danielhanchen commited on
Commit
3aec2a0
·
verified ·
1 Parent(s): f114b84

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,463 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - ibm-granite/granite-4.0-h-tiny-base
4
+ license: apache-2.0
5
+ library_name: transformers
6
+ tags:
7
+ - language
8
+ - unsloth
9
+ - granite-4.0
10
+ ---
11
+ <div>
12
+ <p style="margin-top: 0;margin-bottom: 0;">
13
+ <em><a href="https://docs.unsloth.ai/basics/unsloth-dynamic-v2.0-gguf">Unsloth Dynamic 2.0</a> achieves superior accuracy & outperforms other leading quants.</em>
14
+ </p>
15
+ <div style="display: flex; gap: 5px; align-items: center; ">
16
+ <a href="https://github.com/unslothai/unsloth/">
17
+ <img src="https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png" width="133">
18
+ </a>
19
+ <a href="https://discord.gg/unsloth">
20
+ <img src="https://github.com/unslothai/unsloth/raw/main/images/Discord%20button.png" width="173">
21
+ </a>
22
+ <a href="https://docs.unsloth.ai/">
23
+ <img src="https://raw.githubusercontent.com/unslothai/unsloth/refs/heads/main/images/documentation%20green%20button.png" width="143">
24
+ </a>
25
+ </div>
26
+ </div>
27
+
28
+
29
+ # Granite-4.0-H-Tiny-Base
30
+
31
+ **Model Summary:**
32
+ Granite-4.0-H-Tiny-Base is a decoder-only, long-context language model designed for a wide range of text-to-text generation tasks. It also supports Fill-in-the-Middle (FIM) code completion through the use of specialized prefix and suffix tokens. The model is trained from scratch on approximately 23 trillion tokens following a four-stage training strategy: 15 trillion tokens in the first stage, 5 trillion in the second, 2 trillion in the third, and 0.5 trillion in the final stage.
33
+
34
+ - **Developers:** Granite Team, IBM
35
+ - **HF Collection:** [Granite 4.0 Language Models HF Collection](https://huggingface.co/collections/ibm-granite/granite-40-language-models-6811a18b820ef362d9e5a82c)
36
+ - **GitHub Repository:** [ibm-granite/granite-4.0-language-models](https://github.com/ibm-granite/granite-4.0-language-models)
37
+ - **Website**: [Granite Docs](https://www.ibm.com/granite/docs/)
38
+ - **Release Date**: October 2nd, 2025
39
+ - **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)
40
+
41
+ **Supported Languages:**
42
+ English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, and Chinese. Users may finetune Granite 4.0 models for languages beyond these languages.
43
+
44
+ **Intended Use:**
45
+ Prominent use cases of LLMs in text-to-text generation include summarization, text classification, extraction, question-answering, code-completion (including FIM), and long-context generation tasks. All Granite Base models are able to handle these tasks as they were trained on a large amount of data from various domains. Moreover, they can serve as baseline to create specialized models for specific application scenarios.
46
+
47
+ **Generation:**
48
+ This is a simple example of how to use Granite-4.0-H-Tiny-Base model.
49
+
50
+ Install the following libraries:
51
+
52
+ ```shell
53
+ pip install torch torchvision torchaudio
54
+ pip install accelerate
55
+ pip install transformers
56
+ ```
57
+ Then, copy the code snippet below to run the example.
58
+
59
+ ```python
60
+ from transformers import AutoModelForCausalLM, AutoTokenizer
61
+ device = "cuda"
62
+
63
+ model_path = "ibm-granite/granite-4.0-h-micro-base"
64
+
65
+ tokenizer = AutoTokenizer.from_pretrained(model_path)
66
+ # drop device_map if running on CPU
67
+ model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device)
68
+ model.eval()
69
+ # change input text as desired
70
+ input_text = "The capital of France is"
71
+ # tokenize the text
72
+ input_tokens = tokenizer(input_text, return_tensors="pt").to(device)
73
+ # generate output tokens
74
+ output = model.generate(**input_tokens, max_length=10)
75
+ # decode output tokens into text
76
+ output = tokenizer.batch_decode(output)
77
+ # print output
78
+ print(output[0])
79
+ ```
80
+
81
+ Expected output:
82
+ ```shell
83
+ The capital of France is Paris.
84
+ ```
85
+
86
+ **Evaluation Results:**
87
+
88
+ <table>
89
+ <!-- <caption><b> All Results</b></caption> -->
90
+ <thead>
91
+ <tr>
92
+ <th style="text-align:left; background-color: #001d6c; color: white;">Benchmarks</th>
93
+ <th style="text-align:left; background-color: #001d6c; color: white;">Metric</th>
94
+ <th style="text-align:center; background-color: #001d6c; color: white;">Micro Dense</th>
95
+ <th style="text-align:center; background-color: #001d6c; color: white;">H Micro Dense</th>
96
+ <th style="text-align:center; background-color: #001d6c; color: white;">H Tiny MoE</th>
97
+ <th style="text-align:center; background-color: #001d6c; color: white;">H Small MoE</th>
98
+ </tr>
99
+ </thead>
100
+ <tbody>
101
+ <tr>
102
+ <td colspan="6" style="text-align:center; background-color: #FFFFFF; color: #2D2D2D; font-style:italic;">
103
+ General Tasks
104
+ </td>
105
+ </tr>
106
+ <tr>
107
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MMLU</td>
108
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">5-shot</td>
109
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">66.47</td>
110
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">67.43</td>
111
+ <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">68.90</td>
112
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">75.85</td>
113
+ </tr>
114
+ <tr>
115
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MMLU-Pro</td>
116
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">5-shot,CoT</td>
117
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">37.16</td>
118
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">34.03</td>
119
+ <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">35.47</td>
120
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">48.94</td>
121
+ </tr>
122
+ <tr>
123
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">BBH</td>
124
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">3-shot, CoT</td>
125
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">63.84</td>
126
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">57.65</td>
127
+ <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">59.67</td>
128
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">75.84</td>
129
+ </tr>
130
+ <tr>
131
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">AGI EVAL</td>
132
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">3-shot</td>
133
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">54.32</td>
134
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">54.59</td>
135
+ <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">53.69</td>
136
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">62.05</td>
137
+ </tr>
138
+ <tr>
139
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">DROP</td>
140
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">5-shot</td>
141
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">66.04</td>
142
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">67.44</td>
143
+ <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">64.92</td>
144
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">74.69</td>
145
+ </tr>
146
+ <tr>
147
+ <td colspan="6" style="text-align:center; background-color: #FFFFFF; color: #2D2D2D; font-style:italic;">
148
+ Math Tasks
149
+ </td>
150
+ </tr>
151
+ <tr>
152
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">GSM8K</td>
153
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">8-shot</td>
154
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">72.93</td>
155
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">63.76</td>
156
+ <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">72.55</td>
157
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">82.11</td>
158
+ </tr>
159
+ <tr>
160
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">Minerva Math</td>
161
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">4-shot</td>
162
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">38</td>
163
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">39.7</td>
164
+ <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">40.34</td>
165
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">46.28</td>
166
+ </tr>
167
+ <tr>
168
+ <td colspan="6" style="text-align:center; background-color: #FFFFFF; color: #2D2D2D; font-style:italic;">
169
+ Code Tasks
170
+ </td>
171
+ </tr>
172
+ <tr>
173
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">HumanEval </td>
174
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">pass@1 [StarCoder Prompt]</td>
175
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">76.19</td>
176
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">73.72</td>
177
+ <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">77.59</td>
178
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">83.66</td>
179
+ </tr>
180
+ <tr>
181
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">HumanEval</td>
182
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">pass@1</td>
183
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">59.76</td>
184
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">70.73</td>
185
+ <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">71.34</td>
186
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">76.22</td>
187
+ </tr>
188
+ <tr>
189
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">HumanEval+</td>
190
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">pass@1</td>
191
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">54.27</td>
192
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">67.07</td>
193
+ <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">64.02</td>
194
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">69.51</td>
195
+ </tr>
196
+ <tr>
197
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MBPP</td>
198
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">pass@1</td>
199
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">81.48</td>
200
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">74.87</td>
201
+ <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">81.48</td>
202
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">83.07</td>
203
+ </tr>
204
+ <tr>
205
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MBPP+</td>
206
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">pass@1</td>
207
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">68.25</td>
208
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">63.23</td>
209
+ <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">68.78</td>
210
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">70.37</td>
211
+ </tr>
212
+ <tr>
