 |
+
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 729 |
+
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 730 |
+
"model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors",
|
| 731 |
+
"model.visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
|
| 732 |
+
"model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors",
|
| 733 |
+
"model.visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors",
|
| 734 |
+
"model.visual.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 735 |
+
"model.visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 736 |
+
"model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 737 |
+
"model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 738 |
+
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 739 |
+
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 740 |
+
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 741 |
+
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 742 |
+
"model.visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors",
|
| 743 |
+
"model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors",
|
| 744 |
+
"model.visual.blocks.8.norm2.bias": "model-00002-of-00002.safetensors",
|
| 745 |
+
"model.visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors",
|
| 746 |
+
"model.visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 747 |
+
"model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 748 |
+
"model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 749 |
+
"model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 750 |
+
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 751 |
+
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 752 |
+
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 753 |
+
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 754 |
+
"model.visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors",
|
| 755 |
+
"model.visual.blocks.9.norm1.weight": "model-00002-of-00002.safetensors",
|
| 756 |
+
"model.visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors",
|
| 757 |
+
"model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors",
|
| 758 |
+
"model.visual.merger.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 759 |
+
"model.visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 760 |
+
"model.visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 761 |
+
"model.visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 762 |
+
"model.visual.merger.norm.bias": "model-00002-of-00002.safetensors",
|
| 763 |
+
"model.visual.merger.norm.weight": "model-00002-of-00002.safetensors",
|
| 764 |
+
"model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors",
|
| 765 |
+
"model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors",
|
| 766 |
+
"model.visual.pos_embed.weight": "model-00002-of-00002.safetensors"
|
| 767 |
+
}
|
| 768 |
+
}
|
processor_config.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor": {
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"do_convert_rgb": true,
|
| 5 |
+
"do_normalize": true,
|
| 6 |
+
"do_rescale": true,
|
| 7 |
+
"do_resize": true,
|
| 8 |
+
"image_mean": [
|
| 9 |
+
0.5,
|
| 10 |
+
0.5,
|
| 11 |
+
0.5
|
| 12 |
+
],
|
| 13 |
+
"image_processor_type": "Qwen2VLImageProcessorFast",
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"merge_size": 2,
|
| 20 |
+
"patch_size": 16,
|
| 21 |
+
"resample": 3,
|
| 22 |
+
"rescale_factor": 0.00392156862745098,
|
| 23 |
+
"size": {
|
| 24 |
+
"longest_edge": 16777216,
|
| 25 |
+
"shortest_edge": 65536
|
| 26 |
+
},
|
| 27 |
+
"temporal_patch_size": 2
|
| 28 |
+
},
|
| 29 |
+
"processor_class": "Qwen3VLProcessor",
|
| 30 |
+
"video_processor": {
|
| 31 |
+
"data_format": "channels_first",
|
| 32 |
+
"default_to_square": true,
|
| 33 |
+
"do_convert_rgb": true,
|
| 34 |
+
"do_normalize": true,
|
| 35 |
+
"do_rescale": true,
|
| 36 |
+
"do_resize": true,
|
| 37 |
+
"do_sample_frames": true,
|
| 38 |
+
"fps": 2,
|
| 39 |
+
"image_mean": [
|
| 40 |
+
0.5,
|
| 41 |
+
0.5,
|
| 42 |
+
0.5
|
| 43 |
+
],
|
| 44 |
+
"image_std": [
|
| 45 |
+
0.5,
|
| 46 |
+
0.5,
|
| 47 |
+
0.5
|
| 48 |
+
],
|
| 49 |
+
"max_frames": 768,
|
| 50 |
+
"merge_size": 2,
|
| 51 |
+
"min_frames": 4,
|
| 52 |
+
"patch_size": 16,
|
| 53 |
+
"resample": 3,
|
| 54 |
+
"rescale_factor": 0.00392156862745098,
|
| 55 |
+
"return_metadata": false,
|
| 56 |
+
"size": {
|
| 57 |
+
"longest_edge": 25165824,
|
| 58 |
+
"shortest_edge": 4096
|
| 59 |
+
},
|
| 60 |
+
