Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +399 -0
- config.json +37 -0
- generation_config.json +8 -0
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +932 -0
- quantization_config.json +0 -0
- special_tokens_map.json +33 -0
- tokenizer.json +3 -0
- tokenizer_config.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,399 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model:
|
4 |
+
- Delta-Vector/MS3.2-Austral-24B-KTO
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
library_name: transformers
|
8 |
+
tags:
|
9 |
+
- roleplay
|
10 |
+
- finetune
|
11 |
+
- axolotl
|
12 |
+
- adventure
|
13 |
+
- creative-writing
|
14 |
+
- Mistral
|
15 |
+
- 24B
|
16 |
+
datasets:
|
17 |
+
- PocketDoc/Dans-Prosemaxx-RepRemover-1
|
18 |
+
---
|
19 |
+
<!DOCTYPE html>
|
20 |
+
<html lang="en">
|
21 |
+
<head>
|
22 |
+
<meta charset="UTF-8">
|
23 |
+
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
24 |
+
<title>Austral 24B Winton</title>
|
25 |
+
<link href="" rel="stylesheet">
|
26 |
+
<style>
|
27 |
+
body {
|
28 |
+
font-family: 'Roboto Slab', serif;
|
29 |
+
background: linear-gradient(135deg, #8B4513 0%, #A0522D 25%, #CD853F 50%, #D2691E 75%, #8B4513 100%);
|
30 |
+
background-size: 400% 400%;
|
31 |
+
animation: prehistoricShift 20s ease-in-out infinite;
|
32 |
+
color: #2F1B14;
|
33 |
+
margin: 0;
|
34 |
+
padding: 0;
|
35 |
+
font-size: 16px;
|
36 |
+
min-height: 100vh;
|
37 |
+
}
|
38 |
+
@keyframes prehistoricShift {
|
39 |
+
0%, 100% { background-position: 0% 50%; }
|
40 |
+
50% { background-position: 100% 50%; }
|
41 |
+
}
|
42 |
+
.container {
|
43 |
+
margin: 20px;
|
44 |
+
background: linear-gradient(145deg, #F4E4BC 0%, #DEB887 100%);
|
45 |
+
padding: 20px;
|
46 |
+
border-radius: 15px;
|
47 |
+
box-shadow: 0 8px 25px rgba(0, 0, 0, 0.4), inset 0 2px 5px rgba(255, 255, 255, 0.3);
|
48 |
+
border: 4px solid #8B4513;
|
49 |
+
position: relative;
|
50 |
+
overflow: hidden;
|
51 |
+
}
|
52 |
+
.container::before {
|
53 |
+
content: '';
|
54 |
+
position: absolute;
|
55 |
+
top: 0;
|
56 |
+
left: 0;
|
57 |
+
right: 0;
|
58 |
+
bottom: 0;
|
59 |
+
background-image:
|
60 |
+
radial-gradient(circle at 20% 80%, rgba(139, 69, 19, 0.1) 0%, transparent 50%),
|
61 |
+
radial-gradient(circle at 80% 20%, rgba(160, 82, 45, 0.1) 0%, transparent 50%);
|
62 |
+
pointer-events: none;
|
63 |
+
}
|
64 |
+
.header h1 {
|
65 |
+
font-family: 'Cinzel', serif;
|
66 |
+
font-size: 32px;
|
67 |
+
color: #5D2E0C;
|
68 |
+
margin: 0 0 20px 0;
|
69 |
+
text-align: center;
|
70 |
+
text-shadow: 2px 2px 4px rgba(0, 0, 0, 0.3);
|
71 |
+
letter-spacing: 2px;
|
72 |
+
position: relative;
|
73 |
+
}
|
74 |
+
.section {
|
75 |
+
margin-top: 30px;
|
76 |
+
position: relative;
|
77 |
+
}
|
78 |
+
.section h2 {
|
79 |
+
font-family: 'Cinzel', serif;
|
80 |
+
font-size: 26px;
|
81 |
+
color: #5D2E0C;
|
82 |
+
text-align: center;
|
83 |
+
margin-bottom: 20px;
|
84 |
+
text-shadow: 1px 1px 2px rgba(0, 0, 0, 0.2);
|
85 |
+
letter-spacing: 1px;
|
86 |
+
}
|
87 |
+
.info p {
|
88 |
+
color: #2F1B14;
|
89 |
+
line-height: 1.7;
|
90 |
+
font-size: 16px;
|
91 |
+
text-shadow: 0 1px 1px rgba(255, 255, 255, 0.5);
|
92 |
+
}
|
93 |
+
.info img {
|
94 |
+
width: 85%;
|
95 |
+
border-radius: 12px;
|
96 |
+
margin: 0 auto 15px;
|
97 |
+
display: block;
|
98 |
+
box-shadow: 0 0 25px rgba(0, 0, 0, 0.4);
|
99 |
+
border: 3px solid #8B4513;
|
100 |
+
filter: sepia(20%) contrast(110%);
|
101 |
+
}
|
102 |
+
a {
|
103 |
+
color: #5D2E0C;
|
104 |
+
text-decoration: none;
|
105 |
+
transition: all 0.3s ease;
|
106 |
+
font-weight: 500;
|
107 |
+
}
|
108 |
+
a:hover {
|
109 |
+
color: #8B4513;
|
110 |
+
text-shadow: 1px 1px 2px rgba(0, 0, 0, 0.2);
|
111 |
+
}
|
112 |
+
.button {
|
113 |
+
display: inline-block;
|
114 |
+
background: linear-gradient(145deg, #CD853F, #D2691E);
|
115 |
+
color: #2F1B14;
|
116 |
+
padding: 12px 24px;
|
117 |
+
border-radius: 8px;
|
118 |
+
cursor: pointer;
|
119 |
+
text-decoration: none;
|
120 |
+
transition: all 0.3s ease;
|
121 |
+
box-shadow: 0 4px 8px rgba(0, 0, 0, 0.2);
|
122 |
+
border: 2px solid #8B4513;
|
123 |
+
}
|
124 |
+
.button:hover {
|
125 |
+
background: linear-gradient(145deg, #D2691E, #CD853F);
|
126 |
+
box-shadow: 0 6px 15px rgba(139, 69, 19, 0.4);
|
127 |
+
transform: translateY(-2px);
|
128 |
+
}
|
129 |
+
pre {
|
130 |
+
background: linear-gradient(145deg, #F5DEB3, #DEB887);
|
131 |
+
padding: 20px;
|
132 |
+
border-radius: 8px;
|
133 |
+
overflow-x: auto;
|
134 |
+
border: 2px solid #8B4513;
|
135 |
+
box-shadow: inset 0 2px 5px rgba(0, 0, 0, 0.1);
|
136 |
+
}
|
137 |
+
code {
|
138 |
+
font-family: 'Courier New', monospace;
|
139 |
+
color: #2F1B14;
|
140 |
+
}
|
141 |
+
.info-card {
|
142 |
+
background: linear-gradient(145deg, #F5DEB3, #DEB887);
|
143 |
+
border: 3px solid #8B4513;
|
144 |
+
border-radius: 12px;
|
145 |
+
overflow: hidden;
|
146 |
+
box-shadow: 0 6px 15px rgba(0, 0, 0, 0.2);
|
147 |
+
}
|
148 |
+
.info-header {
|
149 |
+
background: linear-gradient(145deg, #CD853F, #D2691E);
|
150 |
+
padding: 25px;
|
151 |
+
border-bottom: 2px solid #8B4513;
|
152 |
+
}
|
153 |
+
.info-header h3 {
|
154 |
+
font-family: 'Cinzel', serif;
|
155 |
+
color: #2F1B14;
|
156 |
+
margin: 0 0 15px 0;
|
157 |
+
font-size: 22px;
|
158 |
+
text-align: center;
|
159 |
+
text-shadow: 1px 1px 2px rgba(0, 0, 0, 0.2);
|
160 |
+
letter-spacing: 1px;
|
161 |
+
}
|
162 |
+
.model-tags {
|
163 |
+
display: flex;
|
164 |
+
gap: 10px;
|
165 |
+
flex-wrap: wrap;
|
166 |
+
justify-content: center;
|
167 |
+
}
|
168 |
+
.model-tag {
|
169 |
+
background: linear-gradient(145deg, #DEB887, #CD853F);
|
170 |
+
color: #2F1B14;
|
171 |
+
padding: 6px 12px;
|
172 |
+
border-radius: 6px;
|
173 |
+
font-size: 12px;
|
174 |
+
border: 2px solid #8B4513;
|
175 |
+
font-weight: 500;
|
176 |
+
box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1);
|
177 |
+
}
|
178 |
+
.model-composition {
|
179 |
+
padding: 25px;
|
180 |
+
border-bottom: 2px solid #8B4513;
|
181 |
+
}
|
182 |
+
.model-composition h4 {
|
183 |
+
font-family: 'Cinzel', serif;
|
184 |
+
color: #5D2E0C;
|
185 |
+
margin: 0 0 20px 0;
|
186 |
+
font-size: 18px;
|
187 |
+
text-align: center;
|
188 |
+
letter-spacing: 1px;
|
189 |
+
}
|
190 |
+
.composition-list {
|
191 |
+
list-style: none;
|
192 |
+
padding: 0;
|
193 |
+
margin: 0;
|
194 |
+
display: grid;
|
195 |
+
gap: 15px;
|
196 |
+
}
|
197 |
+
.composition-list li {
|
198 |
+
color: #2F1B14;
|
199 |
+
display: flex;
|
200 |
+
align-items: baseline;
|
201 |
+
gap: 12px;
|
202 |
+
padding: 10px;
|
203 |
+
background: rgba(245, 222, 179, 0.5);
|
204 |
+
border-radius: 6px;
|
205 |
+
border-left: 4px solid #8B4513;
|
206 |
+
}
|
207 |
+
.model-component {
|
208 |
+
font-weight: 600;
|
209 |
+
min-width: 120px;
|
210 |
+
}
|
211 |
+
.model-description {
|
212 |
+
padding: 25px;
|
213 |
+
background: linear-gradient(145deg, #F5DEB3, #F4E4BC);
|
214 |
+
}
|
215 |
+
.metrics-section {
|
216 |
+
margin-bottom: 30px;
|
217 |
+
}
|
218 |
+
.metrics-section details {
|
219 |
+
background: linear-gradient(145deg, #F5DEB3, #DEB887);
|
220 |
+
border: 3px solid #8B4513;
|
221 |
+
border-radius: 10px;
|
222 |
+
padding: 20px;
|
223 |
+
margin-bottom: 20px;
|
224 |
+
box-shadow: 0 4px 10px rgba(0, 0, 0, 0.2);
|
225 |
+
}
|
226 |
+
.metrics-section summary {
|
227 |
+
font-family: 'Cinzel', serif;
|
228 |
+
color: #5D2E0C;
|
229 |
+
font-size: 18px;
|
230 |
+
cursor: pointer;
|
231 |
+
outline: none;
|
232 |
+
padding: 10px 0;
|
233 |
+
text-align: center;
|
234 |
+
font-weight: 500;
|
235 |
+
letter-spacing: 1px;
|
236 |
+
}
|
237 |
+
.creator-section {
|
238 |
+
margin: 25px 0;
|
239 |
+
text-align: center;
|
240 |
+
}
|
241 |
+
.creator-badge {
|
242 |
+
display: inline-flex;
|
243 |
+
align-items: center;
|
244 |
+
background: linear-gradient(145deg, #CD853F, #D2691E);
|
245 |
+
border: 3px solid #8B4513;
|
246 |
+
border-radius: 10px;
|
247 |
+
padding: 15px 20px;
|
248 |
+
box-shadow: 0 4px 10px rgba(0, 0, 0, 0.2);
|
249 |
+
}
|
250 |
+
.creator-label {
|
251 |
+
color: #2F1B14;
|
252 |
+
font-size: 14px;
|
253 |
+
margin-right: 10px;
|
254 |
+
font-weight: 500;
|
255 |
+
}
|
256 |
+
.creator-link {
|
257 |
+
display: flex;
|
258 |
+
align-items: center;
|
259 |
+
gap: 8px;
|
260 |
+
color: #2F1B14;
|
261 |
+
text-decoration: none;
|
262 |
+
transition: all 0.3s ease;
|
263 |
+
}
|
264 |
+
.creator-name {
|
265 |
+
font-weight: 600;
|
266 |
+
}
|
267 |
+
.creator-arrow {
|
268 |
+
font-size: 16px;
|
269 |
+
transition: transform 0.3s ease;
|
270 |
+
}
|
271 |
+
.creator-link:hover .creator-arrow {
|
272 |
+
transform: translateX(5px);
|
273 |
+
}
|
274 |
+
.link-arrow {
|
275 |
+
display: inline-block;
|
276 |
+
transition: transform 0.3s ease;
|
277 |
+
}
|
278 |
+
a:hover .link-arrow {
|
279 |
+
transform: translateX(3px);
|
280 |
+
}
|
281 |
+
.axolotl-container {
|
282 |
+
text-align: center;
|
283 |
+
margin: 35px 0;
|
284 |
+
}
|
285 |
+
.axolotl-container img {
|
286 |
+
max-width: 300px;
|
287 |
+
border-radius: 10px;
|
288 |
+
box-shadow: 0 6px 15px rgba(0, 0, 0, 0.3);
|
289 |
+
border: 3px solid #8B4513;
|
290 |
+
filter: sepia(30%) contrast(110%);
|
291 |
+
}
|
292 |
+
.fossil-texture {
|
293 |
+
position: relative;
|
294 |
+
}
|
295 |
+
.fossil-texture::after {
|
296 |
+
content: '';
|
297 |
+
position: absolute;
|
298 |
+
top: 0;
|
299 |
+
left: 0;
|
300 |
+
right: 0;
|
301 |
+
bottom: 0;
|
302 |
+
background-image:
|
303 |
+
radial-gradient(circle at 25% 25%, rgba(139, 69, 19, 0.05) 2px, transparent 2px),
|
304 |
+
radial-gradient(circle at 75% 75%, rgba(160, 82, 45, 0.05) 1px, transparent 1px);
|
305 |
+
background-size: 50px 50px, 30px 30px;
|
306 |
+
pointer-events: none;
|
307 |
+
}
|
308 |
+
</style>
|
309 |
+
</head>
|
310 |
+
<body>
|
311 |
+
<div class="container fossil-texture">
|
312 |
+
<div class="header">
|
313 |
+
<h1>Austral 24B Winton</h1>
|
314 |
+
</p>
|
315 |
+
</div>
|
316 |
+
<div class="info">
|
317 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/66c26b6fb01b19d8c3c2467b/jxUvuFK1bdOdAPiYIcBW5.jpeg" alt="Model banner">
|
318 |
+
<div style="text-align: center;">
|
319 |
+
<div class="creator-section">
|
320 |
+
<div class="creator-badge">
|
321 |
+
<span class="creator-label">Trained by</span>
|
322 |
+
<a href="https://huggingface.co/Delta-Vector" target="_blank" class="creator-link">
|
323 |
+
<span class="creator-name">Delta-Vector</span>
|
324 |
+
</a>
|
325 |
+
</div>
|
326 |
+
</div>
|
327 |
+
<div class="model-info">
|
328 |
+
<h2>Overview</h2>
|
329 |
+
<div class="info-card">
|
330 |
+
<div class="info-header">
|
331 |
+
<h3>Austral 24B - Winton</h3>
|
332 |
+
<div class="model-tags">
|
333 |
+
<span class="model-tag">Codex Finetune</span>
|
334 |
+
<span class="model-tag">Mistral Based</span>
|
335 |
+
<span class ="model-tag">KTO enhanced</span>
|
336 |
+
<span class ="model-tag">Adventure/Roleplay generalist</span>
|
337 |
+
<span class="model-tag">24B Sized model</span>
|
338 |
+
</div>
|
339 |
+
</div>
|
340 |
+
<div class="model-description">
|
341 |
+
<p style="font-weight: bold; font-style: italic;">More than 1.5-metres tall, about six-metres long and up to 1000-kilograms heavy, Australovenator Wintonensis was a fast and agile hunter. The largest known Australian theropod.</p>
|
342 |
+
<p>This is a finetune of Codex 24B to be a generalist Roleplay/Adventure model. I've removed some of the "slops" that i noticed in an otherwise great model aswell as improving the general writing of the model, This was a multi-stage finetune, all previous checkpoints are released aswell. In testing it has shown to be a great model for Adventure cards & Roleplay, Often pushing the plot forward better then other models, While avoiding some of the slops you'd find in models from Drummer and Co.</p>
