eshmoideas qingy2024 commited on
Commit
f6c5cd5
·
0 Parent(s):

Duplicate from Tesslate/WEBGEN-OSS-20B

Browse files

Co-authored-by: Qingyun Li <qingy2024@users.noreply.huggingface.co>

.gitattributes ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,330 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/gpt-oss-20b-bf16
3
+ license: apache-2.0
4
+ language:
5
+ - en
6
+ tags:
7
+ - text-generation-inference
8
+ - transformers
9
+ - unsloth
10
+ - gpt_oss
11
+ - web-generation
12
+ - html
13
+ - css
14
+ - tailwind-css
15
+ - ui-generation
16
+ - web-design
17
+ - small-model
18
+ - qwen3
19
+ - transformers
20
+ ---
21
+
22
+ [Example Output](https://codepen.io/qingy1337/pen/xbwNWGw)
23
+
24
+ <style>
25
+ :root{
26
+ --bg: #0b0c0f;
27
+ --panel: #0f1117;
28
+ --ink: #e9eefc;
29
+ --muted: #9aa3b2;
30
+ --brand: #5b8cff; /* soft indigo */
31
+ --brand-2: #4ef2c8; /* mint accent */
32
+ --border: rgba(255,255,255,.08);
33
+ --glow: rgba(91,140,255,.25);
34
+ --radius: 16px;
35
+ }
36
+ *{ box-sizing: border-box }
37
+ .card{
38
+ background: linear-gradient(180deg,rgba(255,255,255,.02),rgba(255,255,255,.00));
39
+ border:1px solid var(--border);
40
+ border-radius: var(--radius);
41
+ padding:16px;
42
+ }
43
+ .badge{
44
+ display:inline-flex;align-items:center;gap:.5rem;
45
+ padding:.35rem .6rem;border:1px solid var(--border);border-radius:999px;
46
+ color:var(--muted);font-size:.85rem
47
+ }
48
+ .grid{ display:grid; gap:18px }
49
+ .grid-2{ grid-template-columns:repeat(2,minmax(0,1fr)); }
50
+ .grid-3{ grid-template-columns:repeat(3,minmax(0,1fr)); }
51
+ @media(max-width:900px){ .grid-2,.grid-3{ grid-template-columns:1fr } }
52
+ .kicker{
53
+ display:inline-block;letter-spacing:.12em;text-transform:uppercase;
54
+ color:var(--muted);font-size:.75rem;margin-bottom:.5rem
55
+ }
56
+ h1,h2,h3{ color:var(--ink); margin:0 0 .4rem 0; line-height:1.1 }
57
+ h1{ font-size:2.25rem; font-weight:800 }
58
+ h2{ font-size:1.3rem; font-weight:700 }
59
+ h3{ font-size:1.05rem; font-weight:700 }
60
+ p,li{ color:var(--muted); line-height:1.6 }
61
+ hr{ border:none; height:1px; background:var(--border); margin:28px 0 }
62
+ a.btn{
63
+ display:inline-block; padding:.7rem 1rem; border-radius:12px;
64
+ background: linear-gradient(180deg,var(--brand),#3f6fff);
65
+ color:var(--ink); text-decoration:none; font-weight:600;
66
+ box-shadow: 0 10px 30px var(--glow);
67
+ }
68
+ a.btn.ghost{
69
+ background:transparent; color:var(--ink); border:1px solid var(--border)
70
+ }
71
+ kbd{
72
+ background:#0c1322;color:#cfe0ff;border:1px solid #1a2742;border-bottom-color:#142138;
73
+ padding:.12rem .4rem;border-radius:6px;font-size:.85rem
74
+ }
75
+ .codeblock{
76
+ background:#0b1220;border:1px solid #15233d;border-radius:12px;padding: 8px;overflow:auto; /* Changed padding */
77
+ margin: 1rem 0;
78
+ }
79
+ .codeblock pre {
80
+ margin: 0;
81
+ }
82
+ .tagline{
83
+ font-size:1.05rem;color:#c6d5ff
84
+ }
85
+ .pill{
86
+ display:inline-flex;align-items:center;gap:.4rem;
87
+ padding:.35rem .6rem;border-radius:999px;border:1px dashed var(--border);color:#b9c5db
88
+ }
89
+ .hero{
90
+ background:
91
+ radial-gradient(600px 240px at 20% 0%,rgba(91,140,255,.18),transparent 60%),
92
+ radial-gradient(600px 240px at 80% 10%,rgba(78,242,200,.12),transparent 60%);
93
+ border:1px solid var(--border);
94
+ border-radius:20px; padding:28px
95
+ }
96
+ figure.screens{
97
+ display:grid;grid-template-columns:repeat(3,minmax(0,1fr));gap:10px;margin:16px 0 0 0
98
+ }
99
+ figure.screens img{
100
+ width:100%;border-radius:12px;border:1px solid var(--border)
101
+ }
102
+ details{
103
+ border:1px solid var(--border);border-radius:12px;padding:14px;background:rgba(255,255,255,.02)
104
+ }
105
+ summary{ cursor:pointer;color:var(--ink);font-weight:700 }
106
+ blockquote{
107
+ margin:0;padding:14px;border-left:3px solid var(--brand);background:rgba(91,140,255,.06);
108
+ border-radius:0 10px 10px 0;color:#657ce0
109
+ }
110
+ table{ width:100%; border-collapse:collapse }
111
+ th,td{ text-align:left; padding:10px; border-bottom:1px solid var(--border); color:var(--muted) }
112
+ th{ color:#3480eb }
113
+ .callout{
114
+ border:1px solid var(--border);border-radius:14px;padding:14px;background:rgba(255,255,255,.02)
115
+ }
116
+ </style>
117
+
118
+ <div style="background:var(--bg); padding: 28px; border-radius: 18px">
119
+
120
+ <div class="hero">
121
+ <span class="kicker">Tesslate • Research Preview</span>
122
+ <h1>WEBGEN-OSS-20B</h1>
123
+ <p class="tagline">A <strong>web-only generator</strong> that turns one prompt into clean, responsive <strong>HTML/CSS/Tailwind</strong>. Small enough for laptops; opinionated for consistent, modern layouts.</p>
124
+ <div style="display:flex; gap:10px; flex-wrap:wrap; margin-top:12px">
125
+
126
+ <span class="pill">Open weights</span>
127
+ <span class="pill">Web-only bias</span>
128
+ <span class="pill">Mobile-first output</span>
129
+ <span class="pill">No external JS by default</span>
130
+ </div>
131
+ <div style="display:flex; gap:12px; flex-wrap:wrap; margin-top:18px">
132
+ <a class="btn" href="https://huggingface.co/Tesslate/WEBGEN-OSS-20B/resolve/main/README.md">Model card</a>
133
+ <a class="btn ghost" href="https://tesslate.com">Tesslate</a>
134
+ <a class="btn ghost" href="https://uigenoutput.tesslate.com">Demos</a>
135
+ <a class="btn ghost" href="https://discord.gg/EcCpcTv93U">Discord</a>
136
+ </div>
137
+
138
+ <figure class="screens">
139
+ <img alt="Hero sample" src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/G9dpxQKrYJlpnj3Pvw3LV.png">
140
+ <img alt="Pricing sample" src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/2GrgB4W5VzPqnpD4FJsA-.png">
141
+ <img alt="Features sample" src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/lGvrwLBqeS9IJeKgLrMWO.png">
142
+ <img alt="Hero sample" src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/3Kh7TkSuxKctsGOtHGRXJ.png">
143
+ <img alt="Pricing sample" src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/KYwUop65wR8WikMaw5upL.png">
144
+ <img alt="Features sample" src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/H-c5ORCyMpYmlDN52m3im.png">
145
+ </figure>
146
+ </div>
147
+
148
+ <hr/>
149
+
150
+ <div class="grid grid-2" style="margin-top: 1.5rem">
151
+ <div class="card">
152
+ <h3>What it is</h3>
153
+ <p><strong>WEBGEN-OSS-20B</strong> focuses solely on generating production-lean websites. It prefers semantic HTML, sane spacing, and modern component blocks (hero, grids, pricing, FAQ).</p>
154
+ </div>
155
+ <div class="card">
156
+ <h3>Why</h3>
157
+ <p>Small enough for local runs and fast iteration, while retaining strong structure/consistency for HTML/CSS/Tailwind output.</p>
158
+ </div>
159
+ </div>
160
+
161
+ <hr/>
162
+
163
+ ## Quickstart
164
+
165
+ ### Transformers
166
+ <div class="codeblock"><pre>
167
+ from transformers import AutoModelForCausalLM, AutoTokenizer
168
+ import torch
169
+
170
+ model_id = "Tesslate/WEBGEN-OSS-20B"
171
+ tok = AutoTokenizer.from_pretrained(model_id)
172
+ model = AutoModelForCausalLM.from_pretrained(
173
+ model_id,
174
+ torch_dtype=torch.bfloat16,
175
+ device_map="auto"
176
+ )
177
+
178
+ prompt = """Make a single-file landing page for 'LatticeDB'.