213
+ <td colspan="6" style="text-align:center; background-color: #FFFFFF; color: #2D2D2D; font-style:italic;">
214
+ Multilingual Tasks
215
+ </td>
216
+ </tr>
217
+ <tr>
218
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MMMLU</td>
219
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">5-shot</td>
220
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">56.59</td>
221
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">58.5</td>
222
+ <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">62.77</td>
223
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">71.18</td>
224
+ </tr>
225
+ <tr>
226
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">INCLUDE</td>
227
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">5-shot</td>
228
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">51.77</td>
229
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">52.16</td>
230
+ <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">53.78</td>
231
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">66.04</td>
232
+ </tr>
233
+ <tr>
234
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MGSM</td>
235
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">8-shot</td>
236
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">58.48</td>
237
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">47.04</td>
238
+ <td style="text-align:right; background-color: #DAE8FF; color: #2D2D2D;">54.64</td>
239
+ <td style="text-align:right; background-color: #FFFFFF; color: #2D2D2D;">65.2</td>
240
+ </tr>
241
+ </tbody></table>
242
+
243
+
244
+ <table>
245
+ <caption><b>Multilingual Benchmarks and thr included languages:</b></caption>
246
+ <thead>
247
+ <tr>
248
+ <th style="text-align:left; background-color: #001d6c; color: white;">Benchmarks</th>
249
+ <th style="text-align:left; background-color: #001d6c; color: white;"># Langs</th>
250
+ <th style="text-align:center; background-color: #001d6c; color: white;">Languages</th>
251
+ </tr>
252
+ </thead>
253
+ <tbody>
254
+ <tr>
255
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MMMLU</td>
256
+ <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">11</td>
257
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">ar, de, en, es, fr, ja, ko, pt, zh, bn, hi</td>
258
+ </tr>
259
+ <tr>
260
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">INCLUDE</td>
261
+ <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">14</td>
262
+ <!-- <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">hindi, bengali, tamil, telugu, arabic, german, spanish, french, italian, japanese, korean, dutch, portuguese, chinese</td> -->
263
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">hi, bn, ta, te, ar, de, es, fr, it, ja, ko, nl, pt, zh</td>
264
+
265
+ </tr>
266
+ <tr>
267
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">MGSM</td>
268
+ <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">5</td>
269
+ <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">en, es, fr, ja, zh</td>
270
+ </tr>
271
+ </tbody>
272
+ </table>
273
+
274
+ **Model Architecture:**
275
+ Granite-4.0-H-Tiny-Base is based on a decoder-only MoE transformer architecture. Core components of this architecture are: GQA, Mamba2, MoEs with shared experts, SwiGLU activation, RMSNorm, and shared input/output embeddings.
276
+
277
+ <table>
278
+ <thead>
279
+ <tr>
280
+ <th style="text-align:left; background-color: #001d6c; color: white;">Model</th>
281
+ <th style="text-align:center; background-color: #001d6c; color: white;">Micro Dense</th>
282
+ <th style="text-align:center; background-color: #001d6c; color: white;">H Micro Dense</th>
283
+ <th style="text-align:center; background-color: #001d6c; color: white;">H Tiny MoE</th>
284
+ <th style="text-align:center; background-color: #001d6c; color: white;">H Small MoE</th>
285
+ </tr></thead>
286
+ <tbody>
287
+ <tr>
288
+ <td style="text-align:left; background-color: #FFFFFF; color: black;">Embedding size</td>
289
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">2560</td>
290
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">2048</td>
291
+ <td style="text-align:center; background-color: #DAE8FF; color: black;">1536</td>
292
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">4096</td>
293
+ </tr>
294
+ <tr>
295
+ <td style="text-align:left; background-color: #FFFFFF; color: black;">Number of layers</td>
296
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">40 attention</td>
297
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">4 attention / 36 Mamba2</td>
298
+ <td style="text-align:center; background-color: #DAE8FF; color: black;">4 attention / 36 Mamba2</td>
299
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">4 attention / 36 Mamba2</td>
300
+ </tr>
301
+ <tr>
302
+ <td style="text-align:left; background-color: #FFFFFF; color: black;">Attention head size</td>
303
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">64</td>
304
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">64</td>
305
+ <td style="text-align:center; background-color: #DAE8FF; color: black;">128</td>
306
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">128</td>
307
+ </tr>
308
+ <tr>
309
+ <td style="text-align:left; background-color: #FFFFFF; color: black;">Number of attention heads</td>
310
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">40</td>
311
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">32</td>
312
+ <td style="text-align:center; background-color: #DAE8FF; color: black;">12</td>
313
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">32</td>
314
+ </tr>
315
+ <tr>
316
+ <td style="text-align:left; background-color: #FFFFFF; color: black;">Number of KV heads</td>
317
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">8</td>
318
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">8</td>
319
+ <td style="text-align:center; background-color: #DAE8FF; color: black;">4</td>
320
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">8</td>
321
+ </tr>
322
+ <tr>
323
+ <td style="text-align:left; background-color: #FFFFFF; color: black;">Mamba2 state size</td>
324
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">-</td>
325
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">128</td>
326
+ <td style="text-align:center; background-color: #DAE8FF; color: black;">128</td>
327
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">128</td>
328
+ </tr>
329
+ <tr>
330
+ <td style="text-align:left; background-color: #FFFFFF; color: black;">Number of Mamba2 heads</td>
331
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">-</td>
332
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">64</td>
333
+ <td style="text-align:center; background-color: #DAE8FF; color: black;">48</td>
334
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">128</td>
335
+ </tr>
336
+
337
+ <tr>
338
+ <td style="text-align:left; background-color: #FFFFFF; color: black;">MLP / Shared expert hidden size</td>
339
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">8192</td>
340
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">8192</td>
341
+ <td style="text-align:center; background-color: #DAE8FF; color: black;">1024</td>
342
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">1536</td>
343
+ </tr>
344
+
345
+
346
+ <tr>
347
+ <td style="text-align:left; background-color: #FFFFFF; color: black;">Num. Experts</td>
348
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">-</td>
349
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">-</td>
350
+ <td style="text-align:center; background-color: #DAE8FF; color: black;">64</td>
351
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">72</td>
352
+ </tr>
353
+ <tr>
354
+ <td style="text-align:left; background-color: #FFFFFF; color: black;">Num. active Experts</td>
355
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">-</td>
356
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">-</td>
357
+ <td style="text-align:center; background-color: #DAE8FF; color: black;">6</td>
358
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">10</td>
359
+ </tr>
360
+ <tr>
361
+ <td style="text-align:left; background-color: #FFFFFF; color: black;">Expert hidden size</td>
362
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">-</td>
363
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">-</td>
364
+ <td style="text-align:center; background-color: #DAE8FF; color: black;">512</td>
365
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">768</td>
366
+ </tr>
367
+
368
+ <tr>
369
+ <td style="text-align:left; background-color: #FFFFFF; color: black;">MLP activation</td>
370
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">SwiGLU</td>
371
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">SwiGLU</td>
372
+ <td style="text-align:center; background-color: #DAE8FF; color: black;">SwiGLU</td>
373
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">SwiGLU</td>
374
+ </tr>
375
+
376
+ <tr>
377
+ <td style="text-align:left; background-color: #FFFFFF; color: black;">Sequence length</td>
378
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">128K</td>
379
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">128K</td>
380
+ <td style="text-align:center; background-color: #DAE8FF; color: black;">128K</td>
381
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">128K</td>
382
+ </tr>
383
+ <tr>
384
+ <td style="text-align:left; background-color: #FFFFFF; color: black;">Position embedding</td>
385
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">RoPE</td>
386
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">NoPE</td>
387
+ <td style="text-align:center; background-color: #DAE8FF; color: black;">NoPE</td>
388
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">NoPE</td>
389
+ </tr>
390
+ <tr>
391
+ <td style="text-align:left; background-color: #FFFFFF; color: black;"># Parameters</td>
392
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">3B</td>
393
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">3B</td>
394
+ <td style="text-align:center; background-color: #DAE8FF; color: black;">7B</td>
395
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">32B</td>
396
+ </tr>
397
+ <tr>
398
+ <td style="text-align:left; background-color: #FFFFFF; color: black;"># Active parameters</td>
399
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">3B</td>
400
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">3B</td>
401
+ <td style="text-align:center; background-color: #DAE8FF; color: black;">1B</td>
402
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">9B</td>
403
+ </tr>
404
+ </tbody></table>
405
+
406
+
407
+ **Training Data:** This model is trained on a mix of open source and proprietary data following a four-stage training strategy.
