Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- README.md +533 -0
- chat_template.jinja +154 -0
- config.json +129 -0
- generation_config.json +13 -0
- model-00001-of-00011.safetensors +3 -0
- model-00002-of-00011.safetensors +3 -0
- model-00003-of-00011.safetensors +3 -0
- model-00004-of-00011.safetensors +3 -0
- model-00005-of-00011.safetensors +3 -0
- model-00006-of-00011.safetensors +3 -0
- model-00007-of-00011.safetensors +3 -0
- model-00008-of-00011.safetensors +3 -0
- model-00009-of-00011.safetensors +3 -0
- model-00010-of-00011.safetensors +3 -0
- model-00011-of-00011.safetensors +3 -0
- model.safetensors.index.json +859 -0
- tokenizer.json +3 -0
- tokenizer_config.json +33 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,533 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
datasets:
|
| 4 |
+
- zerofata/Instruct-Anime
|
| 5 |
+
- zerofata/Gemini-3.1-Pro-SmallWiki
|
| 6 |
+
- zerofata/Gemini-3.1-Pro-GLM5-Characters
|
| 7 |
+
- zerofata/Roleplay-Anime-Characters
|
| 8 |
+
base_model: zerofata/Q3.5-BlueStar-v2-27B
|
| 9 |
+
pipeline_tag: text-generation
|
| 10 |
+
tags:
|
| 11 |
+
- mlx
|
| 12 |
+
library_name: mlx
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
# beezu/Q3.5-BlueStar-v2-27B-mlx-bf16
|
| 16 |
+
|
| 17 |
+
This model [beezu/Q3.5-BlueStar-v2-27B-mlx-bf16](https://huggingface.co/beezu/Q3.5-BlueStar-v2-27B-mlx-bf16) was converted to MLX format from [zerofata/Q3.5-BlueStar-v2-27B](https://huggingface.co/zerofata/Q3.5-BlueStar-v2-27B) using mlx-lm version **0.31.2**.
|
| 18 |
+
|
| 19 |
+
# Original Model Card
|
| 20 |
+
|
| 21 |
+
<style>
|
| 22 |
+
.gs {
|
| 23 |
+
--bg: #050a12;
|
| 24 |
+
--surface: #0a1019;
|
| 25 |
+
--edge: #121c2c;
|
| 26 |
+
--rule: #192638;
|
| 27 |
+
--text: #8a9db4;
|
| 28 |
+
--dim: #4e6880;
|
| 29 |
+
--bright: #dce8f4;
|
| 30 |
+
--azure: #0077cc;
|
| 31 |
+
--crimson: #00bbff;
|
| 32 |
+
--az-glow: rgba(0,119,204,0.10);
|
| 33 |
+
--cr-glow: rgba(0,187,255,0.06);
|
| 34 |
+
--mono: 'JetBrains Mono', monospace;
|
| 35 |
+
--sans: 'Inter', sans-serif;
|
| 36 |
+
|
| 37 |
+
font-family: var(--sans);
|
| 38 |
+
color: var(--text);
|
| 39 |
+
max-width: 900px;
|
| 40 |
+
margin: 0 auto;
|
| 41 |
+
padding: 0 0 60px;
|
| 42 |
+
line-height: 1.7;
|
| 43 |
+
font-size: 1rem;
|
| 44 |
+
background:
|
| 45 |
+
radial-gradient(ellipse at 50% 0%, rgba(0,140,255,0.04) 0%, transparent 50%),
|
| 46 |
+
radial-gradient(ellipse at 50% 100%, rgba(0,100,200,0.02) 0%, transparent 50%),
|
| 47 |
+
var(--bg);
|
| 48 |
+
}
|
| 49 |
+
|
| 50 |
+
/* ── Hero ── */
|
| 51 |
+
.gs-hero {
|
| 52 |
+
position: relative;
|
| 53 |
+
overflow: hidden;
|
| 54 |
+
}
|
| 55 |
+
.gs-hero img {
|
| 56 |
+
display: block;
|
| 57 |
+
width: 100%;
|
| 58 |
+
}
|
| 59 |
+
.gs-ident {
|
| 60 |
+
position: absolute;
|
| 61 |
+
bottom: 0;
|
| 62 |
+
left: 0;
|
| 63 |
+
right: 0;
|
| 64 |
+
padding: 130px 48px 36px;
|
| 65 |
+
background: linear-gradient(
|
| 66 |
+
to top,
|
| 67 |
+
var(--bg) 0%,
|
| 68 |
+
rgba(5,10,18,0.92) 35%,
|
| 69 |
+
rgba(5,10,18,0.4) 65%,
|
| 70 |
+
transparent 100%
|
| 71 |
+
);
|
| 72 |
+
}
|
| 73 |
+
.gs-name {
|
| 74 |
+
font-family: var(--sans);
|
| 75 |
+
font-size: 3.2rem;
|
| 76 |
+
font-weight: 900;
|
| 77 |
+
color: var(--bright);
|
| 78 |
+
letter-spacing: 0.06em;
|
| 79 |
+
text-transform: uppercase;
|
| 80 |
+
line-height: 1;
|
| 81 |
+
margin: 0 0 10px;
|
| 82 |
+
text-shadow: 0 1px 2px rgba(0,0,0,0.6);
|
| 83 |
+
}
|
| 84 |
+
.gs-base {
|
| 85 |
+
font-family: var(--mono);
|
| 86 |
+
font-size: 0.68rem;
|
| 87 |
+
color: var(--crimson);
|
| 88 |
+
letter-spacing: 0.14em;
|
| 89 |
+
text-transform: uppercase;
|
| 90 |
+
display: block;
|
| 91 |
+
}
|
| 92 |
+
|
| 93 |
+
/* ── Sections ── */
|
| 94 |
+
.gs-section {
|
| 95 |
+
padding: 0;
|
| 96 |
+
}
|
| 97 |
+
.gs-shead {
|
| 98 |
+
display: flex;
|
| 99 |
+
align-items: baseline;
|
| 100 |
+
gap: 14px;
|
| 101 |
+
padding: 16px 44px 14px;
|
| 102 |
+
margin-bottom: 28px;
|
| 103 |
+
border-top: 2px solid;
|
| 104 |
+
border-image: linear-gradient(90deg, var(--crimson), var(--azure)) 1;
|
| 105 |
+
}
|
| 106 |
+
.gs-snum {
|
| 107 |
+
font-family: var(--mono);
|
| 108 |
+
font-size: 0.68rem;
|
| 109 |
+
font-weight: 700;
|
| 110 |
+
color: var(--crimson);
|
| 111 |
+
letter-spacing: 0.12em;
|
| 112 |
+
flex-shrink: 0;
|
| 113 |
+
}
|
| 114 |
+
.gs-stitle {
|
| 115 |
+
font-size: 1.05rem;
|
| 116 |
+
font-weight: 700;
|
| 117 |
+
letter-spacing: 0.1em;
|
| 118 |
+
text-transform: uppercase;
|
| 119 |
+
color: var(--bright);
|
| 120 |
+
}
|
| 121 |
+
.gs-sbody {
|
| 122 |
+
padding: 0 44px 44px;
|
| 123 |
+
}
|
| 124 |
+
.gs-sbody p {
|
| 125 |
+
margin: 0 0 14px;
|
| 126 |
+
font-size: 0.95rem;
|
| 127 |
+
}
|
| 128 |
+
.gs-sbody p:last-child { margin-bottom: 0; }
|
| 129 |
+
|
| 130 |
+
/* ── Data panels ── */
|
| 131 |
+
.gs-stack {
|
| 132 |
+
display: flex;
|
| 133 |
+
flex-direction: column;
|
| 134 |
+
gap: 16px;
|
| 135 |
+
}
|
| 136 |
+
.gs-panel {
|
| 137 |
+
border: 1px solid var(--edge);
|
| 138 |
+
border-left: 2px solid var(--crimson);
|
| 139 |
+
position: relative;
|
| 140 |
+
background: var(--surface);
|
| 141 |
+
box-shadow: 0 0 20px rgba(0,140,255,0.03);
|
| 142 |
+
}
|
| 143 |
+
.gs-panel::before {
|
| 144 |
+
content: '';
|
| 145 |
+
position: absolute;
|
| 146 |
+
top: -1px;
|
| 147 |
+
right: -1px;
|
| 148 |
+
width: 10px;
|
| 149 |
+
height: 10px;
|
| 150 |
+
border-top: 1px solid var(--crimson);
|
| 151 |
+
border-right: 1px solid var(--crimson);
|
| 152 |
+
opacity: 0.5;
|
| 153 |
+
}
|
| 154 |
+
.gs-panel::after {
|
| 155 |
+
content: '';
|
| 156 |
+
position: absolute;
|
| 157 |
+
bottom: -1px;
|
| 158 |
+
right: -1px;
|
| 159 |
+
width: 10px;
|
| 160 |
+
height: 10px;
|
| 161 |
+
border-bottom: 1px solid var(--azure);
|
| 162 |
+
border-right: 1px solid var(--azure);
|
| 163 |
+
opacity: 0.4;
|
| 164 |
+
}
|
| 165 |
+
.gs-panel-head {
|
| 166 |
+
font-family: var(--mono);
|
| 167 |
+
font-size: 0.68rem;
|
| 168 |
+
font-weight: 700;
|
| 169 |
+
letter-spacing: 0.14em;
|
| 170 |
+
text-transform: uppercase;
|
| 171 |
+
color: var(--dim);
|
| 172 |
+
padding: 10px 16px;
|
| 173 |
+
border-bottom: 1px solid var(--edge);
|
| 174 |
+
}
|
| 175 |
+
.gs-row {
|
| 176 |
+
display: grid;
|
| 177 |
+
grid-template-columns: 10ch 1fr;
|
| 178 |
+
align-items: baseline;
|
| 179 |
+
column-gap: 4px;
|
| 180 |
+
padding: 9px 16px;
|
| 181 |
+
border-bottom: 1px solid var(--edge);
|
| 182 |
+
font-size: 0.9rem;
|
| 183 |
+
}
|
| 184 |
+
.gs-row:last-child { border-bottom: none; }
|
| 185 |
+
.gs-key {
|
| 186 |
+
font-family: var(--mono);
|
| 187 |
+
font-size: 0.9rem;
|
| 188 |
+
color: var(--dim);
|
| 189 |
+
}
|
| 190 |
+
.gs-key::after {
|
| 191 |
+
content: ':';
|
| 192 |
+
}
|
| 193 |
+
.gs-val {
|
| 194 |
+
color: var(--bright);
|
| 195 |
+
font-size: 0.9rem;
|
| 196 |
+
}
|
| 197 |
+
.gs-row .gs-val:only-child {
|
| 198 |
+
grid-column: 1 / -1;
|
| 199 |
+
}
|
| 200 |
+
|
| 201 |
+
/* ── Quantizations ── */
|
| 202 |
+
.gs-qrow {
|
| 203 |
+
display: flex;
|
| 204 |
+
gap: 12px;
|
| 205 |
+
flex-wrap: wrap;
|
| 206 |
+
}
|
| 207 |
+
.gs-qpanel {
|
| 208 |
+
background: var(--surface);
|
| 209 |
+
border: 1px solid var(--edge);
|
| 210 |
+
border-left: 2px solid var(--crimson);
|
| 211 |
+
display: flex;
|
| 212 |
+
align-items: center;
|
| 213 |
+
gap: 16px;
|
| 214 |
+
padding: 12px 18px;
|
| 215 |
+
position: relative;
|
| 216 |
+
box-shadow: 0 0 20px rgba(0,140,255,0.03);
|
| 217 |
+
}
|
| 218 |
+
.gs-qpanel::before {
|
| 219 |
+
content: '';
|
| 220 |
+
position: absolute;
|
| 221 |
+
top: -1px;
|
| 222 |
+
right: -1px;
|
| 223 |
+
width: 10px;
|
| 224 |
+
height: 10px;
|
| 225 |
+
border-top: 1px solid var(--crimson);
|
| 226 |
+
border-right: 1px solid var(--crimson);
|
| 227 |
+
opacity: 0.5;
|
| 228 |
+
}
|
| 229 |
+
.gs-qpanel::after {
|
| 230 |
+
content: '';
|
| 231 |
+
position: absolute;
|
| 232 |
+
bottom: -1px;
|
| 233 |
+
right: -1px;
|
| 234 |
+
width: 10px;
|
| 235 |
+
height: 10px;
|
| 236 |
+
border-bottom: 1px solid var(--azure);
|
| 237 |
+
border-right: 1px solid var(--azure);
|
| 238 |
+
opacity: 0.4;
|
| 239 |
+
}
|
| 240 |
+
.gs-qtype {
|
| 241 |
+
font-family: var(--mono);
|
| 242 |
+
font-size: 0.58rem;
|
| 243 |
+
font-weight: 700;
|
| 244 |
+
letter-spacing: 0.18em;
|
| 245 |
+
text-transform: uppercase;
|
| 246 |
+
color: var(--crimson);
|
| 247 |
+
flex-shrink: 0;
|
| 248 |
+
}
|
| 249 |
+
.gs-qsep {
|
| 250 |
+
width: 1px;
|
| 251 |
+
height: 16px;
|
| 252 |
+
background: var(--rule);
|
| 253 |
+
flex-shrink: 0;
|
| 254 |
+
}
|
| 255 |
+
.gs-qpanel a {
|
| 256 |
+
color: var(--bright);
|
| 257 |
+
text-decoration: none;
|
| 258 |
+
font-size: 0.9rem;
|
| 259 |
+
border-bottom: 1px solid var(--rule);
|
| 260 |
+
}
|
| 261 |
+
.gs-qpanel a:hover { color: var(--crimson); border-bottom-color: var(--crimson); }
|
| 262 |
+
|
| 263 |
+
/* ── Links ── */
|
| 264 |
+
.gs a {
|
| 265 |
+
color: var(--bright);
|
| 266 |
+
text-decoration: none;
|
| 267 |
+
border-bottom: 1px solid var(--rule);
|
| 268 |
+
}
|
| 269 |
+
.gs a:hover { color: var(--crimson); border-bottom-color: var(--crimson); }