179
+ Style: modern, generous whitespace, Tailwind, rounded-xl, soft gradients.
180
+ Sections: navbar, hero (headline + 2 CTAs), features grid, pricing (3 tiers),
181
+ FAQ accordion, footer. Constraints: semantic HTML, no external JS."""
182
+
183
+ inputs = tok(prompt, return_tensors="pt").to(model.device)
184
+ out = model.generate(**inputs, max_new_tokens=2000, temperature=0.7, top_p=0.9)
185
+ print(tok.decode(out[0], skip_special_tokens=True))
186
+ </pre></div>
187
+
188
+ ### vLLM
189
+ <div class="codeblock"><pre>
190
+ vllm serve Tesslate/WEBGEN-OSS-20B \
191
+ --host 0.0.0.0 --port 8000 \
192
+ --max-model-len 65536 \
193
+ --gpu-memory-utilization 0.92
194
+ </pre></div>
195
+
196
+ ### sglang
197
+ <div class="codeblock"><pre>
198
+ python -m sglang.launch_server \
199
+ --model-path Tesslate/WEBGEN-OSS-20B \
200
+ --host 0.0.0.0 --port 5000 \
201
+ --mem-fraction-static 0.94 \
202
+ --attention-backend flashinfer
203
+ </pre></div>
204
+
205
+ > **Tip:** Lower temperature (e.g., `0.4–0.6`) yields stricter, cleaner markup. Raise it for more visual variety.
206
+
207
+ <hr/>
208
+
209
+ ## Inference Settings (suggested)
210
+
211
+ <table>
212
+ <thead><tr><th>Param</th><th>Value</th><th>Notes</th></tr></thead>
213
+ <tbody>
214
+ <tr><td><code>temperature</code></td><td>0.6</td><td>Balance creativity &amp; consistency (lower if quantized)</td></tr>
215
+ <tr><td><code>top_p</code></td><td>0.9</td><td>Nucleus sampling</td></tr>
216
+ <tr><td><code>top_k</code></td><td>40</td><td>Optional vocab restriction</td></tr>
217
+ <tr><td><code>max_new_tokens</code></td><td>1200–2500</td><td>Single-file sites often fit &lt; 1500</td></tr>
218
+ <tr><td><code>repetition_penalty</code></td><td>1.1</td><td>Reduces repetitive classes/markup</td></tr>
219
+ </tbody>
220
+ </table>
221
+
222
+ <hr/>
223
+
224
+ ## Prompts that work well
225
+
226
+ <div class="grid grid-2">
227
+ <div class="card">
228
+ <h3>Starter</h3>
229
+ <div class="codeblock"><pre>
230
+ Make a single-file landing page for "RasterFlow" (GPU video pipeline).
231
+ Style: modern tech, muted palette, Tailwind, rounded-xl, subtle gradients.
232
+ Sections: navbar, hero (big headline + 2 CTAs), logos row, features (3x cards),
233
+ code block (copyable), pricing (3 tiers), FAQ accordion, footer.
234
+ Constraints: semantic HTML, no external JS. Return ONLY the HTML code.
235
+ </pre></div>
236
+ </div>
237
+ <div class="card">
238
+ <h3>Design-strict</h3>
239
+ <div class="codeblock"><pre>
240
+ Use an 8pt spacing system. Palette: slate with indigo accents.
241
+ Typography scale: 14/16/18/24/36/56. Max width: 1200px.
242
+ Avoid shadows &gt; md; prefer borders/dividers.
243
+ </pre></div>
244
+ </div>
245
+ </div>
246
+
247
+ <hr/>
248
+
249
+ ## Quantization & VRAM (example)
250
+
251
+ <table>
252
+ <thead><tr><th>Format</th><th>Footprint</th><th>Notes</th></tr></thead>
253
+ <tbody>
254
+ <tr><td>BF16</td><td>8.05 GB</td><td>Fastest, best fidelity</td></tr>
255
+ <tr><td>GGUF Q5_K_M</td><td>2.89 GB</td><td>Great quality/size trade-off</td></tr>
256
+ <tr><td>GGUF Q4_K_M</td><td>2.5 GB</td><td>Smallest comfortable for laptops</td></tr>
257
+ </tbody>
258
+ </table>
259
+ <hr/>
260
+
261
+ ## Intended Use & Scope
262
+
263
+ - **Primary:** Generate complete, single-file websites (landing pages, marketing pages, simple docs) with **semantic HTML** and **Tailwind** classes.
264
+ - **Secondary:** Component blocks (hero, pricing, FAQ) for manual composition.
265
+
266
+ <details>
267
+ <summary><strong>Limitations</strong></summary>
268
+ <ul>
269
+ <li>Accessibility: adds headings/labels but ARIA coverage may need review.</li>
270
+ <li>JS widgets: kept light unless explicitly requested in prompt.</li>
271
+ </ul>
272
+ </details>
273
+
274
+ <details>
275
+ <summary><strong>Ethical Considerations</strong></summary>
276
+ <ul>
277
+ <li>Curate prompts appropriately.</li>
278
+ <li>When using third-party logos/assets, ensure you have rights or use open sources.</li>
279
+ </ul>
280
+ </details>
281
+
282
+ <hr/>
283
+
284
+ ## Training Summary (research preview)
285
+
286
+ - **Objective:** Tight web-only bias; reward semantic structure, spacing rhythm, and responsiveness.
287
+ - **Data:** Mixture of curated HTML/CSS/Tailwind snippets, component libraries, and synthetic page specs.
288
+ - **Recipe:** SFT with format constraints → instruction tuning → style/rhythm preference optimization.
289
+ - **Context:** effective ~64k; trained to keep default outputs within practical page length.