408
+
409
+ <table>
410
+ <thead>
411
+ <tr>
412
+ <th style="text-align:left; background-color: #001d6c; color: white;">Stage</th>
413
+ <th style="text-align:left; background-color: #001d6c; color: white;">Characteristics</th>
414
+ <th style="text-align:center; background-color: #001d6c; color: white;">Micro Dense</th>
415
+ <th style="text-align:center; background-color: #001d6c; color: white;">H Micro Dense</th>
416
+ <th style="text-align:center; background-color: #001d6c; color: white;">H Tiny MoE</th>
417
+ <th style="text-align:center; background-color: #001d6c; color: white;">H Small MoE</th>
418
+ </tr></thead>
419
+ <tbody>
420
+ <tr>
421
+ <td style="text-align:left; background-color: #FFFFFF; color: black;">I</td>
422
+ <td style="text-align:left; background-color: #FFFFFF; color: black;">General mixture of training data, warmup, and power scheduler for learning rate.</td>
423
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">10</td>
424
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">10</td>
425
+ <td style="text-align:center; background-color: #DAE8FF; color: black;">15</td>
426
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">15</td>
427
+ </tr>
428
+ <tr>
429
+ <td style="text-align:left; background-color: #FFFFFF; color: black;">II</td>
430
+ <td style="text-align:left; background-color: #FFFFFF; color: black;">General mixture of training data with higher percentages of code and math with power scheduler for learning rate.</td>
431
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">2</td>
432
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">5</td>
433
+ <td style="text-align:center; background-color: #DAE8FF; color: black;">5</td>
434
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">5</td>
435
+ </tr>
436
+ <tr>
437
+ <td style="text-align:left; background-color: #FFFFFF; color: black;">III</td>
438
+ <td style="text-align:left; background-color: #FFFFFF; color: black;">High quality training data, exponential decay of learning rate.</td>
439
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">2</td>
440
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">2</td>
441
+ <td style="text-align:center; background-color: #DAE8FF; color: black;">2</td>
442
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">2</td>
443
+ </tr>
444
+ <tr>
445
+ <td style="text-align:left; background-color: #FFFFFF; color: black;">IV</td>
446
+ <td style="text-align:left; background-color: #FFFFFF; color: black;">High quality training data, linear decay to zero for learning rate.</td>
447
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">0.5</td>
448
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">0.5</td>
449
+ <td style="text-align:center; background-color: #DAE8FF; color: black;">0.5</td>
450
+ <td style="text-align:center; background-color: #FFFFFF; color: black;">0.5</td>
451
+ </tr>
452
+ </tbody></table>
453
+
454
+ **Infrastructure:**
455
+ We trained the Granite 4.0 Language Models utilizing an NVIDIA GB200 NVL72 cluster hosted in CoreWeave. Intra-rack communication occurs via the 72-GPU NVLink domain, and a non-blocking, full Fat-Tree NDR 400 Gb/s InfiniBand network provides inter-rack communication. This cluster provides a scalable and efficient infrastructure for training our models over thousands of GPUs.
456
+
457
+ **Ethical Considerations and Limitations:**
458
+ The use of Large Language Models involves risks and ethical considerations people must be aware of, including but not limited to: bias and fairness, misinformation, and autonomous decision-making. Granite-4.0-H-Tiny-Base model is not the exception in this regard. Even though this model is suited for multiple generative AI tasks, it has not undergone any safety alignment, there it may produce problematic outputs. Additionally, it remains uncertain whether smaller models might exhibit increased susceptibility to hallucination in generation scenarios by copying text verbatim from the training dataset due to their reduced sizes and memorization capacities. This aspect is currently an active area of research, and we anticipate more rigorous exploration, comprehension, and mitigations in this domain. Regarding ethics, a latent risk associated with all Large Language Models is their malicious utilization. We urge the community to use Granite-4.0-H-Tiny-Base model with ethical intentions and in a responsible way.
459
+
460
+ **Resources**
461
+ - ⭐️ Learn about the latest updates with Granite: https://www.ibm.com/granite
462
+ - 📄 Get started with tutorials, best practices, and prompt engineering advice: https://www.ibm.com/granite/docs/
463
+ - 💡 Learn about the latest Granite learning resources: https://github.com/ibm-granite-community/
config.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GraniteMoeHybridForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "attention_multiplier": 0.0078125,
8
+ "bos_token_id": 100257,
9
+ "torch_dtype": "bfloat16",
10
+ "embedding_multiplier": 12,
11
+ "eos_token_id": 100257,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 1536,
14
+ "initializer_range": 0.1,
15
+ "intermediate_size": 512,
16
+ "layer_types": [
17
+ "mamba",
18
+ "mamba",
19
+ "mamba",
20
+ "mamba",
21
+ "mamba",
22
+ "attention",
23
+ "mamba",
24
+ "mamba",
25
+ "mamba",
26
+ "mamba",
27
+ "mamba",
28
+ "mamba",
29
+ "mamba",
30
+ "mamba",
31
+ "mamba",
32
+ "attention",
33
+ "mamba",
34
+ "mamba",
35
+ "mamba",
36
+ "mamba",
37
+ "mamba",
38
+ "mamba",
39
+ "mamba",
40
+ "mamba",
41
+ "mamba",
42
+ "attention",
43
+ "mamba",
44
+ "mamba",
45
+ "mamba",
46
+ "mamba",
47
+ "mamba",
48
+ "mamba",
49
+ "mamba",
50
+ "mamba",
51
+ "mamba",
52
+ "attention",
53
+ "mamba",
54
+ "mamba",
55
+ "mamba",
56
+ "mamba"
57
+ ],
58
+ "logits_scaling": 6,
59
+ "mamba_chunk_size": 256,
60
+ "mamba_conv_bias": true,
61
+ "mamba_d_conv": 4,
62
+ "mamba_d_head": 64,
63
+ "mamba_d_state": 128,
64
+ "mamba_expand": 2,
65
+ "mamba_n_groups": 1,
66
+ "mamba_n_heads": 48,
67
+ "mamba_proj_bias": false,
68
+ "max_position_embeddings": 131072,
69
+ "model_type": "granitemoehybrid",
70
+ "normalization_function": "rmsnorm",
71
+ "num_attention_heads": 12,
72
+ "num_experts_per_tok": 6,
73
+ "num_hidden_layers": 40,
74
+ "num_key_value_heads": 4,
75
+ "num_local_experts": 64,
76
+ "output_router_logits": false,
77
+ "pad_token_id": 100256,
78
+ "position_embedding_type": "nope",
79
+ "residual_multiplier": 0.22,
80
+ "rms_norm_eps": 1e-05,
81
+ "rope_scaling": null,
82
+ "rope_theta": 10000,
83
+ "router_aux_loss_coef": 0.0,
84
+ "shared_intermediate_size": 1024,
85
+ "tie_word_embeddings": true,
86
+ "transformers_version": "4.56.2",
87
+ "unsloth_fixed": true,
88
+ "use_cache": true,
89
+ "vocab_size": 100352
90
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 100257,
4
+ "eos_token_id": 100257,
5
+ "max_length": 131072,
6
+ "pad_token_id": 100256,
7
+ "transformers_version": "4.56.2"
8
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aff219de2a1b3d92897a6866a284fb5817b1e1a62acbd97df314538f34e44b95
3
+ size 4924822608
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:968dc01bcef15155124a2de8a7b128a18384591606aae366fc9f7f8865e2a71e
3
+ size 4879018632
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d525fed75834f785b636bbfa8dea2bf39210a166ff61f69d4c445a05f814a26
3
+ size 4074301016
model.safetensors.index.json ADDED
@@ -0,0 +1,594 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 6939037248,
4
+ "total_size": 13878074496
5
+ },
6
+ "weight_map": {
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.mamba.A_log": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.mamba.D": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.mamba.dt_bias": "model-00001-of-00003.safetensors",
17
+ "model.layers.0.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.0.mamba.norm.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.0.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.0.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.0.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
27
+ "model.layers.1.mamba.A_log": "model-00001-of-00003.safetensors",
28
+ "model.layers.1.mamba.D": "model-00001-of-00003.safetensors",
29
+ "model.layers.1.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
30
+ "model.layers.1.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
31
+ "model.layers.1.mamba.dt_bias": "model-00001-of-00003.safetensors",
32
+ "model.layers.1.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
33
+ "model.layers.1.mamba.norm.weight": "model-00001-of-00003.safetensors",
34
+ "model.layers.1.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
35
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
36
+ "model.layers.1.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
37
+ "model.layers.1.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
38
+ "model.layers.10.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
39
+ "model.layers.10.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
40
+ "model.layers.10.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
41
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
42
+ "model.layers.10.mamba.A_log": "model-00001-of-00003.safetensors",
43
+ "model.layers.10.mamba.D": "model-00001-of-00003.safetensors",
44
+ "model.layers.10.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
45
+ "model.layers.10.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
46
+ "model.layers.10.mamba.dt_bias": "model-00001-of-00003.safetensors",
47
+ "model.layers.10.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
48
+ "model.layers.10.mamba.norm.weight": "model-00001-of-00003.safetensors",
49
+ "model.layers.10.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
50
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
51
+ "model.layers.10.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
52
+ "model.layers.10.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
53
+ "model.layers.11.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
54
+ "model.layers.11.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
55
+ "model.layers.11.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
56
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
57
+ "model.layers.11.mamba.A_log": "model-00001-of-00003.safetensors",
58
+ "model.layers.11.mamba.D": "model-00001-of-00003.safetensors",