|
343 |
+
<p>Support my finetunes / Me on Kofi: https://Ko-fi.com/deltavector | Thank you to Auri for helping/Testing ♥</p>
|
344 |
+
</div>
|
345 |
+
</div>
|
346 |
+
</div>
|
347 |
+
<div class="section">
|
348 |
+
<h2>Quants</h2>
|
349 |
+
<div class="info-card">
|
350 |
+
<div class="model-composition">
|
351 |
+
<h4>Quants Formats</h4>
|
352 |
+
<ul class="composition-list">
|
353 |
+
<li><span class="model-component"><a href="" target="_blank">GGUF</a></span>For use with LLama.cpp & Forks (coming soon!))</li>
|
354 |
+
<li><span class="model-component"><a href="" target="_blank">EXL3</a></span>For use with TabbyAPI (Coming soon!)</li>
|
355 |
+
</ul>
|
356 |
+
</div>
|
357 |
+
</div>
|
358 |
+
</div>
|
359 |
+
<div class="section">
|
360 |
+
<h2>Chat Format</h2>
|
361 |
+
<p>This model utilizes ChatML.</p>
|
362 |
+
<pre><code><|im_start|>user
|
363 |
+
Hi there!<|im_end|>
|
364 |
+
<|im_start|>assistant
|
365 |
+
Nice to meet you!<|im_end|>
|
366 |
+
<|im_start|>user
|
367 |
+
Can I ask a question?<|im_end|>
|
368 |
+
<|im_start|>assistant</code></pre>
|
369 |
+
</div>
|
370 |
+
<div class="section">
|
371 |
+
<h2>Training</h2>
|
372 |
+
<p>As the the Austral/Francois tradition, I built off another great finetune Codex-24B, I did 4 epochs ontop with roughly the same datamix as Francois-Huali/Austral 70B as a R128 Lora, then KTO alignment with a mix of Instruct/Small writing datasets and then finally another 4 epoch SFT with Rep_remover (Thanks Pocket!)</p>
|
373 |
+
<div class="metrics-section">
|
374 |
+
<details>
|
375 |
+
<summary>Config(Post-KTO SFT)</summary>
|
376 |
+
<pre><code>https://wandb.ai/new-eden/austral/runs/i85da0c6?nw=nwuserdeltavector</code></pre>
|
377 |
+
</details>
|
378 |
+
</div>
|
379 |
+
</div>
|
380 |
+
<div class="section">
|
381 |
+
<h2Fossil Formation Process</h2>
|
382 |
+
<p>This model was trained over 4 epochs using 8 x A100s (Ty to my work, Cognitive Computations) for the base SFT, Then i used KTO to clean up some coherency issues for 1 epoch, then finally training for another 4 epochs on Rep_Remover to delete slops. Total was roughly 80 hours total.</p>
|
383 |
+
<p style="text-align: center; margin-top: 20px;">
|
384 |
+
<div class="axolotl-container">
|
385 |
+
<a href="https://github.com/OpenAccess-AI-Collective/axolotl" target="_blank">
|
386 |
+
<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl">
|
387 |
+
</a>
|
388 |
+
</div>
|
389 |
+
<div class="section">
|
390 |
+
<h2>Credits</h2>
|
391 |
+
<p>TYSM to my friends: Auri, Lucy, Trappu, Alicat, Kubernetes Bad, Intervitens, NyxKrage & Kalomaze</p>
|
392 |
+
</p>
|
393 |
+
</div>
|
394 |
+
</div>
|
395 |
+
</div>
|
396 |
+
</div>
|
397 |
+
</div>
|
398 |
+
</body>
|
399 |
+
</html>
|
config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"MistralForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_dropout": 0.0,
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 999,
|
8 |
+
"head_dim": 128,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 5120,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 32768,
|
13 |
+
"max_position_embeddings": 131072,
|
14 |
+
"model_type": "mistral",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_hidden_layers": 40,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"rms_norm_eps": 1e-05,
|
19 |
+
"rope_theta": 1000000000.0,
|
20 |
+
"sliding_window": null,
|
21 |
+
"tie_word_embeddings": false,
|
22 |
+
"torch_dtype": "bfloat16",
|
23 |
+
"transformers_version": "4.51.3",
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 131072,
|
26 |
+
"quantization_config": {
|
27 |
+
"quant_method": "exl3",
|
28 |
+
"version": "0.0.4",
|
29 |
+
"bits": 6.0,
|
30 |
+
"head_bits": 6,
|
31 |
+
"calibration": {
|
32 |
+
"rows": 100,
|
33 |
+
"cols": 2048
|
34 |
+
},
|
35 |
+
"out_scales": "auto"
|
36 |
+
}
|
37 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"do_sample": true,
|
5 |
+
"eos_token_id": 999,
|
6 |
+
"transformers_version": "4.51.3",
|
7 |
+
"use_cache": false
|
8 |
+
}
|
model-00001-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3fc5c8b69532d96343be740b35a61c4c04ed536b0f131448cc71e14420dbdc95
|
3 |
+
size 8433230232
|
model-00002-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6ac4940c4641dcf2a1ed15a3fe3daafca785a2d29b2da59b9b2e3726d6c08fc
|
3 |
+
size 8342413328
|
model-00003-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dde709c412f29322a6d880f1c918173c50e7cd031c6d430a47556c36a60770ca
|
3 |
+
size 1754961368
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,932 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 18530504704
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
7 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
8 |
+
"model.layers.0.mlp.down_proj.suh": "model-00001-of-00003.safetensors",
|
9 |
+
"model.layers.0.mlp.down_proj.svh": "model-00001-of-00003.safetensors",
|
10 |
+
"model.layers.0.mlp.gate_proj.suh": "model-00001-of-00003.safetensors",
|
11 |
+
"model.layers.0.mlp.gate_proj.svh": "model-00001-of-00003.safetensors",
|
12 |
+
"model.layers.0.mlp.up_proj.suh": "model-00001-of-00003.safetensors",
|
13 |
+
"model.layers.0.mlp.up_proj.svh": "model-00001-of-00003.safetensors",
|
14 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
15 |
+
"model.layers.0.self_attn.k_proj.suh": "model-00001-of-00003.safetensors",
|
16 |
+
"model.layers.0.self_attn.k_proj.svh": "model-00001-of-00003.safetensors",
|
17 |
+
"model.layers.0.self_attn.o_proj.suh": "model-00001-of-00003.safetensors",
|
18 |
+
"model.layers.0.self_attn.o_proj.svh": "model-00001-of-00003.safetensors",
|
19 |
+
"model.layers.0.self_attn.q_proj.suh": "model-00001-of-00003.safetensors",
|
20 |
+
"model.layers.0.self_attn.q_proj.svh": "model-00001-of-00003.safetensors",
|
21 |
+
"model.layers.0.self_attn.v_proj.suh": "model-00001-of-00003.safetensors",
|
22 |
+
"model.layers.0.self_attn.v_proj.svh": "model-00001-of-00003.safetensors",
|
23 |
+
"model.layers.0.mlp.down_proj.trellis": "model-00001-of-00003.safetensors",
|
24 |
+
"model.layers.0.mlp.gate_proj.trellis": "model-00001-of-00003.safetensors",
|
25 |
+
"model.layers.0.mlp.up_proj.trellis": "model-00001-of-00003.safetensors",
|
26 |
+
"model.layers.0.self_attn.k_proj.trellis": "model-00001-of-00003.safetensors",
|
27 |
+
"model.layers.0.self_attn.o_proj.trellis": "model-00001-of-00003.safetensors",
|
28 |
+
"model.layers.0.self_attn.q_proj.trellis": "model-00001-of-00003.safetensors",
|
29 |
+
"model.layers.0.self_attn.v_proj.trellis": "model-00001-of-00003.safetensors",
|
30 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
31 |
+
"model.layers.1.mlp.down_proj.suh": "model-00001-of-00003.safetensors",
|
32 |
+
"model.layers.1.mlp.down_proj.svh": "model-00001-of-00003.safetensors",
|
33 |
+
"model.layers.1.mlp.gate_proj.suh": "model-00001-of-00003.safetensors",
|
34 |
+
"model.layers.1.mlp.gate_proj.svh": "model-00001-of-00003.safetensors",
|
35 |
+
"model.layers.1.mlp.up_proj.suh": "model-00001-of-00003.safetensors",
|
36 |
+
"model.layers.1.mlp.up_proj.svh": "model-00001-of-00003.safetensors",
|
37 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
38 |
+
"model.layers.1.self_attn.k_proj.suh": "model-00001-of-00003.safetensors",
|
39 |
+
"model.layers.1.self_attn.k_proj.svh": "model-00001-of-00003.safetensors",
|
40 |
+
"model.layers.1.self_attn.o_proj.suh": "model-00001-of-00003.safetensors",
|
41 |
+
"model.layers.1.self_attn.o_proj.svh": "model-00001-of-00003.safetensors",
|
42 |
+
"model.layers.1.self_attn.q_proj.suh": "model-00001-of-00003.safetensors",
|
43 |
+
"model.layers.1.self_attn.q_proj.svh": "model-00001-of-00003.safetensors",
|
44 |
+
"model.layers.1.self_attn.v_proj.suh": "model-00001-of-00003.safetensors",
|
45 |
+
"model.layers.1.self_attn.v_proj.svh": "model-00001-of-00003.safetensors",
|
46 |
+
"model.layers.1.mlp.down_proj.trellis": "model-00001-of-00003.safetensors",
|
47 |
+
"model.layers.1.mlp.gate_proj.trellis": "model-00001-of-00003.safetensors",
|
48 |
+
"model.layers.1.mlp.up_proj.trellis": "model-00001-of-00003.safetensors",
|
49 |
+
"model.layers.1.self_attn.k_proj.trellis": "model-00001-of-00003.safetensors",
|
50 |
+
"model.layers.1.self_attn.o_proj.trellis": "model-00001-of-00003.safetensors",
|
51 |
+
"model.layers.1.self_attn.q_proj.trellis": "model-00001-of-00003.safetensors",
|
52 |
+
"model.layers.1.self_attn.v_proj.trellis": "model-00001-of-00003.safetensors",
|
53 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
54 |
+
"model.layers.2.mlp.down_proj.suh": "model-00001-of-00003.safetensors",
|
55 |
+
"model.layers.2.mlp.down_proj.svh": "model-00001-of-00003.safetensors",
|
56 |
+
"model.layers.2.mlp.gate_proj.suh": "model-00001-of-00003.safetensors",
|
57 |
+
"model.layers.2.mlp.gate_proj.svh": "model-00001-of-00003.safetensors",
|
58 |
+
"model.layers.2.mlp.up_proj.suh": "model-00001-of-00003.safetensors",
|
59 |
+
"model.layers.2.mlp.up_proj.svh": "model-00001-of-00003.safetensors",
|
60 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
61 |
+
"model.layers.2.self_attn.k_proj.suh": "model-00001-of-00003.safetensors",
|
62 |
+
"model.layers.2.self_attn.k_proj.svh": "model-00001-of-00003.safetensors",
|
63 |
+
"model.layers.2.self_attn.o_proj.suh": "model-00001-of-00003.safetensors",
|
64 |
+
"model.layers.2.self_attn.o_proj.svh": "model-00001-of-00003.safetensors",
|
65 |
+
"model.layers.2.self_attn.q_proj.suh": "model-00001-of-00003.safetensors",
|
66 |
+
"model.layers.2.self_attn.q_proj.svh": "model-00001-of-00003.safetensors",
|
67 |
+
"model.layers.2.self_attn.v_proj.suh": "model-00001-of-00003.safetensors",
|
68 |
+
"model.layers.2.self_attn.v_proj.svh": "model-00001-of-00003.safetensors",
|
69 |
+
"model.layers.2.mlp.down_proj.trellis": "model-00001-of-00003.safetensors",
|
70 |
+
"model.layers.2.mlp.gate_proj.trellis": "model-00001-of-00003.safetensors",
|
71 |
+
"model.layers.2.mlp.up_proj.trellis": "model-00001-of-00003.safetensors",
|
72 |
+
"model.layers.2.self_attn.k_proj.trellis": "model-00001-of-00003.safetensors",
|
73 |
+
"model.layers.2.self_attn.o_proj.trellis": "model-00001-of-00003.safetensors",
|
74 |
+
"model.layers.2.self_attn.q_proj.trellis": "model-00001-of-00003.safetensors",
|
75 |
+
"model.layers.2.self_attn.v_proj.trellis": "model-00001-of-00003.safetensors",
|
76 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
77 |
+
"model.layers.3.mlp.down_proj.suh": "model-00001-of-00003.safetensors",
|
78 |
+
"model.layers.3.mlp.down_proj.svh": "model-00001-of-00003.safetensors",
|
79 |
+
"model.layers.3.mlp.gate_proj.suh": "model-00001-of-00003.safetensors",
|
80 |
+
"model.layers.3.mlp.gate_proj.svh": "model-00001-of-00003.safetensors",
|
81 |
+
"model.layers.3.mlp.up_proj.suh": "model-00001-of-00003.safetensors",
|
82 |
+
"model.layers.3.mlp.up_proj.svh": "model-00001-of-00003.safetensors",
|
83 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
84 |
+
"model.layers.3.self_attn.k_proj.suh": "model-00001-of-00003.safetensors",
|
85 |
+
"model.layers.3.self_attn.k_proj.svh": "model-00001-of-00003.safetensors",
|
86 |
+
"model.layers.3.self_attn.o_proj.suh": "model-00001-of-00003.safetensors",
|
87 |
+
"model.layers.3.self_attn.o_proj.svh": "model-00001-of-00003.safetensors",
|
88 |
+
"model.layers.3.self_attn.q_proj.suh": "model-00001-of-00003.safetensors",
|
89 |
+