290
+
291
+
292
+ <hr/>
293
+
294
+ ## Example Outputs
295
+
296
+ ## Community
297
+
298
+ - **Examples:** <a href="https://uigenoutput.tesslate.com">uigenoutput.tesslate.com</a>
299
+ - **Discord:** <a href="https://discord.gg/EcCpcTv93U">discord.gg/EcCpcTv93U</a>
300
+ - **Website:** <a href="https://tesslate.com">tesslate.com</a>
301
+
302
+ <blockquote>
303
+ “Why are good design models so expensive” — Tesslate Team
304
+ </blockquote>
305
+
306
+ <hr/>
307
+
308
+ ## Citation
309
+
310
+ ```
311
+ @misc{tesslate_webgen_oss_preview_2025,
312
+ title = {WEBGEN-OSS-20B: Design-first web generation},
313
+ author = {Tesslate Team},
314
+ year = {2025},
315
+ url = {https://huggingface.co/Tesslate/WEBGEN-OSS-20B}
316
+ }
317
+ ```
318
+
319
+ </div>
320
+
321
+ <!----
322
+
323
+ <div class="grid grid-3">
324
+ <div class="card"><img alt="Sample A" src="https://YOUR_CDN/out-a.png" style="width:100%;border-radius:10px;border:1px solid var(--border)"><p style="margin-top:.5rem">Marketing page (product launch)</p></div>
325
+ <div class="card"><img alt="Sample B" src="https://YOUR_CDN/out-b.png" style="width:100%;border-radius:10px;border:1px solid var(--border)"><p style="margin-top:.5rem">SaaS pricing + FAQ</p></div>
326
+ <div class="card"><img alt="Sample C" src="https://YOUR_CDN/out-c.png" style="width:100%;border-radius:10px;border:1px solid var(--border)"><p style="margin-top:.5rem">Docs-style layout</p></div>
327
+ </div>
328
+
329
+ <hr/>
330
+ ---->
adapter_config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": {
4
+ "base_model_class": "GptOssForCausalLM",
5
+ "parent_library": "transformers.models.gpt_oss.modeling_gpt_oss"
6
+ },
7
+ "base_model_name_or_path": "unsloth/gpt-oss-20b-bf16",
8
+ "bias": "none",
9
+ "corda_config": null,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 128,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0,
22
+ "megatron_config": null,
23
+ "megatron_core": "megatron.core",
24
+ "modules_to_save": null,
25
+ "peft_type": "LORA",
26
+ "qalora_group_size": 16,
27
+ "r": 128,
28
+ "rank_pattern": {},
29
+ "revision": null,
30
+ "target_modules": [
31
+ "q_proj",
32
+ "gate_proj",
33
+ "down_proj",
34
+ "v_proj",
35
+ "k_proj",
36
+ "up_proj",
37
+ "o_proj"
38
+ ],
39
+ "target_parameters": null,
40
+ "task_type": null,
41
+ "trainable_token_indices": null,
42
+ "use_dora": false,
43
+ "use_qalora": false,
44
+ "use_rslora": false
45
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed261461bfac9fe9728cb8acd00ac5727b296c545898c847a5607705a734e007
3
+ size 254830208
cfg_old.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GptOssForCausalLM"
4
+ ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 200002,
9
+ "experts_per_token": 4,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2880,
13
+ "initial_context_length": 4096,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 2880,
16
+ "layer_types": [
17
+ "sliding_attention",
18
+ "full_attention",
19
+ "sliding_attention",
20
+ "full_attention",
21
+ "sliding_attention",
22
+ "full_attention",
23
+ "sliding_attention",
24
+ "full_attention",
25
+ "sliding_attention",
26
+ "full_attention",
27
+ "sliding_attention",
28
+ "full_attention",
29
+ "sliding_attention",
30
+ "full_attention",
31
+ "sliding_attention",
32
+ "full_attention",
33
+ "sliding_attention",
34
+ "full_attention",
35
+ "sliding_attention",
36
+ "full_attention",
37
+ "sliding_attention",
38
+ "full_attention",
39
+ "sliding_attention",
40
+ "full_attention"
41
+ ],
42
+ "max_position_embeddings": 131072,
43
+ "model_type": "gpt_oss",
44
+ "num_attention_heads": 64,
45
+ "num_experts_per_tok": 4,
46
+ "num_hidden_layers": 24,
47
+ "num_key_value_heads": 8,
48
+ "num_local_experts": 32,
49
+ "output_router_logits": false,
50
+ "pad_token_id": 199999,
51
+ "rms_norm_eps": 1e-05,
52
+ "rope_scaling": {
53
+ "beta_fast": 32.0,
54
+ "beta_slow": 1.0,
55
+ "factor": 32.0,
56
+ "original_max_position_embeddings": 4096,
57
+ "rope_type": "yarn",
58
+ "truncate": false
59
+ },
60
+ "rope_theta": 150000,
61
+ "router_aux_loss_coef": 0.9,
62
+ "sliding_window": 128,
63
+ "swiglu_limit": 7.0,
64
+ "tie_word_embeddings": false,
65
+ "transformers_version": "4.56.0",
66
+ "unsloth_version": "2025.9.4",
67
+ "use_cache": true,
68
+ "vocab_size": 201088
69
+ }
chat_template.jinja ADDED
@@ -0,0 +1,315 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {# Copyright 2025-present Unsloth. Apache 2.0 License. Unsloth chat template fixes. Edited from ggml-org & OpenAI #}
2
+ {#-
3
+ In addition to the normal inputs of `messages` and `tools`, this template also accepts the
4
+ following kwargs:
5
+ - "builtin_tools": A list, can contain "browser" and/or "python".
6
+ - "model_identity": A string that optionally describes the model identity.
7
+ - "reasoning_effort": A string that describes the reasoning effort, defaults to "medium".
8
+ #}
9
+
10
+ {#- Tool Definition Rendering ============================================== #}
11
+ {%- macro render_typescript_type(param_spec, required_params, is_nullable=false) -%}
12
+ {%- if param_spec.type == "array" -%}
13
+ {%- if param_spec['items'] -%}
14
+ {%- if param_spec['items']['type'] == "string" -%}
15
+ {{- "string[]" }}
16
+ {%- elif param_spec['items']['type'] == "number" -%}
17
+ {{- "number[]" }}
18
+ {%- elif param_spec['items']['type'] == "integer" -%}
19
+ {{- "number[]" }}
20
+ {%- elif param_spec['items']['type'] == "boolean" -%}
21
+ {{- "boolean[]" }}
22
+ {%- else -%}
23
+ {%- set inner_type = render_typescript_type(param_spec['items'], required_params) -%}
24
+ {%- if inner_type == "object | object" or inner_type|length > 50 -%}
25
+ {{- "any[]" }}
26
+ {%- else -%}
27
+ {{- inner_type + "[]" }}
28
+ {%- endif -%}
29
+ {%- endif -%}
30
+ {%- if param_spec.nullable -%}
31
+ {{- " | null" }}
32
+ {%- endif -%}
33
+ {%- else -%}
34
+ {{- "any[]" }}
35
+ {%- if param_spec.nullable -%}
36
+ {{- " | null" }}
37
+ {%- endif -%}
38
+ {%- endif -%}
39
+ {%- elif param_spec.type is defined and param_spec.type is iterable and param_spec.type is not string and param_spec.type is not mapping and param_spec.type[0] is defined -%}
40
+ {#- Handle array of types like ["object", "object"] from Union[dict, list] #}
41
+ {%- if param_spec.type | length > 1 -%}
42
+ {{- param_spec.type | join(" | ") }}
43
+ {%- else -%}
44
+ {{- param_spec.type[0] }}
45
+ {%- endif -%}
46
+ {%- elif param_spec.oneOf -%}
47
+ {#- Handle oneOf schemas - check for complex unions and fallback to any #}
48
+ {%- set has_object_variants = false -%}
49
+ {%- for variant in param_spec.oneOf -%}
50
+ {%- if variant.type == "object" -%}
51
+ {%- set has_object_variants = true -%}
52
+ {%- endif -%}
53
+ {%- endfor -%}
54
+ {%- if has_object_variants and param_spec.oneOf|length > 1 -%}
55
+ {{- "any" }}
56
+ {%- else -%}
57
+ {%- for variant in param_spec.oneOf -%}
58
+ {{- render_typescript_type(variant, required_params) -}}
59
+ {%- if variant.description %}
60
+ {{- "// " + variant.description }}
61
+ {%- endif -%}
62
+ {%- if variant.default is defined %}
63
+ {{ "// default: " + variant.default|tojson }}
64
+ {%- endif -%}
65
+ {%- if not loop.last %}
66
+ {{- " | " }}
67
+ {% endif -%}
68
+ {%- endfor -%}
69
+ {%- endif -%}
70
+ {%- elif param_spec.type == "string" -%}
71
+ {%- if param_spec.enum -%}
72
+ {{- '"' + param_spec.enum|join('" | "') + '"' -}}
73
+ {%- else -%}
74
+ {{- "string" }}
75
+ {%- if param_spec.nullable %}
76
+ {{- " | null" }}
77
+ {%- endif -%}
78
+ {%- endif -%}
79
+ {%- elif param_spec.type == "number" -%}
80
+ {{- "number" }}
81
+ {%- elif param_spec.type == "integer" -%}
82
+ {{- "number" }}
83
+ {%- elif param_spec.type == "boolean" -%}
84
+ {{- "boolean" }}
85
+
86
+ {%- elif param_spec.type == "object" -%}
87
+ {%- if param_spec.properties -%}
88
+ {{- "{\n" }}
89
+ {%- for prop_name, prop_spec in param_spec.properties.items() -%}
90
+ {{- prop_name -}}
91
+ {%- if prop_name not in (param_spec.required or []) -%}
92
+ {{- "?" }}
93
+ {%- endif -%}
94
+ {{- ": " }}
95
+ {{ render_typescript_type(prop_spec, param_spec.required or []) }}
96
+ {%- if not loop.last -%}
97
+ {{-", " }}
98
+ {%- endif -%}
99
+ {%- endfor -%}
100
+ {{- "}" }}
101
+ {%- else -%}
102
+ {{- "object" }}
103
+ {%- endif -%}
104
+ {%- else -%}
105
+ {{- "any" }}
106
+ {%- endif -%}
107
+ {%- endmacro -%}
108
+
109
+ {%- macro render_tool_namespace(namespace_name, tools) -%}
110
+ {{- "## " + namespace_name + "\n\n" }}
111
+ {{- "namespace " + namespace_name + " {\n\n" }}
112
+ {%- for tool in tools %}
113
+ {%- set tool = tool.function %}
114
+ {{- "// " + tool.description + "\n" }}
115
+ {{- "type "+ tool.name + " = " }}
116
+ {%- if tool.parameters and tool.parameters.properties -%}
117
+ {{- "(_: " }}
118
+ {{- "{\n" }}
119
+ {%- for param_name, param_spec in tool.parameters.properties.items() %}
120
+ {{- "// " + param_spec.description + "\n" }}
121
+ {{- param_name }}
122
+ {%- if param_name not in (tool.parameters.required or []) -%}
123
+ {{- "?" }}
124
+ {%- endif -%}
125
+ {{- ": " }}
126
+ {{- render_typescript_type(param_spec, tool.parameters.required or []) }}
127
+ {%- if param_spec.default is defined -%}
128
+ {%- if param_spec.enum %}
129
+ {{- ", // default: " + param_spec.default }}
130