|
| 270 |
+
|
| 271 |
+
/* ── Dropdown ── */
|
| 272 |
+
.gs details {
|
| 273 |
+
border: 1px solid var(--edge);
|
| 274 |
+
border-left: 2px solid var(--crimson);
|
| 275 |
+
margin-top: 24px;
|
| 276 |
+
position: relative;
|
| 277 |
+
background: var(--surface);
|
| 278 |
+
box-shadow: 0 0 20px rgba(0,140,255,0.03);
|
| 279 |
+
}
|
| 280 |
+
.gs details::before {
|
| 281 |
+
content: '';
|
| 282 |
+
position: absolute;
|
| 283 |
+
top: -1px;
|
| 284 |
+
right: -1px;
|
| 285 |
+
width: 10px;
|
| 286 |
+
height: 10px;
|
| 287 |
+
border-top: 1px solid var(--crimson);
|
| 288 |
+
border-right: 1px solid var(--crimson);
|
| 289 |
+
opacity: 0.5;
|
| 290 |
+
}
|
| 291 |
+
.gs details::after {
|
| 292 |
+
content: '';
|
| 293 |
+
position: absolute;
|
| 294 |
+
bottom: -1px;
|
| 295 |
+
right: -1px;
|
| 296 |
+
width: 10px;
|
| 297 |
+
height: 10px;
|
| 298 |
+
border-bottom: 1px solid var(--azure);
|
| 299 |
+
border-right: 1px solid var(--azure);
|
| 300 |
+
opacity: 0.4;
|
| 301 |
+
}
|
| 302 |
+
.gs summary {
|
| 303 |
+
list-style: none;
|
| 304 |
+
padding: 11px 16px;
|
| 305 |
+
cursor: pointer;
|
| 306 |
+
font-family: var(--mono);
|
| 307 |
+
font-size: 0.72rem;
|
| 308 |
+
font-weight: 700;
|
| 309 |
+
letter-spacing: 0.12em;
|
| 310 |
+
text-transform: uppercase;
|
| 311 |
+
color: var(--dim);
|
| 312 |
+
user-select: none;
|
| 313 |
+
display: flex;
|
| 314 |
+
align-items: center;
|
| 315 |
+
gap: 10px;
|
| 316 |
+
}
|
| 317 |
+
.gs summary::-webkit-details-marker { display: none; }
|
| 318 |
+
.gs summary::before {
|
| 319 |
+
content: '+';
|
| 320 |
+
color: var(--crimson);
|
| 321 |
+
font-size: 1rem;
|
| 322 |
+
line-height: 1;
|
| 323 |
+
flex-shrink: 0;
|
| 324 |
+
}
|
| 325 |
+
.gs details[open] summary::before { content: '−'; }
|
| 326 |
+
.gs summary:hover { color: var(--bright); }
|
| 327 |
+
.gs-detail-body {
|
| 328 |
+
padding: 22px 18px;
|
| 329 |
+
border-top: 1px solid var(--edge);
|
| 330 |
+
}
|
| 331 |
+
.gs-detail-body p { margin: 0 0 16px; font-size: 0.9rem; }
|
| 332 |
+
.gs-cfg-title {
|
| 333 |
+
font-family: var(--mono);
|
| 334 |
+
font-size: 0.72rem;
|
| 335 |
+
font-weight: 700;
|
| 336 |
+
letter-spacing: 0.1em;
|
| 337 |
+
text-transform: uppercase;
|
| 338 |
+
color: var(--dim);
|
| 339 |
+
margin: 0 0 8px;
|
| 340 |
+
}
|
| 341 |
+
|
| 342 |
+
/* ── Code ── */
|
| 343 |
+
.gs pre {
|
| 344 |
+
background: #030810;
|
| 345 |
+
border: 1px solid var(--edge);
|
| 346 |
+
border-left: 2px solid var(--azure);
|
| 347 |
+
padding: 16px 18px;
|
| 348 |
+
overflow-x: auto;
|
| 349 |
+
font-family: var(--mono);
|
| 350 |
+
font-size: 0.76rem;
|
| 351 |
+
line-height: 1.6;
|
| 352 |
+
color: var(--text);
|
| 353 |
+
margin: 0 0 22px;
|
| 354 |
+
}
|
| 355 |
+
.gs pre:last-child { margin-bottom: 0; }
|
| 356 |
+
.gs pre code { background: none; color: inherit; padding: 0; }
|
| 357 |
+
.gs code {
|
| 358 |
+
font-family: var(--mono);
|
| 359 |
+
font-size: 0.875em;
|
| 360 |
+
color: var(--crimson);
|
| 361 |
+
background: var(--az-glow);
|
| 362 |
+
padding: 2px 5px;
|
| 363 |
+
}
|
| 364 |
+
</style>
|
| 365 |
+
<html lang="en">
|
| 366 |
+
<head>
|
| 367 |
+
<meta charset="UTF-8">
|
| 368 |
+
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
| 369 |
+
<title>BlueStar</title>
|
| 370 |
+
<link rel="preconnect" href="https://fonts.googleapis.com">
|
| 371 |
+
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
|
| 372 |
+
<link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;600;700;900&family=JetBrains+Mono:wght@400;700&display=swap" rel="stylesheet">
|
| 373 |
+
</head>
|
| 374 |
+
<body>
|
| 375 |
+
<div class="gs">
|
| 376 |
+
|
| 377 |
+
<div class="gs-hero">
|
| 378 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/65b19c6c638328850e12d38c/ruIMSzVP1DU1_HxUqBmFx.png" alt="image">
|
| 379 |
+
<div class="gs-ident">
|
| 380 |
+
<h1 class="gs-name">BlueStar v2</h1>
|
| 381 |
+
<span class="gs-base">Qwen3.5 27B</span>
|
| 382 |
+
</div>
|
| 383 |
+
</div>
|
| 384 |
+
|
| 385 |
+
|
| 386 |
+
<div class="gs-section">
|
| 387 |
+
<div class="gs-shead">
|
| 388 |
+
<span class="gs-snum">01</span>
|
| 389 |
+
<span class="gs-stitle">Overview</span>
|
| 390 |
+
</div>
|
| 391 |
+
<div class="gs-sbody">
|
| 392 |
+
<p>Designed for RP and writing tasks.</p>
|
| 393 |
+
<p>Feels like a good improvement on v1. This version aims to fix the rep and improve the intelligence while keeping the creativity.</p>
|
| 394 |
+
<p>Non thinking and thinking are both supported. If you want to use thinking, it is required to prefill the <code><think>\n</code> as that is how it was trained.</p>
|
| 395 |
+
</div>
|
| 396 |
+
</div>
|
| 397 |
+
|
| 398 |
+
|
| 399 |
+
<div class="gs-section">
|
| 400 |
+
<div class="gs-shead">
|
| 401 |
+
<span class="gs-snum">02</span>
|
| 402 |
+
<span class="gs-stitle">SillyTavern Settings</span>
|
| 403 |
+
</div>
|
| 404 |
+
<div class="gs-sbody">
|
| 405 |
+
<div class="gs-stack">
|
| 406 |
+
<div class="gs-panel">
|
| 407 |
+
<div class="gs-panel-head">Recommended Roleplay Format</div>
|
| 408 |
+
<div class="gs-row"><span class="gs-key">Actions</span><span class="gs-val">In plaintext</span></div>
|
| 409 |
+
<div class="gs-row"><span class="gs-key">Dialogue</span><span class="gs-val">"In quotes"</span></div>
|
| 410 |
+
<div class="gs-row"><span class="gs-key">Thoughts</span><span class="gs-val">*In asterisks*</span></div>
|
| 411 |
+
</div>
|
| 412 |
+
<div class="gs-panel">
|
| 413 |
+
<div class="gs-panel-head">Recommended Samplers</div>
|
| 414 |
+
<div class="gs-row"><span class="gs-key">Temp</span><span class="gs-val">0.8 - 1.0</span></div>
|
| 415 |
+
<div class="gs-row"><span class="gs-key">MinP</span><span class="gs-val">0.05 - 0.075</span></div>
|
| 416 |
+
</div>
|
| 417 |
+
<div class="gs-panel">
|
| 418 |
+
<div class="gs-panel-head">Instruct</div>
|
| 419 |
+
<div class="gs-row"><span class="gs-val"><a href="https://huggingface.co/zerofata/Q3.5-BlueStar-v2-27B/raw/main/ChatML-Q3.5-Think.json">ChatML - Think</a></span></div>
|
| 420 |
+
<div class="gs-row"><span class="gs-val"><a href="https://huggingface.co/zerofata/Q3.5-BlueStar-v2-27B/raw/main/ChatML-Q3.5-NoThink.json">ChatML - NoThink</a></span></div>
|
| 421 |
+
</div>
|
| 422 |
+
</div>
|
| 423 |
+
</div>
|
| 424 |
+
</div>
|
| 425 |
+
|
| 426 |
+
|
| 427 |
+
<div class="gs-section">
|
| 428 |
+
<div class="gs-shead">
|
| 429 |
+
<span class="gs-snum">03</span>
|
| 430 |
+
<span class="gs-stitle">Quantizations</span>
|
| 431 |
+
</div>
|
| 432 |
+
<div class="gs-sbody">
|
| 433 |
+
<div class="gs-qrow">
|
| 434 |
+
<div class="gs-qpanel">
|
| 435 |
+
<span class="gs-qtype">GGUF</span>
|
| 436 |
+
<div class="gs-qsep"></div>
|
| 437 |
+
<a href="https://huggingface.co/zerofata/Q3.5-BlueStar-v2-27B-GGUF">iMatrix</a>
|
| 438 |
+
</div>
|
| 439 |
+
</div>
|
| 440 |
+
</div>
|
| 441 |
+
</div>
|
| 442 |
+
|
| 443 |
+
|
| 444 |
+
<div class="gs-section">
|
| 445 |
+
<div class="gs-shead">
|
| 446 |
+
<span class="gs-snum">04</span>
|
| 447 |
+
<span class="gs-stitle">Creation Process</span>
|
| 448 |
+
</div>
|
| 449 |
+
<div class="gs-sbody">
|
| 450 |
+
<p>Creation Process: SFT</p>
|
| 451 |
+
<p>SFT on approx 27 million tokens.</p>
|
| 452 |
+
<p>I've confirmed the repetition coming from the RP datasets. Despite the extensive filtering, human editing, rewriting and deduping. Compared to other types of data like chat and writing, RP is just somewhat repetitive in nature. One idea to fix this is to just not use the RP datasets, or use less of them. This does seem to *sort of* work, but the model performs noticably worse at RP as a result. Which makes sense, given that's the entire idea of having RP data to begin with.</p>
|
| 453 |
+
<p>The current solution I'm testing is using custom loss masking with the RP datasets. Most common phrases of slop are masked out, so the model doesn't get rewarded for learning these patterns. Overused words within a conversation also get masked out in later turns.</p>
|
| 454 |
+
<p>It... seems to have worked? Repetition from my testing is greatly reduced after a few hours of using the model. It can still latch onto phrases, but I've seen much less verbatim repetition.</p>
|
| 455 |
+
<p>Trained using Axolotl.</p>
|
| 456 |
+
<details>
|
| 457 |
+
<summary>Axolotl Config</summary>
|
| 458 |
+
<div class="gs-detail-body">
|
| 459 |
+
<div class="gs-cfg-title">SFT (4×H200)</div>
|
| 460 |
+
<pre><code>base_model: Qwen/Qwen3.5-27B
|
| 461 |
+
 
|
| 462 |
+
plugins:
|
| 463 |
+
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
|
| 464 |
+
strict: false
|
| 465 |
+
 
|
| 466 |
+
datasets:
|
| 467 |
+
- path: ./data/bluestar_v2_sft_3_all_rp_attempt_masked_20260318_075236.jsonl
|
| 468 |
+
 
|
| 469 |
+
val_set_size: 0.02
|
| 470 |
+
output_dir: ./Qwen3.5-27B-v2-SFT-5
|
| 471 |
+
 
|
| 472 |
+
sequence_len: 10756
|
| 473 |
+
sample_packing: true
|
| 474 |
+
 
|
| 475 |
+
load_in_8bit: true
|
| 476 |
+
adapter: lora
|
| 477 |
+
lora_r: 128
|
| 478 |
+
lora_alpha: 128
|
| 479 |
+
peft_use_rslora: true
|
| 480 |
+
lora_target_modules:
|
| 481 |
+
- q_proj
|
| 482 |
+
- k_proj
|
| 483 |
+
- v_proj
|
| 484 |
+
- o_proj
|
| 485 |
+
- down_proj
|
| 486 |
+
- up_proj
|
| 487 |
+
# Uncomment below to also target the linear attention projections.
|
| 488 |
+
# These use separate in_proj_qkv / in_proj_z / out_proj (Qwen3.5-specific).
|
| 489 |
+
- linear_attn.in_proj_qkv
|
| 490 |
+
- linear_attn.in_proj_z
|
| 491 |
+
- linear_attn.out_proj
|
| 492 |
+
 
|
| 493 |
+
wandb_project: Qwen3.5-27B-SFT
|
| 494 |
+
wandb_name: Qwen3.5-27B-v2-SFT-5
|
| 495 |
+
 
|
| 496 |
+
gradient_accumulation_steps: 4
|
| 497 |
+
micro_batch_size: 1
|
| 498 |
+
num_epochs: 2
|
| 499 |
+
optimizer: adamw_torch_8bit
|
| 500 |
+
lr_scheduler: cosine
|
| 501 |
+
learning_rate: 1.2e-5
|
| 502 |
+
weight_decay: 0.01
|
| 503 |
+
warmup_ratio: 0.05
|
| 504 |
+
 
|
| 505 |
+
bf16: auto
|
| 506 |
+
tf32: true
|
| 507 |
+
 
|
| 508 |
+
resume_from_checkpoint:
|
| 509 |
+
logging_steps: 1
|
| 510 |
+
flash_attention: true
|
| 511 |
+
 
|
| 512 |
+
evals_per_epoch: 4
|
| 513 |
+
saves_per_epoch: 4
|
| 514 |
+
special_tokens:
|
| 515 |
+
 
|
| 516 |
+
fsdp_config:
|
| 517 |
+
fsdp_version: 2
|
| 518 |
+
offload_params: false
|
| 519 |
+
cpu_ram_efficient_loading: false
|
| 520 |
+
auto_wrap_policy: TRANSFORMER_BASED_WRAP
|
| 521 |
+
transformer_layer_cls_to_wrap: Qwen3_5DecoderLayer
|
| 522 |
+
state_dict_type: FULL_STATE_DICT
|
| 523 |
+
sharding_strategy: FULL_SHARD
|
| 524 |
+
reshard_after_forward: true
|
| 525 |
+
activation_checkpointing: true</code></pre>
|
| 526 |
+
</div>
|
| 527 |
+
</details>
|
| 528 |
+
</div>
|
| 529 |
+
</div>
|
| 530 |
+
|
| 531 |
+
</div>
|
| 532 |
+
</body>
|
| 533 |
+
</html>
|
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 +1,129 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"eos_token_id": [
|
| 7 |
+
248046,
|
| 8 |
+
248044
|
| 9 |
+
],
|
| 10 |
+
"image_token_id": 248056,
|
| 11 |
+
"model_type": "qwen3_5",
|
| 12 |
+
"text_config": {
|
| 13 |
+
"attention_bias": false,
|
| 14 |
+
"attention_dropout": 0.0,
|
| 15 |
+
"attn_output_gate": true,
|
| 16 |
+
"bos_token_id": null,
|
| 17 |
+
"dtype": "bfloat16",
|
| 18 |
+
"eos_token_id": 248044,
|
| 19 |
+
"full_attention_interval": 4,
|
| 20 |
+
"head_dim": 256,
|
| 21 |
+
"hidden_act": "silu",
|
| 22 |
+
"hidden_size": 5120,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 17408,
|
| 25 |
+
"layer_types": [
|
| 26 |
+
"linear_attention",
|
| 27 |
+
"linear_attention",
|
| 28 |
+
"linear_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"linear_attention",
|
| 31 |
+
"linear_attention",
|
| 32 |
+
"linear_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"linear_attention",
|
| 35 |
+
"linear_attention",
|
| 36 |
+
"linear_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"linear_attention",
|
| 39 |
+
"linear_attention",
|
| 40 |
+
"linear_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"linear_attention",
|
| 43 |
+
"linear_attention",
|
| 44 |
+
"linear_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"linear_attention",
|
| 47 |
+
"linear_attention",
|
| 48 |
+
"linear_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"linear_attention",
|
| 51 |
+
"linear_attention",
|
| 52 |
+
"linear_attention",
|
| 53 |
+
"full_attention",
|
| 54 |
+
"linear_attention",
|
| 55 |
+
"linear_attention",
|
| 56 |
+
"linear_attention",
|
| 57 |
+
"full_attention",
|
| 58 |
+
"linear_attention",
|
| 59 |
+
"linear_attention",
|
| 60 |
+
"linear_attention",
|
| 61 |
+
"full_attention",
|
| 62 |
+
"linear_attention",
|
| 63 |
+
"linear_attention",
|
| 64 |
+
"linear_attention",
|
| 65 |
+
"full_attention",
|
| 66 |
+
"linear_attention",
|
| 67 |
+
"linear_attention",
|
| 68 |
+
"linear_attention",
|
| 69 |
+
"full_attention",
|
| 70 |
+
"linear_attention",
|
| 71 |
+
"linear_attention",
|
| 72 |
+
"linear_attention",
|
| 73 |
+
"full_attention",
|
| 74 |
+
"linear_attention",
|
| 75 |
+
"linear_attention",
|
| 76 |
+
"linear_attention",
|
| 77 |
+
"full_attention",
|
| 78 |
+
"linear_attention",
|
| 79 |
+
"linear_attention",
|
| 80 |
+
"linear_attention",
|
| 81 |
+
"full_attention",
|
| 82 |
+
"linear_attention",
|
| 83 |
+
"linear_attention",
|
| 84 |
+
"linear_attention",
|
| 85 |
+
"full_attention",
|
| 86 |
+
"linear_attention",
|
| 87 |
+
"linear_attention",
|
| 88 |
+
"linear_attention",
|
| 89 |
+
"full_attention"
|
| 90 |
+
],
|
| 91 |
+
"linear_conv_kernel_dim": 4,
|
| 92 |
+
"linear_key_head_dim": 128,
|
| 93 |
+
"linear_num_key_heads": 16,
|
| 94 |
+
"linear_num_value_heads": 48,
|
| 95 |
+
"linear_value_head_dim": 128,
|
| 96 |
+
"mamba_ssm_dtype": "float32",
|
| 97 |
+
"max_position_embeddings": 262144,
|
| 98 |
+
"mlp_only_layers": [],
|
| 99 |
+
"model_type": "qwen3_5_text",
|
| 100 |
+
"mtp_num_hidden_layers": 1,
|
| 101 |
+
"mtp_use_dedicated_embeddings": false,
|
| 102 |
+
"num_attention_heads": 24,
|
| 103 |
+
"num_hidden_layers": 64,
|
| 104 |
+
"num_key_value_heads": 4,
|
| 105 |
+
"pad_token_id": null,
|
| 106 |
+
"partial_rotary_factor": 0.25,
|
| 107 |
+
"rms_norm_eps": 1e-06,
|
| 108 |
+
"rope_parameters": {
|
| 109 |
+
"mrope_interleaved": true,
|
| 110 |
+
"mrope_section": [
|
| 111 |
+
11,
|
| 112 |
+
11,
|
| 113 |
+
10
|
| 114 |
+
],
|
| 115 |
+
"partial_rotary_factor": 0.25,
|
| 116 |
+
"rope_theta": 10000000,
|
| 117 |
+
"type": "default"
|
| 118 |
+
},
|
| 119 |
+
"tie_word_embeddings": false,
|
| 120 |
+
"use_cache": false,
|
| 121 |
+
"vocab_size": 248320
|
| 122 |
+
},
|
| 123 |
+
"tie_word_embeddings": false,
|
| 124 |
+
"transformers_version": "5.3.0",
|
| 125 |
+
"use_cache": true,
|
| 126 |
+
"video_token_id": 248057,
|
| 127 |
+
"vision_end_token_id": 248054,
|
| 128 |
+
"vision_start_token_id": 248053
|
| 129 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 248044,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
248046,
|
| 6 |
+
248044
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 248044,
|
| 9 |
+
"temperature": 0.6,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.95,
|
| 12 |
+
"transformers_version": "5.3.0"
|
| 13 |
+
}
|
model-00001-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7836cd2676ca7b9c24f44362bf8f08bef20647fb5134bb00c0cf6c7ae87f199
|
| 3 |
+
size 5230437313
|
model-00002-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49a9ca8ea6d26fb8cf5a894e859b7093ec8e94e3a7803a2c9cc5a5008303abfe
|
| 3 |
+
size 5343801040
|
model-00003-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:081d1c7678ddffd8b67d83725358b77fa56c97fb0406e001f6d3cc0b86382740
|
| 3 |
+
size 5321764848
|
model-00004-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0fc5432963b9885ba65491291abbf27a62207db886ecf92bed34e2fcb6e03c02
|
| 3 |
+
size 5321764862
|
model-00005-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f328ca668d790e18c07795c307bd0581d1134672225ba25a3762cc261a2b4f55
|
| 3 |
+
size 5321764850
|
model-00006-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:758bd9166e3d9eddc1c3699aede633b9c3353582098e5c7d177d0877d912b5c2
|
| 3 |
+
size 5343801187
|
model-00007-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0cc0cf082bbc73edafaade32489d0b80bf5b4a8878fa985ba78fb3a330cf77a7
|
| 3 |
+
size 5321764858
|
model-00008-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99ec5f0da86d2971820f6e31bd9209fbb31aeba5dcccd8a09afea7816b81848d
|
| 3 |
+
size 5321764872
|
model-00009-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce8018a3a1b5288b13ab4d4f48020d38411ccd7bfb9166a595d648aa04cf7374
|
| 3 |
+
size 5321764870
|
model-00010-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:631ac2d12ead099494288aaa0f6fa6cf0bac0168ee0e149f41ff24c4ef2ac4c0
|
| 3 |
+
size 3400682987
|
model-00011-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8e8a1e795be1b3df2a2b07eb06f681e725581a19ad223c3b420ff3ecd7076c0
|
| 3 |
+
size 2542796942
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,859 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 53791996928,
|
| 4 |
+
"total_parameters": 26895993856
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"language_model.lm_head.weight": "model-00011-of-00011.safetensors",
|
| 8 |
+
"language_model.model.embed_tokens.weight": "model-00001-of-00011.safetensors",
|
| 9 |
+
"language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors",
|
| 10 |
+
"language_model.model.layers.0.linear_attn.A_log": "model-00001-of-00011.safetensors",
|
| 11 |
+
"language_model.model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00011.safetensors",
|
| 12 |
+
"language_model.model.layers.0.linear_attn.dt_bias": "model-00001-of-00011.safetensors",
|
| 13 |
+
"language_model.model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00011.safetensors",
|
| 14 |
+
"language_model.model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00011.safetensors",
|
| 15 |
+
"language_model.model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00011.safetensors",
|
| 16 |
+
"language_model.model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00011.safetensors",
|
| 17 |
+
"language_model.model.layers.0.linear_attn.norm.weight": "model-00001-of-00011.safetensors",
|
| 18 |
+
"language_model.model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 19 |
+
"language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
|
| 20 |
+
"language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
|
| 21 |
+
"language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
|
| 22 |
+
"language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
|
| 23 |
+
"language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00011.safetensors",
|
| 24 |
+
"language_model.model.layers.1.linear_attn.A_log": "model-00001-of-00011.safetensors",
|
| 25 |
+
"language_model.model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00011.safetensors",
|
| 26 |
+
"language_model.model.layers.1.linear_attn.dt_bias": "model-00001-of-00011.safetensors",
|
| 27 |
+
"language_model.model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00011.safetensors",
|
| 28 |
+
"language_model.model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00011.safetensors",
|
| 29 |
+
"language_model.model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00011.safetensors",
|
| 30 |
+
"language_model.model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00011.safetensors",
|
| 31 |
+
"language_model.model.layers.1.linear_attn.norm.weight": "model-00001-of-00011.safetensors",
|
| 32 |
+
"language_model.model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 33 |
+
"language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
|
| 34 |
+
"language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
|
| 35 |
+
"language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
|
| 36 |
+
"language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
|
| 37 |
+
"language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00011.safetensors",
|
| 38 |
+
"language_model.model.layers.10.linear_attn.A_log": "model-00002-of-00011.safetensors",
|
| 39 |
+
"language_model.model.layers.10.linear_attn.conv1d.weight": "model-00002-of-00011.safetensors",
|
| 40 |
+
"language_model.model.layers.10.linear_attn.dt_bias": "model-00002-of-00011.safetensors",
|
| 41 |
+
"language_model.model.layers.10.linear_attn.in_proj_a.weight": "model-00002-of-00011.safetensors",
|
| 42 |
+
"language_model.model.layers.10.linear_attn.in_proj_b.weight": "model-00002-of-00011.safetensors",
|
| 43 |
+
"language_model.model.layers.10.linear_attn.in_proj_qkv.weight": "model-00002-of-00011.safetensors",
|
| 44 |
+
"language_model.model.layers.10.linear_attn.in_proj_z.weight": "model-00002-of-00011.safetensors",
|
| 45 |
+
"language_model.model.layers.10.linear_attn.norm.weight": "model-00002-of-00011.safetensors",
|
| 46 |
+
"language_model.model.layers.10.linear_attn.out_proj.weight": "model-00002-of-00011.safetensors",
|
| 47 |
+
"language_model.model.layers.10.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
|
| 48 |
+
"language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
|
| 49 |
+
"language_model.model.layers.10.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
|
| 50 |
+
"language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
|
| 51 |
+
"language_model.model.layers.11.input_layernorm.weight": "model-00003-of-00011.safetensors",
|
| 52 |
+
"language_model.model.layers.11.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
|
| 53 |
+
"language_model.model.layers.11.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
|
| 54 |
+
"language_model.model.layers.11.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
|
| 55 |
+
"language_model.model.layers.11.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
|
| 56 |
+
"language_model.model.layers.11.self_attn.k_norm.weight": "model-00003-of-00011.safetensors",
|
| 57 |
+
"language_model.model.layers.11.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
|
| 58 |
+
"language_model.model.layers.11.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
|
| 59 |
+
"language_model.model.layers.11.self_attn.q_norm.weight": "model-00003-of-00011.safetensors",
|
| 60 |
+
"language_model.model.layers.11.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
|
| 61 |
+
"language_model.model.layers.11.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
|
| 62 |
+
"language_model.model.layers.12.input_layernorm.weight": "model-00003-of-00011.safetensors",
|
| 63 |
+
"language_model.model.layers.12.linear_attn.A_log": "model-00003-of-00011.safetensors",
|
| 64 |
+
"language_model.model.layers.12.linear_attn.conv1d.weight": "model-00003-of-00011.safetensors",
|
| 65 |
+
"language_model.model.layers.12.linear_attn.dt_bias": "model-00003-of-00011.safetensors",
|
| 66 |
+
"language_model.model.layers.12.linear_attn.in_proj_a.weight": "model-00003-of-00011.safetensors",
|
| 67 |
+
"language_model.model.layers.12.linear_attn.in_proj_b.weight": "model-00003-of-00011.safetensors",
|
| 68 |
+
"language_model.model.layers.12.linear_attn.in_proj_qkv.weight": "model-00003-of-00011.safetensors",
|
| 69 |
+
"language_model.model.layers.12.linear_attn.in_proj_z.weight": "model-00003-of-00011.safetensors",
|
| 70 |
+
"language_model.model.layers.12.linear_attn.norm.weight": "model-00003-of-00011.safetensors",
|
| 71 |
+
"language_model.model.layers.12.linear_attn.out_proj.weight": "model-00003-of-00011.safetensors",
|
| 72 |
+
"language_model.model.layers.12.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
|
| 73 |
+
"language_model.model.layers.12.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
|
| 74 |
+
"language_model.model.layers.12.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
|
| 75 |
+
"language_model.model.layers.12.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
|
| 76 |
+
"language_model.model.layers.13.input_layernorm.weight": "model-00003-of-00011.safetensors",
|
| 77 |
+
"language_model.model.layers.13.linear_attn.A_log": "model-00003-of-00011.safetensors",
|
| 78 |
+
"language_model.model.layers.13.linear_attn.conv1d.weight": "model-00003-of-00011.safetensors",
|
| 79 |
+
"language_model.model.layers.13.linear_attn.dt_bias": "model-00003-of-00011.safetensors",
|
| 80 |
+
"language_model.model.layers.13.linear_attn.in_proj_a.weight": "model-00003-of-00011.safetensors",
|
| 81 |
+
"language_model.model.layers.13.linear_attn.in_proj_b.weight": "model-00003-of-00011.safetensors",
|
| 82 |
+
"language_model.model.layers.13.linear_attn.in_proj_qkv.weight": "model-00003-of-00011.safetensors",
|
| 83 |
+
"language_model.model.layers.13.linear_attn.in_proj_z.weight": "model-00003-of-00011.safetensors",
|
| 84 |
+
"language_model.model.layers.13.linear_attn.norm.weight": "model-00003-of-00011.safetensors",
|
| 85 |
+
"language_model.model.layers.13.linear_attn.out_proj.weight": "model-00003-of-00011.safetensors",
|
| 86 |
+
"language_model.model.layers.13.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
|
| 87 |
+
"language_model.model.layers.13.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