"model.layers.3.self_attn.q_proj.svh": "model-00001-of-00003.safetensors",
|
90 |
+
"model.layers.3.self_attn.v_proj.suh": "model-00001-of-00003.safetensors",
|
91 |
+
"model.layers.3.self_attn.v_proj.svh": "model-00001-of-00003.safetensors",
|
92 |
+
"model.layers.3.mlp.down_proj.trellis": "model-00001-of-00003.safetensors",
|
93 |
+
"model.layers.3.mlp.gate_proj.trellis": "model-00001-of-00003.safetensors",
|
94 |
+
"model.layers.3.mlp.up_proj.trellis": "model-00001-of-00003.safetensors",
|
95 |
+
"model.layers.3.self_attn.k_proj.trellis": "model-00001-of-00003.safetensors",
|
96 |
+
"model.layers.3.self_attn.o_proj.trellis": "model-00001-of-00003.safetensors",
|
97 |
+
"model.layers.3.self_attn.q_proj.trellis": "model-00001-of-00003.safetensors",
|
98 |
+
"model.layers.3.self_attn.v_proj.trellis": "model-00001-of-00003.safetensors",
|
99 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
100 |
+
"model.layers.4.mlp.down_proj.suh": "model-00001-of-00003.safetensors",
|
101 |
+
"model.layers.4.mlp.down_proj.svh": "model-00001-of-00003.safetensors",
|
102 |
+
"model.layers.4.mlp.gate_proj.suh": "model-00001-of-00003.safetensors",
|
103 |
+
"model.layers.4.mlp.gate_proj.svh": "model-00001-of-00003.safetensors",
|
104 |
+
"model.layers.4.mlp.up_proj.suh": "model-00001-of-00003.safetensors",
|
105 |
+
"model.layers.4.mlp.up_proj.svh": "model-00001-of-00003.safetensors",
|
106 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
107 |
+
"model.layers.4.self_attn.k_proj.suh": "model-00001-of-00003.safetensors",
|
108 |
+
"model.layers.4.self_attn.k_proj.svh": "model-00001-of-00003.safetensors",
|
109 |
+
"model.layers.4.self_attn.o_proj.suh": "model-00001-of-00003.safetensors",
|
110 |
+
"model.layers.4.self_attn.o_proj.svh": "model-00001-of-00003.safetensors",
|
111 |
+
"model.layers.4.self_attn.q_proj.suh": "model-00001-of-00003.safetensors",
|
112 |
+
"model.layers.4.self_attn.q_proj.svh": "model-00001-of-00003.safetensors",
|
113 |
+
"model.layers.4.self_attn.v_proj.suh": "model-00001-of-00003.safetensors",
|
114 |
+
"model.layers.4.self_attn.v_proj.svh": "model-00001-of-00003.safetensors",
|
115 |
+
"model.layers.4.mlp.down_proj.trellis": "model-00001-of-00003.safetensors",
|
116 |
+
"model.layers.4.mlp.gate_proj.trellis": "model-00001-of-00003.safetensors",
|
117 |
+
"model.layers.4.mlp.up_proj.trellis": "model-00001-of-00003.safetensors",
|
118 |
+
"model.layers.4.self_attn.k_proj.trellis": "model-00001-of-00003.safetensors",
|
119 |
+
"model.layers.4.self_attn.o_proj.trellis": "model-00001-of-00003.safetensors",
|
120 |
+
"model.layers.4.self_attn.q_proj.trellis": "model-00001-of-00003.safetensors",
|
121 |
+
"model.layers.4.self_attn.v_proj.trellis": "model-00001-of-00003.safetensors",
|
122 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
123 |
+
"model.layers.5.mlp.down_proj.suh": "model-00001-of-00003.safetensors",
|
124 |
+
"model.layers.5.mlp.down_proj.svh": "model-00001-of-00003.safetensors",
|
125 |
+
"model.layers.5.mlp.gate_proj.suh": "model-00001-of-00003.safetensors",
|
126 |
+
"model.layers.5.mlp.gate_proj.svh": "model-00001-of-00003.safetensors",
|
127 |
+
"model.layers.5.mlp.up_proj.suh": "model-00001-of-00003.safetensors",
|
128 |
+
"model.layers.5.mlp.up_proj.svh": "model-00001-of-00003.safetensors",
|
129 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
130 |
+
"model.layers.5.self_attn.k_proj.suh": "model-00001-of-00003.safetensors",
|
131 |
+
"model.layers.5.self_attn.k_proj.svh": "model-00001-of-00003.safetensors",
|
132 |
+
"model.layers.5.self_attn.o_proj.suh": "model-00001-of-00003.safetensors",
|
133 |
+
"model.layers.5.self_attn.o_proj.svh": "model-00001-of-00003.safetensors",
|
134 |
+
"model.layers.5.self_attn.q_proj.suh": "model-00001-of-00003.safetensors",
|
135 |
+
"model.layers.5.self_attn.q_proj.svh": "model-00001-of-00003.safetensors",
|
136 |
+
"model.layers.5.self_attn.v_proj.suh": "model-00001-of-00003.safetensors",
|
137 |
+
"model.layers.5.self_attn.v_proj.svh": "model-00001-of-00003.safetensors",
|
138 |
+
"model.layers.5.mlp.down_proj.trellis": "model-00001-of-00003.safetensors",
|
139 |
+
"model.layers.5.mlp.gate_proj.trellis": "model-00001-of-00003.safetensors",
|
140 |
+
"model.layers.5.mlp.up_proj.trellis": "model-00001-of-00003.safetensors",
|
141 |
+
"model.layers.5.self_attn.k_proj.trellis": "model-00001-of-00003.safetensors",
|
142 |
+
"model.layers.5.self_attn.o_proj.trellis": "model-00001-of-00003.safetensors",
|
143 |
+
"model.layers.5.self_attn.q_proj.trellis": "model-00001-of-00003.safetensors",
|
144 |
+
"model.layers.5.self_attn.v_proj.trellis": "model-00001-of-00003.safetensors",
|
145 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
146 |
+
"model.layers.6.mlp.down_proj.suh": "model-00001-of-00003.safetensors",
|
147 |
+
"model.layers.6.mlp.down_proj.svh": "model-00001-of-00003.safetensors",
|
148 |
+
"model.layers.6.mlp.gate_proj.suh": "model-00001-of-00003.safetensors",
|
149 |
+
"model.layers.6.mlp.gate_proj.svh": "model-00001-of-00003.safetensors",
|
150 |
+
"model.layers.6.mlp.up_proj.suh": "model-00001-of-00003.safetensors",
|
151 |
+
"model.layers.6.mlp.up_proj.svh": "model-00001-of-00003.safetensors",
|
152 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
153 |
+
"model.layers.6.self_attn.k_proj.suh": "model-00001-of-00003.safetensors",
|
154 |
+
"model.layers.6.self_attn.k_proj.svh": "model-00001-of-00003.safetensors",
|
155 |
+
"model.layers.6.self_attn.o_proj.suh": "model-00001-of-00003.safetensors",
|
156 |
+
"model.layers.6.self_attn.o_proj.svh": "model-00001-of-00003.safetensors",
|
157 |
+
"model.layers.6.self_attn.q_proj.suh": "model-00001-of-00003.safetensors",
|
158 |
+
"model.layers.6.self_attn.q_proj.svh": "model-00001-of-00003.safetensors",
|
159 |
+
"model.layers.6.self_attn.v_proj.suh": "model-00001-of-00003.safetensors",
|
160 |
+
"model.layers.6.self_attn.v_proj.svh": "model-00001-of-00003.safetensors",
|
161 |
+
"model.layers.6.mlp.down_proj.trellis": "model-00001-of-00003.safetensors",
|
162 |
+
"model.layers.6.mlp.gate_proj.trellis": "model-00001-of-00003.safetensors",
|
163 |
+
"model.layers.6.mlp.up_proj.trellis": "model-00001-of-00003.safetensors",
|
164 |
+
"model.layers.6.self_attn.k_proj.trellis": "model-00001-of-00003.safetensors",
|
165 |
+
"model.layers.6.self_attn.o_proj.trellis": "model-00001-of-00003.safetensors",
|
166 |
+
"model.layers.6.self_attn.q_proj.trellis": "model-00001-of-00003.safetensors",
|
167 |
+
"model.layers.6.self_attn.v_proj.trellis": "model-00001-of-00003.safetensors",
|
168 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
169 |
+
"model.layers.7.mlp.down_proj.suh": "model-00001-of-00003.safetensors",
|
170 |
+
"model.layers.7.mlp.down_proj.svh": "model-00001-of-00003.safetensors",
|
171 |
+
"model.layers.7.mlp.gate_proj.suh": "model-00001-of-00003.safetensors",
|
172 |
+
"model.layers.7.mlp.gate_proj.svh": "model-00001-of-00003.safetensors",
|
173 |
+
"model.layers.7.mlp.up_proj.suh": "model-00001-of-00003.safetensors",
|
174 |
+
"model.layers.7.mlp.up_proj.svh": "model-00001-of-00003.safetensors",
|
175 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
176 |
+
"model.layers.7.self_attn.k_proj.suh": "model-00001-of-00003.safetensors",
|
177 |
+
"model.layers.7.self_attn.k_proj.svh": "model-00001-of-00003.safetensors",
|
178 |
+
"model.layers.7.self_attn.o_proj.suh": "model-00001-of-00003.safetensors",
|
179 |
+
"model.layers.7.self_attn.o_proj.svh": "model-00001-of-00003.safetensors",
|
180 |
+
"model.layers.7.self_attn.q_proj.suh": "model-00001-of-00003.safetensors",
|
181 |
+
"model.layers.7.self_attn.q_proj.svh": "model-00001-of-00003.safetensors",
|
182 |
+
"model.layers.7.self_attn.v_proj.suh": "model-00001-of-00003.safetensors",
|
183 |
+
"model.layers.7.self_attn.v_proj.svh": "model-00001-of-00003.safetensors",
|
184 |
+
"model.layers.7.mlp.down_proj.trellis": "model-00001-of-00003.safetensors",
|
185 |
+
"model.layers.7.mlp.gate_proj.trellis": "model-00001-of-00003.safetensors",
|
186 |
+
"model.layers.7.mlp.up_proj.trellis": "model-00001-of-00003.safetensors",
|
187 |
+
"model.layers.7.self_attn.k_proj.trellis": "model-00001-of-00003.safetensors",
|
188 |
+
"model.layers.7.self_attn.o_proj.trellis": "model-00001-of-00003.safetensors",
|
189 |
+
"model.layers.7.self_attn.q_proj.trellis": "model-00001-of-00003.safetensors",
|
190 |
+
"model.layers.7.self_attn.v_proj.trellis": "model-00001-of-00003.safetensors",
|
191 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
192 |
+
"model.layers.8.mlp.down_proj.suh": "model-00001-of-00003.safetensors",
|
193 |
+
"model.layers.8.mlp.down_proj.svh": "model-00001-of-00003.safetensors",
|
194 |
+
"model.layers.8.mlp.gate_proj.suh": "model-00001-of-00003.safetensors",
|
195 |
+
"model.layers.8.mlp.gate_proj.svh": "model-00001-of-00003.safetensors",
|
196 |
+
"model.layers.8.mlp.up_proj.suh": "model-00001-of-00003.safetensors",
|
197 |
+
"model.layers.8.mlp.up_proj.svh": "model-00001-of-00003.safetensors",
|
198 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
199 |
+
"model.layers.8.self_attn.k_proj.suh": "model-00001-of-00003.safetensors",
|
200 |
+
"model.layers.8.self_attn.k_proj.svh": "model-00001-of-00003.safetensors",
|
201 |
+
"model.layers.8.self_attn.o_proj.suh": "model-00001-of-00003.safetensors",
|
202 |
+
"model.layers.8.self_attn.o_proj.svh": "model-00001-of-00003.safetensors",
|
203 |
+
"model.layers.8.self_attn.q_proj.suh": "model-00001-of-00003.safetensors",
|
204 |
+
"model.layers.8.self_attn.q_proj.svh": "model-00001-of-00003.safetensors",
|
205 |
+
"model.layers.8.self_attn.v_proj.suh": "model-00001-of-00003.safetensors",
|
206 |
+
"model.layers.8.self_attn.v_proj.svh": "model-00001-of-00003.safetensors",
|
207 |
+
"model.layers.8.mlp.down_proj.trellis": "model-00001-of-00003.safetensors",
|
208 |
+
"model.layers.8.mlp.gate_proj.trellis": "model-00001-of-00003.safetensors",
|
209 |
+
"model.layers.8.mlp.up_proj.trellis": "model-00001-of-00003.safetensors",
|
210 |
+
"model.layers.8.self_attn.k_proj.trellis": "model-00001-of-00003.safetensors",
|
211 |
+
"model.layers.8.self_attn.o_proj.trellis": "model-00001-of-00003.safetensors",
|
212 |
+
"model.layers.8.self_attn.q_proj.trellis": "model-00001-of-00003.safetensors",
|
213 |
+
"model.layers.8.self_attn.v_proj.trellis": "model-00001-of-00003.safetensors",
|
214 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
215 |
+
"model.layers.9.mlp.down_proj.suh": "model-00001-of-00003.safetensors",
|
216 |
+
"model.layers.9.mlp.down_proj.svh": "model-00001-of-00003.safetensors",
|
217 |
+
"model.layers.9.mlp.gate_proj.suh": "model-00001-of-00003.safetensors",
|
218 |
+
"model.layers.9.mlp.gate_proj.svh": "model-00001-of-00003.safetensors",
|
219 |
+
"model.layers.9.mlp.up_proj.suh": "model-00001-of-00003.safetensors",
|
220 |
+
"model.layers.9.mlp.up_proj.svh": "model-00001-of-00003.safetensors",
|
221 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
222 |
+
"model.layers.9.self_attn.k_proj.suh": "model-00001-of-00003.safetensors",
|
223 |
+
"model.layers.9.self_attn.k_proj.svh": "model-00001-of-00003.safetensors",
|
224 |
+
"model.layers.9.self_attn.o_proj.suh": "model-00001-of-00003.safetensors",
|
225 |
+
"model.layers.9.self_attn.o_proj.svh": "model-00001-of-00003.safetensors",
|
226 |
+
"model.layers.9.self_attn.q_proj.suh": "model-00001-of-00003.safetensors",
|
227 |
+
"model.layers.9.self_attn.q_proj.svh": "model-00001-of-00003.safetensors",
|
228 |
+
"model.layers.9.self_attn.v_proj.suh": "model-00001-of-00003.safetensors",
|
229 |
+