59
+ "model.layers.11.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
60
+ "model.layers.11.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
61
+ "model.layers.11.mamba.dt_bias": "model-00001-of-00003.safetensors",
62
+ "model.layers.11.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
63
+ "model.layers.11.mamba.norm.weight": "model-00001-of-00003.safetensors",
64
+ "model.layers.11.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
65
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
66
+ "model.layers.11.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
67
+ "model.layers.11.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
68
+ "model.layers.12.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
69
+ "model.layers.12.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
70
+ "model.layers.12.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
71
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
72
+ "model.layers.12.mamba.A_log": "model-00001-of-00003.safetensors",
73
+ "model.layers.12.mamba.D": "model-00001-of-00003.safetensors",
74
+ "model.layers.12.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
75
+ "model.layers.12.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
76
+ "model.layers.12.mamba.dt_bias": "model-00001-of-00003.safetensors",
77
+ "model.layers.12.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
78
+ "model.layers.12.mamba.norm.weight": "model-00001-of-00003.safetensors",
79
+ "model.layers.12.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
80
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
81
+ "model.layers.12.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
82
+ "model.layers.12.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
83
+ "model.layers.13.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
84
+ "model.layers.13.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.13.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.13.mamba.A_log": "model-00002-of-00003.safetensors",
88
+ "model.layers.13.mamba.D": "model-00002-of-00003.safetensors",
89
+ "model.layers.13.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
90
+ "model.layers.13.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.13.mamba.dt_bias": "model-00002-of-00003.safetensors",
92
+ "model.layers.13.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.13.mamba.norm.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.13.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.13.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.13.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.14.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.14.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.14.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.14.mamba.A_log": "model-00002-of-00003.safetensors",
103
+ "model.layers.14.mamba.D": "model-00002-of-00003.safetensors",
104
+ "model.layers.14.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
105
+ "model.layers.14.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.14.mamba.dt_bias": "model-00002-of-00003.safetensors",
107
+ "model.layers.14.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.14.mamba.norm.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.14.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.14.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.14.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.15.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.15.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.15.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
117
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
118
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
119
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
120
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
121
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
122
+ "model.layers.15.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
123
+ "model.layers.15.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
124
+ "model.layers.16.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
125
+ "model.layers.16.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
126
+ "model.layers.16.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.16.mamba.A_log": "model-00002-of-00003.safetensors",
129
+ "model.layers.16.mamba.D": "model-00002-of-00003.safetensors",
130
+ "model.layers.16.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
131
+ "model.layers.16.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.16.mamba.dt_bias": "model-00002-of-00003.safetensors",
133
+ "model.layers.16.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.16.mamba.norm.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.16.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
136
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.16.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
138
+ "model.layers.16.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
139
+ "model.layers.17.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
140
+ "model.layers.17.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
141
+ "model.layers.17.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
142
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
143
+ "model.layers.17.mamba.A_log": "model-00002-of-00003.safetensors",
144
+ "model.layers.17.mamba.D": "model-00002-of-00003.safetensors",
145
+ "model.layers.17.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
146
+ "model.layers.17.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
147
+ "model.layers.17.mamba.dt_bias": "model-00002-of-00003.safetensors",
148
+ "model.layers.17.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
149
+ "model.layers.17.mamba.norm.weight": "model-00002-of-00003.safetensors",
150
+ "model.layers.17.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
151
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
152
+ "model.layers.17.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
153
+ "model.layers.17.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
154
+ "model.layers.18.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
155
+ "model.layers.18.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
156
+ "model.layers.18.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
157
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
158
+ "model.layers.18.mamba.A_log": "model-00002-of-00003.safetensors",
159
+ "model.layers.18.mamba.D": "model-00002-of-00003.safetensors",
160
+ "model.layers.18.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
161
+ "model.layers.18.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
162
+ "model.layers.18.mamba.dt_bias": "model-00002-of-00003.safetensors",
163
+ "model.layers.18.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
164
+ "model.layers.18.mamba.norm.weight": "model-00002-of-00003.safetensors",
165
+ "model.layers.18.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
166
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
167
+ "model.layers.18.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
168
+ "model.layers.18.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
169
+ "model.layers.19.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
170
+ "model.layers.19.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
171
+ "model.layers.19.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
172
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
173
+ "model.layers.19.mamba.A_log": "model-00002-of-00003.safetensors",
174
+ "model.layers.19.mamba.D": "model-00002-of-00003.safetensors",
175
+ "model.layers.19.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
176
+ "model.layers.19.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
177
+ "model.layers.19.mamba.dt_bias": "model-00002-of-00003.safetensors",
178
+ "model.layers.19.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
179
+ "model.layers.19.mamba.norm.weight": "model-00002-of-00003.safetensors",
180
+ "model.layers.19.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
181
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
182
+ "model.layers.19.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
183
+ "model.layers.19.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
184
+ "model.layers.2.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
185
+ "model.layers.2.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
186
+ "model.layers.2.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
187
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
188
+ "model.layers.2.mamba.A_log": "model-00001-of-00003.safetensors",
189
+ "model.layers.2.mamba.D": "model-00001-of-00003.safetensors",
190
+ "model.layers.2.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
191
+ "model.layers.2.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
192
+ "model.layers.2.mamba.dt_bias": "model-00001-of-00003.safetensors",
193
+ "model.layers.2.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
194
+ "model.layers.2.mamba.norm.weight": "model-00001-of-00003.safetensors",
195
+ "model.layers.2.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
196
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
197
+ "model.layers.2.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
198
+ "model.layers.2.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
199
+ "model.layers.20.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
200
+ "model.layers.20.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
201
+ "model.layers.20.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
202
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
203
+ "model.layers.20.mamba.A_log": "model-00002-of-00003.safetensors",
204
+ "model.layers.20.mamba.D": "model-00002-of-00003.safetensors",
205
+ "model.layers.20.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
206
+ "model.layers.20.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
207
+ "model.layers.20.mamba.dt_bias": "model-00002-of-00003.safetensors",
208
+ "model.layers.20.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
209
+ "model.layers.20.mamba.norm.weight": "model-00002-of-00003.safetensors",
210
+ "model.layers.20.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
211