|
| 88 |
+
"language_model.model.layers.13.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
|
| 89 |
+
"language_model.model.layers.13.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
|
| 90 |
+
"language_model.model.layers.14.input_layernorm.weight": "model-00003-of-00011.safetensors",
|
| 91 |
+
"language_model.model.layers.14.linear_attn.A_log": "model-00003-of-00011.safetensors",
|
| 92 |
+
"language_model.model.layers.14.linear_attn.conv1d.weight": "model-00003-of-00011.safetensors",
|
| 93 |
+
"language_model.model.layers.14.linear_attn.dt_bias": "model-00003-of-00011.safetensors",
|
| 94 |
+
"language_model.model.layers.14.linear_attn.in_proj_a.weight": "model-00003-of-00011.safetensors",
|
| 95 |
+
"language_model.model.layers.14.linear_attn.in_proj_b.weight": "model-00003-of-00011.safetensors",
|
| 96 |
+
"language_model.model.layers.14.linear_attn.in_proj_qkv.weight": "model-00003-of-00011.safetensors",
|
| 97 |
+
"language_model.model.layers.14.linear_attn.in_proj_z.weight": "model-00003-of-00011.safetensors",
|
| 98 |
+
"language_model.model.layers.14.linear_attn.norm.weight": "model-00003-of-00011.safetensors",
|
| 99 |
+
"language_model.model.layers.14.linear_attn.out_proj.weight": "model-00003-of-00011.safetensors",
|
| 100 |
+
"language_model.model.layers.14.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
|
| 101 |
+
"language_model.model.layers.14.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
|
| 102 |
+
"language_model.model.layers.14.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
|
| 103 |
+
"language_model.model.layers.14.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
|
| 104 |
+
"language_model.model.layers.15.input_layernorm.weight": "model-00003-of-00011.safetensors",
|
| 105 |
+
"language_model.model.layers.15.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
|
| 106 |
+
"language_model.model.layers.15.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
|
| 107 |
+
"language_model.model.layers.15.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
|
| 108 |
+
"language_model.model.layers.15.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
|
| 109 |
+
"language_model.model.layers.15.self_attn.k_norm.weight": "model-00003-of-00011.safetensors",
|
| 110 |
+
"language_model.model.layers.15.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
|
| 111 |
+
"language_model.model.layers.15.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
|
| 112 |
+
"language_model.model.layers.15.self_attn.q_norm.weight": "model-00003-of-00011.safetensors",
|
| 113 |
+
"language_model.model.layers.15.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
|
| 114 |
+
"language_model.model.layers.15.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
|
| 115 |
+
"language_model.model.layers.16.input_layernorm.weight": "model-00003-of-00011.safetensors",
|
| 116 |
+
"language_model.model.layers.16.linear_attn.A_log": "model-00003-of-00011.safetensors",
|
| 117 |
+
"language_model.model.layers.16.linear_attn.conv1d.weight": "model-00003-of-00011.safetensors",
|
| 118 |
+
"language_model.model.layers.16.linear_attn.dt_bias": "model-00003-of-00011.safetensors",
|
| 119 |
+
"language_model.model.layers.16.linear_attn.in_proj_a.weight": "model-00003-of-00011.safetensors",
|
| 120 |
+
"language_model.model.layers.16.linear_attn.in_proj_b.weight": "model-00003-of-00011.safetensors",
|
| 121 |
+
"language_model.model.layers.16.linear_attn.in_proj_qkv.weight": "model-00003-of-00011.safetensors",
|
| 122 |
+
"language_model.model.layers.16.linear_attn.in_proj_z.weight": "model-00003-of-00011.safetensors",
|
| 123 |
+
"language_model.model.layers.16.linear_attn.norm.weight": "model-00003-of-00011.safetensors",
|
| 124 |
+
"language_model.model.layers.16.linear_attn.out_proj.weight": "model-00003-of-00011.safetensors",
|
| 125 |
+
"language_model.model.layers.16.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
|
| 126 |
+
"language_model.model.layers.16.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
|
| 127 |
+
"language_model.model.layers.16.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
|
| 128 |
+
"language_model.model.layers.16.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
|
| 129 |
+
"language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00011.safetensors",
|
| 130 |
+
"language_model.model.layers.17.linear_attn.A_log": "model-00003-of-00011.safetensors",
|
| 131 |
+
"language_model.model.layers.17.linear_attn.conv1d.weight": "model-00003-of-00011.safetensors",
|
| 132 |
+
"language_model.model.layers.17.linear_attn.dt_bias": "model-00003-of-00011.safetensors",
|
| 133 |
+
"language_model.model.layers.17.linear_attn.in_proj_a.weight": "model-00003-of-00011.safetensors",
|
| 134 |
+
"language_model.model.layers.17.linear_attn.in_proj_b.weight": "model-00003-of-00011.safetensors",
|
| 135 |
+
"language_model.model.layers.17.linear_attn.in_proj_qkv.weight": "model-00003-of-00011.safetensors",
|
| 136 |
+
"language_model.model.layers.17.linear_attn.in_proj_z.weight": "model-00003-of-00011.safetensors",
|
| 137 |
+
"language_model.model.layers.17.linear_attn.norm.weight": "model-00003-of-00011.safetensors",
|
| 138 |
+
"language_model.model.layers.17.linear_attn.out_proj.weight": "model-00003-of-00011.safetensors",
|
| 139 |
+
"language_model.model.layers.17.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
|
| 140 |
+
"language_model.model.layers.17.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
|
| 141 |
+
"language_model.model.layers.17.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
|
| 142 |
+
"language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
|
| 143 |
+
"language_model.model.layers.18.input_layernorm.weight": "model-00004-of-00011.safetensors",
|
| 144 |
+
"language_model.model.layers.18.linear_attn.A_log": "model-00004-of-00011.safetensors",
|
| 145 |
+
"language_model.model.layers.18.linear_attn.conv1d.weight": "model-00004-of-00011.safetensors",
|
| 146 |
+
"language_model.model.layers.18.linear_attn.dt_bias": "model-00004-of-00011.safetensors",
|
| 147 |
+
"language_model.model.layers.18.linear_attn.in_proj_a.weight": "model-00004-of-00011.safetensors",
|
| 148 |
+
"language_model.model.layers.18.linear_attn.in_proj_b.weight": "model-00004-of-00011.safetensors",
|
| 149 |
+
"language_model.model.layers.18.linear_attn.in_proj_qkv.weight": "model-00004-of-00011.safetensors",
|
| 150 |
+
"language_model.model.layers.18.linear_attn.in_proj_z.weight": "model-00004-of-00011.safetensors",
|
| 151 |
+
"language_model.model.layers.18.linear_attn.norm.weight": "model-00004-of-00011.safetensors",
|
| 152 |
+
"language_model.model.layers.18.linear_attn.out_proj.weight": "model-00004-of-00011.safetensors",
|
| 153 |
+
"language_model.model.layers.18.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
|
| 154 |
+
"language_model.model.layers.18.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
|
| 155 |
+
"language_model.model.layers.18.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
|
| 156 |
+
"language_model.model.layers.18.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
|
| 157 |
+
"language_model.model.layers.19.input_layernorm.weight": "model-00004-of-00011.safetensors",
|
| 158 |
+
"language_model.model.layers.19.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
|
| 159 |
+
"language_model.model.layers.19.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
|
| 160 |
+
"language_model.model.layers.19.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
|
| 161 |
+
"language_model.model.layers.19.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
|
| 162 |
+
"language_model.model.layers.19.self_attn.k_norm.weight": "model-00004-of-00011.safetensors",
|
| 163 |
+
"language_model.model.layers.19.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
|
| 164 |
+
"language_model.model.layers.19.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
|
| 165 |
+
"language_model.model.layers.19.self_attn.q_norm.weight": "model-00004-of-00011.safetensors",
|
| 166 |
+
"language_model.model.layers.19.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
|
| 167 |
+
"language_model.model.layers.19.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
|
| 168 |
+
"language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00011.safetensors",
|
| 169 |
+
"language_model.model.layers.2.linear_attn.A_log": "model-00001-of-00011.safetensors",
|
| 170 |
+
"language_model.model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00011.safetensors",
|
| 171 |
+
"language_model.model.layers.2.linear_attn.dt_bias": "model-00001-of-00011.safetensors",
|
| 172 |
+
"language_model.model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00011.safetensors",
|
| 173 |
+
"language_model.model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00011.safetensors",
|
| 174 |
+
"language_model.model.layers.2.linear_attn.in_proj_qkv.weight": "model-00001-of-00011.safetensors",
|
| 175 |
+
"language_model.model.layers.2.linear_attn.in_proj_z.weight": "model-00001-of-00011.safetensors",
|
| 176 |
+
"language_model.model.layers.2.linear_attn.norm.weight": "model-00001-of-00011.safetensors",
|
| 177 |
+
"language_model.model.layers.2.linear_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 178 |
+
"language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
|
| 179 |
+
"language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
|
| 180 |
+
"language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
|
| 181 |
+
"language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
|
| 182 |
+
"language_model.model.layers.20.input_layernorm.weight": "model-00004-of-00011.safetensors",
|
| 183 |
+
"language_model.model.layers.20.linear_attn.A_log": "model-00004-of-00011.safetensors",
|
| 184 |
+
"language_model.model.layers.20.linear_attn.conv1d.weight": "model-00004-of-00011.safetensors",
|
| 185 |
+
"language_model.model.layers.20.linear_attn.dt_bias": "model-00004-of-00011.safetensors",
|
| 186 |
+
"language_model.model.layers.20.linear_attn.in_proj_a.weight": "model-00004-of-00011.safetensors",
|
| 187 |
+
"language_model.model.layers.20.linear_attn.in_proj_b.weight": "model-00004-of-00011.safetensors",
|
| 188 |
+
"language_model.model.layers.20.linear_attn.in_proj_qkv.weight": "model-00004-of-00011.safetensors",
|
| 189 |
+
"language_model.model.layers.20.linear_attn.in_proj_z.weight": "model-00004-of-00011.safetensors",
|
| 190 |
+
"language_model.model.layers.20.linear_attn.norm.weight": "model-00004-of-00011.safetensors",
|
| 191 |
+
"language_model.model.layers.20.linear_attn.out_proj.weight": "model-00004-of-00011.safetensors",
|
| 192 |
+
"language_model.model.layers.20.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
|
| 193 |
+
"language_model.model.layers.20.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
|
| 194 |
+
"language_model.model.layers.20.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
|
| 195 |
+
"language_model.model.layers.20.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
|
| 196 |
+
"language_model.model.layers.21.input_layernorm.weight": "model-00004-of-00011.safetensors",
|
| 197 |
+
"language_model.model.layers.21.linear_attn.A_log": "model-00004-of-00011.safetensors",
|
| 198 |
+
"language_model.model.layers.21.linear_attn.conv1d.weight": "model-00004-of-00011.safetensors",
|
| 199 |
+
"language_model.model.layers.21.linear_attn.dt_bias": "model-00004-of-00011.safetensors",
|
| 200 |
+
"language_model.model.layers.21.linear_attn.in_proj_a.weight": "model-00004-of-00011.safetensors",
|
| 201 |
+
"language_model.model.layers.21.linear_attn.in_proj_b.weight": "model-00004-of-00011.safetensors",
|
| 202 |
+
"language_model.model.layers.21.linear_attn.in_proj_qkv.weight": "model-00004-of-00011.safetensors",
|
| 203 |
+
"language_model.model.layers.21.linear_attn.in_proj_z.weight": "model-00004-of-00011.safetensors",
|
| 204 |
+
"language_model.model.layers.21.linear_attn.norm.weight": "model-00004-of-00011.safetensors",
|
| 205 |
+
"language_model.model.layers.21.linear_attn.out_proj.weight": "model-00004-of-00011.safetensors",
|
| 206 |
+
"language_model.model.layers.21.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
|
| 207 |
+
"language_model.model.layers.21.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
|
| 208 |
+
"language_model.model.layers.21.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
|
| 209 |
+
"language_model.model.layers.21.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
|
| 210 |
+
"language_model.model.layers.22.input_layernorm.weight": "model-00004-of-00011.safetensors",
|
| 211 |
+
"language_model.model.layers.22.linear_attn.A_log": "model-00004-of-00011.safetensors",
|
| 212 |
+
"language_model.model.layers.22.linear_attn.conv1d.weight": "model-00004-of-00011.safetensors",
|
| 213 |
+
"language_model.model.layers.22.linear_attn.dt_bias": "model-00004-of-00011.safetensors",
|
| 214 |
+
"language_model.model.layers.22.linear_attn.in_proj_a.weight": "model-00004-of-00011.safetensors",
|
| 215 |
+
"language_model.model.layers.22.linear_attn.in_proj_b.weight": "model-00004-of-00011.safetensors",
|
| 216 |
+
"language_model.model.layers.22.linear_attn.in_proj_qkv.weight": "model-00004-of-00011.safetensors",
|
| 217 |
+
"language_model.model.layers.22.linear_attn.in_proj_z.weight": "model-00004-of-00011.safetensors",
|
| 218 |
+
"language_model.model.layers.22.linear_attn.norm.weight": "model-00004-of-00011.safetensors",
|
| 219 |
+
"language_model.model.layers.22.linear_attn.out_proj.weight": "model-00004-of-00011.safetensors",
|
| 220 |
+
"language_model.model.layers.22.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
|
| 221 |
+
"language_model.model.layers.22.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
|
| 222 |
+
"language_model.model.layers.22.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
|
| 223 |
+
"language_model.model.layers.22.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
|
| 224 |
+
"language_model.model.layers.23.input_layernorm.weight": "model-00004-of-00011.safetensors",
|
| 225 |
+
"language_model.model.layers.23.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
|
| 226 |
+
"language_model.model.layers.23.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
|
| 227 |
+
"language_model.model.layers.23.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
|
| 228 |
+
"language_model.model.layers.23.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
|
| 229 |
+
"language_model.model.layers.23.self_attn.k_norm.weight": "model-00004-of-00011.safetensors",
|
| 230 |
+
"language_model.model.layers.23.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
|
| 231 |
+
"language_model.model.layers.23.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
|
| 232 |
+
"language_model.model.layers.23.self_attn.q_norm.weight": "model-00004-of-00011.safetensors",
|
| 233 |
+
"language_model.model.layers.23.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
|
| 234 |
+
"language_model.model.layers.23.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
|
| 235 |
+
"language_model.model.layers.24.input_layernorm.weight": "model-00004-of-00011.safetensors",
|
| 236 |
+
"language_model.model.layers.24.linear_attn.A_log": "model-00004-of-00011.safetensors",
|
| 237 |
+
"language_model.model.layers.24.linear_attn.conv1d.weight": "model-00004-of-00011.safetensors",
|
| 238 |
+
"language_model.model.layers.24.linear_attn.dt_bias": "model-00004-of-00011.safetensors",
|
| 239 |
+
"language_model.model.layers.24.linear_attn.in_proj_a.weight": "model-00004-of-00011.safetensors",
|
| 240 |
+
"language_model.model.layers.24.linear_attn.in_proj_b.weight": "model-00004-of-00011.safetensors",
|
| 241 |
+
"language_model.model.layers.24.linear_attn.in_proj_qkv.weight": "model-00004-of-00011.safetensors",
|
| 242 |
+
"language_model.model.layers.24.linear_attn.in_proj_z.weight": "model-00004-of-00011.safetensors",
|
| 243 |
+
"language_model.model.layers.24.linear_attn.norm.weight": "model-00004-of-00011.safetensors",
|
| 244 |
+
"language_model.model.layers.24.linear_attn.out_proj.weight": "model-00004-of-00011.safetensors",
|
| 245 |
+
"language_model.model.layers.24.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
|
| 246 |
+
"language_model.model.layers.24.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
|
| 247 |
+
"language_model.model.layers.24.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
|
| 248 |
+
"language_model.model.layers.24.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
|
| 249 |
+
"language_model.model.layers.25.input_layernorm.weight": "model-00005-of-00011.safetensors",
|
| 250 |
+
"language_model.model.layers.25.linear_attn.A_log": "model-00005-of-00011.safetensors",
|
| 251 |
+
"language_model.model.layers.25.linear_attn.conv1d.weight": "model-00005-of-00011.safetensors",
|
| 252 |
+
"language_model.model.layers.25.linear_attn.dt_bias": "model-00005-of-00011.safetensors",
|
| 253 |
+
"language_model.model.layers.25.linear_attn.in_proj_a.weight": "model-00005-of-00011.safetensors",
|
| 254 |
+
"language_model.model.layers.25.linear_attn.in_proj_b.weight": "model-00005-of-00011.safetensors",
|
| 255 |
+
"language_model.model.layers.25.linear_attn.in_proj_qkv.weight": "model-00005-of-00011.safetensors",
|
| 256 |
+
"language_model.model.layers.25.linear_attn.in_proj_z.weight": "model-00005-of-00011.safetensors",
|
| 257 |
+
"language_model.model.layers.25.linear_attn.norm.weight": "model-00005-of-00011.safetensors",
|
| 258 |
+
"language_model.model.layers.25.linear_attn.out_proj.weight": "model-00005-of-00011.safetensors",
|
| 259 |
+
"language_model.model.layers.25.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
|
| 260 |
+
"language_model.model.layers.25.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
|
| 261 |
+
"language_model.model.layers.25.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
|
| 262 |
+
"language_model.model.layers.25.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
|
| 263 |
+
"language_model.model.layers.26.input_layernorm.weight": "model-00005-of-00011.safetensors",
|
| 264 |
+
"language_model.model.layers.26.linear_attn.A_log": "model-00005-of-00011.safetensors",
|
| 265 |
+
"language_model.model.layers.26.linear_attn.conv1d.weight": "model-00005-of-00011.safetensors",
|
| 266 |
+
"language_model.model.layers.26.linear_attn.dt_bias": "model-00005-of-00011.safetensors",
|
| 267 |
+
"language_model.model.layers.26.linear_attn.in_proj_a.weight": "model-00005-of-00011.safetensors",
|
| 268 |
+
"language_model.model.layers.26.linear_attn.in_proj_b.weight": "model-00005-of-00011.safetensors",
|
| 269 |
+
"language_model.model.layers.26.linear_attn.in_proj_qkv.weight": "model-00005-of-00011.safetensors",
|
| 270 |
+
"language_model.model.layers.26.linear_attn.in_proj_z.weight": "model-00005-of-00011.safetensors",
|
| 271 |
+
"language_model.model.layers.26.linear_attn.norm.weight": "model-00005-of-00011.safetensors",
|
| 272 |
+
"language_model.model.layers.26.linear_attn.out_proj.weight": "model-00005-of-00011.safetensors",
|
| 273 |
+
"language_model.model.layers.26.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
|
| 274 |
+
"language_model.model.layers.26.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
|
| 275 |
+
"language_model.model.layers.26.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
|
| 276 |
+
"language_model.model.layers.26.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
|
| 277 |
+
"language_model.model.layers.27.input_layernorm.weight": "model-00005-of-00011.safetensors",
|
| 278 |
+
"language_model.model.layers.27.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
|
| 279 |
+
"language_model.model.layers.27.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
|
| 280 |
+
"language_model.model.layers.27.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
|
| 281 |
+
"language_model.model.layers.27.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
|
| 282 |
+
"language_model.model.layers.27.self_attn.k_norm.weight": "model-00005-of-00011.safetensors",
|
| 283 |
+
"language_model.model.layers.27.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
|
| 284 |
+
"language_model.model.layers.27.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
|
| 285 |
+
"language_model.model.layers.27.self_attn.q_norm.weight": "model-00005-of-00011.safetensors",
|
| 286 |
+
"language_model.model.layers.27.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
|
| 287 |
+
"language_model.model.layers.27.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
|
| 288 |
+
"language_model.model.layers.28.input_layernorm.weight": "model-00005-of-00011.safetensors",
|
| 289 |
+
"language_model.model.layers.28.linear_attn.A_log": "model-00005-of-00011.safetensors",
|
| 290 |
+
"language_model.model.layers.28.linear_attn.conv1d.weight": "model-00005-of-00011.safetensors",
|
| 291 |
+
"language_model.model.layers.28.linear_attn.dt_bias": "model-00005-of-00011.safetensors",
|
| 292 |
+
"language_model.model.layers.28.linear_attn.in_proj_a.weight": "model-00005-of-00011.safetensors",
|
| 293 |
+
"language_model.model.layers.28.linear_attn.in_proj_b.weight": "model-00005-of-00011.safetensors",
|
| 294 |
+
"language_model.model.layers.28.linear_attn.in_proj_qkv.weight": "model-00005-of-00011.safetensors",
|
| 295 |
+
"language_model.model.layers.28.linear_attn.in_proj_z.weight": "model-00005-of-00011.safetensors",
|
| 296 |
+
"language_model.model.layers.28.linear_attn.norm.weight": "model-00005-of-00011.safetensors",
|
| 297 |
+
"language_model.model.layers.28.linear_attn.out_proj.weight": "model-00005-of-00011.safetensors",
|
| 298 |
+
"language_model.model.layers.28.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
|
| 299 |
+
"language_model.model.layers.28.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
|
| 300 |
+
"language_model.model.layers.28.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
|
| 301 |
+
"language_model.model.layers.28.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
|
| 302 |
+
"language_model.model.layers.29.input_layernorm.weight": "model-00005-of-00011.safetensors",
|
| 303 |
+
"language_model.model.layers.29.linear_attn.A_log": "model-00005-of-00011.safetensors",
|
| 304 |
+
"language_model.model.layers.29.linear_attn.conv1d.weight": "model-00005-of-00011.safetensors",
|
| 305 |
+
"language_model.model.layers.29.linear_attn.dt_bias": "model-00005-of-00011.safetensors",
|
| 306 |
+
"language_model.model.layers.29.linear_attn.in_proj_a.weight": "model-00005-of-00011.safetensors",
|
| 307 |
+
"language_model.model.layers.29.linear_attn.in_proj_b.weight": "model-00005-of-00011.safetensors",
|
| 308 |
+
"language_model.model.layers.29.linear_attn.in_proj_qkv.weight": "model-00005-of-00011.safetensors",
|
| 309 |
+
"language_model.model.layers.29.linear_attn.in_proj_z.weight": "model-00005-of-00011.safetensors",
|
| 310 |
+
"language_model.model.layers.29.linear_attn.norm.weight": "model-00005-of-00011.safetensors",
|
| 311 |
+
"language_model.model.layers.29.linear_attn.out_proj.weight": "model-00005-of-00011.safetensors",
|
| 312 |
+
"language_model.model.layers.29.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
|
| 313 |
+
"language_model.model.layers.29.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
|
| 314 |
+
"language_model.model.layers.29.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
|
| 315 |
+
"language_model.model.layers.29.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
|
| 316 |
+
"language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00011.safetensors",
|
| 317 |
+
"language_model.model.layers.3.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
|
| 318 |
+
"language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
|
| 319 |
+
"language_model.model.layers.3.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
|
| 320 |
+
"language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
|
| 321 |
+
"language_model.model.layers.3.self_attn.k_norm.weight": "model-00001-of-00011.safetensors",
|
| 322 |
+
"language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 323 |
+
"language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
|
| 324 |
+
"language_model.model.layers.3.self_attn.q_norm.weight": "model-00001-of-00011.safetensors",
|
| 325 |
+
"language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 326 |
+
"language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 327 |
+
"language_model.model.layers.30.input_layernorm.weight": "model-00005-of-00011.safetensors",
|
| 328 |
+
"language_model.model.layers.30.linear_attn.A_log": "model-00005-of-00011.safetensors",
|
| 329 |
+
"language_model.model.layers.30.linear_attn.conv1d.weight": "model-00005-of-00011.safetensors",
|
| 330 |
+
"language_model.model.layers.30.linear_attn.dt_bias": "model-00005-of-00011.safetensors",
|
| 331 |
+
"language_model.model.layers.30.linear_attn.in_proj_a.weight": "model-00005-of-00011.safetensors",
|
| 332 |
+
"language_model.model.layers.30.linear_attn.in_proj_b.weight": "model-00005-of-00011.safetensors",
|
| 333 |
+
"language_model.model.layers.30.linear_attn.in_proj_qkv.weight": "model-00005-of-00011.safetensors",
|
| 334 |
+
"language_model.model.layers.30.linear_attn.in_proj_z.weight": "model-00005-of-00011.safetensors",
|
| 335 |
+
"language_model.model.layers.30.linear_attn.norm.weight": "model-00005-of-00011.safetensors",
|
| 336 |
+
"language_model.model.layers.30.linear_attn.out_proj.weight": "model-00005-of-00011.safetensors",
|
| 337 |
+
"language_model.model.layers.30.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
|
| 338 |
+
"language_model.model.layers.30.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
|
| 339 |
+
"language_model.model.layers.30.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
|
| 340 |
+
"language_model.model.layers.30.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
|
| 341 |
+
"language_model.model.layers.31.input_layernorm.weight": "model-00005-of-00011.safetensors",
|
| 342 |
+
"language_model.model.layers.31.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
|
| 343 |
+
"language_model.model.layers.31.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
|
| 344 |
+
"language_model.model.layers.31.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
|
| 345 |
+
"language_model.model.layers.31.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
|
| 346 |
+
"language_model.model.layers.31.self_attn.k_norm.weight": "model-00005-of-00011.safetensors",
|
| 347 |
+
"language_model.model.layers.31.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
|
| 348 |
+
"language_model.model.layers.31.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
|
| 349 |
+
"language_model.model.layers.31.self_attn.q_norm.weight": "model-00005-of-00011.safetensors",
|
| 350 |
+
"language_model.model.layers.31.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
|
| 351 |
+
"language_model.model.layers.31.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
|
| 352 |
+
"language_model.model.layers.32.input_layernorm.weight": "model-00006-of-00011.safetensors",
|
| 353 |
+
"language_model.model.layers.32.linear_attn.A_log": "model-00006-of-00011.safetensors",
|
| 354 |
+
"language_model.model.layers.32.linear_attn.conv1d.weight": "model-00006-of-00011.safetensors",
|
| 355 |
+
"language_model.model.layers.32.linear_attn.dt_bias": "model-00006-of-00011.safetensors",
|
| 356 |
+
"language_model.model.layers.32.linear_attn.in_proj_a.weight": "model-00006-of-00011.safetensors",
|
| 357 |
+
"language_model.model.layers.32.linear_attn.in_proj_b.weight": "model-00006-of-00011.safetensors",
|
| 358 |
+
"language_model.model.layers.32.linear_attn.in_proj_qkv.weight": "model-00006-of-00011.safetensors",
|
| 359 |
+
"language_model.model.layers.32.linear_attn.in_proj_z.weight": "model-00006-of-00011.safetensors",
|
| 360 |
+
"language_model.model.layers.32.linear_attn.norm.weight": "model-00006-of-00011.safetensors",
|
| 361 |
+
"language_model.model.layers.32.linear_attn.out_proj.weight": "model-00006-of-00011.safetensors",
|
| 362 |
+
"language_model.model.layers.32.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
|
| 363 |
+
"language_model.model.layers.32.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
|
| 364 |
+
"language_model.model.layers.32.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
|
| 365 |
+
"language_model.model.layers.32.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
|
| 366 |
+
"language_model.model.layers.33.input_layernorm.weight": "model-00006-of-00011.safetensors",
|
| 367 |
+
"language_model.model.layers.33.linear_attn.A_log": "model-00006-of-00011.safetensors",
|
| 368 |
+
"language_model.model.layers.33.linear_attn.conv1d.weight": "model-00006-of-00011.safetensors",
|
| 369 |
+
"language_model.model.layers.33.linear_attn.dt_bias": "model-00006-of-00011.safetensors",
|
| 370 |
+
"language_model.model.layers.33.linear_attn.in_proj_a.weight": "model-00006-of-00011.safetensors",
|
| 371 |
+
"language_model.model.layers.33.linear_attn.in_proj_b.weight": "model-00006-of-00011.safetensors",
|
| 372 |
+
"language_model.model.layers.33.linear_attn.in_proj_qkv.weight": "model-00006-of-00011.safetensors",
|
| 373 |
+
"language_model.model.layers.33.linear_attn.in_proj_z.weight": "model-00006-of-00011.safetensors",
|
| 374 |
+
"language_model.model.layers.33.linear_attn.norm.weight": "model-00006-of-00011.safetensors",
|
| 375 |
+
"language_model.model.layers.33.linear_attn.out_proj.weight": "model-00006-of-00011.safetensors",
|
| 376 |
+
"language_model.model.layers.33.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
|
| 377 |
+
"language_model.model.layers.33.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
|
| 378 |
+
"language_model.model.layers.33.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
|
| 379 |
+
"language_model.model.layers.33.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
|
| 380 |
+
"language_model.model.layers.34.input_layernorm.weight": "model-00006-of-00011.safetensors",
|
| 381 |
+
"language_model.model.layers.34.linear_attn.A_log": "model-00006-of-00011.safetensors",
|
| 382 |
+
"language_model.model.layers.34.linear_attn.conv1d.weight": "model-00006-of-00011.safetensors",
|
| 383 |
+
"language_model.model.layers.34.linear_attn.dt_bias": "model-00006-of-00011.safetensors",
|
| 384 |
+
"language_model.model.layers.34.linear_attn.in_proj_a.weight": "model-00006-of-00011.safetensors",
|
| 385 |
+
"language_model.model.layers.34.linear_attn.in_proj_b.weight": "model-00006-of-00011.safetensors",
|
| 386 |
+
"language_model.model.layers.34.linear_attn.in_proj_qkv.weight": "model-00006-of-00011.safetensors",
|
| 387 |
+
"language_model.model.layers.34.linear_attn.in_proj_z.weight": "model-00006-of-00011.safetensors",
|
| 388 |
+
"language_model.model.layers.34.linear_attn.norm.weight": "model-00006-of-00011.safetensors",
|
| 389 |
+
"language_model.model.layers.34.linear_attn.out_proj.weight": "model-00006-of-00011.safetensors",
|
| 390 |
+
"language_model.model.layers.34.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
|
| 391 |
+
"language_model.model.layers.34.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
|
| 392 |
+
"language_model.model.layers.34.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
|
| 393 |
+
"language_model.model.layers.34.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
|
| 394 |
+
"language_model.model.layers.35.input_layernorm.weight": "model-00006-of-00011.safetensors",
|
| 395 |
+
"language_model.model.layers.35.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
|
| 396 |
+
"language_model.model.layers.35.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
|
| 397 |
+
"language_model.model.layers.35.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
|
| 398 |
+
"language_model.model.layers.35.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
|
| 399 |
+
"language_model.model.layers.35.self_attn.k_norm.weight": "model-00006-of-00011.safetensors",
|
| 400 |
+
"language_model.model.layers.35.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
|
| 401 |
+
"language_model.model.layers.35.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
|
| 402 |
+
"language_model.model.layers.35.self_attn.q_norm.weight": "model-00006-of-00011.safetensors",
|
| 403 |
+
"language_model.model.layers.35.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
|
| 404 |
+
"language_model.model.layers.35.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
|
| 405 |
+
"language_model.model.layers.36.input_layernorm.weight": "model-00006-of-00011.safetensors",
|
| 406 |
+
"language_model.model.layers.36.linear_attn.A_log": "model-00006-of-00011.safetensors",
|
| 407 |
+
"language_model.model.layers.36.linear_attn.conv1d.weight": "model-00006-of-00011.safetensors",
|
| 408 |
+
"language_model.model.layers.36.linear_attn.dt_bias": "model-00006-of-00011.safetensors",
|
| 409 |
+
"language_model.model.layers.36.linear_attn.in_proj_a.weight": "model-00006-of-00011.safetensors",
|
| 410 |
+
"language_model.model.layers.36.linear_attn.in_proj_b.weight": "model-00006-of-00011.safetensors",
|
| 411 |
+
"language_model.model.layers.36.linear_attn.in_proj_qkv.weight": "model-00006-of-00011.safetensors",
|
| 412 |
+
"language_model.model.layers.36.linear_attn.in_proj_z.weight": "model-00006-of-00011.safetensors",
|
| 413 |
+
"language_model.model.layers.36.linear_attn.norm.weight": "model-00006-of-00011.safetensors",
|
| 414 |
+
"language_model.model.layers.36.linear_attn.out_proj.weight": "model-00006-of-00011.safetensors",
|
| 415 |
+
"language_model.model.layers.36.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
|
| 416 |
+
"language_model.model.layers.36.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
|
| 417 |
+
"language_model.model.layers.36.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
|
| 418 |
+
"language_model.model.layers.36.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
|
| 419 |
+
"language_model.model.layers.37.input_layernorm.weight": "model-00006-of-00011.safetensors",
|
| 420 |
+
"language_model.model.layers.37.linear_attn.A_log": "model-00006-of-00011.safetensors",
|
| 421 |
+
"language_model.model.layers.37.linear_attn.conv1d.weight": "model-00006-of-00011.safetensors",
|
| 422 |
+
"language_model.model.layers.37.linear_attn.dt_bias": "model-00006-of-00011.safetensors",
|
| 423 |
+
"language_model.model.layers.37.linear_attn.in_proj_a.weight": "model-00006-of-00011.safetensors",
|
| 424 |
+
"language_model.model.layers.37.linear_attn.in_proj_b.weight": "model-00006-of-00011.safetensors",
|
| 425 |
+
"language_model.model.layers.37.linear_attn.in_proj_qkv.weight": "model-00006-of-00011.safetensors",
|
| 426 |
+
"language_model.model.layers.37.linear_attn.in_proj_z.weight": "model-00006-of-00011.safetensors",
|
| 427 |
+
"language_model.model.layers.37.linear_attn.norm.weight": "model-00006-of-00011.safetensors",
|
| 428 |
+
"language_model.model.layers.37.linear_attn.out_proj.weight": "model-00006-of-00011.safetensors",
|
| 429 |
+
"language_model.model.layers.37.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
|
| 430 |
+
"language_model.model.layers.37.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
|
| 431 |
+
"language_model.model.layers.37.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
|
| 432 |
+
"language_model.model.layers.37.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
|
| 433 |
+
"language_model.model.layers.38.input_layernorm.weight": "model-00006-of-00011.safetensors",
|
| 434 |
+
"language_model.model.layers.38.linear_attn.A_log": "model-00006-of-00011.safetensors",
|
| 435 |
+
"language_model.model.layers.38.linear_attn.conv1d.weight": "model-00006-of-00011.safetensors",
|
| 436 |
+
"language_model.model.layers.38.linear_attn.dt_bias": "model-00006-of-00011.safetensors",
|
| 437 |
+
"language_model.model.layers.38.linear_attn.in_proj_a.weight": "model-00006-of-00011.safetensors",
|
| 438 |
+
"language_model.model.layers.38.linear_attn.in_proj_b.weight": "model-00006-of-00011.safetensors",
|
| 439 |
+
"language_model.model.layers.38.linear_attn.in_proj_qkv.weight": "model-00006-of-00011.safetensors",
|
| 440 |
+
"language_model.model.layers.38.linear_attn.in_proj_z.weight": "model-00006-of-00011.safetensors",
|
| 441 |
+
"language_model.model.layers.38.linear_attn.norm.weight": "model-00006-of-00011.safetensors",
|
| 442 |
+
"language_model.model.layers.38.linear_attn.out_proj.weight": "model-00006-of-00011.safetensors",
|
| 443 |
+
"language_model.model.layers.38.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
|
| 444 |
+
"language_model.model.layers.38.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
|
| 445 |
+
"language_model.model.layers.38.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
|
| 446 |
+
"language_model.model.layers.38.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
|
| 447 |
+
"language_model.model.layers.39.input_layernorm.weight": "model-00007-of-00011.safetensors",
|
| 448 |
+
"language_model.model.layers.39.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
|
| 449 |
+
"language_model.model.layers.39.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
|
| 450 |
+
"language_model.model.layers.39.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
|
| 451 |
+
"language_model.model.layers.39.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
|
| 452 |
+
"language_model.model.layers.39.self_attn.k_norm.weight": "model-00007-of-00011.safetensors",
|
| 453 |
+
"language_model.model.layers.39.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
|
| 454 |
+
"language_model.model.layers.39.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
|
| 455 |
+
"language_model.model.layers.39.self_attn.q_norm.weight": "model-00007-of-00011.safetensors",
|
| 456 |
+
"language_model.model.layers.39.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
|
| 457 |
+
"language_model.model.layers.39.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
|
| 458 |
+
"language_model.model.layers.4.input_layernorm.weight": "model-00002-of-00011.safetensors",
|
| 459 |
+
"language_model.model.layers.4.linear_attn.A_log": "model-00002-of-00011.safetensors",
|
| 460 |
+
"language_model.model.layers.4.linear_attn.conv1d.weight": "model-00002-of-00011.safetensors",
|
| 461 |
+
"language_model.model.layers.4.linear_attn.dt_bias": "model-00002-of-00011.safetensors",
|
| 462 |
+
"language_model.model.layers.4.linear_attn.in_proj_a.weight": "model-00002-of-00011.safetensors",
|
| 463 |
+
"language_model.model.layers.4.linear_attn.in_proj_b.weight": "model-00002-of-00011.safetensors",
|
| 464 |
+
"language_model.model.layers.4.linear_attn.in_proj_qkv.weight": "model-00002-of-00011.safetensors",
|
| 465 |
+
"language_model.model.layers.4.linear_attn.in_proj_z.weight": "model-00002-of-00011.safetensors",
|
| 466 |
+
"language_model.model.layers.4.linear_attn.norm.weight": "model-00002-of-00011.safetensors",
|
| 467 |
+
"language_model.model.layers.4.linear_attn.out_proj.weight": "model-00002-of-00011.safetensors",
|
| 468 |
+
"language_model.model.layers.4.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
|
| 469 |
+
"language_model.model.layers.4.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
|
| 470 |
+
"language_model.model.layers.4.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
|
| 471 |
+
"language_model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
|
| 472 |
+
"language_model.model.layers.40.input_layernorm.weight": "model-00007-of-00011.safetensors",
|
| 473 |
+
"language_model.model.layers.40.linear_attn.A_log": "model-00007-of-00011.safetensors",
|
| 474 |
+
"language_model.model.layers.40.linear_attn.conv1d.weight": "model-00007-of-00011.safetensors",
|
| 475 |
+
"language_model.model.layers.40.linear_attn.dt_bias": "model-00007-of-00011.safetensors",
|
| 476 |
+
"language_model.model.layers.40.linear_attn.in_proj_a.weight": "model-00007-of-00011.safetensors",
|
| 477 |
+
"language_model.model.layers.40.linear_attn.in_proj_b.weight": "model-00007-of-00011.safetensors",
|
| 478 |
+
"language_model.model.layers.40.linear_attn.in_proj_qkv.weight": "model-00007-of-00011.safetensors",
|
| 479 |
+
"language_model.model.layers.40.linear_attn.in_proj_z.weight": "model-00007-of-00011.safetensors",
|
| 480 |
+
"language_model.model.layers.40.linear_attn.norm.weight": "model-00007-of-00011.safetensors",
|
| 481 |
+
"language_model.model.layers.40.linear_attn.out_proj.weight": "model-00007-of-00011.safetensors",
|
| 482 |
+
"language_model.model.layers.40.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
|
| 483 |
+
"language_model.model.layers.40.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
|
| 484 |
+
"language_model.model.layers.40.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
|
| 485 |
+
"language_model.model.layers.40.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
|
| 486 |
+
"language_model.model.layers.41.input_layernorm.weight": "model-00007-of-00011.safetensors",
|
| 487 |
+
"language_model.model.layers.41.linear_attn.A_log": "model-00007-of-00011.safetensors",
|
| 488 |
+
"language_model.model.layers.41.linear_attn.conv1d.weight": "model-00007-of-00011.safetensors",
|
| 489 |
+
"language_model.model.layers.41.linear_attn.dt_bias": "model-00007-of-00011.safetensors",
|
| 490 |
+
"language_model.model.layers.41.linear_attn.in_proj_a.weight": "model-00007-of-00011.safetensors",
|
| 491 |
+
"language_model.model.layers.41.linear_attn.in_proj_b.weight": "model-00007-of-00011.safetensors",
|
| 492 |
+
"language_model.model.layers.41.linear_attn.in_proj_qkv.weight": "model-00007-of-00011.safetensors",
|
| 493 |
+
"language_model.model.layers.41.linear_attn.in_proj_z.weight": "model-00007-of-00011.safetensors",
|
| 494 |
+
"language_model.model.layers.41.linear_attn.norm.weight": "model-00007-of-00011.safetensors",
|
| 495 |
+
"language_model.model.layers.41.linear_attn.out_proj.weight": "model-00007-of-00011.safetensors",
|
| 496 |
+
"language_model.model.layers.41.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
|
| 497 |
+
"language_model.model.layers.41.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
|
| 498 |
+
"language_model.model.layers.41.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
|
| 499 |
+
"language_model.model.layers.41.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
|
| 500 |
+
"language_model.model.layers.42.input_layernorm.weight": "model-00007-of-00011.safetensors",
|
| 501 |
+
"language_model.model.layers.42.linear_attn.A_log": "model-00007-of-00011.safetensors",
|
| 502 |
+
"language_model.model.layers.42.linear_attn.conv1d.weight": "model-00007-of-00011.safetensors",
|
| 503 |
+
"language_model.model.layers.42.linear_attn.dt_bias": "model-00007-of-00011.safetensors",
|
| 504 |
+
"language_model.model.layers.42.linear_attn.in_proj_a.weight": "model-00007-of-00011.safetensors",
|
| 505 |
+
"language_model.model.layers.42.linear_attn.in_proj_b.weight": "model-00007-of-00011.safetensors",
|
| 506 |
+
"language_model.model.layers.42.linear_attn.in_proj_qkv.weight": "model-00007-of-00011.safetensors",
|
| 507 |
+
"language_model.model.layers.42.linear_attn.in_proj_z.weight": "model-00007-of-00011.safetensors",
|
| 508 |
+
"language_model.model.layers.42.linear_attn.norm.weight": "model-00007-of-00011.safetensors",
|
| 509 |
+
"language_model.model.layers.42.linear_attn.out_proj.weight": "model-00007-of-00011.safetensors",
|
| 510 |
+
"language_model.model.layers.42.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
|
| 511 |
+
"language_model.model.layers.42.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
|
| 512 |
+
"language_model.model.layers.42.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
|
| 513 |
+
"language_model.model.layers.42.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
|
| 514 |
+
"language_model.model.layers.43.input_layernorm.weight": "model-00007-of-00011.safetensors",
|
| 515 |
+
"language_model.model.layers.43.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
|
| 516 |
+
"language_model.model.layers.43.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
|
| 517 |
+
"language_model.model.layers.43.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
|
| 518 |
+
"language_model.model.layers.43.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
|
| 519 |
+
"language_model.model.layers.43.self_attn.k_norm.weight": "model-00007-of-00011.safetensors",
|
| 520 |
+
"language_model.model.layers.43.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
|
| 521 |
+
"language_model.model.layers.43.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
|
| 522 |
+
"language_model.model.layers.43.self_attn.q_norm.weight": "model-00007-of-00011.safetensors",
|
| 523 |
+
"language_model.model.layers.43.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
|
| 524 |
+
"language_model.model.layers.43.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
|
| 525 |
+
"language_model.model.layers.44.input_layernorm.weight": "model-00007-of-00011.safetensors",
|
| 526 |
+
"language_model.model.layers.44.linear_attn.A_log": "model-00007-of-00011.safetensors",
|
| 527 |
+
"language_model.model.layers.44.linear_attn.conv1d.weight": "model-00007-of-00011.safetensors",
|
| 528 |
+
"language_model.model.layers.44.linear_attn.dt_bias": "model-00007-of-00011.safetensors",
|
| 529 |
+
"language_model.model.layers.44.linear_attn.in_proj_a.weight": "model-00007-of-00011.safetensors",
|
| 530 |
+
"language_model.model.layers.44.linear_attn.in_proj_b.weight": "model-00007-of-00011.safetensors",
|
| 531 |
+
"language_model.model.layers.44.linear_attn.in_proj_qkv.weight": "model-00007-of-00011.safetensors",
|
| 532 |
+
"language_model.model.layers.44.linear_attn.in_proj_z.weight": "model-00007-of-00011.safetensors",
|
| 533 |
+
"language_model.model.layers.44.linear_attn.norm.weight": "model-00007-of-00011.safetensors",
|
| 534 |
+
"language_model.model.layers.44.linear_attn.out_proj.weight": "model-00007-of-00011.safetensors",
|
| 535 |
+
"language_model.model.layers.44.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
|
| 536 |
+
"language_model.model.layers.44.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
|
| 537 |
+
"language_model.model.layers.44.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
|
| 538 |
+
"language_model.model.layers.44.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
|
| 539 |
+
"language_model.model.layers.45.input_layernorm.weight": "model-00007-of-00011.safetensors",
|
| 540 |
+
"language_model.model.layers.45.linear_attn.A_log": "model-00007-of-00011.safetensors",
|
| 541 |
+
"language_model.model.layers.45.linear_attn.conv1d.weight": "model-00007-of-00011.safetensors",
|
| 542 |
+
"language_model.model.layers.45.linear_attn.dt_bias": "model-00007-of-00011.safetensors",
|
| 543 |
+
"language_model.model.layers.45.linear_attn.in_proj_a.weight": "model-00007-of-00011.safetensors",
|
| 544 |
+
"language_model.model.layers.45.linear_attn.in_proj_b.weight": "model-00007-of-00011.safetensors",
|
| 545 |
+
"language_model.model.layers.45.linear_attn.in_proj_qkv.weight": "model-00007-of-00011.safetensors",
|
| 546 |
+
"language_model.model.layers.45.linear_attn.in_proj_z.weight": "model-00007-of-00011.safetensors",
|
| 547 |
+
"language_model.model.layers.45.linear_attn.norm.weight": "model-00007-of-00011.safetensors",
|
| 548 |
+
"language_model.model.layers.45.linear_attn.out_proj.weight": "model-00007-of-00011.safetensors",
|
| 549 |
+
"language_model.model.layers.45.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
|
| 550 |
+
"language_model.model.layers.45.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
|
| 551 |
+