"model.layers.9.self_attn.v_proj.svh": "model-00001-of-00003.safetensors",
|
230 |
+
"model.layers.9.mlp.down_proj.trellis": "model-00001-of-00003.safetensors",
|
231 |
+
"model.layers.9.mlp.gate_proj.trellis": "model-00001-of-00003.safetensors",
|
232 |
+
"model.layers.9.mlp.up_proj.trellis": "model-00001-of-00003.safetensors",
|
233 |
+
"model.layers.9.self_attn.k_proj.trellis": "model-00001-of-00003.safetensors",
|
234 |
+
"model.layers.9.self_attn.o_proj.trellis": "model-00001-of-00003.safetensors",
|
235 |
+
"model.layers.9.self_attn.q_proj.trellis": "model-00001-of-00003.safetensors",
|
236 |
+
"model.layers.9.self_attn.v_proj.trellis": "model-00001-of-00003.safetensors",
|
237 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
238 |
+
"model.layers.10.mlp.down_proj.suh": "model-00001-of-00003.safetensors",
|
239 |
+
"model.layers.10.mlp.down_proj.svh": "model-00001-of-00003.safetensors",
|
240 |
+
"model.layers.10.mlp.gate_proj.suh": "model-00001-of-00003.safetensors",
|
241 |
+
"model.layers.10.mlp.gate_proj.svh": "model-00001-of-00003.safetensors",
|
242 |
+
"model.layers.10.mlp.up_proj.suh": "model-00001-of-00003.safetensors",
|
243 |
+
"model.layers.10.mlp.up_proj.svh": "model-00001-of-00003.safetensors",
|
244 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
245 |
+
"model.layers.10.self_attn.k_proj.suh": "model-00001-of-00003.safetensors",
|
246 |
+
"model.layers.10.self_attn.k_proj.svh": "model-00001-of-00003.safetensors",
|
247 |
+
"model.layers.10.self_attn.o_proj.suh": "model-00001-of-00003.safetensors",
|
248 |
+
"model.layers.10.self_attn.o_proj.svh": "model-00001-of-00003.safetensors",
|
249 |
+
"model.layers.10.self_attn.q_proj.suh": "model-00001-of-00003.safetensors",
|
250 |
+
"model.layers.10.self_attn.q_proj.svh": "model-00001-of-00003.safetensors",
|
251 |
+
"model.layers.10.self_attn.v_proj.suh": "model-00001-of-00003.safetensors",
|
252 |
+
"model.layers.10.self_attn.v_proj.svh": "model-00001-of-00003.safetensors",
|
253 |
+
"model.layers.10.mlp.down_proj.trellis": "model-00001-of-00003.safetensors",
|
254 |
+
"model.layers.10.mlp.gate_proj.trellis": "model-00001-of-00003.safetensors",
|
255 |
+
"model.layers.10.mlp.up_proj.trellis": "model-00001-of-00003.safetensors",
|
256 |
+
"model.layers.10.self_attn.k_proj.trellis": "model-00001-of-00003.safetensors",
|
257 |
+
"model.layers.10.self_attn.o_proj.trellis": "model-00001-of-00003.safetensors",
|
258 |
+
"model.layers.10.self_attn.q_proj.trellis": "model-00001-of-00003.safetensors",
|
259 |
+
"model.layers.10.self_attn.v_proj.trellis": "model-00001-of-00003.safetensors",
|
260 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
261 |
+
"model.layers.11.mlp.down_proj.suh": "model-00001-of-00003.safetensors",
|
262 |
+
"model.layers.11.mlp.down_proj.svh": "model-00001-of-00003.safetensors",
|
263 |
+
"model.layers.11.mlp.gate_proj.suh": "model-00001-of-00003.safetensors",
|
264 |
+
"model.layers.11.mlp.gate_proj.svh": "model-00001-of-00003.safetensors",
|
265 |
+
"model.layers.11.mlp.up_proj.suh": "model-00001-of-00003.safetensors",
|
266 |
+
"model.layers.11.mlp.up_proj.svh": "model-00001-of-00003.safetensors",
|
267 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
268 |
+
"model.layers.11.self_attn.k_proj.suh": "model-00001-of-00003.safetensors",
|
269 |
+
"model.layers.11.self_attn.k_proj.svh": "model-00001-of-00003.safetensors",
|
270 |
+
"model.layers.11.self_attn.o_proj.suh": "model-00001-of-00003.safetensors",
|
271 |
+
"model.layers.11.self_attn.o_proj.svh": "model-00001-of-00003.safetensors",
|
272 |
+
"model.layers.11.self_attn.q_proj.suh": "model-00001-of-00003.safetensors",
|
273 |
+
"model.layers.11.self_attn.q_proj.svh": "model-00001-of-00003.safetensors",
|
274 |
+
"model.layers.11.self_attn.v_proj.suh": "model-00001-of-00003.safetensors",
|
275 |
+
"model.layers.11.self_attn.v_proj.svh": "model-00001-of-00003.safetensors",
|
276 |
+
"model.layers.11.mlp.down_proj.trellis": "model-00001-of-00003.safetensors",
|
277 |
+
"model.layers.11.mlp.gate_proj.trellis": "model-00001-of-00003.safetensors",
|
278 |
+
"model.layers.11.mlp.up_proj.trellis": "model-00001-of-00003.safetensors",
|
279 |
+
"model.layers.11.self_attn.k_proj.trellis": "model-00001-of-00003.safetensors",
|
280 |
+
"model.layers.11.self_attn.o_proj.trellis": "model-00001-of-00003.safetensors",
|
281 |
+
"model.layers.11.self_attn.q_proj.trellis": "model-00001-of-00003.safetensors",
|
282 |
+
"model.layers.11.self_attn.v_proj.trellis": "model-00001-of-00003.safetensors",
|
283 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
284 |
+
"model.layers.12.mlp.down_proj.suh": "model-00001-of-00003.safetensors",
|
285 |
+
"model.layers.12.mlp.down_proj.svh": "model-00001-of-00003.safetensors",
|
286 |
+
"model.layers.12.mlp.gate_proj.suh": "model-00001-of-00003.safetensors",
|
287 |
+
"model.layers.12.mlp.gate_proj.svh": "model-00001-of-00003.safetensors",
|
288 |
+
"model.layers.12.mlp.up_proj.suh": "model-00001-of-00003.safetensors",
|
289 |
+
"model.layers.12.mlp.up_proj.svh": "model-00001-of-00003.safetensors",
|
290 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
291 |
+
"model.layers.12.self_attn.k_proj.suh": "model-00001-of-00003.safetensors",
|
292 |
+
"model.layers.12.self_attn.k_proj.svh": "model-00001-of-00003.safetensors",
|
293 |
+
"model.layers.12.self_attn.o_proj.suh": "model-00001-of-00003.safetensors",
|
294 |
+
"model.layers.12.self_attn.o_proj.svh": "model-00001-of-00003.safetensors",
|
295 |
+
"model.layers.12.self_attn.q_proj.suh": "model-00001-of-00003.safetensors",
|
296 |
+
"model.layers.12.self_attn.q_proj.svh": "model-00001-of-00003.safetensors",
|
297 |
+
"model.layers.12.self_attn.v_proj.suh": "model-00001-of-00003.safetensors",
|
298 |
+
"model.layers.12.self_attn.v_proj.svh": "model-00001-of-00003.safetensors",
|
299 |
+
"model.layers.12.mlp.down_proj.trellis": "model-00001-of-00003.safetensors",
|
300 |
+
"model.layers.12.mlp.gate_proj.trellis": "model-00001-of-00003.safetensors",
|
301 |
+
"model.layers.12.mlp.up_proj.trellis": "model-00001-of-00003.safetensors",
|
302 |
+
"model.layers.12.self_attn.k_proj.trellis": "model-00001-of-00003.safetensors",
|
303 |
+
"model.layers.12.self_attn.o_proj.trellis": "model-00001-of-00003.safetensors",
|
304 |
+
"model.layers.12.self_attn.q_proj.trellis": "model-00001-of-00003.safetensors",
|
305 |
+
"model.layers.12.self_attn.v_proj.trellis": "model-00001-of-00003.safetensors",
|
306 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
307 |
+
"model.layers.13.mlp.down_proj.suh": "model-00001-of-00003.safetensors",
|
308 |
+
"model.layers.13.mlp.down_proj.svh": "model-00001-of-00003.safetensors",
|
309 |
+
"model.layers.13.mlp.gate_proj.suh": "model-00001-of-00003.safetensors",
|
310 |
+
"model.layers.13.mlp.gate_proj.svh": "model-00001-of-00003.safetensors",
|
311 |
+
"model.layers.13.mlp.up_proj.suh": "model-00001-of-00003.safetensors",
|
312 |
+
"model.layers.13.mlp.up_proj.svh": "model-00001-of-00003.safetensors",
|
313 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
314 |
+
"model.layers.13.self_attn.k_proj.suh": "model-00001-of-00003.safetensors",
|
315 |
+
"model.layers.13.self_attn.k_proj.svh": "model-00001-of-00003.safetensors",
|
316 |
+
"model.layers.13.self_attn.o_proj.suh": "model-00001-of-00003.safetensors",
|
317 |
+
"model.layers.13.self_attn.o_proj.svh": "model-00001-of-00003.safetensors",
|
318 |
+
"model.layers.13.self_attn.q_proj.suh": "model-00001-of-00003.safetensors",
|
319 |
+
"model.layers.13.self_attn.q_proj.svh": "model-00001-of-00003.safetensors",
|
320 |
+
"model.layers.13.self_attn.v_proj.suh": "model-00001-of-00003.safetensors",
|
321 |
+
"model.layers.13.self_attn.v_proj.svh": "model-00001-of-00003.safetensors",
|
322 |
+
"model.layers.13.mlp.down_proj.trellis": "model-00001-of-00003.safetensors",
|
323 |
+
"model.layers.13.mlp.gate_proj.trellis": "model-00001-of-00003.safetensors",
|
324 |
+
"model.layers.13.mlp.up_proj.trellis": "model-00001-of-00003.safetensors",
|
325 |
+
"model.layers.13.self_attn.k_proj.trellis": "model-00001-of-00003.safetensors",
|
326 |
+
"model.layers.13.self_attn.o_proj.trellis": "model-00001-of-00003.safetensors",
|
327 |
+
"model.layers.13.self_attn.q_proj.trellis": "model-00001-of-00003.safetensors",
|
328 |
+
"model.layers.13.self_attn.v_proj.trellis": "model-00001-of-00003.safetensors",
|
329 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
330 |
+
"model.layers.14.mlp.down_proj.suh": "model-00001-of-00003.safetensors",
|
331 |
+
"model.layers.14.mlp.down_proj.svh": "model-00001-of-00003.safetensors",
|
332 |
+
"model.layers.14.mlp.gate_proj.suh": "model-00001-of-00003.safetensors",
|
333 |
+
"model.layers.14.mlp.gate_proj.svh": "model-00001-of-00003.safetensors",
|
334 |
+
"model.layers.14.mlp.up_proj.suh": "model-00001-of-00003.safetensors",
|
335 |
+
"model.layers.14.mlp.up_proj.svh": "model-00001-of-00003.safetensors",
|
336 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
337 |
+
"model.layers.14.self_attn.k_proj.suh": "model-00001-of-00003.safetensors",
|
338 |
+
"model.layers.14.self_attn.k_proj.svh": "model-00001-of-00003.safetensors",
|
339 |
+
"model.layers.14.self_attn.o_proj.suh": "model-00001-of-00003.safetensors",
|
340 |
+
"model.layers.14.self_attn.o_proj.svh": "model-00001-of-00003.safetensors",
|
341 |
+
"model.layers.14.self_attn.q_proj.suh": "model-00001-of-00003.safetensors",
|
342 |
+
"model.layers.14.self_attn.q_proj.svh": "model-00001-of-00003.safetensors",
|
343 |
+
"model.layers.14.self_attn.v_proj.suh": "model-00001-of-00003.safetensors",
|
344 |
+
"model.layers.14.self_attn.v_proj.svh": "model-00001-of-00003.safetensors",
|
345 |
+
"model.layers.14.mlp.down_proj.trellis": "model-00001-of-00003.safetensors",
|
346 |
+
"model.layers.14.mlp.gate_proj.trellis": "model-00001-of-00003.safetensors",
|
347 |
+
"model.layers.14.mlp.up_proj.trellis": "model-00001-of-00003.safetensors",
|
348 |
+
"model.layers.14.self_attn.k_proj.trellis": "model-00001-of-00003.safetensors",
|
349 |
+
"model.layers.14.self_attn.o_proj.trellis": "model-00001-of-00003.safetensors",
|
350 |
+
"model.layers.14.self_attn.q_proj.trellis": "model-00001-of-00003.safetensors",
|
351 |
+
"model.layers.14.self_attn.v_proj.trellis": "model-00001-of-00003.safetensors",
|
352 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
353 |
+
"model.layers.15.mlp.down_proj.suh": "model-00001-of-00003.safetensors",
|
354 |
+
"model.layers.15.mlp.down_proj.svh": "model-00001-of-00003.safetensors",
|
355 |
+
"model.layers.15.mlp.gate_proj.suh": "model-00001-of-00003.safetensors",
|
356 |
+
"model.layers.15.mlp.gate_proj.svh": "model-00001-of-00003.safetensors",
|
357 |
+
"model.layers.15.mlp.up_proj.suh": "model-00001-of-00003.safetensors",
|
358 |
+
"model.layers.15.mlp.up_proj.svh": "model-00001-of-00003.safetensors",
|
359 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
360 |
+
"model.layers.15.self_attn.k_proj.suh": "model-00001-of-00003.safetensors",
|
361 |
+
"model.layers.15.self_attn.k_proj.svh": "model-00001-of-00003.safetensors",
|
362 |
+
"model.layers.15.self_attn.o_proj.suh": "model-00001-of-00003.safetensors",
|
363 |
+
"model.layers.15.self_attn.o_proj.svh": "model-00001-of-00003.safetensors",
|
364 |
+
"model.layers.15.self_attn.q_proj.suh": "model-00001-of-00003.safetensors",
|
365 |
+
"model.layers.15.self_attn.q_proj.svh": "model-00001-of-00003.safetensors",
|
366 |
+
"model.layers.15.self_attn.v_proj.suh": "model-00001-of-00003.safetensors",
|
367 |
+