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
212
+ "model.layers.20.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
213
+ "model.layers.20.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
214
+ "model.layers.21.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
215
+ "model.layers.21.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
216
+ "model.layers.21.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
217
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
218
+ "model.layers.21.mamba.A_log": "model-00002-of-00003.safetensors",
219
+ "model.layers.21.mamba.D": "model-00002-of-00003.safetensors",
220
+ "model.layers.21.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
221
+ "model.layers.21.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
222
+ "model.layers.21.mamba.dt_bias": "model-00002-of-00003.safetensors",
223
+ "model.layers.21.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
224
+ "model.layers.21.mamba.norm.weight": "model-00002-of-00003.safetensors",
225
+ "model.layers.21.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
226
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
227
+ "model.layers.21.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
228
+ "model.layers.21.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
229
+ "model.layers.22.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
230
+ "model.layers.22.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
231
+ "model.layers.22.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
232
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
233
+ "model.layers.22.mamba.A_log": "model-00002-of-00003.safetensors",
234
+ "model.layers.22.mamba.D": "model-00002-of-00003.safetensors",
235
+ "model.layers.22.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
236
+ "model.layers.22.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
237
+ "model.layers.22.mamba.dt_bias": "model-00002-of-00003.safetensors",
238
+ "model.layers.22.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
239
+ "model.layers.22.mamba.norm.weight": "model-00002-of-00003.safetensors",
240
+ "model.layers.22.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
241
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
242
+ "model.layers.22.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
243
+ "model.layers.22.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
244
+ "model.layers.23.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
245
+ "model.layers.23.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
246
+ "model.layers.23.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
247
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
248
+ "model.layers.23.mamba.A_log": "model-00002-of-00003.safetensors",
249
+ "model.layers.23.mamba.D": "model-00002-of-00003.safetensors",
250
+ "model.layers.23.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
251
+ "model.layers.23.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
252
+ "model.layers.23.mamba.dt_bias": "model-00002-of-00003.safetensors",
253
+ "model.layers.23.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
254
+ "model.layers.23.mamba.norm.weight": "model-00002-of-00003.safetensors",
255
+ "model.layers.23.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
256
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
257
+ "model.layers.23.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
258
+ "model.layers.23.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
259
+ "model.layers.24.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
260
+ "model.layers.24.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
261
+ "model.layers.24.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
262
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
263
+ "model.layers.24.mamba.A_log": "model-00002-of-00003.safetensors",
264
+ "model.layers.24.mamba.D": "model-00002-of-00003.safetensors",
265
+ "model.layers.24.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
266
+ "model.layers.24.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
267
+ "model.layers.24.mamba.dt_bias": "model-00002-of-00003.safetensors",
268
+ "model.layers.24.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
269
+ "model.layers.24.mamba.norm.weight": "model-00002-of-00003.safetensors",
270
+ "model.layers.24.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
271
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
272
+ "model.layers.24.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
273
+ "model.layers.24.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
274
+ "model.layers.25.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
275
+ "model.layers.25.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
276
+ "model.layers.25.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
277
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
278
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
279
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
280
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
281
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
282
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
283
+ "model.layers.25.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
284
+ "model.layers.25.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
285
+ "model.layers.26.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
286
+ "model.layers.26.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
287
+ "model.layers.26.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
288
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
289
+ "model.layers.26.mamba.A_log": "model-00002-of-00003.safetensors",
290
+ "model.layers.26.mamba.D": "model-00002-of-00003.safetensors",
291
+ "model.layers.26.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
292
+ "model.layers.26.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
293
+ "model.layers.26.mamba.dt_bias": "model-00002-of-00003.safetensors",
294
+ "model.layers.26.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
295
+ "model.layers.26.mamba.norm.weight": "model-00002-of-00003.safetensors",
296
+ "model.layers.26.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
297
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
298
+ "model.layers.26.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
299
+ "model.layers.26.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
300
+ "model.layers.27.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
301
+ "model.layers.27.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
302
+ "model.layers.27.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
303
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
304
+ "model.layers.27.mamba.A_log": "model-00002-of-00003.safetensors",
305
+ "model.layers.27.mamba.D": "model-00002-of-00003.safetensors",
306
+ "model.layers.27.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
307
+ "model.layers.27.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
308
+ "model.layers.27.mamba.dt_bias": "model-00002-of-00003.safetensors",
309
+ "model.layers.27.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
310
+ "model.layers.27.mamba.norm.weight": "model-00002-of-00003.safetensors",
311
+ "model.layers.27.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
312
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
313
+ "model.layers.27.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
314
+ "model.layers.27.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
315
+ "model.layers.28.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
316
+ "model.layers.28.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
317
+ "model.layers.28.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
318
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
319
+ "model.layers.28.mamba.A_log": "model-00003-of-00003.safetensors",
320
+ "model.layers.28.mamba.D": "model-00003-of-00003.safetensors",
321
+ "model.layers.28.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
322
+ "model.layers.28.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
323
+ "model.layers.28.mamba.dt_bias": "model-00003-of-00003.safetensors",
324
+ "model.layers.28.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
325
+ "model.layers.28.mamba.norm.weight": "model-00003-of-00003.safetensors",
326
+ "model.layers.28.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
327
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
328
+ "model.layers.28.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
329
+ "model.layers.28.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
330
+ "model.layers.29.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
331
+ "model.layers.29.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
332
+ "model.layers.29.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
333
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
334
+ "model.layers.29.mamba.A_log": "model-00003-of-00003.safetensors",
335
+ "model.layers.29.mamba.D": "model-00003-of-00003.safetensors",
336
+ "model.layers.29.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
337
+ "model.layers.29.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
338
+ "model.layers.29.mamba.dt_bias": "model-00003-of-00003.safetensors",
339
+ "model.layers.29.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
340
+ "model.layers.29.mamba.norm.weight": "model-00003-of-00003.safetensors",
341
+ "model.layers.29.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
342
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
343
+ "model.layers.29.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
344
+ "model.layers.29.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
345
+ "model.layers.3.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
346
+ "model.layers.3.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
347
+ "model.layers.3.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
348
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
349
+ "model.layers.3.mamba.A_log": "model-00001-of-00003.safetensors",
350
+ "model.layers.3.mamba.D": "model-00001-of-00003.safetensors",
351
+ "model.layers.3.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
352
+ "model.layers.3.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