"temporal_patch_size": 2,
|
| 61 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 62 |
+
}
|
| 63 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:394a997fc1db2fd404ef14b59385a73f10f0164a92db69f87090cc658c9abc10
|
| 3 |
+
size 19989610
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": null,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|im_end|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"image_token": "<|image_pad|>",
|
| 12 |
+
"is_local": false,
|
| 13 |
+
"model_max_length": 262144,
|
| 14 |
+
"model_specific_special_tokens": {
|
| 15 |
+
"audio_bos_token": "<|audio_start|>",
|
| 16 |
+
"audio_eos_token": "<|audio_end|>",
|
| 17 |
+
"audio_token": "<|audio_pad|>",
|
| 18 |
+
"image_token": "<|image_pad|>",
|
| 19 |
+
"video_token": "<|video_pad|>",
|
| 20 |
+
"vision_bos_token": "<|vision_start|>",
|
| 21 |
+
"vision_eos_token": "<|vision_end|>"
|
| 22 |
+
},
|
| 23 |
+
"pad_token": "<|endoftext|>",
|
| 24 |
+
"padding_side": "right",
|
| 25 |
+
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 26 |
+
"processor_class": "Qwen3VLProcessor",
|
| 27 |
+
"split_special_tokens": false,
|
| 28 |
+
"tokenizer_class": "TokenizersBackend",
|
| 29 |
+
"unk_token": null,
|
| 30 |
+
"video_token": "<|video_pad|>",
|
| 31 |
+
"vision_bos_token": "<|vision_start|>",
|
| 32 |
+
"vision_eos_token": "<|vision_end|>",
|
| 33 |
+
"chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n {%- if content is string %}\n {{- content }}\n {%- elif content is iterable and content is not mapping %}\n {%- for item in content %}\n {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain images.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Picture ' ~ image_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n {%- elif 'video' in item or item.type == 'video' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain videos.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Video ' ~ video_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n {%- elif 'text' in item %}\n {{- item.text }}\n {%- else %}\n {{- raise_exception('Unexpected item type in content.') }}\n {%- endif %}\n {%- endfor %}\n {%- elif content is none or content is undefined %}\n {{- '' }}\n {%- else %}\n {{- raise_exception('Unexpected content type.') }}\n {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n {{- '<|im_start|>system\\n' }}\n {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\" }}\n {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n<parameter=example_parameter_2>\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\nReminder:\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n</IMPORTANT>' }}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {%- if content %}\n {{- '\\n\\n' + content }}\n {%- endif %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {{- '<|im_start|>system\\n' + content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" %}\n {%- set content = render_content(message.content, false)|trim %}\n {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n {{- raise_exception('No user query found in messages.') }}\n{%- endif %}\n{%- for message in messages %}\n {%- set content = render_content(message.content, true)|trim %}\n {%- if message.role == \"system\" %}\n {%- if not loop.first %}\n {{- raise_exception('System message must be at the beginning.') }}\n {%- endif %}\n {%- elif message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- set reasoning_content = reasoning_content|trim %}\n {%- if loop.index0 > ns.last_query_index %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {%- if loop.first %}\n {%- if content|trim %}\n {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- else %}\n {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- else %}\n {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- if tool_call.arguments is defined %}\n {%- for args_name, args_value in tool_call.arguments|items %}\n {{- '<parameter=' + args_name + '>\\n' }}\n {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}\n {{- args_value }}\n {{- '\\n</parameter>\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '</function>\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>\\n' }}\n {%- elif loop.last %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- else %}\n {{- raise_exception('Unexpected message role.') }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- else %}\n {{- '<think>\\n' }}\n {%- endif %}\n{%- endif %}"
|
| 34 |
+
}
|