"model.layers.15.self_attn.v_proj.svh": "model-00001-of-00003.safetensors",
|
368 |
+
"model.layers.15.mlp.down_proj.trellis": "model-00001-of-00003.safetensors",
|
369 |
+
"model.layers.15.mlp.gate_proj.trellis": "model-00001-of-00003.safetensors",
|
370 |
+
"model.layers.15.mlp.up_proj.trellis": "model-00001-of-00003.safetensors",
|
371 |
+
"model.layers.15.self_attn.k_proj.trellis": "model-00001-of-00003.safetensors",
|
372 |
+
"model.layers.15.self_attn.o_proj.trellis": "model-00001-of-00003.safetensors",
|
373 |
+
"model.layers.15.self_attn.q_proj.trellis": "model-00001-of-00003.safetensors",
|
374 |
+
"model.layers.15.self_attn.v_proj.trellis": "model-00001-of-00003.safetensors",
|
375 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
376 |
+
"model.layers.16.mlp.down_proj.suh": "model-00001-of-00003.safetensors",
|
377 |
+
"model.layers.16.mlp.down_proj.svh": "model-00001-of-00003.safetensors",
|
378 |
+
"model.layers.16.mlp.gate_proj.suh": "model-00001-of-00003.safetensors",
|
379 |
+
"model.layers.16.mlp.gate_proj.svh": "model-00001-of-00003.safetensors",
|
380 |
+
"model.layers.16.mlp.up_proj.suh": "model-00001-of-00003.safetensors",
|
381 |
+
"model.layers.16.mlp.up_proj.svh": "model-00001-of-00003.safetensors",
|
382 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
383 |
+
"model.layers.16.self_attn.k_proj.suh": "model-00001-of-00003.safetensors",
|
384 |
+
"model.layers.16.self_attn.k_proj.svh": "model-00001-of-00003.safetensors",
|
385 |
+
"model.layers.16.self_attn.o_proj.suh": "model-00001-of-00003.safetensors",
|
386 |
+
"model.layers.16.self_attn.o_proj.svh": "model-00001-of-00003.safetensors",
|
387 |
+
"model.layers.16.self_attn.q_proj.suh": "model-00001-of-00003.safetensors",
|
388 |
+
"model.layers.16.self_attn.q_proj.svh": "model-00001-of-00003.safetensors",
|
389 |
+
"model.layers.16.self_attn.v_proj.suh": "model-00001-of-00003.safetensors",
|
390 |
+
"model.layers.16.self_attn.v_proj.svh": "model-00001-of-00003.safetensors",
|
391 |
+
"model.layers.16.mlp.down_proj.trellis": "model-00001-of-00003.safetensors",
|
392 |
+
"model.layers.16.mlp.gate_proj.trellis": "model-00001-of-00003.safetensors",
|
393 |
+
"model.layers.16.mlp.up_proj.trellis": "model-00001-of-00003.safetensors",
|
394 |
+
"model.layers.16.self_attn.k_proj.trellis": "model-00001-of-00003.safetensors",
|
395 |
+
"model.layers.16.self_attn.o_proj.trellis": "model-00001-of-00003.safetensors",
|
396 |
+
"model.layers.16.self_attn.q_proj.trellis": "model-00001-of-00003.safetensors",
|
397 |
+
"model.layers.16.self_attn.v_proj.trellis": "model-00001-of-00003.safetensors",
|
398 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
399 |
+
"model.layers.17.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
|
400 |
+
"model.layers.17.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
|
401 |
+
"model.layers.17.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
|
402 |
+
"model.layers.17.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
|
403 |
+
"model.layers.17.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
|
404 |
+
"model.layers.17.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
|
405 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
406 |
+
"model.layers.17.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
|
407 |
+
"model.layers.17.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
|
408 |
+
"model.layers.17.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
|
409 |
+
"model.layers.17.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
|
410 |
+
"model.layers.17.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
|
411 |
+
"model.layers.17.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
|
412 |
+
"model.layers.17.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
|
413 |
+
"model.layers.17.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
|
414 |
+
"model.layers.17.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
|
415 |
+
"model.layers.17.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
|
416 |
+
"model.layers.17.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
|
417 |
+
"model.layers.17.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
|
418 |
+
"model.layers.17.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
|
419 |
+
"model.layers.17.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
|
420 |
+
"model.layers.17.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
|
421 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
422 |
+
"model.layers.18.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
|
423 |
+
"model.layers.18.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
|
424 |
+
"model.layers.18.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
|
425 |
+
"model.layers.18.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
|
426 |
+
"model.layers.18.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
|
427 |
+
"model.layers.18.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
|
428 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
429 |
+
"model.layers.18.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
|
430 |
+
"model.layers.18.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
|
431 |
+
"model.layers.18.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
|
432 |
+
"model.layers.18.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
|
433 |
+
"model.layers.18.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
|
434 |
+
"model.layers.18.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
|
435 |
+
"model.layers.18.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
|
436 |
+
"model.layers.18.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
|
437 |
+
"model.layers.18.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
|
438 |
+
"model.layers.18.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
|
439 |
+
"model.layers.18.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
|
440 |
+
"model.layers.18.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
|
441 |
+
"model.layers.18.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
|
442 |
+
"model.layers.18.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
|
443 |
+
"model.layers.18.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
|
444 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
445 |
+
"model.layers.19.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
|
446 |
+
"model.layers.19.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
|
447 |
+
"model.layers.19.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
|
448 |
+
"model.layers.19.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
|
449 |
+
"model.layers.19.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
|
450 |
+
"model.layers.19.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
|
451 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
452 |
+
"model.layers.19.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
|
453 |
+
"model.layers.19.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
|
454 |
+
"model.layers.19.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
|
455 |
+
"model.layers.19.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
|
456 |
+
"model.layers.19.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
|
457 |
+
"model.layers.19.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
|
458 |
+
"model.layers.19.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
|
459 |
+
"model.layers.19.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
|
460 |
+
"model.layers.19.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
|
461 |
+
"model.layers.19.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
|
462 |
+
"model.layers.19.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
|
463 |
+
"model.layers.19.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
|
464 |
+
"model.layers.19.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
|
465 |
+
"model.layers.19.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
|
466 |
+
"model.layers.19.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
|
467 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
468 |
+
"model.layers.20.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
|
469 |
+
"model.layers.20.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
|
470 |
+
"model.layers.20.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
|
471 |
+
"model.layers.20.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
|
472 |
+
"model.layers.20.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
|
473 |
+
"model.layers.20.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
|
474 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
475 |
+
"model.layers.20.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
|
476 |
+
"model.layers.20.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
|
477 |
+
"model.layers.20.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
|
478 |
+
"model.layers.20.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
|
479 |
+
"model.layers.20.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
|
480 |
+
"model.layers.20.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
|
481 |
+
"model.layers.20.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
|
482 |
+
"model.layers.20.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
|
483 |
+
"model.layers.20.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
|
484 |
+
"model.layers.20.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
|
485 |
+
"model.layers.20.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
|
486 |
+
"model.layers.20.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
|
487 |
+
"model.layers.20.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
|
488 |
+
"model.layers.20.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
|
489 |
+
"model.layers.20.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
|
490 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
491 |
+
"model.layers.21.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
|
492 |
+
"model.layers.21.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
|
493 |
+
"model.layers.21.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
|
494 |
+
"model.layers.21.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
|
495 |
+
"model.layers.21.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
|
496 |
+
"model.layers.21.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
|
497 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
498 |
+
"model.layers.21.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
|
499 |
+
"model.layers.21.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
|
500 |
+
"model.layers.21.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
|
501 |
+
"model.layers.21.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
|
502 |
+
"model.layers.21.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
|
503 |
+
"model.layers.21.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
|
504 |
+
"model.layers.21.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
|
505 |
+
"model.layers.21.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
|
506 |
+
"model.layers.21.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
|
507 |
+
"model.layers.21.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
|
508 |
+
"model.layers.21.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
|
509 |
+
"model.layers.21.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
|
510 |
+
"model.layers.21.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
|
511 |
+
"model.layers.21.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
|
512 |
+
"model.layers.21.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
|
513 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
514 |
+
"model.layers.22.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
|
515 |
+
"model.layers.22.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
|
516 |
+
"model.layers.22.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
|
517 |
+
"model.layers.22.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
|
518 |
+
"model.layers.22.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
|
519 |
+
"model.layers.22.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
|
520 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
521 |
+
"model.layers.22.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
|
522 |
+
"model.layers.22.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
|
523 |
+
"model.layers.22.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
|
524 |
+
"model.layers.22.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
|
525 |
+
"model.layers.22.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
|
526 |
+
"model.layers.22.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
|
527 |
+
"model.layers.22.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
|
528 |
+
"model.layers.22.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
|
529 |
+
"model.layers.22.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
|
530 |
+
"model.layers.22.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
|
531 |
+
"model.layers.22.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
|
532 |
+
"model.layers.22.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
|
533 |
+
"model.layers.22.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
|
534 |
+
"model.layers.22.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
|
535 |
+
"model.layers.22.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
|
536 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
537 |
+
"model.layers.23.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
|
538 |
+
"model.layers.23.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
|
539 |
+
"model.layers.23.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
|
540 |
+
"model.layers.23.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
|
541 |
+
"model.layers.23.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
|
542 |
+
"model.layers.23.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
|
543 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
544 |
+
"model.layers.23.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
|
545 |
+
"model.layers.23.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
|
546 |
+
"model.layers.23.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
|
547 |
+
"model.layers.23.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
|
548 |
+
"model.layers.23.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
|
549 |
+
"model.layers.23.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
|
550 |
+
"model.layers.23.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
|
551 |
+
"model.layers.23.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
|
552 |
+
"model.layers.23.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
|
553 |
+
"model.layers.23.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
|
554 |
+
"model.layers.23.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
|
555 |
+
"model.layers.23.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
|
556 |
+
"model.layers.23.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
|
557 |
+
"model.layers.23.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
|
558 |
+
"model.layers.23.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
|
559 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
560 |
+
"model.layers.24.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
|
561 |
+
"model.layers.24.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
|
562 |
+
"model.layers.24.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
|
563 |
+
"model.layers.24.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
|
564 |
+
"model.layers.24.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
|
565 |
+
"model.layers.24.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
|
566 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
567 |
+
"model.layers.24.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
|
568 |
+
"model.layers.24.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
|
569 |
+
"model.layers.24.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
|
570 |
+
"model.layers.24.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
|
571 |
+
"model.layers.24.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
|
572 |
+
"model.layers.24.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
|
573 |
+
"model.layers.24.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
|
574 |
+
"model.layers.24.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
|
575 |
+
"model.layers.24.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
|
576 |
+
"model.layers.24.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
|
577 |
+
"model.layers.24.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
|
578 |
+
"model.layers.24.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
|
579 |
+
"model.layers.24.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
|
580 |
+
"model.layers.24.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
|
581 |
+
"model.layers.24.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
|
582 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
583 |
+
"model.layers.25.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
|
584 |
+
"model.layers.25.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
|
585 |
+
"model.layers.25.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
|
586 |
+
"model.layers.25.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
|
587 |
+
"model.layers.25.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
|
588 |
+
"model.layers.25.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
|
589 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
590 |
+
"model.layers.25.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
|
591 |
+
"model.layers.25.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
|
592 |
+
"model.layers.25.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
|
593 |
+
"model.layers.25.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
|
594 |
+
"model.layers.25.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
|
595 |
+
"model.layers.25.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
|
596 |
+
"model.layers.25.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
|
597 |
+
"model.layers.25.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
|
598 |
+
"model.layers.25.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
|
599 |
+
"model.layers.25.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
|
600 |
+
"model.layers.25.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
|
601 |
+
"model.layers.25.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
|
602 |
+
"model.layers.25.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
|
603 |
+
"model.layers.25.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
|
604 |
+
"model.layers.25.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
|
605 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
606 |
+
"model.layers.26.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
|
607 |
+
"model.layers.26.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
|
608 |
+
"model.layers.26.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
|
609 |
+
"model.layers.26.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
|
610 |
+
"model.layers.26.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
|
611 |
+
"model.layers.26.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
|
612 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
613 |
+
"model.layers.26.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
|
614 |
+
"model.layers.26.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
|
615 |
+
"model.layers.26.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
|
616 |
+
"model.layers.26.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
|
617 |
+
"model.layers.26.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
|
618 |
+
"model.layers.26.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
|
619 |
+
"model.layers.26.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
|
620 |
+
"model.layers.26.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
|
621 |
+
"model.layers.26.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
|
622 |
+
"model.layers.26.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
|
623 |
+
"model.layers.26.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
|
624 |
+
"model.layers.26.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
|
625 |
+
"model.layers.26.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
|
626 |
+
"model.layers.26.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
|
627 |
+
"model.layers.26.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
|
628 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
629 |
+
"model.layers.27.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
|
630 |
+
"model.layers.27.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
|
631 |
+
"model.layers.27.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
|
632 |
+
"model.layers.27.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
|
633 |
+
"model.layers.27.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
|
634 |
+
"model.layers.27.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
|
635 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
636 |
+
"model.layers.27.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
|
637 |
+
"model.layers.27.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
|
638 |
+
"model.layers.27.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
|
639 |
+
"model.layers.27.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
|
640 |
+
"model.layers.27.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
|
641 |
+
"model.layers.27.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
|
642 |
+
"model.layers.27.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
|
643 |
+
"model.layers.27.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
|
644 |
+
"model.layers.27.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
|
645 |
+
"model.layers.27.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
|
646 |
+
"model.layers.27.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
|
647 |
+
"model.layers.27.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
|
648 |
+
"model.layers.27.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
|
649 |
+
"model.layers.27.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
|
650 |
+
"model.layers.27.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
|
651 |
+
"model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
652 |
+
"model.layers.28.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
|
653 |
+
"model.layers.28.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
|
654 |
+
"model.layers.28.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
|
655 |
+
"model.layers.28.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
|
656 |
+
"model.layers.28.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
|
657 |
+