353
+ "model.layers.3.mamba.dt_bias": "model-00001-of-00003.safetensors",
354
+ "model.layers.3.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
355
+ "model.layers.3.mamba.norm.weight": "model-00001-of-00003.safetensors",
356
+ "model.layers.3.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
357
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
358
+ "model.layers.3.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
359
+ "model.layers.3.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
360
+ "model.layers.30.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
361
+ "model.layers.30.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
362
+ "model.layers.30.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
363
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
364
+ "model.layers.30.mamba.A_log": "model-00003-of-00003.safetensors",
365
+ "model.layers.30.mamba.D": "model-00003-of-00003.safetensors",
366
+ "model.layers.30.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
367
+ "model.layers.30.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
368
+ "model.layers.30.mamba.dt_bias": "model-00003-of-00003.safetensors",
369
+ "model.layers.30.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
370
+ "model.layers.30.mamba.norm.weight": "model-00003-of-00003.safetensors",
371
+ "model.layers.30.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
372
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
373
+ "model.layers.30.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
374
+ "model.layers.30.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
375
+ "model.layers.31.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
376
+ "model.layers.31.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
377
+ "model.layers.31.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
378
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
379
+ "model.layers.31.mamba.A_log": "model-00003-of-00003.safetensors",
380
+ "model.layers.31.mamba.D": "model-00003-of-00003.safetensors",
381
+ "model.layers.31.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
382
+ "model.layers.31.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
383
+ "model.layers.31.mamba.dt_bias": "model-00003-of-00003.safetensors",
384
+ "model.layers.31.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
385
+ "model.layers.31.mamba.norm.weight": "model-00003-of-00003.safetensors",
386
+ "model.layers.31.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
387
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
388
+ "model.layers.31.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
389
+ "model.layers.31.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
390
+ "model.layers.32.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
391
+ "model.layers.32.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
392
+ "model.layers.32.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
393
+ "model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
394
+ "model.layers.32.mamba.A_log": "model-00003-of-00003.safetensors",
395
+ "model.layers.32.mamba.D": "model-00003-of-00003.safetensors",
396
+ "model.layers.32.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
397
+ "model.layers.32.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
398
+ "model.layers.32.mamba.dt_bias": "model-00003-of-00003.safetensors",
399
+ "model.layers.32.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
400
+ "model.layers.32.mamba.norm.weight": "model-00003-of-00003.safetensors",
401
+ "model.layers.32.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
402
+ "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
403
+ "model.layers.32.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
404
+ "model.layers.32.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
405
+ "model.layers.33.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
406
+ "model.layers.33.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
407
+ "model.layers.33.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
408
+ "model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
409
+ "model.layers.33.mamba.A_log": "model-00003-of-00003.safetensors",
410
+ "model.layers.33.mamba.D": "model-00003-of-00003.safetensors",
411
+ "model.layers.33.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
412
+ "model.layers.33.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
413
+ "model.layers.33.mamba.dt_bias": "model-00003-of-00003.safetensors",
414
+ "model.layers.33.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
415
+ "model.layers.33.mamba.norm.weight": "model-00003-of-00003.safetensors",
416
+ "model.layers.33.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
417
+ "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
418
+ "model.layers.33.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
419
+ "model.layers.33.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
420
+ "model.layers.34.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
421
+ "model.layers.34.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
422
+ "model.layers.34.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
423
+ "model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
424
+ "model.layers.34.mamba.A_log": "model-00003-of-00003.safetensors",
425
+ "model.layers.34.mamba.D": "model-00003-of-00003.safetensors",
426
+ "model.layers.34.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
427
+ "model.layers.34.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
428
+ "model.layers.34.mamba.dt_bias": "model-00003-of-00003.safetensors",
429
+ "model.layers.34.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
430
+ "model.layers.34.mamba.norm.weight": "model-00003-of-00003.safetensors",
431
+ "model.layers.34.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
432
+ "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
433
+ "model.layers.34.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
434
+ "model.layers.34.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
435
+ "model.layers.35.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
436
+ "model.layers.35.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
437
+ "model.layers.35.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
438
+ "model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
439
+ "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
440
+ "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
441
+ "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
442
+ "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
443
+ "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
444
+ "model.layers.35.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
445
+ "model.layers.35.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
446
+ "model.layers.36.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
447
+ "model.layers.36.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
448
+ "model.layers.36.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
449
+ "model.layers.36.input_layernorm.weight": "model-00003-of-00003.safetensors",
450
+ "model.layers.36.mamba.A_log": "model-00003-of-00003.safetensors",
451
+ "model.layers.36.mamba.D": "model-00003-of-00003.safetensors",
452
+ "model.layers.36.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
453
+ "model.layers.36.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
454
+ "model.layers.36.mamba.dt_bias": "model-00003-of-00003.safetensors",
455
+ "model.layers.36.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
456
+ "model.layers.36.mamba.norm.weight": "model-00003-of-00003.safetensors",
457
+ "model.layers.36.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
458
+ "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
459
+ "model.layers.36.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
460
+ "model.layers.36.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
461
+ "model.layers.37.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
462
+ "model.layers.37.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
463
+ "model.layers.37.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
464
+ "model.layers.37.input_layernorm.weight": "model-00003-of-00003.safetensors",
465
+ "model.layers.37.mamba.A_log": "model-00003-of-00003.safetensors",
466
+ "model.layers.37.mamba.D": "model-00003-of-00003.safetensors",
467
+ "model.layers.37.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
468
+ "model.layers.37.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
469
+ "model.layers.37.mamba.dt_bias": "model-00003-of-00003.safetensors",
470
+ "model.layers.37.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
471
+ "model.layers.37.mamba.norm.weight": "model-00003-of-00003.safetensors",
472
+ "model.layers.37.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
473
+ "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
474
+ "model.layers.37.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
475
+ "model.layers.37.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
476
+ "model.layers.38.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
477
+ "model.layers.38.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
478
+ "model.layers.38.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
479
+ "model.layers.38.input_layernorm.weight": "model-00003-of-00003.safetensors",
480
+ "model.layers.38.mamba.A_log": "model-00003-of-00003.safetensors",
481
+ "model.layers.38.mamba.D": "model-00003-of-00003.safetensors",
482
+ "model.layers.38.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
483
+ "model.layers.38.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
484
+ "model.layers.38.mamba.dt_bias": "model-00003-of-00003.safetensors",
485
+ "model.layers.38.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
486
+ "model.layers.38.mamba.norm.weight": "model-00003-of-00003.safetensors",
487
+ "model.layers.38.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
488
+ "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
489
+ "model.layers.38.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
490
+ "model.layers.38.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
491
+ "model.layers.39.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
492