+ {%- elif param_spec.oneOf %}
131
+ {{- "// default: " + param_spec.default }}
132
+ {%- else %}
133
+ {{- ", // default: " + param_spec.default|tojson }}
134
+ {%- endif -%}
135
+ {%- endif -%}
136
+ {%- if not loop.last %}
137
+ {{- ",\n" }}
138
+ {%- else %}
139
+ {{- "\n" }}
140
+ {%- endif -%}
141
+ {%- endfor %}
142
+ {{- "}) => any;\n\n" }}
143
+ {%- else -%}
144
+ {{- "() => any;\n\n" }}
145
+ {%- endif -%}
146
+ {%- endfor %}
147
+ {{- "} // namespace " + namespace_name }}
148
+ {%- endmacro -%}
149
+
150
+ {%- macro render_builtin_tools(browser_tool, python_tool) -%}
151
+ {%- if browser_tool %}
152
+ {{- "## browser\n\n" }}
153
+ {{- "// Tool for browsing.\n" }}
154
+ {{- "// The `cursor` appears in brackets before each browsing display: `[{cursor}]`.\n" }}
155
+ {{- "// Cite information from the tool using the following format:\n" }}
156
+ {{- "// `【{cursor}†L{line_start}(-L{line_end})?】`, for example: `【6†L9-L11】` or `【8†L3】`.\n" }}
157
+ {{- "// Do not quote more than 10 words directly from the tool output.\n" }}
158
+ {{- "// sources=web (default: web)\n" }}
159
+ {{- "namespace browser {\n\n" }}
160
+ {{- "// Searches for information related to `query` and displays `topn` results.\n" }}
161
+ {{- "type search = (_: {\n" }}
162
+ {{- "query: string,\n" }}
163
+ {{- "topn?: number, // default: 10\n" }}
164
+ {{- "source?: string,\n" }}
165
+ {{- "}) => any;\n\n" }}
166
+ {{- "// Opens the link `id` from the page indicated by `cursor` starting at line number `loc`, showing `num_lines` lines.\n" }}
167
+ {{- "// Valid link ids are displayed with the formatting: `【{id}†.*】`.\n" }}
168
+ {{- "// If `cursor` is not provided, the most recent page is implied.\n" }}
169
+ {{- "// If `id` is a string, it is treated as a fully qualified URL associated with `source`.\n" }}
170
+ {{- "// If `loc` is not provided, the viewport will be positioned at the beginning of the document or centered on the most relevant passage, if available.\n" }}
171
+ {{- "// Use this function without `id` to scroll to a new location of an opened page.\n" }}
172
+ {{- "type open = (_: {\n" }}
173
+ {{- "id?: number | string, // default: -1\n" }}
174
+ {{- "cursor?: number, // default: -1\n" }}
175
+ {{- "loc?: number, // default: -1\n" }}
176
+ {{- "num_lines?: number, // default: -1\n" }}
177
+ {{- "view_source?: boolean, // default: false\n" }}
178
+ {{- "source?: string,\n" }}
179
+ {{- "}) => any;\n\n" }}
180
+ {{- "// Finds exact matches of `pattern` in the current page, or the page given by `cursor`.\n" }}
181
+ {{- "type find = (_: {\n" }}
182
+ {{- "pattern: string,\n" }}
183
+ {{- "cursor?: number, // default: -1\n" }}
184
+ {{- "}) => any;\n\n" }}
185
+ {{- "} // namespace browser\n\n" }}
186
+ {%- endif -%}
187
+
188
+ {%- if python_tool %}
189
+ {{- "## python\n\n" }}
190
+ {{- "Use this tool to execute Python code in your chain of thought. The code will not be shown to the user. This tool should be used for internal reasoning, but not for code that is intended to be visible to the user (e.g. when creating plots, tables, or files).\n\n" }}
191
+ {{- "When you send a message containing Python code to python, it will be executed in a stateful Jupyter notebook environment. python will respond with the output of the execution or time out after 120.0 seconds. The drive at '/mnt/data' can be used to save and persist user files. Internet access for this session is UNKNOWN. Depends on the cluster.\n\n" }}
192
+ {%- endif -%}
193
+ {%- endmacro -%}
194
+
195
+ {#- System Message Construction ============================================ #}
196
+ {%- macro build_system_message() -%}
197
+ {%- if model_identity is not defined %}
198
+ {{- "You are ChatGPT, a large language model trained by OpenAI.\n" -}}
199
+ {%- else %}
200
+ {{- model_identity }}
201
+ {%- endif %}
202
+ {{- "Knowledge cutoff: 2024-06\n" }}
203
+ {{- "Current date: " + strftime_now("%Y-%m-%d") + "\n\n" }}
204
+ {%- if reasoning_effort is not defined %}
205
+ {%- set reasoning_effort = "medium" %}
206
+ {%- endif %}
207
+ {{- "Reasoning: " + reasoning_effort + "\n\n" }}
208
+ {%- if builtin_tools is defined %}
209
+ {{- "# Tools\n\n" }}
210
+ {%- set available_builtin_tools = namespace(browser=false, python=false) %}
211
+ {%- for tool in builtin_tools %}
212
+ {%- if tool == "browser" %}
213
+ {%- set available_builtin_tools.browser = true %}
214
+ {%- elif tool == "python" %}
215
+ {%- set available_builtin_tools.python = true %}
216
+ {%- endif %}
217
+ {%- endfor %}
218
+ {{- render_builtin_tools(available_builtin_tools.browser, available_builtin_tools.python) }}
219
+ {%- endif -%}
220
+ {{- "# Valid channels: analysis, commentary, final. Channel must be included for every message." }}
221
+ {%- if tools is defined -%}
222
+ {{- "\nCalls to these tools must go to the commentary channel: 'functions'." }}
223
+ {%- endif -%}
224
+ {%- endmacro -%}
225
+
226
+ {#- Main Template Logic ================================================= #}
227
+ {#- Set defaults #}
228
+
229
+ {#- Render system message #}
230
+ {{- "<|start|>system<|message|>" }}
231
+ {{- build_system_message() }}
232
+ {{- "<|end|>" }}
233
+
234
+ {#- Extract developer message #}
235
+ {%- if messages[0].role == "developer" or messages[0].role == "system" %}
236
+ {%- set developer_message = messages[0].content %}
237
+ {%- set loop_messages = messages[1:] %}
238
+ {%- else %}
239
+ {%- set developer_message = "" %}
240
+ {%- set loop_messages = messages %}
241
+ {%- endif %}
242
+
243
+ {#- Render developer message #}
244
+ {%- if developer_message or tools %}
245
+ {{- "<|start|>developer<|message|>" }}
246
+ {%- if developer_message %}
247
+ {{- "# Instructions\n\n" }}
248
+ {{- developer_message }}
249
+ {%- endif %}
250
+ {%- if tools -%}
251
+ {{- "\n\n" }}
252
+ {{- "# Tools\n\n" }}
253
+ {{- render_tool_namespace("functions", tools) }}
254
+ {%- endif -%}
255
+ {{- "<|end|>" }}
256
+ {%- endif %}
257
+
258
+ {#- Render messages #}
259
+ {%- set last_tool_call = namespace(name=none) %}
260
+ {%- for message in loop_messages -%}
261
+ {#- At this point only assistant/user/tool messages should remain #}
262
+ {%- if message.role == 'assistant' -%}
263
+ {%- if "tool_calls" in message %}
264
+ {#- We assume max 1 tool call per message, and so we infer the tool call name #}
265
+ {#- in "tool" messages from the most recent assistant tool call name #}
266
+ {%- set tool_call = message.tool_calls[0] %}
267
+ {%- if tool_call.function %}
268
+ {%- set tool_call = tool_call.function %}
269
+ {%- endif %}
270
+ {%- if message.content %}
271
+ {{- "<|start|>assistant<|channel|>analysis<|message|>" + message.content + "<|end|>" }}
272
+ {%- endif %}
273
+ {{- "<|start|>assistant to=" }}
274
+ {{- "functions." + tool_call.name + "<|channel|>commentary json<|message|>" }}
275
+ {{- tool_call.arguments|tojson }}
276
+ {{- "<|call|>" }}
277
+ {%- set last_tool_call.name = tool_call.name %}
278
+ {%- elif "thinking" in message and loop.last and not add_generation_prompt %}
279
+ {#- Only render the CoT if the final turn is an assistant turn and add_generation_prompt is false #}
280
+ {#- This is a situation that should only occur in training, never in inference. #}
281
+ {{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
282
+ {#- <|return|> indicates the end of generation, but <|end|> does not #}
283
+ {#- <|return|> should never be an input to the model, but we include it as the final token #}
284
+ {#- when training, so the model learns to emit it. #}
285
+ {{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|return|>" }}
286
+ {%- set last_tool_call.name = none %}
287
+ {%- elif "thinking" in message %}
288
+ {#- CoT is dropped during all previous turns, so we never render it for inference #}
289
+ {{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|end|>" }}
290
+ {%- set last_tool_call.name = none %}
291
+ {%- elif loop.last and not add_generation_prompt %}
292
+ {#- <|return|> indicates the end of generation, but <|end|> does not #}
293
+ {#- <|return|> should never be an input to the model, but we include it as the final token #}
294
+ {#- when training, so the model learns to emit it. #}
295
+ {{- "<|start|>assistant<|message|>" + message.content + "<|return|>" }}
296
+ {%- else %}
297
+ {{- "<|start|>assistant<|message|>" + message.content + "<|end|>" }}
298
+ {%- set last_tool_call.name = none %}
299
+ {%- endif %}
300
+ {%- elif message.role == 'tool' -%}
301
+ {%- if last_tool_call.name is none %}
302
+ {{- raise_exception("Message has tool role, but there was no previous assistant message with a tool call!") }}
303
+ {%- endif %}
304
+ {{- "<|start|>functions." + last_tool_call.name }}
305
+ {{- " to=assistant<|channel|>commentary<|message|>" + message.content|tojson + "<|end|>" }}
306
+ {%- else -%}
307
+ {{- "<|start|>user<|message|>" + message.content + "<|end|>" }}
308
+ {%- endif -%}
309
+ {%- endfor -%}
310
+
311
+ {#- Generation prompt #}
312
+ {%- if add_generation_prompt -%}
313
+ <|start|>assistant
314
+ {%- endif -%}
315
+ {# Copyright 2025-present Unsloth. Apache 2.0 License. Unsloth chat template fixes. Edited from ggml-org & OpenAI #}
config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GptOssForCausalLM"
4
+ ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 200002,