"model.layers.28.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
|
658 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
659 |
+
"model.layers.28.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
|
660 |
+
"model.layers.28.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
|
661 |
+
"model.layers.28.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
|
662 |
+
"model.layers.28.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
|
663 |
+
"model.layers.28.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
|
664 |
+
"model.layers.28.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
|
665 |
+
"model.layers.28.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
|
666 |
+
"model.layers.28.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
|
667 |
+
"model.layers.28.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
|
668 |
+
"model.layers.28.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
|
669 |
+
"model.layers.28.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
|
670 |
+
"model.layers.28.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
|
671 |
+
"model.layers.28.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
|
672 |
+
"model.layers.28.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
|
673 |
+
"model.layers.28.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
|
674 |
+
"model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
675 |
+
"model.layers.29.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
|
676 |
+
"model.layers.29.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
|
677 |
+
"model.layers.29.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
|
678 |
+
"model.layers.29.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
|
679 |
+
"model.layers.29.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
|
680 |
+
"model.layers.29.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
|
681 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
682 |
+
"model.layers.29.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
|
683 |
+
"model.layers.29.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
|
684 |
+
"model.layers.29.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
|
685 |
+
"model.layers.29.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
|
686 |
+
"model.layers.29.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
|
687 |
+
"model.layers.29.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
|
688 |
+
"model.layers.29.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
|
689 |
+
"model.layers.29.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
|
690 |
+
"model.layers.29.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
|
691 |
+
"model.layers.29.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
|
692 |
+
"model.layers.29.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
|
693 |
+
"model.layers.29.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
|
694 |
+
"model.layers.29.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
|
695 |
+
"model.layers.29.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
|
696 |
+
"model.layers.29.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
|
697 |
+
"model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
698 |
+
"model.layers.30.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
|
699 |
+
"model.layers.30.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
|
700 |
+
"model.layers.30.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
|
701 |
+
"model.layers.30.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
|
702 |
+
"model.layers.30.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
|
703 |
+
"model.layers.30.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
|
704 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
705 |
+
"model.layers.30.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
|
706 |
+
"model.layers.30.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
|
707 |
+
"model.layers.30.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
|
708 |
+
"model.layers.30.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
|
709 |
+
"model.layers.30.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
|
710 |
+
"model.layers.30.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
|
711 |
+
"model.layers.30.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
|
712 |
+
"model.layers.30.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
|
713 |
+
"model.layers.30.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
|
714 |
+
"model.layers.30.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
|
715 |
+
"model.layers.30.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
|
716 |
+
"model.layers.30.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
|
717 |
+
"model.layers.30.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
|
718 |
+
"model.layers.30.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
|
719 |
+
"model.layers.30.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
|
720 |
+
"model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
721 |
+
"model.layers.31.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
|
722 |
+
"model.layers.31.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
|
723 |
+
"model.layers.31.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
|
724 |
+
"model.layers.31.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
|
725 |
+
"model.layers.31.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
|
726 |
+
"model.layers.31.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
|
727 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
728 |
+
"model.layers.31.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
|
729 |
+
"model.layers.31.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
|
730 |
+
"model.layers.31.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
|
731 |
+
"model.layers.31.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
|
732 |
+
"model.layers.31.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
|
733 |
+
"model.layers.31.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
|
734 |
+
"model.layers.31.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
|
735 |
+
"model.layers.31.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
|
736 |
+
"model.layers.31.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
|
737 |
+
"model.layers.31.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
|
738 |
+
"model.layers.31.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
|
739 |
+
"model.layers.31.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
|
740 |
+
"model.layers.31.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
|
741 |
+
"model.layers.31.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
|
742 |
+
"model.layers.31.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
|
743 |
+
"model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
744 |
+
"model.layers.32.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
|
745 |
+
"model.layers.32.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
|
746 |
+
"model.layers.32.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
|
747 |
+
"model.layers.32.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
|
748 |
+
"model.layers.32.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
|
749 |
+
"model.layers.32.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
|
750 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
751 |
+
"model.layers.32.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
|
752 |
+
"model.layers.32.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
|
753 |
+
"model.layers.32.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
|
754 |
+
"model.layers.32.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
|
755 |
+
"model.layers.32.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
|
756 |
+
"model.layers.32.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
|
757 |
+
"model.layers.32.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
|
758 |
+
"model.layers.32.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
|
759 |
+
"model.layers.32.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
|
760 |
+
"model.layers.32.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
|
761 |
+
"model.layers.32.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
|
762 |
+
"model.layers.32.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
|
763 |
+
"model.layers.32.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
|
764 |
+
"model.layers.32.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
|
765 |
+
"model.layers.32.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
|
766 |
+
"model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
767 |
+
"model.layers.33.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
|
768 |
+
"model.layers.33.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
|
769 |
+
"model.layers.33.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
|
770 |
+
"model.layers.33.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
|
771 |
+
"model.layers.33.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
|
772 |
+
"model.layers.33.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
|
773 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
774 |
+
"model.layers.33.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
|
775 |
+
"model.layers.33.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
|
776 |
+
"model.layers.33.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
|
777 |
+
"model.layers.33.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
|
778 |
+
"model.layers.33.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
|
779 |
+
"model.layers.33.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
|
780 |
+
"model.layers.33.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
|
781 |
+
"model.layers.33.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
|
782 |
+
"model.layers.33.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
|
783 |
+
"model.layers.33.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
|
784 |
+
"model.layers.33.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
|
785 |
+
"model.layers.33.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
|
786 |
+
"model.layers.33.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
|
787 |
+
"model.layers.33.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
|
788 |
+
"model.layers.33.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
|
789 |
+
"model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
790 |
+
"model.layers.34.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
|
791 |
+
"model.layers.34.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
|
792 |
+
"model.layers.34.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
|
793 |
+
"model.layers.34.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
|
794 |
+
"model.layers.34.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
|
795 |
+
"model.layers.34.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
|
796 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
797 |
+
"model.layers.34.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
|
798 |
+
"model.layers.34.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
|
799 |
+
"model.layers.34.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
|
800 |
+
"model.layers.34.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
|
801 |
+
"model.layers.34.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
|
802 |
+
"model.layers.34.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
|
803 |
+
"model.layers.34.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
|
804 |
+
"model.layers.34.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
|
805 |
+
"model.layers.34.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
|
806 |
+
"model.layers.34.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
|
807 |
+
"model.layers.34.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
|
808 |
+
"model.layers.34.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
|
809 |
+
"model.layers.34.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
|
810 |
+
"model.layers.34.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
|
811 |
+
"model.layers.34.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
|
812 |
+
"model.layers.35.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
813 |
+
"model.layers.35.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
|
814 |
+
"model.layers.35.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
|
815 |
+
"model.layers.35.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
|
816 |
+
"model.layers.35.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
|
817 |
+
"model.layers.35.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
|
818 |
+
"model.layers.35.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
|
819 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
820 |
+
"model.layers.35.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
|
821 |
+
"model.layers.35.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
|
822 |
+
"model.layers.35.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
|
823 |
+
"model.layers.35.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
|
824 |
+
"model.layers.35.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
|
825 |
+
"model.layers.35.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
|
826 |
+
"model.layers.35.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
|
827 |
+
"model.layers.35.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
|
828 |
+
"model.layers.35.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
|
829 |
+
"model.layers.35.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
|
830 |
+
"model.layers.35.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
|
831 |
+
"model.layers.35.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
|
832 |
+
"model.layers.35.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
|
833 |
+
"model.layers.35.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
|
834 |
+
"model.layers.35.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
|
835 |
+
"model.layers.36.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
836 |
+
"model.layers.36.mlp.down_proj.suh": "model-00002-of-00003.safetensors",
|
837 |
+
"model.layers.36.mlp.down_proj.svh": "model-00002-of-00003.safetensors",
|
838 |
+
"model.layers.36.mlp.gate_proj.suh": "model-00002-of-00003.safetensors",
|
839 |
+
"model.layers.36.mlp.gate_proj.svh": "model-00002-of-00003.safetensors",
|
840 |
+
"model.layers.36.mlp.up_proj.suh": "model-00002-of-00003.safetensors",
|
841 |
+
"model.layers.36.mlp.up_proj.svh": "model-00002-of-00003.safetensors",
|
842 |
+
"model.layers.36.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
843 |
+
"model.layers.36.self_attn.k_proj.suh": "model-00002-of-00003.safetensors",
|
844 |
+
"model.layers.36.self_attn.k_proj.svh": "model-00002-of-00003.safetensors",
|
845 |
+
"model.layers.36.self_attn.o_proj.suh": "model-00002-of-00003.safetensors",
|
846 |
+
"model.layers.36.self_attn.o_proj.svh": "model-00002-of-00003.safetensors",
|
847 |
+
"model.layers.36.self_attn.q_proj.suh": "model-00002-of-00003.safetensors",
|
848 |
+
"model.layers.36.self_attn.q_proj.svh": "model-00002-of-00003.safetensors",
|
849 |
+
"model.layers.36.self_attn.v_proj.suh": "model-00002-of-00003.safetensors",
|
850 |
+
"model.layers.36.self_attn.v_proj.svh": "model-00002-of-00003.safetensors",
|
851 |
+
"model.layers.36.mlp.down_proj.trellis": "model-00002-of-00003.safetensors",
|
852 |
+
"model.layers.36.mlp.gate_proj.trellis": "model-00002-of-00003.safetensors",
|
853 |
+
"model.layers.36.mlp.up_proj.trellis": "model-00002-of-00003.safetensors",
|
854 |
+
"model.layers.36.self_attn.k_proj.trellis": "model-00002-of-00003.safetensors",
|
855 |
+
"model.layers.36.self_attn.o_proj.trellis": "model-00002-of-00003.safetensors",
|
856 |
+
"model.layers.36.self_attn.q_proj.trellis": "model-00002-of-00003.safetensors",
|
857 |
+
"model.layers.36.self_attn.v_proj.trellis": "model-00002-of-00003.safetensors",
|
858 |
+
"model.layers.37.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
859 |
+
"model.layers.37.mlp.down_proj.suh": "model-00003-of-00003.safetensors",
|
860 |
+
"model.layers.37.mlp.down_proj.svh": "model-00003-of-00003.safetensors",
|
861 |
+
"model.layers.37.mlp.gate_proj.suh": "model-00003-of-00003.safetensors",
|
862 |
+
"model.layers.37.mlp.gate_proj.svh": "model-00003-of-00003.safetensors",
|
863 |
+
"model.layers.37.mlp.up_proj.suh": "model-00003-of-00003.safetensors",
|
864 |
+
"model.layers.37.mlp.up_proj.svh": "model-00003-of-00003.safetensors",
|
865 |
+
"model.layers.37.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
866 |
+
"model.layers.37.self_attn.k_proj.suh": "model-00003-of-00003.safetensors",
|
867 |
+
"model.layers.37.self_attn.k_proj.svh": "model-00003-of-00003.safetensors",
|
868 |
+
"model.layers.37.self_attn.o_proj.suh": "model-00003-of-00003.safetensors",
|
869 |
+
"model.layers.37.self_attn.o_proj.svh": "model-00003-of-00003.safetensors",
|
870 |
+
"model.layers.37.self_attn.q_proj.suh": "model-00003-of-00003.safetensors",
|
871 |
+
"model.layers.37.self_attn.q_proj.svh": "model-00003-of-00003.safetensors",
|
872 |
+
"model.layers.37.self_attn.v_proj.suh": "model-00003-of-00003.safetensors",
|
873 |
+
"model.layers.37.self_attn.v_proj.svh": "model-00003-of-00003.safetensors",
|
874 |
+
"model.layers.37.mlp.down_proj.trellis": "model-00003-of-00003.safetensors",
|
875 |
+
"model.layers.37.mlp.gate_proj.trellis": "model-00003-of-00003.safetensors",
|
876 |
+
"model.layers.37.mlp.up_proj.trellis": "model-00003-of-00003.safetensors",
|
877 |
+
"model.layers.37.self_attn.k_proj.trellis": "model-00003-of-00003.safetensors",
|
878 |
+
"model.layers.37.self_attn.o_proj.trellis": "model-00003-of-00003.safetensors",
|
879 |
+
"model.layers.37.self_attn.q_proj.trellis": "model-00003-of-00003.safetensors",
|
880 |
+
"model.layers.37.self_attn.v_proj.trellis": "model-00003-of-00003.safetensors",
|
881 |
+
"model.layers.38.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
882 |
+
"model.layers.38.mlp.down_proj.suh": "model-00003-of-00003.safetensors",
|
883 |
+
"model.layers.38.mlp.down_proj.svh": "model-00003-of-00003.safetensors",
|
884 |
+
"model.layers.38.mlp.gate_proj.suh": "model-00003-of-00003.safetensors",
|
885 |
+
"model.layers.38.mlp.gate_proj.svh": "model-00003-of-00003.safetensors",
|
886 |
+
"model.layers.38.mlp.up_proj.suh": "model-00003-of-00003.safetensors",
|
887 |
+
"model.layers.38.mlp.up_proj.svh": "model-00003-of-00003.safetensors",
|
888 |
+
"model.layers.38.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
889 |
+
"model.layers.38.self_attn.k_proj.suh": "model-00003-of-00003.safetensors",
|
890 |
+
"model.layers.38.self_attn.k_proj.svh": "model-00003-of-00003.safetensors",
|
891 |
+
"model.layers.38.self_attn.o_proj.suh": "model-00003-of-00003.safetensors",
|
892 |
+
"model.layers.38.self_attn.o_proj.svh": "model-00003-of-00003.safetensors",
|
893 |
+
"model.layers.38.self_attn.q_proj.suh": "model-00003-of-00003.safetensors",
|
894 |
+
"model.layers.38.self_attn.q_proj.svh": "model-00003-of-00003.safetensors",
|
895 |
+
"model.layers.38.self_attn.v_proj.suh": "model-00003-of-00003.safetensors",
|
896 |
+
"model.layers.38.self_attn.v_proj.svh": "model-00003-of-00003.safetensors",
|
897 |
+
"model.layers.38.mlp.down_proj.trellis": "model-00003-of-00003.safetensors",
|
898 |
+
"model.layers.38.mlp.gate_proj.trellis": "model-00003-of-00003.safetensors",
|
899 |
+
"model.layers.38.mlp.up_proj.trellis": "model-00003-of-00003.safetensors",
|
900 |
+
"model.layers.38.self_attn.k_proj.trellis": "model-00003-of-00003.safetensors",
|
901 |
+
"model.layers.38.self_attn.o_proj.trellis": "model-00003-of-00003.safetensors",
|
902 |
+
"model.layers.38.self_attn.q_proj.trellis": "model-00003-of-00003.safetensors",
|
903 |
+
"model.layers.38.self_attn.v_proj.trellis": "model-00003-of-00003.safetensors",
|
904 |
+
"model.layers.39.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
905 |
+
"model.layers.39.mlp.down_proj.suh": "model-00003-of-00003.safetensors",
|
906 |
+
"model.layers.39.mlp.down_proj.svh": "model-00003-of-00003.safetensors",
|
907 |
+
"model.layers.39.mlp.gate_proj.suh": "model-00003-of-00003.safetensors",
|
908 |
+
"model.layers.39.mlp.gate_proj.svh": "model-00003-of-00003.safetensors",
|
909 |
+
"model.layers.39.mlp.up_proj.suh": "model-00003-of-00003.safetensors",
|
910 |
+
"model.layers.39.mlp.up_proj.svh": "model-00003-of-00003.safetensors",
|
911 |
+
"model.layers.39.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
912 |
+
"model.layers.39.self_attn.k_proj.suh": "model-00003-of-00003.safetensors",
|
913 |
+
"model.layers.39.self_attn.k_proj.svh": "model-00003-of-00003.safetensors",
|
914 |
+
"model.layers.39.self_attn.o_proj.suh": "model-00003-of-00003.safetensors",
|
915 |
+
"model.layers.39.self_attn.o_proj.svh": "model-00003-of-00003.safetensors",
|
916 |
+
"model.layers.39.self_attn.q_proj.suh": "model-00003-of-00003.safetensors",
|
917 |
+
"model.layers.39.self_attn.q_proj.svh": "model-00003-of-00003.safetensors",
|
918 |
+
"model.layers.39.self_attn.v_proj.suh": "model-00003-of-00003.safetensors",
|
919 |
+
"model.layers.39.self_attn.v_proj.svh": "model-00003-of-00003.safetensors",
|
920 |
+
"model.layers.39.mlp.down_proj.trellis": "model-00003-of-00003.safetensors",
|
921 |
+
"model.layers.39.mlp.gate_proj.trellis": "model-00003-of-00003.safetensors",
|
922 |
+
"model.layers.39.mlp.up_proj.trellis": "model-00003-of-00003.safetensors",
|
923 |
+
"model.layers.39.self_attn.k_proj.trellis": "model-00003-of-00003.safetensors",
|
924 |
+
"model.layers.39.self_attn.o_proj.trellis": "model-00003-of-00003.safetensors",
|
925 |
+
"model.layers.39.self_attn.q_proj.trellis": "model-00003-of-00003.safetensors",
|
926 |
+
"model.layers.39.self_attn.v_proj.trellis": "model-00003-of-00003.safetensors",
|
927 |
+
"model.norm.weight": "model-00003-of-00003.safetensors",
|
928 |
+
"lm_head.suh": "model-00003-of-00003.safetensors",
|
929 |
+
"lm_head.svh": "model-00003-of-00003.safetensors",
|
930 |
+
"lm_head.trellis": "model-00003-of-00003.safetensors"
|
931 |
+
}
|
932 |
+
}
|
quantization_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>"
|
4 |
+
],
|
5 |
+
"bos_token": {
|
6 |
+
"content": "<s>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"eos_token": {
|
13 |
+
"content": "<|im_end|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false
|
18 |
+
},
|
19 |
+
"pad_token": {
|
20 |
+
"content": "<pad>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false
|
25 |
+
},
|
26 |
+
"unk_token": {
|
27 |
+
"content": "<unk>",
|
28 |
+
"lstrip": false,
|
29 |
+
"normalized": false,
|
30 |
+
"rstrip": false,
|
31 |
+
"single_word": false
|
32 |
+
}
|
33 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1e5daf1e619597fd56ff036925ea189916417c665d5bdd61b80199cf8d4e6d2
|
3 |
+
size 17078029
|
tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|