"language_model.model.layers.45.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
|
| 552 |
+
"language_model.model.layers.45.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
|
| 553 |
+
"language_model.model.layers.46.input_layernorm.weight": "model-00008-of-00011.safetensors",
|
| 554 |
+
"language_model.model.layers.46.linear_attn.A_log": "model-00008-of-00011.safetensors",
|
| 555 |
+
"language_model.model.layers.46.linear_attn.conv1d.weight": "model-00008-of-00011.safetensors",
|
| 556 |
+
"language_model.model.layers.46.linear_attn.dt_bias": "model-00008-of-00011.safetensors",
|
| 557 |
+
"language_model.model.layers.46.linear_attn.in_proj_a.weight": "model-00008-of-00011.safetensors",
|
| 558 |
+
"language_model.model.layers.46.linear_attn.in_proj_b.weight": "model-00008-of-00011.safetensors",
|
| 559 |
+
"language_model.model.layers.46.linear_attn.in_proj_qkv.weight": "model-00008-of-00011.safetensors",
|
| 560 |
+
"language_model.model.layers.46.linear_attn.in_proj_z.weight": "model-00008-of-00011.safetensors",
|
| 561 |
+
"language_model.model.layers.46.linear_attn.norm.weight": "model-00008-of-00011.safetensors",
|
| 562 |
+
"language_model.model.layers.46.linear_attn.out_proj.weight": "model-00008-of-00011.safetensors",
|
| 563 |
+
"language_model.model.layers.46.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
|
| 564 |
+
"language_model.model.layers.46.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
|
| 565 |
+
"language_model.model.layers.46.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
|
| 566 |
+
"language_model.model.layers.46.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
|
| 567 |
+
"language_model.model.layers.47.input_layernorm.weight": "model-00008-of-00011.safetensors",
|
| 568 |
+
"language_model.model.layers.47.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
|
| 569 |
+
"language_model.model.layers.47.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
|
| 570 |
+
"language_model.model.layers.47.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
|
| 571 |
+
"language_model.model.layers.47.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
|
| 572 |
+
"language_model.model.layers.47.self_attn.k_norm.weight": "model-00008-of-00011.safetensors",
|
| 573 |
+
"language_model.model.layers.47.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
|
| 574 |
+
"language_model.model.layers.47.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
|
| 575 |
+
"language_model.model.layers.47.self_attn.q_norm.weight": "model-00008-of-00011.safetensors",
|
| 576 |
+
"language_model.model.layers.47.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
|
| 577 |
+
"language_model.model.layers.47.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
|
| 578 |
+
"language_model.model.layers.48.input_layernorm.weight": "model-00008-of-00011.safetensors",
|
| 579 |
+
"language_model.model.layers.48.linear_attn.A_log": "model-00008-of-00011.safetensors",
|
| 580 |
+
"language_model.model.layers.48.linear_attn.conv1d.weight": "model-00008-of-00011.safetensors",
|
| 581 |
+
"language_model.model.layers.48.linear_attn.dt_bias": "model-00008-of-00011.safetensors",
|
| 582 |
+
"language_model.model.layers.48.linear_attn.in_proj_a.weight": "model-00008-of-00011.safetensors",
|
| 583 |
+
"language_model.model.layers.48.linear_attn.in_proj_b.weight": "model-00008-of-00011.safetensors",
|
| 584 |
+
"language_model.model.layers.48.linear_attn.in_proj_qkv.weight": "model-00008-of-00011.safetensors",
|
| 585 |
+
"language_model.model.layers.48.linear_attn.in_proj_z.weight": "model-00008-of-00011.safetensors",
|
| 586 |
+
"language_model.model.layers.48.linear_attn.norm.weight": "model-00008-of-00011.safetensors",
|
| 587 |
+
"language_model.model.layers.48.linear_attn.out_proj.weight": "model-00008-of-00011.safetensors",
|
| 588 |
+
"language_model.model.layers.48.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
|
| 589 |
+
"language_model.model.layers.48.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
|
| 590 |
+
"language_model.model.layers.48.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
|
| 591 |
+
"language_model.model.layers.48.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
|
| 592 |
+
"language_model.model.layers.49.input_layernorm.weight": "model-00008-of-00011.safetensors",
|
| 593 |
+
"language_model.model.layers.49.linear_attn.A_log": "model-00008-of-00011.safetensors",
|
| 594 |
+
"language_model.model.layers.49.linear_attn.conv1d.weight": "model-00008-of-00011.safetensors",
|
| 595 |
+
"language_model.model.layers.49.linear_attn.dt_bias": "model-00008-of-00011.safetensors",
|
| 596 |
+
"language_model.model.layers.49.linear_attn.in_proj_a.weight": "model-00008-of-00011.safetensors",
|
| 597 |
+
"language_model.model.layers.49.linear_attn.in_proj_b.weight": "model-00008-of-00011.safetensors",
|
| 598 |
+
"language_model.model.layers.49.linear_attn.in_proj_qkv.weight": "model-00008-of-00011.safetensors",
|
| 599 |
+
"language_model.model.layers.49.linear_attn.in_proj_z.weight": "model-00008-of-00011.safetensors",
|
| 600 |
+
"language_model.model.layers.49.linear_attn.norm.weight": "model-00008-of-00011.safetensors",
|
| 601 |
+
"language_model.model.layers.49.linear_attn.out_proj.weight": "model-00008-of-00011.safetensors",
|
| 602 |
+
"language_model.model.layers.49.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
|
| 603 |
+
"language_model.model.layers.49.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
|
| 604 |
+
"language_model.model.layers.49.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
|
| 605 |
+
"language_model.model.layers.49.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
|
| 606 |
+
"language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00011.safetensors",
|
| 607 |
+
"language_model.model.layers.5.linear_attn.A_log": "model-00002-of-00011.safetensors",
|
| 608 |
+
"language_model.model.layers.5.linear_attn.conv1d.weight": "model-00002-of-00011.safetensors",
|
| 609 |
+
"language_model.model.layers.5.linear_attn.dt_bias": "model-00002-of-00011.safetensors",
|
| 610 |
+
"language_model.model.layers.5.linear_attn.in_proj_a.weight": "model-00002-of-00011.safetensors",
|
| 611 |
+
"language_model.model.layers.5.linear_attn.in_proj_b.weight": "model-00002-of-00011.safetensors",
|
| 612 |
+
"language_model.model.layers.5.linear_attn.in_proj_qkv.weight": "model-00002-of-00011.safetensors",
|
| 613 |
+
"language_model.model.layers.5.linear_attn.in_proj_z.weight": "model-00002-of-00011.safetensors",
|
| 614 |
+
"language_model.model.layers.5.linear_attn.norm.weight": "model-00002-of-00011.safetensors",
|
| 615 |
+
"language_model.model.layers.5.linear_attn.out_proj.weight": "model-00002-of-00011.safetensors",
|
| 616 |
+
"language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
|
| 617 |
+
"language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
|
| 618 |
+
"language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
|
| 619 |
+
"language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
|
| 620 |
+
"language_model.model.layers.50.input_layernorm.weight": "model-00008-of-00011.safetensors",
|
| 621 |
+
"language_model.model.layers.50.linear_attn.A_log": "model-00008-of-00011.safetensors",
|
| 622 |
+
"language_model.model.layers.50.linear_attn.conv1d.weight": "model-00008-of-00011.safetensors",
|
| 623 |
+
"language_model.model.layers.50.linear_attn.dt_bias": "model-00008-of-00011.safetensors",
|
| 624 |
+
"language_model.model.layers.50.linear_attn.in_proj_a.weight": "model-00008-of-00011.safetensors",
|
| 625 |
+
"language_model.model.layers.50.linear_attn.in_proj_b.weight": "model-00008-of-00011.safetensors",
|
| 626 |
+
"language_model.model.layers.50.linear_attn.in_proj_qkv.weight": "model-00008-of-00011.safetensors",
|
| 627 |
+
"language_model.model.layers.50.linear_attn.in_proj_z.weight": "model-00008-of-00011.safetensors",
|
| 628 |
+
"language_model.model.layers.50.linear_attn.norm.weight": "model-00008-of-00011.safetensors",
|
| 629 |
+
"language_model.model.layers.50.linear_attn.out_proj.weight": "model-00008-of-00011.safetensors",
|
| 630 |
+
"language_model.model.layers.50.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
|
| 631 |
+
"language_model.model.layers.50.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
|
| 632 |
+
"language_model.model.layers.50.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
|
| 633 |
+
"language_model.model.layers.50.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
|
| 634 |
+
"language_model.model.layers.51.input_layernorm.weight": "model-00008-of-00011.safetensors",
|
| 635 |
+
"language_model.model.layers.51.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
|
| 636 |
+
"language_model.model.layers.51.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
|
| 637 |
+
"language_model.model.layers.51.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
|
| 638 |
+
"language_model.model.layers.51.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
|
| 639 |
+
"language_model.model.layers.51.self_attn.k_norm.weight": "model-00008-of-00011.safetensors",
|
| 640 |
+
"language_model.model.layers.51.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
|
| 641 |
+
"language_model.model.layers.51.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
|
| 642 |
+
"language_model.model.layers.51.self_attn.q_norm.weight": "model-00008-of-00011.safetensors",
|
| 643 |
+
"language_model.model.layers.51.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
|
| 644 |
+
"language_model.model.layers.51.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
|
| 645 |
+
"language_model.model.layers.52.input_layernorm.weight": "model-00008-of-00011.safetensors",
|
| 646 |
+
"language_model.model.layers.52.linear_attn.A_log": "model-00008-of-00011.safetensors",
|
| 647 |
+
"language_model.model.layers.52.linear_attn.conv1d.weight": "model-00008-of-00011.safetensors",
|
| 648 |
+
"language_model.model.layers.52.linear_attn.dt_bias": "model-00008-of-00011.safetensors",
|
| 649 |
+
"language_model.model.layers.52.linear_attn.in_proj_a.weight": "model-00008-of-00011.safetensors",
|
| 650 |
+
"language_model.model.layers.52.linear_attn.in_proj_b.weight": "model-00008-of-00011.safetensors",
|
| 651 |
+
"language_model.model.layers.52.linear_attn.in_proj_qkv.weight": "model-00008-of-00011.safetensors",
|
| 652 |
+
"language_model.model.layers.52.linear_attn.in_proj_z.weight": "model-00008-of-00011.safetensors",
|
| 653 |
+
"language_model.model.layers.52.linear_attn.norm.weight": "model-00008-of-00011.safetensors",
|
| 654 |
+
"language_model.model.layers.52.linear_attn.out_proj.weight": "model-00008-of-00011.safetensors",
|
| 655 |
+
"language_model.model.layers.52.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
|
| 656 |
+
"language_model.model.layers.52.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
|
| 657 |
+
"language_model.model.layers.52.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
|
| 658 |
+
"language_model.model.layers.52.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
|
| 659 |
+
"language_model.model.layers.53.input_layernorm.weight": "model-00009-of-00011.safetensors",
|
| 660 |
+
"language_model.model.layers.53.linear_attn.A_log": "model-00009-of-00011.safetensors",
|
| 661 |
+
"language_model.model.layers.53.linear_attn.conv1d.weight": "model-00009-of-00011.safetensors",
|
| 662 |
+
"language_model.model.layers.53.linear_attn.dt_bias": "model-00009-of-00011.safetensors",
|
| 663 |
+
"language_model.model.layers.53.linear_attn.in_proj_a.weight": "model-00009-of-00011.safetensors",
|
| 664 |
+
"language_model.model.layers.53.linear_attn.in_proj_b.weight": "model-00009-of-00011.safetensors",
|
| 665 |
+
"language_model.model.layers.53.linear_attn.in_proj_qkv.weight": "model-00009-of-00011.safetensors",
|
| 666 |
+
"language_model.model.layers.53.linear_attn.in_proj_z.weight": "model-00009-of-00011.safetensors",
|
| 667 |
+
"language_model.model.layers.53.linear_attn.norm.weight": "model-00009-of-00011.safetensors",
|
| 668 |
+
"language_model.model.layers.53.linear_attn.out_proj.weight": "model-00009-of-00011.safetensors",
|
| 669 |
+
"language_model.model.layers.53.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
|
| 670 |
+
"language_model.model.layers.53.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
|
| 671 |
+
"language_model.model.layers.53.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
|
| 672 |
+
"language_model.model.layers.53.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
|
| 673 |
+
"language_model.model.layers.54.input_layernorm.weight": "model-00009-of-00011.safetensors",
|
| 674 |
+
"language_model.model.layers.54.linear_attn.A_log": "model-00009-of-00011.safetensors",
|
| 675 |
+
"language_model.model.layers.54.linear_attn.conv1d.weight": "model-00009-of-00011.safetensors",
|
| 676 |
+
"language_model.model.layers.54.linear_attn.dt_bias": "model-00009-of-00011.safetensors",
|
| 677 |
+
"language_model.model.layers.54.linear_attn.in_proj_a.weight": "model-00009-of-00011.safetensors",
|
| 678 |
+
"language_model.model.layers.54.linear_attn.in_proj_b.weight": "model-00009-of-00011.safetensors",
|
| 679 |
+
"language_model.model.layers.54.linear_attn.in_proj_qkv.weight": "model-00009-of-00011.safetensors",
|
| 680 |
+
"language_model.model.layers.54.linear_attn.in_proj_z.weight": "model-00009-of-00011.safetensors",
|
| 681 |
+
"language_model.model.layers.54.linear_attn.norm.weight": "model-00009-of-00011.safetensors",
|
| 682 |
+
"language_model.model.layers.54.linear_attn.out_proj.weight": "model-00009-of-00011.safetensors",
|
| 683 |
+
"language_model.model.layers.54.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
|
| 684 |
+
"language_model.model.layers.54.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
|
| 685 |
+
"language_model.model.layers.54.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
|
| 686 |
+
"language_model.model.layers.54.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
|
| 687 |
+
"language_model.model.layers.55.input_layernorm.weight": "model-00009-of-00011.safetensors",
|
| 688 |
+
"language_model.model.layers.55.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
|
| 689 |
+
"language_model.model.layers.55.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
|
| 690 |
+
"language_model.model.layers.55.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
|
| 691 |
+
"language_model.model.layers.55.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
|
| 692 |
+
"language_model.model.layers.55.self_attn.k_norm.weight": "model-00009-of-00011.safetensors",
|
| 693 |
+
"language_model.model.layers.55.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
|
| 694 |
+
"language_model.model.layers.55.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
|
| 695 |
+
"language_model.model.layers.55.self_attn.q_norm.weight": "model-00009-of-00011.safetensors",
|
| 696 |
+
"language_model.model.layers.55.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
|
| 697 |
+
"language_model.model.layers.55.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
|
| 698 |
+
"language_model.model.layers.56.input_layernorm.weight": "model-00009-of-00011.safetensors",
|
| 699 |
+
"language_model.model.layers.56.linear_attn.A_log": "model-00009-of-00011.safetensors",
|
| 700 |
+
"language_model.model.layers.56.linear_attn.conv1d.weight": "model-00009-of-00011.safetensors",
|
| 701 |
+
"language_model.model.layers.56.linear_attn.dt_bias": "model-00009-of-00011.safetensors",
|
| 702 |
+
"language_model.model.layers.56.linear_attn.in_proj_a.weight": "model-00009-of-00011.safetensors",
|
| 703 |
+
"language_model.model.layers.56.linear_attn.in_proj_b.weight": "model-00009-of-00011.safetensors",
|
| 704 |
+
"language_model.model.layers.56.linear_attn.in_proj_qkv.weight": "model-00009-of-00011.safetensors",
|
| 705 |
+