9
+ "experts_per_token": 4,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2880,
13
+ "initial_context_length": 4096,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 2880,
16
+ "layer_types": [
17
+ "sliding_attention",
18
+ "full_attention",
19
+ "sliding_attention",
20
+ "full_attention",
21
+ "sliding_attention",
22
+ "full_attention",
23
+ "sliding_attention",
24
+ "full_attention",
25
+ "sliding_attention",
26
+ "full_attention",
27
+ "sliding_attention",
28
+ "full_attention",
29
+ "sliding_attention",
30
+ "full_attention",
31
+ "sliding_attention",
32
+ "full_attention",
33
+ "sliding_attention",
34
+ "full_attention",
35
+ "sliding_attention",
36
+ "full_attention",
37
+ "sliding_attention",
38
+ "full_attention",
39
+ "sliding_attention",
40
+ "full_attention"
41
+ ],
42
+ "max_position_embeddings": 131072,
43
+ "model_type": "gpt_oss",
44
+ "num_attention_heads": 64,
45
+ "num_experts_per_tok": 4,
46
+ "num_hidden_layers": 24,
47
+ "num_key_value_heads": 8,
48
+ "num_local_experts": 32,
49
+ "output_router_logits": false,
50
+ "pad_token_id": 199999,
51
+ "rms_norm_eps": 1e-05,
52
+ "rope_scaling": {
53
+ "beta_fast": 32.0,
54
+ "beta_slow": 1.0,
55
+ "factor": 32.0,
56
+ "original_max_position_embeddings": 4096,
57
+ "rope_type": "yarn",
58
+ "truncate": false
59
+ },
60
+ "rope_theta": 150000,
61
+ "router_aux_loss_coef": 0.9,
62
+ "sliding_window": 128,
63
+ "swiglu_limit": 7.0,
64
+ "tie_word_embeddings": false,
65
+ "transformers_version": "4.56.0",
66
+ "unsloth_version": "2025.9.4",
67
+ "use_cache": true,
68
+ "vocab_size": 201088
69
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 199998,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 200002,
6
+ 199999
7
+ ],
8
+ "max_length": 131072,
9
+ "pad_token_id": 199999,
10
+ "transformers_version": "4.56.0"
11
+ }
model-00001-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e02df73242ff01c499641e25faf737a3e65e9a82179aee2746f0b89bb787c356
3
+ size 4504304664
model-00002-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42c32028fb4df2f9621962b0508efcd6729770878492cd13ed9a06e6975ec968
3
+ size 4939127656
model-00003-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7c97af51a1c2644a7de2b18eeebfb054df90f1acb35d8ebcf21437357384dde
3
+ size 4939127656
model-00004-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14a3a2763785ad73b961437484d8297857e26529257a1cbb42b78960fe064a5d
3
+ size 4939127680
model-00005-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:890952b10d905b539f1defc6b72d82227c4cd0b8846251b23b8a4de764af395b
3
+ size 4939127704
model-00006-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6841360c2b8e7631e3faf23830f6ea9c85ec97f79ab8774535c355b4cee045b0
3
+ size 4939127704
model-00007-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db6c4c799d0fd9c5359cd0257658793e912229ee5fdbbe43d6694fc479deef0f
3
+ size 4939127704
model-00008-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7267c7711e86656acc0b39dd1e4529ef57c24629d284ff9fd6c0e452611fa268
3
+ size 4939127704
model-00009-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c1951ff65d233bcb7f50485d294cced6497b8e0d9707f57087912fc2352492e
3
+ size 2751362856
model.safetensors.index.json ADDED
@@ -0,0 +1,419 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 20914757184,
4
+ "total_size": 41829514368
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00009-of-00009.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00009.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
10
+ "model.layers.0.mlp.experts.down_proj": "model-00001-of-00009.safetensors",
11
+ "model.layers.0.mlp.experts.down_proj_bias": "model-00001-of-00009.safetensors",
12
+ "model.layers.0.mlp.experts.gate_up_proj": "model-00001-of-00009.safetensors",
13
+ "model.layers.0.mlp.experts.gate_up_proj_bias": "model-00001-of-00009.safetensors",
14
+ "model.layers.0.mlp.router.bias": "model-00001-of-00009.safetensors",
15
+ "model.layers.0.mlp.router.weight": "model-00001-of-00009.safetensors",
16
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
17
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00009.safetensors",
18
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
19
+ "model.layers.0.self_attn.o_proj.bias": "model-00001-of-00009.safetensors",
20
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
21
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00009.safetensors",
22
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
23
+ "model.layers.0.self_attn.sinks": "model-00001-of-00009.safetensors",
24
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00009.safetensors",
25
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
26
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors",
27
+ "model.layers.1.mlp.experts.down_proj": "model-00001-of-00009.safetensors",
28
+ "model.layers.1.mlp.experts.down_proj_bias": "model-00001-of-00009.safetensors",
29
+ "model.layers.1.mlp.experts.gate_up_proj": "model-00001-of-00009.safetensors",
30
+ "model.layers.1.mlp.experts.gate_up_proj_bias": "model-00001-of-00009.safetensors",
31
+ "model.layers.1.mlp.router.bias": "model-00001-of-00009.safetensors",
32
+ "model.layers.1.mlp.router.weight": "model-00001-of-00009.safetensors",
33
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
34
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00009.safetensors",
35
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
36
+ "model.layers.1.self_attn.o_proj.bias": "model-00001-of-00009.safetensors",
37
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
38
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00009.safetensors",
39
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
40
+ "model.layers.1.self_attn.sinks": "model-00001-of-00009.safetensors",
41
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00009.safetensors",
42
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
43
+ "model.layers.10.input_layernorm.weight": "model-00004-of-00009.safetensors",
44
+ "model.layers.10.mlp.experts.down_proj": "model-00004-of-00009.safetensors",
45
+ "model.layers.10.mlp.experts.down_proj_bias": "model-00004-of-00009.safetensors",
46
+ "model.layers.10.mlp.experts.gate_up_proj": "model-00004-of-00009.safetensors",
47
+ "model.layers.10.mlp.experts.gate_up_proj_bias": "model-00004-of-00009.safetensors",
48
+ "model.layers.10.mlp.router.bias": "model-00004-of-00009.safetensors",
49
+ "model.layers.10.mlp.router.weight": "model-00004-of-00009.safetensors",
50
+ "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
51
+ "model.layers.10.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
52
+ "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
53
+ "model.layers.10.self_attn.o_proj.bias": "model-00004-of-00009.safetensors",
54
+ "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
55
+ "model.layers.10.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
56
+ "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
57
+ "model.layers.10.self_attn.sinks": "model-00004-of-00009.safetensors",
58
+ "model.layers.10.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
59
+ "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
60
+ "model.layers.11.input_layernorm.weight": "model-00005-of-00009.safetensors",
61
+ "model.layers.11.mlp.experts.down_proj": "model-00005-of-00009.safetensors",
62
+ "model.layers.11.mlp.experts.down_proj_bias": "model-00005-of-00009.safetensors",
63
+ "model.layers.11.mlp.experts.gate_up_proj": "model-00005-of-00009.safetensors",
64
+ "model.layers.11.mlp.experts.gate_up_proj_bias": "model-00005-of-00009.safetensors",
65
+ "model.layers.11.mlp.router.bias": "model-00004-of-00009.safetensors",
66
+ "model.layers.11.mlp.router.weight": "model-00004-of-00009.safetensors",
67
+ "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
68
+ "model.layers.11.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
69
+ "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
70
+ "model.layers.11.self_attn.o_proj.bias": "model-00004-of-00009.safetensors",
71
+ "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
72
+ "model.layers.11.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
73
+ "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
74
+ "model.layers.11.self_attn.sinks": "model-00004-of-00009.safetensors",
75
+ "model.layers.11.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
76
+ "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
77
+ "model.layers.12.input_layernorm.weight": "model-00005-of-00009.safetensors",
78
+ "model.layers.12.mlp.experts.down_proj": "model-00005-of-00009.safetensors",
79
+ "model.layers.12.mlp.experts.down_proj_bias": "model-00005-of-00009.safetensors",
80
+ "model.layers.12.mlp.experts.gate_up_proj": "model-00005-of-00009.safetensors",
81
+ "model.layers.12.mlp.experts.gate_up_proj_bias": "model-00005-of-00009.safetensors",
82
+ "model.layers.12.mlp.router.bias": "model-00005-of-00009.safetensors",
83
+ "model.layers.12.mlp.router.weight": "model-00005-of-00009.safetensors",
84
+ "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
85
+ "model.layers.12.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
86
+ "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
87
+ "model.layers.12.self_attn.o_proj.bias": "model-00005-of-00009.safetensors",
88
+ "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
89
+ "model.layers.12.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
90
+ "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
91
+ "model.layers.12.self_attn.sinks": "model-00005-of-00009.safetensors",
92
+ "model.layers.12.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
93
+ "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
94
+ "model.layers.13.input_layernorm.weight": "model-00005-of-00009.safetensors",
95
+ "model.layers.13.mlp.experts.down_proj": "model-00005-of-00009.safetensors",
96
+ "model.layers.13.mlp.experts.down_proj_bias": "model-00005-of-00009.safetensors",
97
+ "model.layers.13.mlp.experts.gate_up_proj": "model-00005-of-00009.safetensors",
98
+ "model.layers.13.mlp.experts.gate_up_proj_bias": "model-00005-of-00009.safetensors",
99
+ "model.layers.13.mlp.router.bias": "model-00005-of-00009.safetensors",
100
+ "model.layers.13.mlp.router.weight": "model-00005-of-00009.safetensors",
101
+ "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
102
+ "model.layers.13.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
103
+ "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
104
+ "model.layers.13.self_attn.o_proj.bias": "model-00005-of-00009.safetensors",
105
+ "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
106
+ "model.layers.13.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
107
+ "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
108
+ "model.layers.13.self_attn.sinks": "model-00005-of-00009.safetensors",
109
+ "model.layers.13.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
110
+ "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
111
+ "model.layers.14.input_layernorm.weight": "model-00006-of-00009.safetensors",
112
+ "model.layers.14.mlp.experts.down_proj": "model-00006-of-00009.safetensors",
113
+ "model.layers.14.mlp.experts.down_proj_bias": "model-00006-of-00009.safetensors",
114
+ "model.layers.14.mlp.experts.gate_up_proj": "model-00006-of-00009.safetensors",
115
+ "model.layers.14.mlp.experts.gate_up_proj_bias": "model-00006-of-00009.safetensors",
116
+ "model.layers.14.mlp.router.bias": "model-00005-of-00009.safetensors",
117
+ "model.layers.14.mlp.router.weight": "model-00005-of-00009.safetensors",
118
+ "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
119
+ "model.layers.14.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
120
+ "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
121
+ "model.layers.14.self_attn.o_proj.bias": "model-00005-of-00009.safetensors",
122
+ "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
123
+ "model.layers.14.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
124
+ "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
125
+ "model.layers.14.self_attn.sinks": "model-00005-of-00009.safetensors",
126
+ "model.layers.14.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
127
+ "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
128
+ "model.layers.15.input_layernorm.weight": "model-00006-of-00009.safetensors",
129
+ "model.layers.15.mlp.experts.down_proj": "model-00006-of-00009.safetensors",
130
+ "model.layers.15.mlp.experts.down_proj_bias": "model-00006-of-00009.safetensors",
131
+ "model.layers.15.mlp.experts.gate_up_proj": "model-00006-of-00009.safetensors",
132
+ "model.layers.15.mlp.experts.gate_up_proj_bias": "model-00006-of-00009.safetensors",
133
+ "model.layers.15.mlp.router.bias": "model-00006-of-00009.safetensors",
134
+ "model.layers.15.mlp.router.weight": "model-00006-of-00009.safetensors",
135
+ "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
136
+ "model.layers.15.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
137
+ "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
138
+ "model.layers.15.self_attn.o_proj.bias": "model-00006-of-00009.safetensors",
139
+ "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
140
+ "model.layers.15.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
141
+ "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
142
+ "model.layers.15.self_attn.sinks": "model-00006-of-00009.safetensors",
143
+ "model.layers.15.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
144
+ "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
145
+ "model.layers.16.input_layernorm.weight": "model-00006-of-00009.safetensors",
146
+ "model.layers.16.mlp.experts.down_proj": "model-00006-of-00009.safetensors",
147
+ "model.layers.16.mlp.experts.down_proj_bias": "model-00006-of-00009.safetensors",
148
+ "model.layers.16.mlp.experts.gate_up_proj": "model-00006-of-00009.safetensors",
149
+ "model.layers.16.mlp.experts.gate_up_proj_bias": "model-00006-of-00009.safetensors",
150
+ "model.layers.16.mlp.router.bias": "model-00006-of-00009.safetensors",
151
+ "model.layers.16.mlp.router.weight": "model-00006-of-00009.safetensors",
152
+ "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
153
+ "model.layers.16.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
154
+ "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
155
+ "model.layers.16.self_attn.o_proj.bias": "model-00006-of-00009.safetensors",
156
+ "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
157
+ "model.layers.16.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
158
+ "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
159
+ "model.layers.16.self_attn.sinks": "model-00006-of-00009.safetensors",
160
+ "model.layers.16.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
161
+ "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
162
+ "model.layers.17.input_layernorm.weight": "model-00007-of-00009.safetensors",
163
+ "model.layers.17.mlp.experts.down_proj": "model-00007-of-00009.safetensors",
164
+ "model.layers.17.mlp.experts.down_proj_bias": "model-00007-of-00009.safetensors",
165
+ "model.layers.17.mlp.experts.gate_up_proj": "model-00007-of-00009.safetensors",
166
+ "model.layers.17.mlp.experts.gate_up_proj_bias": "model-00007-of-00009.safetensors",
167
+ "model.layers.17.mlp.router.bias": "model-00006-of-00009.safetensors",
168
+ "model.layers.17.mlp.router.weight": "model-00006-of-00009.safetensors",
169
+ "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
170
+ "model.layers.17.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
171
+ "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
172
+ "model.layers.17.self_attn.o_proj.bias": "model-00006-of-00009.safetensors",
173
+ "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
174
+ "model.layers.17.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
175
+ "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
176
+ "model.layers.17.self_attn.sinks": "model-00006-of-00009.safetensors",
177
+ "model.layers.17.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
178
+ "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
179
+ "model.layers.18.input_layernorm.weight": "model-00007-of-00009.safetensors",
180
+ "model.layers.18.mlp.experts.down_proj": "model-00007-of-00009.safetensors",
181
+ "model.layers.18.mlp.experts.down_proj_bias": "model-00007-of-00009.safetensors",
182
+ "model.layers.18.mlp.experts.gate_up_proj": "model-00007-of-00009.safetensors",
183
+ "model.layers.18.mlp.experts.gate_up_proj_bias": "model-00007-of-00009.safetensors",
184
+ "model.layers.18.mlp.router.bias": "model-00007-of-00009.safetensors",
185
+ "model.layers.18.mlp.router.weight": "model-00007-of-00009.safetensors",
186
+ "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
187
+ "model.layers.18.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
188
+ "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
189
+ "model.layers.18.self_attn.o_proj.bias": "model-00007-of-00009.safetensors",
190
+ "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
191
+ "model.layers.18.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
192
+ "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
193
+ "model.layers.18.self_attn.sinks": "model-00007-of-00009.safetensors",
194
+ "model.layers.18.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
195
+ "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
196
+ "model.layers.19.input_layernorm.weight": "model-00007-of-00009.safetensors",
197
+ "model.layers.19.mlp.experts.down_proj": "model-00007-of-00009.safetensors",
198
+ "model.layers.19.mlp.experts.down_proj_bias": "model-00007-of-00009.safetensors",
199
+ "model.layers.19.mlp.experts.gate_up_proj": "model-00007-of-00009.safetensors",
200
+ "model.layers.19.mlp.experts.gate_up_proj_bias": "model-00007-of-00009.safetensors",
201
+ "model.layers.19.mlp.router.bias": "model-00007-of-00009.safetensors",
202
+ "model.layers.19.mlp.router.weight": "model-00007-of-00009.safetensors",
203
+ "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
204
+ "model.layers.19.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
205
+ "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
206
+ "model.layers.19.self_attn.o_proj.bias": "model-00007-of-00009.safetensors",
207
+ "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
208
+ "model.layers.19.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
209
+ "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
210
+ "model.layers.19.self_attn.sinks": "model-00007-of-00009.safetensors",