+ "model.layers.39.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
493
+ "model.layers.39.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
494
+ "model.layers.39.input_layernorm.weight": "model-00003-of-00003.safetensors",
495
+ "model.layers.39.mamba.A_log": "model-00003-of-00003.safetensors",
496
+ "model.layers.39.mamba.D": "model-00003-of-00003.safetensors",
497
+ "model.layers.39.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
498
+ "model.layers.39.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
499
+ "model.layers.39.mamba.dt_bias": "model-00003-of-00003.safetensors",
500
+ "model.layers.39.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
501
+ "model.layers.39.mamba.norm.weight": "model-00003-of-00003.safetensors",
502
+ "model.layers.39.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
503
+ "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
504
+ "model.layers.39.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
505
+ "model.layers.39.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
506
+ "model.layers.4.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
507
+ "model.layers.4.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
508
+ "model.layers.4.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
509
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
510
+ "model.layers.4.mamba.A_log": "model-00001-of-00003.safetensors",
511
+ "model.layers.4.mamba.D": "model-00001-of-00003.safetensors",
512
+ "model.layers.4.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
513
+ "model.layers.4.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
514
+ "model.layers.4.mamba.dt_bias": "model-00001-of-00003.safetensors",
515
+ "model.layers.4.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
516
+ "model.layers.4.mamba.norm.weight": "model-00001-of-00003.safetensors",
517
+ "model.layers.4.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
518
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
519
+ "model.layers.4.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
520
+ "model.layers.4.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
521
+ "model.layers.5.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
522
+ "model.layers.5.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
523
+ "model.layers.5.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
524
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
525
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
526
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
527
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
528
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
529
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
530
+ "model.layers.5.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
531
+ "model.layers.5.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
532
+ "model.layers.6.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
533
+ "model.layers.6.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
534
+ "model.layers.6.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
535
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
536
+ "model.layers.6.mamba.A_log": "model-00001-of-00003.safetensors",
537
+ "model.layers.6.mamba.D": "model-00001-of-00003.safetensors",
538
+ "model.layers.6.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
539
+ "model.layers.6.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
540
+ "model.layers.6.mamba.dt_bias": "model-00001-of-00003.safetensors",
541
+ "model.layers.6.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
542
+ "model.layers.6.mamba.norm.weight": "model-00001-of-00003.safetensors",
543
+ "model.layers.6.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
544
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
545
+ "model.layers.6.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
546
+ "model.layers.6.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
547
+ "model.layers.7.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
548
+ "model.layers.7.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
549
+ "model.layers.7.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
550
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
551
+ "model.layers.7.mamba.A_log": "model-00001-of-00003.safetensors",
552
+ "model.layers.7.mamba.D": "model-00001-of-00003.safetensors",
553
+ "model.layers.7.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
554
+ "model.layers.7.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
555
+ "model.layers.7.mamba.dt_bias": "model-00001-of-00003.safetensors",
556
+ "model.layers.7.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
557
+ "model.layers.7.mamba.norm.weight": "model-00001-of-00003.safetensors",
558
+ "model.layers.7.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
559
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
560
+ "model.layers.7.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
561
+ "model.layers.7.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
562
+ "model.layers.8.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
563
+ "model.layers.8.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
564
+ "model.layers.8.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
565
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
566
+ "model.layers.8.mamba.A_log": "model-00001-of-00003.safetensors",
567
+ "model.layers.8.mamba.D": "model-00001-of-00003.safetensors",
568
+ "model.layers.8.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
569
+ "model.layers.8.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
570
+ "model.layers.8.mamba.dt_bias": "model-00001-of-00003.safetensors",
571
+ "model.layers.8.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
572
+ "model.layers.8.mamba.norm.weight": "model-00001-of-00003.safetensors",
573
+ "model.layers.8.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
574
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
575
+ "model.layers.8.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
576
+ "model.layers.8.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
577
+ "model.layers.9.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
578
+ "model.layers.9.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
579
+ "model.layers.9.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
580
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
581
+ "model.layers.9.mamba.A_log": "model-00001-of-00003.safetensors",
582
+ "model.layers.9.mamba.D": "model-00001-of-00003.safetensors",
583
+ "model.layers.9.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
584
+ "model.layers.9.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
585
+ "model.layers.9.mamba.dt_bias": "model-00001-of-00003.safetensors",
586
+ "model.layers.9.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
587
+ "model.layers.9.mamba.norm.weight": "model-00001-of-00003.safetensors",
588
+ "model.layers.9.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
589
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
590
+ "model.layers.9.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
591
+ "model.layers.9.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
592
+ "model.norm.weight": "model-00003-of-00003.safetensors"
593
+ }
594
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|end_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|pad|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|unk|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,783 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "100256": {
6
+ "content": "<|pad|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "100257": {
14
+ "content": "<|end_of_text|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "100258": {
22
+ "content": "<|fim_prefix|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "100259": {
30
+ "content": "<|fim_middle|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": false
36
+ },
37
+ "100260": {
38
+ "content": "<|fim_suffix|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "100261": {
46
+ "content": "<|fim_pad|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "100262": {
54
+ "content": "<|filename|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "100263": {
62
+ "content": "<|reponame|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": false
68
+ },
69
+ "100264": {
70
+ "content": "<|start_of_role|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "100265": {
78
+ "content": "<|end_of_role|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "100266": {
86
+ "content": "<|unused_1|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "100267": {
94
+ "content": "<|start_of_plugin|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "100268": {
102
+ "content": "<|end_of_plugin|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "100269": {
110
+ "content": "<|unk|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "100270": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "100271": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "100272": {
134
+ "content": "<tool_response>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "100273": {
142
+ "content": "</tool_response>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "100274": {
150
+ "content": "<think>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "100275": {
158
+ "content": "</think>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "100276": {
166
+ "content": "<think_on>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "100277": {
174
+ "content": "<think_off>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "100278": {
182
+ "content": "<schema>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "100279": {
190
+ "content": "</schema>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "100280": {
198
+ "content": "<tools>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "100281": {
206
+ "content": "</tools>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "100282": {
214
+ "content": "<documents>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "100283": {
222
+ "content": "</documents>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "100284": {
230
+ "content": "<|unused_15|>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "100285": {
238