"language_model.model.layers.56.linear_attn.in_proj_z.weight": "model-00009-of-00011.safetensors",
|
| 706 |
+
"language_model.model.layers.56.linear_attn.norm.weight": "model-00009-of-00011.safetensors",
|
| 707 |
+
"language_model.model.layers.56.linear_attn.out_proj.weight": "model-00009-of-00011.safetensors",
|
| 708 |
+
"language_model.model.layers.56.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
|
| 709 |
+
"language_model.model.layers.56.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
|
| 710 |
+
"language_model.model.layers.56.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
|
| 711 |
+
"language_model.model.layers.56.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
|
| 712 |
+
"language_model.model.layers.57.input_layernorm.weight": "model-00009-of-00011.safetensors",
|
| 713 |
+
"language_model.model.layers.57.linear_attn.A_log": "model-00009-of-00011.safetensors",
|
| 714 |
+
"language_model.model.layers.57.linear_attn.conv1d.weight": "model-00009-of-00011.safetensors",
|
| 715 |
+
"language_model.model.layers.57.linear_attn.dt_bias": "model-00009-of-00011.safetensors",
|
| 716 |
+
"language_model.model.layers.57.linear_attn.in_proj_a.weight": "model-00009-of-00011.safetensors",
|
| 717 |
+
"language_model.model.layers.57.linear_attn.in_proj_b.weight": "model-00009-of-00011.safetensors",
|
| 718 |
+
"language_model.model.layers.57.linear_attn.in_proj_qkv.weight": "model-00009-of-00011.safetensors",
|
| 719 |
+
"language_model.model.layers.57.linear_attn.in_proj_z.weight": "model-00009-of-00011.safetensors",
|
| 720 |
+
"language_model.model.layers.57.linear_attn.norm.weight": "model-00009-of-00011.safetensors",
|
| 721 |
+
"language_model.model.layers.57.linear_attn.out_proj.weight": "model-00009-of-00011.safetensors",
|
| 722 |
+
"language_model.model.layers.57.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
|
| 723 |
+
"language_model.model.layers.57.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
|
| 724 |
+
"language_model.model.layers.57.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
|
| 725 |
+
"language_model.model.layers.57.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
|
| 726 |
+
"language_model.model.layers.58.input_layernorm.weight": "model-00009-of-00011.safetensors",
|
| 727 |
+
"language_model.model.layers.58.linear_attn.A_log": "model-00009-of-00011.safetensors",
|
| 728 |
+
"language_model.model.layers.58.linear_attn.conv1d.weight": "model-00009-of-00011.safetensors",
|
| 729 |
+
"language_model.model.layers.58.linear_attn.dt_bias": "model-00009-of-00011.safetensors",
|
| 730 |
+
"language_model.model.layers.58.linear_attn.in_proj_a.weight": "model-00009-of-00011.safetensors",
|
| 731 |
+
"language_model.model.layers.58.linear_attn.in_proj_b.weight": "model-00009-of-00011.safetensors",
|
| 732 |
+
"language_model.model.layers.58.linear_attn.in_proj_qkv.weight": "model-00009-of-00011.safetensors",
|
| 733 |
+
"language_model.model.layers.58.linear_attn.in_proj_z.weight": "model-00009-of-00011.safetensors",
|
| 734 |
+
"language_model.model.layers.58.linear_attn.norm.weight": "model-00009-of-00011.safetensors",
|
| 735 |
+
"language_model.model.layers.58.linear_attn.out_proj.weight": "model-00009-of-00011.safetensors",
|
| 736 |
+
"language_model.model.layers.58.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
|
| 737 |
+
"language_model.model.layers.58.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
|
| 738 |
+
"language_model.model.layers.58.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
|
| 739 |
+
"language_model.model.layers.58.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
|
| 740 |
+
"language_model.model.layers.59.input_layernorm.weight": "model-00009-of-00011.safetensors",
|
| 741 |
+
"language_model.model.layers.59.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
|
| 742 |
+
"language_model.model.layers.59.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
|
| 743 |
+
"language_model.model.layers.59.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
|
| 744 |
+
"language_model.model.layers.59.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
|
| 745 |
+
"language_model.model.layers.59.self_attn.k_norm.weight": "model-00009-of-00011.safetensors",
|
| 746 |
+
"language_model.model.layers.59.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
|
| 747 |
+
"language_model.model.layers.59.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
|
| 748 |
+
"language_model.model.layers.59.self_attn.q_norm.weight": "model-00009-of-00011.safetensors",
|
| 749 |
+
"language_model.model.layers.59.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
|
| 750 |
+
"language_model.model.layers.59.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
|
| 751 |
+
"language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00011.safetensors",
|
| 752 |
+
"language_model.model.layers.6.linear_attn.A_log": "model-00002-of-00011.safetensors",
|
| 753 |
+
"language_model.model.layers.6.linear_attn.conv1d.weight": "model-00002-of-00011.safetensors",
|
| 754 |
+
"language_model.model.layers.6.linear_attn.dt_bias": "model-00002-of-00011.safetensors",
|
| 755 |
+
"language_model.model.layers.6.linear_attn.in_proj_a.weight": "model-00002-of-00011.safetensors",
|
| 756 |
+
"language_model.model.layers.6.linear_attn.in_proj_b.weight": "model-00002-of-00011.safetensors",
|
| 757 |
+
"language_model.model.layers.6.linear_attn.in_proj_qkv.weight": "model-00002-of-00011.safetensors",
|
| 758 |
+
"language_model.model.layers.6.linear_attn.in_proj_z.weight": "model-00002-of-00011.safetensors",
|
| 759 |
+
"language_model.model.layers.6.linear_attn.norm.weight": "model-00002-of-00011.safetensors",
|
| 760 |
+
"language_model.model.layers.6.linear_attn.out_proj.weight": "model-00002-of-00011.safetensors",
|
| 761 |
+
"language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
|
| 762 |
+
"language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
|
| 763 |
+
"language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
|
| 764 |
+
"language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
|
| 765 |
+
"language_model.model.layers.60.input_layernorm.weight": "model-00010-of-00011.safetensors",
|
| 766 |
+
"language_model.model.layers.60.linear_attn.A_log": "model-00010-of-00011.safetensors",
|
| 767 |
+
"language_model.model.layers.60.linear_attn.conv1d.weight": "model-00010-of-00011.safetensors",
|
| 768 |
+
"language_model.model.layers.60.linear_attn.dt_bias": "model-00010-of-00011.safetensors",
|
| 769 |
+
"language_model.model.layers.60.linear_attn.in_proj_a.weight": "model-00010-of-00011.safetensors",
|
| 770 |
+
"language_model.model.layers.60.linear_attn.in_proj_b.weight": "model-00010-of-00011.safetensors",
|
| 771 |
+
"language_model.model.layers.60.linear_attn.in_proj_qkv.weight": "model-00010-of-00011.safetensors",
|
| 772 |
+
"language_model.model.layers.60.linear_attn.in_proj_z.weight": "model-00010-of-00011.safetensors",
|
| 773 |
+
"language_model.model.layers.60.linear_attn.norm.weight": "model-00010-of-00011.safetensors",
|
| 774 |
+
"language_model.model.layers.60.linear_attn.out_proj.weight": "model-00010-of-00011.safetensors",
|
| 775 |
+
"language_model.model.layers.60.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
|
| 776 |
+
"language_model.model.layers.60.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
|
| 777 |
+
"language_model.model.layers.60.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
|
| 778 |
+
"language_model.model.layers.60.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
|
| 779 |
+
"language_model.model.layers.61.input_layernorm.weight": "model-00010-of-00011.safetensors",
|
| 780 |
+
"language_model.model.layers.61.linear_attn.A_log": "model-00010-of-00011.safetensors",
|
| 781 |
+
"language_model.model.layers.61.linear_attn.conv1d.weight": "model-00010-of-00011.safetensors",
|
| 782 |
+
"language_model.model.layers.61.linear_attn.dt_bias": "model-00010-of-00011.safetensors",
|
| 783 |
+
"language_model.model.layers.61.linear_attn.in_proj_a.weight": "model-00010-of-00011.safetensors",
|
| 784 |
+
"language_model.model.layers.61.linear_attn.in_proj_b.weight": "model-00010-of-00011.safetensors",
|
| 785 |
+
"language_model.model.layers.61.linear_attn.in_proj_qkv.weight": "model-00010-of-00011.safetensors",
|
| 786 |
+
"language_model.model.layers.61.linear_attn.in_proj_z.weight": "model-00010-of-00011.safetensors",
|
| 787 |
+
"language_model.model.layers.61.linear_attn.norm.weight": "model-00010-of-00011.safetensors",
|
| 788 |
+
"language_model.model.layers.61.linear_attn.out_proj.weight": "model-00010-of-00011.safetensors",
|
| 789 |
+
"language_model.model.layers.61.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
|
| 790 |
+
"language_model.model.layers.61.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
|
| 791 |
+
"language_model.model.layers.61.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
|
| 792 |
+
"language_model.model.layers.61.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
|
| 793 |
+
"language_model.model.layers.62.input_layernorm.weight": "model-00010-of-00011.safetensors",
|
| 794 |
+
"language_model.model.layers.62.linear_attn.A_log": "model-00010-of-00011.safetensors",
|
| 795 |
+
"language_model.model.layers.62.linear_attn.conv1d.weight": "model-00010-of-00011.safetensors",
|
| 796 |
+
"language_model.model.layers.62.linear_attn.dt_bias": "model-00010-of-00011.safetensors",
|
| 797 |
+
"language_model.model.layers.62.linear_attn.in_proj_a.weight": "model-00010-of-00011.safetensors",
|
| 798 |
+
"language_model.model.layers.62.linear_attn.in_proj_b.weight": "model-00010-of-00011.safetensors",
|
| 799 |
+
"language_model.model.layers.62.linear_attn.in_proj_qkv.weight": "model-00010-of-00011.safetensors",
|
| 800 |
+
"language_model.model.layers.62.linear_attn.in_proj_z.weight": "model-00010-of-00011.safetensors",
|
| 801 |
+
"language_model.model.layers.62.linear_attn.norm.weight": "model-00010-of-00011.safetensors",
|
| 802 |
+
"language_model.model.layers.62.linear_attn.out_proj.weight": "model-00010-of-00011.safetensors",
|
| 803 |
+
"language_model.model.layers.62.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
|
| 804 |
+
"language_model.model.layers.62.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
|
| 805 |
+
"language_model.model.layers.62.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
|
| 806 |
+
"language_model.model.layers.62.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
|
| 807 |
+
"language_model.model.layers.63.input_layernorm.weight": "model-00010-of-00011.safetensors",
|
| 808 |
+
"language_model.model.layers.63.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
|
| 809 |
+
"language_model.model.layers.63.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
|
| 810 |
+
"language_model.model.layers.63.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
|
| 811 |
+
"language_model.model.layers.63.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
|
| 812 |
+
"language_model.model.layers.63.self_attn.k_norm.weight": "model-00010-of-00011.safetensors",
|
| 813 |
+
"language_model.model.layers.63.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
|
| 814 |
+
"language_model.model.layers.63.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
|
| 815 |
+
"language_model.model.layers.63.self_attn.q_norm.weight": "model-00010-of-00011.safetensors",
|
| 816 |
+
"language_model.model.layers.63.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
|
| 817 |
+
"language_model.model.layers.63.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
|
| 818 |
+
"language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00011.safetensors",
|
| 819 |
+
"language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
|
| 820 |
+
"language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
|
| 821 |
+
"language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
|
| 822 |
+
"language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
|
| 823 |
+
"language_model.model.layers.7.self_attn.k_norm.weight": "model-00002-of-00011.safetensors",
|
| 824 |
+
"language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
|
| 825 |
+
"language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
|
| 826 |
+
"language_model.model.layers.7.self_attn.q_norm.weight": "model-00002-of-00011.safetensors",
|
| 827 |
+
"language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
|
| 828 |
+
"language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
|
| 829 |
+
"language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00011.safetensors",
|
| 830 |
+
"language_model.model.layers.8.linear_attn.A_log": "model-00002-of-00011.safetensors",
|
| 831 |
+
"language_model.model.layers.8.linear_attn.conv1d.weight": "model-00002-of-00011.safetensors",
|
| 832 |
+
"language_model.model.layers.8.linear_attn.dt_bias": "model-00002-of-00011.safetensors",
|
| 833 |
+
"language_model.model.layers.8.linear_attn.in_proj_a.weight": "model-00002-of-00011.safetensors",
|
| 834 |
+
"language_model.model.layers.8.linear_attn.in_proj_b.weight": "model-00002-of-00011.safetensors",
|
| 835 |
+
"language_model.model.layers.8.linear_attn.in_proj_qkv.weight": "model-00002-of-00011.safetensors",
|
| 836 |
+
"language_model.model.layers.8.linear_attn.in_proj_z.weight": "model-00002-of-00011.safetensors",
|
| 837 |
+
"language_model.model.layers.8.linear_attn.norm.weight": "model-00002-of-00011.safetensors",
|
| 838 |
+
"language_model.model.layers.8.linear_attn.out_proj.weight": "model-00002-of-00011.safetensors",
|
| 839 |
+
"language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
|
| 840 |
+
"language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
|
| 841 |
+
"language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
|
| 842 |
+
"language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
|
| 843 |
+
"language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00011.safetensors",
|
| 844 |
+
"language_model.model.layers.9.linear_attn.A_log": "model-00002-of-00011.safetensors",
|
| 845 |
+
"language_model.model.layers.9.linear_attn.conv1d.weight": "model-00002-of-00011.safetensors",
|
| 846 |
+
"language_model.model.layers.9.linear_attn.dt_bias": "model-00002-of-00011.safetensors",
|
| 847 |
+
"language_model.model.layers.9.linear_attn.in_proj_a.weight": "model-00002-of-00011.safetensors",
|
| 848 |
+
"language_model.model.layers.9.linear_attn.in_proj_b.weight": "model-00002-of-00011.safetensors",
|
| 849 |
+
"language_model.model.layers.9.linear_attn.in_proj_qkv.weight": "model-00002-of-00011.safetensors",
|
| 850 |
+
"language_model.model.layers.9.linear_attn.in_proj_z.weight": "model-00002-of-00011.safetensors",
|
| 851 |
+
"language_model.model.layers.9.linear_attn.norm.weight": "model-00002-of-00011.safetensors",
|
| 852 |
+
"language_model.model.layers.9.linear_attn.out_proj.weight": "model-00002-of-00011.safetensors",
|
| 853 |
+
"language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
|
| 854 |
+
"language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
|
| 855 |
+
"language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
|
| 856 |
+
"language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
|
| 857 |
+
"language_model.model.norm.weight": "model-00010-of-00011.safetensors"
|
| 858 |
+
}
|
| 859 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
|
| 3 |
+
size 19989343
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": true,
|
| 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 |
+
"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+",
|
| 25 |
+
"processor_class": "Qwen3VLProcessor",
|
| 26 |
+
"split_special_tokens": false,
|
| 27 |
+
"tokenizer_class": "TokenizersBackend",
|
| 28 |
+
"tool_parser_type": "qwen3_coder",
|
| 29 |
+
"unk_token": null,
|
| 30 |
+
"video_token": "<|video_pad|>",
|
| 31 |
+
"vision_bos_token": "<|vision_start|>",
|
| 32 |
+
"vision_eos_token": "<|vision_end|>"
|
| 33 |
+
}
|