211
+ "model.layers.19.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
212
+ "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
213
+ "model.layers.2.input_layernorm.weight": "model-00002-of-00009.safetensors",
214
+ "model.layers.2.mlp.experts.down_proj": "model-00002-of-00009.safetensors",
215
+ "model.layers.2.mlp.experts.down_proj_bias": "model-00002-of-00009.safetensors",
216
+ "model.layers.2.mlp.experts.gate_up_proj": "model-00002-of-00009.safetensors",
217
+ "model.layers.2.mlp.experts.gate_up_proj_bias": "model-00002-of-00009.safetensors",
218
+ "model.layers.2.mlp.router.bias": "model-00001-of-00009.safetensors",
219
+ "model.layers.2.mlp.router.weight": "model-00001-of-00009.safetensors",
220
+ "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
221
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00009.safetensors",
222
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
223
+ "model.layers.2.self_attn.o_proj.bias": "model-00001-of-00009.safetensors",
224
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
225
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00009.safetensors",
226
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
227
+ "model.layers.2.self_attn.sinks": "model-00001-of-00009.safetensors",
228
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00009.safetensors",
229
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
230
+ "model.layers.20.input_layernorm.weight": "model-00008-of-00009.safetensors",
231
+ "model.layers.20.mlp.experts.down_proj": "model-00008-of-00009.safetensors",
232
+ "model.layers.20.mlp.experts.down_proj_bias": "model-00008-of-00009.safetensors",
233
+ "model.layers.20.mlp.experts.gate_up_proj": "model-00008-of-00009.safetensors",
234
+ "model.layers.20.mlp.experts.gate_up_proj_bias": "model-00008-of-00009.safetensors",
235
+ "model.layers.20.mlp.router.bias": "model-00007-of-00009.safetensors",
236
+ "model.layers.20.mlp.router.weight": "model-00007-of-00009.safetensors",
237
+ "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
238
+ "model.layers.20.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
239
+ "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
240
+ "model.layers.20.self_attn.o_proj.bias": "model-00007-of-00009.safetensors",
241
+ "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
242
+ "model.layers.20.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
243
+ "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
244
+ "model.layers.20.self_attn.sinks": "model-00007-of-00009.safetensors",
245
+ "model.layers.20.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
246
+ "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
247
+ "model.layers.21.input_layernorm.weight": "model-00008-of-00009.safetensors",
248
+ "model.layers.21.mlp.experts.down_proj": "model-00008-of-00009.safetensors",
249
+ "model.layers.21.mlp.experts.down_proj_bias": "model-00008-of-00009.safetensors",
250
+ "model.layers.21.mlp.experts.gate_up_proj": "model-00008-of-00009.safetensors",
251
+ "model.layers.21.mlp.experts.gate_up_proj_bias": "model-00008-of-00009.safetensors",
252
+ "model.layers.21.mlp.router.bias": "model-00008-of-00009.safetensors",
253
+ "model.layers.21.mlp.router.weight": "model-00008-of-00009.safetensors",
254
+ "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
255
+ "model.layers.21.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
256
+ "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
257
+ "model.layers.21.self_attn.o_proj.bias": "model-00008-of-00009.safetensors",
258
+ "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
259
+ "model.layers.21.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
260
+ "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
261
+ "model.layers.21.self_attn.sinks": "model-00008-of-00009.safetensors",
262
+ "model.layers.21.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
263
+ "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
264
+ "model.layers.22.input_layernorm.weight": "model-00008-of-00009.safetensors",
265
+ "model.layers.22.mlp.experts.down_proj": "model-00008-of-00009.safetensors",
266
+ "model.layers.22.mlp.experts.down_proj_bias": "model-00008-of-00009.safetensors",
267
+ "model.layers.22.mlp.experts.gate_up_proj": "model-00008-of-00009.safetensors",
268
+ "model.layers.22.mlp.experts.gate_up_proj_bias": "model-00008-of-00009.safetensors",
269
+ "model.layers.22.mlp.router.bias": "model-00008-of-00009.safetensors",
270
+ "model.layers.22.mlp.router.weight": "model-00008-of-00009.safetensors",
271
+ "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
272
+ "model.layers.22.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
273
+ "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
274
+ "model.layers.22.self_attn.o_proj.bias": "model-00008-of-00009.safetensors",
275
+ "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
276
+ "model.layers.22.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
277
+ "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
278
+ "model.layers.22.self_attn.sinks": "model-00008-of-00009.safetensors",
279
+ "model.layers.22.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
280
+ "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
281
+ "model.layers.23.input_layernorm.weight": "model-00009-of-00009.safetensors",
282
+ "model.layers.23.mlp.experts.down_proj": "model-00009-of-00009.safetensors",
283
+ "model.layers.23.mlp.experts.down_proj_bias": "model-00009-of-00009.safetensors",
284
+ "model.layers.23.mlp.experts.gate_up_proj": "model-00009-of-00009.safetensors",
285
+ "model.layers.23.mlp.experts.gate_up_proj_bias": "model-00009-of-00009.safetensors",
286
+ "model.layers.23.mlp.router.bias": "model-00008-of-00009.safetensors",
287
+ "model.layers.23.mlp.router.weight": "model-00008-of-00009.safetensors",
288
+ "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
289
+ "model.layers.23.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
290
+ "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
291
+ "model.layers.23.self_attn.o_proj.bias": "model-00008-of-00009.safetensors",
292
+ "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
293
+ "model.layers.23.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
294
+ "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
295
+ "model.layers.23.self_attn.sinks": "model-00008-of-00009.safetensors",
296
+ "model.layers.23.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
297
+ "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
298
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00009.safetensors",
299
+ "model.layers.3.mlp.experts.down_proj": "model-00002-of-00009.safetensors",
300
+ "model.layers.3.mlp.experts.down_proj_bias": "model-00002-of-00009.safetensors",
301
+ "model.layers.3.mlp.experts.gate_up_proj": "model-00002-of-00009.safetensors",
302
+ "model.layers.3.mlp.experts.gate_up_proj_bias": "model-00002-of-00009.safetensors",
303
+ "model.layers.3.mlp.router.bias": "model-00002-of-00009.safetensors",
304
+ "model.layers.3.mlp.router.weight": "model-00002-of-00009.safetensors",
305
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
306
+ "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
307
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
308
+ "model.layers.3.self_attn.o_proj.bias": "model-00002-of-00009.safetensors",
309
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
310
+ "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
311
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
312
+ "model.layers.3.self_attn.sinks": "model-00002-of-00009.safetensors",
313
+ "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
314
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
315
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors",
316
+ "model.layers.4.mlp.experts.down_proj": "model-00002-of-00009.safetensors",
317
+ "model.layers.4.mlp.experts.down_proj_bias": "model-00002-of-00009.safetensors",
318
+ "model.layers.4.mlp.experts.gate_up_proj": "model-00002-of-00009.safetensors",
319
+ "model.layers.4.mlp.experts.gate_up_proj_bias": "model-00002-of-00009.safetensors",
320
+ "model.layers.4.mlp.router.bias": "model-00002-of-00009.safetensors",
321
+ "model.layers.4.mlp.router.weight": "model-00002-of-00009.safetensors",
322
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
323
+ "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
324
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
325
+ "model.layers.4.self_attn.o_proj.bias": "model-00002-of-00009.safetensors",
326
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
327
+ "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
328
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
329
+ "model.layers.4.self_attn.sinks": "model-00002-of-00009.safetensors",
330
+ "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
331
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
332
+ "model.layers.5.input_layernorm.weight": "model-00003-of-00009.safetensors",
333
+ "model.layers.5.mlp.experts.down_proj": "model-00003-of-00009.safetensors",
334
+ "model.layers.5.mlp.experts.down_proj_bias": "model-00003-of-00009.safetensors",
335
+ "model.layers.5.mlp.experts.gate_up_proj": "model-00003-of-00009.safetensors",
336
+ "model.layers.5.mlp.experts.gate_up_proj_bias": "model-00003-of-00009.safetensors",
337
+ "model.layers.5.mlp.router.bias": "model-00002-of-00009.safetensors",
338
+ "model.layers.5.mlp.router.weight": "model-00002-of-00009.safetensors",
339
+ "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
340
+ "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
341
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
342
+ "model.layers.5.self_attn.o_proj.bias": "model-00002-of-00009.safetensors",
343
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
344
+ "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
345
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
346
+ "model.layers.5.self_attn.sinks": "model-00002-of-00009.safetensors",
347
+ "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
348
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
349
+ "model.layers.6.input_layernorm.weight": "model-00003-of-00009.safetensors",
350
+ "model.layers.6.mlp.experts.down_proj": "model-00003-of-00009.safetensors",
351
+ "model.layers.6.mlp.experts.down_proj_bias": "model-00003-of-00009.safetensors",
352
+ "model.layers.6.mlp.experts.gate_up_proj": "model-00003-of-00009.safetensors",
353
+ "model.layers.6.mlp.experts.gate_up_proj_bias": "model-00003-of-00009.safetensors",
354
+ "model.layers.6.mlp.router.bias": "model-00003-of-00009.safetensors",
355
+ "model.layers.6.mlp.router.weight": "model-00003-of-00009.safetensors",
356
+ "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
357
+ "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
358
+ "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
359
+ "model.layers.6.self_attn.o_proj.bias": "model-00003-of-00009.safetensors",
360
+ "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
361
+ "model.layers.6.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
362
+ "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
363
+ "model.layers.6.self_attn.sinks": "model-00003-of-00009.safetensors",
364
+ "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
365
+ "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
366
+ "model.layers.7.input_layernorm.weight": "model-00003-of-00009.safetensors",
367
+ "model.layers.7.mlp.experts.down_proj": "model-00003-of-00009.safetensors",
368
+ "model.layers.7.mlp.experts.down_proj_bias": "model-00003-of-00009.safetensors",
369
+ "model.layers.7.mlp.experts.gate_up_proj": "model-00003-of-00009.safetensors",
370
+ "model.layers.7.mlp.experts.gate_up_proj_bias": "model-00003-of-00009.safetensors",
371
+ "model.layers.7.mlp.router.bias": "model-00003-of-00009.safetensors",
372
+ "model.layers.7.mlp.router.weight": "model-00003-of-00009.safetensors",
373
+ "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
374
+ "model.layers.7.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
375
+ "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
376
+ "model.layers.7.self_attn.o_proj.bias": "model-00003-of-00009.safetensors",
377
+ "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
378
+ "model.layers.7.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
379
+ "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
380
+ "model.layers.7.self_attn.sinks": "model-00003-of-00009.safetensors",
381
+ "model.layers.7.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
382
+ "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
383
+ "model.layers.8.input_layernorm.weight": "model-00004-of-00009.safetensors",
384
+ "model.layers.8.mlp.experts.down_proj": "model-00004-of-00009.safetensors",
385
+ "model.layers.8.mlp.experts.down_proj_bias": "model-00004-of-00009.safetensors",
386
+ "model.layers.8.mlp.experts.gate_up_proj": "model-00004-of-00009.safetensors",
387
+ "model.layers.8.mlp.experts.gate_up_proj_bias": "model-00004-of-00009.safetensors",
388
+ "model.layers.8.mlp.router.bias": "model-00003-of-00009.safetensors",
389
+ "model.layers.8.mlp.router.weight": "model-00003-of-00009.safetensors",
390
+ "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
391
+ "model.layers.8.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
392
+ "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
393
+ "model.layers.8.self_attn.o_proj.bias": "model-00003-of-00009.safetensors",
394
+ "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
395
+ "model.layers.8.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
396
+ "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
397
+ "model.layers.8.self_attn.sinks": "model-00003-of-00009.safetensors",
398
+ "model.layers.8.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
399
+ "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
400
+ "model.layers.9.input_layernorm.weight": "model-00004-of-00009.safetensors",
401
+ "model.layers.9.mlp.experts.down_proj": "model-00004-of-00009.safetensors",
402
+ "model.layers.9.mlp.experts.down_proj_bias": "model-00004-of-00009.safetensors",
403
+ "model.layers.9.mlp.experts.gate_up_proj": "model-00004-of-00009.safetensors",
404
+ "model.layers.9.mlp.experts.gate_up_proj_bias": "model-00004-of-00009.safetensors",
405
+ "model.layers.9.mlp.router.bias": "model-00004-of-00009.safetensors",
406
+ "model.layers.9.mlp.router.weight": "model-00004-of-00009.safetensors",
407
+ "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
408
+ "model.layers.9.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
409
+ "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
410
+ "model.layers.9.self_attn.o_proj.bias": "model-00004-of-00009.safetensors",
411
+ "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
412
+ "model.layers.9.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
413
+ "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
414
+ "model.layers.9.self_attn.sinks": "model-00004-of-00009.safetensors",
415
+ "model.layers.9.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
416
+ "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
417
+ "model.norm.weight": "model-00009-of-00009.safetensors"
418
+ }
419
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e8e083cfe222900d35bd514cf33c3a21faf521ec86ebe1cbc67a95ff7315d3d
3
+ size 129620043
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1d565802a8e26c4e8a31328752b7a7fdc186d9401aa008e65697d0ad8c22e33
3
+ size 14645
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6150922260c44c3f207da31c83ab00f490c1066544adaa7c45e4bf16c85e0cb8
3
+ size 1465
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|return|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3
3
+ size 27868174
tokenizer_config.json ADDED
@@ -0,0 +1,184 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "199998": {
4
+ "content": "<|startoftext|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "199999": {
12
+ "content": "<|endoftext|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "200000": {
20
+ "content": "<|reserved_200000|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "200001": {
28
+ "content": "<|reserved_200001|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "200002": {
36
+ "content": "<|return|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "200003": {
44
+ "content": "<|constrain|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "200004": {
52
+ "content": "<|reserved_200004|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "200005": {
60
+ "content": "<|channel|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "200006": {
68
+ "content": "<|start|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "200007": {
76
+ "content": "<|end|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "200008": {
84
+ "content": "<|message|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "200009": {
92
+ "content": "<|reserved_200009|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "200010": {
100
+ "content": "<|reserved_200010|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "200011": {
108
+ "content": "<|reserved_200011|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "200012": {
116
+ "content": "<|call|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "200013": {
124
+ "content": "<|reserved_200013|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "200014": {
132
+ "content": "<|reserved_200014|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "200015": {
140
+ "content": "<|reserved_200015|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "200016": {
148
+ "content": "<|reserved_200016|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "200017": {
156
+ "content": "<|reserved_200017|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "200018": {
164
+ "content": "<|endofprompt|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ }
171
+ },
172
+ "bos_token": "<|startoftext|>",
173
+ "clean_up_tokenization_spaces": false,
174
+ "eos_token": "<|return|>",
175
+ "extra_special_tokens": {},
176
+ "model_input_names": [
177
+ "input_ids",
178
+ "attention_mask"
179
+ ],
180
+ "model_max_length": 1000000000000000019884624838656,
181
+ "pad_token": "<|endoftext|>",
182
+ "padding_side": "left",
183
+ "tokenizer_class": "PreTrainedTokenizerFast"
184
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd8db0e589b7a84a14977c6d431b09e251651dfd307da9e2ab00a72179e5ed19
3
+ size 6225