+ "content": "<|unused_16|>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "100286": {
246
+ "content": "<|unused_17|>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "100287": {
254
+ "content": "<|unused_18|>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "100288": {
262
+ "content": "<|unused_19|>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "100289": {
270
+ "content": "<|unused_20|>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "100290": {
278
+ "content": "<|unused_21|>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "100291": {
286
+ "content": "<|unused_22|>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "100292": {
294
+ "content": "<|unused_23|>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "100293": {
302
+ "content": "<|unused_24|>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "100294": {
310
+ "content": "<|unused_25|>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "100295": {
318
+ "content": "<|unused_26|>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "100296": {
326
+ "content": "<|unused_27|>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": true
332
+ },
333
+ "100297": {
334
+ "content": "<|unused_28|>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": true
340
+ },
341
+ "100298": {
342
+ "content": "<|unused_29|>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": true
348
+ },
349
+ "100299": {
350
+ "content": "<|unused_30|>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": true
356
+ },
357
+ "100300": {
358
+ "content": "<|unused_31|>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": true
364
+ },
365
+ "100301": {
366
+ "content": "<|unused_32|>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": true
372
+ },
373
+ "100302": {
374
+ "content": "<|unused_33|>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": true
380
+ },
381
+ "100303": {
382
+ "content": "<|unused_34|>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": true
388
+ },
389
+ "100304": {
390
+ "content": "<|unused_35|>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": true
396
+ },
397
+ "100305": {
398
+ "content": "<|unused_36|>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": true
404
+ },
405
+ "100306": {
406
+ "content": "<|unused_37|>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": true
412
+ },
413
+ "100307": {
414
+ "content": "<|unused_38|>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": true
420
+ },
421
+ "100308": {
422
+ "content": "<|unused_39|>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": true
428
+ },
429
+ "100309": {
430
+ "content": "<|unused_40|>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": true
436
+ },
437
+ "100310": {
438
+ "content": "<|unused_41|>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": true
444
+ },
445
+ "100311": {
446
+ "content": "<|unused_42|>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": true
452
+ },
453
+ "100312": {
454
+ "content": "<|unused_43|>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": true
460
+ },
461
+ "100313": {
462
+ "content": "<|unused_44|>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": true
468
+ },
469
+ "100314": {
470
+ "content": "<|unused_45|>",
471
+ "lstrip": false,
472
+ "normalized": false,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": true
476
+ },
477
+ "100315": {
478
+ "content": "<|unused_46|>",
479
+ "lstrip": false,
480
+ "normalized": false,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": true
484
+ },
485
+ "100316": {
486
+ "content": "<|unused_47|>",
487
+ "lstrip": false,
488
+ "normalized": false,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": true
492
+ },
493
+ "100317": {
494
+ "content": "<|unused_48|>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": true
500
+ },
501
+ "100318": {
502
+ "content": "<|unused_49|>",
503
+ "lstrip": false,
504
+ "normalized": false,
505
+ "rstrip": false,
506
+ "single_word": false,
507
+ "special": true
508
+ },
509
+ "100319": {
510
+ "content": "<|unused_50|>",
511
+ "lstrip": false,
512
+ "normalized": false,
513
+ "rstrip": false,
514
+ "single_word": false,
515
+ "special": true
516
+ },
517
+ "100320": {
518
+ "content": "<|unused_51|>",
519
+ "lstrip": false,
520
+ "normalized": false,
521
+ "rstrip": false,
522
+ "single_word": false,
523
+ "special": true
524
+ },
525
+ "100321": {
526
+ "content": "<|unused_52|>",
527
+ "lstrip": false,
528
+ "normalized": false,
529
+ "rstrip": false,
530
+ "single_word": false,
531
+ "special": true
532
+ },
533
+ "100322": {
534
+ "content": "<|unused_53|>",
535
+ "lstrip": false,
536
+ "normalized": false,
537
+ "rstrip": false,
538
+ "single_word": false,
539
+ "special": true
540
+ },
541
+ "100323": {
542
+ "content": "<|unused_54|>",
543
+ "lstrip": false,
544
+ "normalized": false,
545
+ "rstrip": false,
546
+ "single_word": false,
547
+ "special": true
548
+ },
549
+ "100324": {
550
+ "content": "<|unused_55|>",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false,
555
+ "special": true
556
+ },
557
+ "100325": {
558
+ "content": "<|unused_56|>",
559
+ "lstrip": false,
560
+ "normalized": false,
561
+ "rstrip": false,
562
+ "single_word": false,
563
+ "special": true
564
+ },
565
+ "100326": {
566
+ "content": "<|unused_57|>",
567
+ "lstrip": false,
568
+ "normalized": false,
569
+ "rstrip": false,
570
+ "single_word": false,
571
+ "special": true
572
+ },
573
+ "100327": {
574
+ "content": "<|unused_58|>",
575
+ "lstrip": false,
576
+ "normalized": false,
577
+ "rstrip": false,
578
+ "single_word": false,
579
+ "special": true
580
+ },
581
+ "100328": {
582
+ "content": "<|unused_59|>",
583
+ "lstrip": false,
584
+ "normalized": false,
585
+ "rstrip": false,
586
+ "single_word": false,
587
+ "special": true
588
+ },
589
+ "100329": {
590
+ "content": "<|unused_60|>",
591
+ "lstrip": false,
592
+ "normalized": false,
593
+ "rstrip": false,
594
+ "single_word": false,
595
+ "special": true
596
+ },
597
+ "100330": {
598
+ "content": "<|unused_61|>",
599
+ "lstrip": false,
600
+ "normalized": false,
601
+ "rstrip": false,
602
+ "single_word": false,
603
+ "special": true
604
+ },
605
+ "100331": {
606
+ "content": "<|unused_62|>",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false,
611
+ "special": true
612
+ },
613
+ "100332": {
614
+ "content": "<|unused_63|>",
615
+ "lstrip": false,
616
+ "normalized": false,
617
+ "rstrip": false,
618
+ "single_word": false,
619
+ "special": true
620
+ },
621
+ "100333": {
622
+ "content": "<|unused_64|>",
623
+ "lstrip": false,
624
+ "normalized": false,
625
+ "rstrip": false,
626
+ "single_word": false,
627
+ "special": true
628
+ },
629
+ "100334": {
630
+ "content": "<|unused_65|>",
631
+ "lstrip": false,
632
+ "normalized": false,
633
+ "rstrip": false,
634
+ "single_word": false,
635
+ "special": true
636
+ },
637
+ "100335": {
638
+ "content": "<|unused_66|>",
639
+ "lstrip": false,
640
+ "normalized": false,
641
+ "rstrip": false,
642
+ "single_word": false,
643
+ "special": true
644
+ },
645
+ "100336": {
646
+ "content": "<|unused_67|>",
647
+ "lstrip": false,
648
+ "normalized": false,
649
+ "rstrip": false,
650
+ "single_word": false,
651
+ "special": true
652
+ },
653
+ "100337": {
654
+ "content": "<|unused_68|>",
655
+ "lstrip": false,
656
+ "normalized": false,
657
+ "rstrip": false,
658
+ "single_word": false,
659
+ "special": true
660
+ },
661
+ "100338": {
662
+ "content": "<|unused_69|>",
663
+ "lstrip": false,
664
+ "normalized": false,
665
+ "rstrip": false,
666
+ "single_word": false,
667
+ "special": true
668
+ },
669
+ "100339": {
670
+ "content": "<|unused_70|>",
671
+ "lstrip": false,
672
+ "normalized": false,
673
+ "rstrip": false,
674
+ "single_word": false,
675
+ "special": true
676
+ },
677
+ "100340": {
678
+ "content": "<|unused_71|>",
679
+ "lstrip": false,
680
+ "normalized": false,
681
+ "rstrip": false,
682
+ "single_word": false,
683
+ "special": true
684
+ },
685
+ "100341": {
686
+ "content": "<|unused_72|>",
687
+ "lstrip": false,
688
+ "normalized": false,
689
+ "rstrip": false,
690
+ "single_word": false,
691
+ "special": true
692
+ },
693
+ "100342": {
694
+ "content": "<|unused_73|>",
695
+ "lstrip": false,
696
+ "normalized": false,
697
+ "rstrip": false,
698
+ "single_word": false,
699
+ "special": true
700
+ },
701
+ "100343": {
702
+ "content": "<|unused_74|>",
703
+ "lstrip": false,
704
+ "normalized": false,
705
+ "rstrip": false,
706
+ "single_word": false,
707
+ "special": true
708
+ },
709
+ "100344": {
710
+ "content": "<|unused_75|>",
711
+ "lstrip": false,
712
+ "normalized": false,
713
+ "rstrip": false,
714
+ "single_word": false,
715
+ "special": true
716
+ },
717
+ "100345": {
718
+ "content": "<|unused_76|>",
719
+ "lstrip": false,
720
+ "normalized": false,
721
+ "rstrip": false,
722
+ "single_word": false,
723
+ "special": true
724
+ },
725
+ "100346": {
726
+ "content": "<|unused_77|>",
727
+ "lstrip": false,
728
+ "normalized": false,
729
+ "rstrip": false,
730
+ "single_word": false,
731
+ "special": true
732
+ },
733
+ "100347": {
734
+ "content": "<|unused_78|>",
735
+ "lstrip": false,
736
+ "normalized": false,
737
+ "rstrip": false,
738
+ "single_word": false,
739
+ "special": true
740
+ },
741
+ "100348": {
742
+ "content": "<|unused_79|>",
743
+ "lstrip": false,
744
+ "normalized": false,
745
+ "rstrip": false,
746
+ "single_word": false,
747
+ "special": true
748
+ },
749
+ "100349": {
750
+ "content": "<|unused_80|>",
751
+ "lstrip": false,
752
+ "normalized": false,
753
+ "rstrip": false,
754
+ "single_word": false,
755
+ "special": true
756
+ },
757
+ "100350": {
758
+ "content": "<|unused_81|>",
759
+ "lstrip": false,
760
+ "normalized": false,
761
+ "rstrip": false,
762
+ "single_word": false,
763
+ "special": true
764
+ },
765
+ "100351": {
766
+ "content": "<|unused_82|>",
767
+ "lstrip": false,
768
+ "normalized": false,
769
+ "rstrip": false,
770
+ "single_word": false,
771
+ "special": true
772
+ }
773
+ },
774
+ "bos_token": "<|end_of_text|>",
775
+ "clean_up_tokenization_spaces": false,
776
+ "eos_token": "<|end_of_text|>",
777
+ "extra_special_tokens": {},
778
+ "model_max_length": 131072,
779
+ "pad_token": "<|pad|>",
780
+ "padding_side": "left",
781
+ "tokenizer_class": "GPT2Tokenizer",
782
+ "unk_token": "<|unk|>"
783
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff