slimfrikha-tii
commited on
Commit
•
3abb65b
0
Parent(s):
falcon3 release
Browse files- .gitattributes +35 -0
- README.md +217 -0
- config.json +35 -0
- generation_config.json +10 -0
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +650 -0
- special_tokens_map.json +36 -0
- tokenizer.json +0 -0
- tokenizer_config.json +130 -0
.gitattributes
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,217 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
tags:
|
5 |
+
- falcon3
|
6 |
+
- falcon3_mamba
|
7 |
+
- falcon_mamba
|
8 |
+
base_model:
|
9 |
+
- tiiuae/Falcon3-Mamba-7B-Base
|
10 |
+
---
|
11 |
+
|
12 |
+
# Falcon3-Mamba-7B-Instruct
|
13 |
+
|
14 |
+
**Falcon3** family of Open Foundation Models is a set of pretrained and instruct LLMs ranging from 1B to 10B.
|
15 |
+
|
16 |
+
This repository contains the **Falcon3-Mamba-7B-Instruct**. It achieves, compared to similar SSM-based models of the same size, state of art results (at release's time) on reasoning, language understanding, instruction following, code and mathematics tasks.
|
17 |
+
Falcon3-Mamba-7B-Instruct supports a context length up to 32K and was mainly trained on english corpus.
|
18 |
+
|
19 |
+
## Model Details
|
20 |
+
- Architecture (same as [Falcon-Mamba-7b](https://huggingface.co/tiiuae/falcon-mamba-7b))
|
21 |
+
- Mamba1 based causal decoder only architecture trained on a causal language modeling task (i.e., predict the next token).
|
22 |
+
- 64 decoder blocks
|
23 |
+
- width: 4096
|
24 |
+
- state_size: 16
|
25 |
+
- 32k context length
|
26 |
+
- 65k vocab size
|
27 |
+
- Continue Pretrained from [Falcon Mamba 7B](https://huggingface.co/tiiuae/falcon-mamba-7b), with another 1500 Gigatokens of data comprising of web, code, STEM and high quality data.
|
28 |
+
- Postrained on 1.2 million samples of STEM, conversations, code, and safety.
|
29 |
+
- Developed by [Technology Innovation Institute](https://www.tii.ae)
|
30 |
+
- License: TII Falcon-LLM License 2.0
|
31 |
+
- Model Release Date: December 2024
|
32 |
+
|
33 |
+
|
34 |
+
## Getting started
|
35 |
+
|
36 |
+
<details>
|
37 |
+
<summary> Click to expand </summary>
|
38 |
+
|
39 |
+
```python
|
40 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
41 |
+
|
42 |
+
|
43 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
44 |
+
|
45 |
+
model_name = "tiiuae/Falcon3-Mamba-7B-Instruct"
|
46 |
+
|
47 |
+
model = AutoModelForCausalLM.from_pretrained(
|
48 |
+
model_name,
|
49 |
+
torch_dtype="auto",
|
50 |
+
device_map="auto"
|
51 |
+
)
|
52 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
53 |
+
|
54 |
+
prompt = "How many hours in one day?"
|
55 |
+
messages = [
|
56 |
+
{"role": "system", "content": "You are a helpful friendly assistant Falcon3 from TII, try to follow instructions as much as possible."},
|
57 |
+
{"role": "user", "content": prompt}
|
58 |
+
]
|
59 |
+
text = tokenizer.apply_chat_template(
|
60 |
+
messages,
|
61 |
+
tokenize=False,
|
62 |
+
add_generation_prompt=True
|
63 |
+
)
|
64 |
+
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
65 |
+
|
66 |
+
generated_ids = model.generate(
|
67 |
+
**model_inputs,
|
68 |
+
max_new_tokens=1024
|
69 |
+
)
|
70 |
+
generated_ids = [
|
71 |
+
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
|
72 |
+
]
|
73 |
+
|
74 |
+
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
75 |
+
print(response)
|
76 |
+
```
|
77 |
+
|
78 |
+
</details>
|
79 |
+
|
80 |
+
<br>
|
81 |
+
|
82 |
+
# Benchmarks
|
83 |
+
We report in the following table our internal pipeline benchmarks. For the benchmarks marked by star, we normalize the results with HuggingFace score normalization:
|
84 |
+
|
85 |
+
<table border="1" style="width: 100%; text-align: center; border-collapse: collapse;">
|
86 |
+
<colgroup>
|
87 |
+
<col style="width: 10%;">
|
88 |
+
<col style="width: 10%;">
|
89 |
+
<col style="width: 7%;">
|
90 |
+
<col style="width: 7%;">
|
91 |
+
<col style="width: 7%;">
|
92 |
+
<col style="background-color: rgba(80, 15, 213, 0.5); width: 7%;">
|
93 |
+
</colgroup>
|
94 |
+
<thead>
|
95 |
+
<tr>
|
96 |
+
<th>Category</th>
|
97 |
+
<th>Benchmark</th>
|
98 |
+
<th>Zamba2-7B-instruct</th>
|
99 |
+
<th>Jamba-1.5-Mini</th>
|
100 |
+
<th>Llama-3.1-8B-Instruct</th>
|
101 |
+
<th>Falcon3-Mamba-7B-Instruct</th>
|
102 |
+
</tr>
|
103 |
+
</thead>
|
104 |
+
<tbody>
|
105 |
+
<tr>
|
106 |
+
<td rowspan="3">General</td>
|
107 |
+
<td>MMLU (5-shot)</td>
|
108 |
+
<td>-</td>
|
109 |
+
<td>68.7%</td>
|
110 |
+
<td>55.9%</td>
|
111 |
+
<td>65.3%</td>
|
112 |
+
</tr>
|
113 |
+
<tr>
|
114 |
+
<td>MMLU-PRO (5-shot)*</td>
|
115 |
+
<td>32.4%</td>
|
116 |
+
<td>31.6%</td>
|
117 |
+
<td>21.8%</td>
|
118 |
+
<td>26.3%</td>
|
119 |
+
</tr>
|
120 |
+
<tr>
|
121 |
+
<td>IFEval</td>
|
122 |
+
<td>69.9%</td>
|
123 |
+
<td>65.7%</td>
|
124 |
+
<td>78.8%</td>
|
125 |
+
<td>71.7%</td>
|
126 |
+
</tr>
|
127 |
+
<tr>
|
128 |
+
<td rowspan="2">Math</td>
|
129 |
+
<td>GSM8K (5-shot)</td>
|
130 |
+
<td>-</td>
|
131 |
+
<td>74.9%</td>
|
132 |
+
<td>19.2%</td>
|
133 |
+
<td>65.2%</td>
|
134 |
+
</tr>
|
135 |
+
<tr>
|
136 |
+
<td>MATH Lvl-5 (4-shot)</td>
|
137 |
+
<td>-</td>
|
138 |
+
<td>6.9%</td>
|
139 |
+
<td>10.4%</td>
|
140 |
+
<td>27.3%</td>
|
141 |
+
</tr>
|
142 |
+
<tr>
|
143 |
+
<td rowspan="4">Reasoning</td>
|
144 |
+
<td>Arc Challenge (25-shot)</td>
|
145 |
+
<td>-</td>
|
146 |
+
<td>54.3%</td>
|
147 |
+
<td>46.6%</td>
|
148 |
+
<td>53.7%</td>
|
149 |
+
</tr>
|
150 |
+
<tr>
|
151 |
+
<td>GPQA (0-shot)*</td>
|
152 |
+
<td>10.3%</td>
|
153 |
+
<td>11.1%</td>
|
154 |
+
<td>33.6%</td>
|
155 |
+
<td>7.2%</td>
|
156 |
+
</tr>
|
157 |
+
<tr>
|
158 |
+
<td>MUSR (0-shot)*</td>
|
159 |
+
<td>8.2%</td>
|
160 |
+
<td>12.2%</td>
|
161 |
+
<td>38.6%</td>
|
162 |
+
<td>8.3%</td>
|
163 |
+
</tr>
|
164 |
+
<tr>
|
165 |
+
<td>BBH (3-shot)*</td>
|
166 |
+
<td>33.3%</td>
|
167 |
+
<td>35.3%</td>
|
168 |
+
<td>43.7%</td>
|
169 |
+
<td>25.2%</td>
|
170 |
+
</tr>
|
171 |
+
<tr>
|
172 |
+
<td rowspan="4">CommonSense Understanding</td>
|
173 |
+
<td>PIQA (0-shot)</td>
|
174 |
+
<td>-</td>
|
175 |
+
<td>82.3%</td>
|
176 |
+
<td>78.9%</td>
|
177 |
+
<td>80.9%</td>
|
178 |
+
</tr>
|
179 |
+
<tr>
|
180 |
+
<td>SciQ (0-shot)</td>
|
181 |
+
<td>-</td>
|
182 |
+
<td>94.9%</td>
|
183 |
+
<td>80.2%</td>
|
184 |
+
<td>93.6%</td>
|
185 |
+
</tr>
|
186 |
+
<tr>
|
187 |
+
<td>Winogrande (0-shot)</td>
|
188 |
+
<td>-</td>
|
189 |
+
<td>64.5%</td>
|
190 |
+
<td>-</td>
|
191 |
+
<td>-</td>
|
192 |
+
</tr>
|
193 |
+
<tr>
|
194 |
+
<td>OpenbookQA (0-shot)</td>
|
195 |
+
<td>-</td>
|
196 |
+
<td>34.6%</td>
|
197 |
+
<td>46.2%</td>
|
198 |
+
<td>47.2%</td>
|
199 |
+
</tr>
|
200 |
+
</tbody>
|
201 |
+
</table>
|
202 |
+
|
203 |
+
## Useful links
|
204 |
+
- View our [release blogpost](https://huggingface.co/blog/falcon3).
|
205 |
+
- Feel free to join [our discord server](https://discord.gg/fwXpMyGc) if you have any questions or to interact with our researchers and developers.
|
206 |
+
|
207 |
+
## Citation
|
208 |
+
If the Falcon3 family of models were helpful to your work, feel free to give us a cite.
|
209 |
+
|
210 |
+
```
|
211 |
+
@misc{Falcon3,
|
212 |
+
title = {The Falcon 3 Family of Open Models},
|
213 |
+
author = {Falcon-LLM Team},
|
214 |
+
month = {December},
|
215 |
+
year = {2024}
|
216 |
+
}
|
217 |
+
```
|
config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"FalconMambaForCausalLM"
|
4 |
+
],
|
5 |
+
"bos_token_id": 0,
|
6 |
+
"conv_kernel": 4,
|
7 |
+
"eos_token_id": 0,
|
8 |
+
"expand": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"initializer_range": 0.1,
|
12 |
+
"intermediate_size": 8192,
|
13 |
+
"layer_norm_epsilon": 1e-05,
|
14 |
+
"mixer_rms_eps": 1e-05,
|
15 |
+
"model_type": "falcon_mamba",
|
16 |
+
"num_hidden_layers": 64,
|
17 |
+
"pad_token_id": 0,
|
18 |
+
"rescale_prenorm_residual": false,
|
19 |
+
"residual_in_fp32": true,
|
20 |
+
"state_size": 16,
|
21 |
+
"tie_word_embeddings": false,
|
22 |
+
"time_step_floor": 0.0001,
|
23 |
+
"time_step_init_scheme": "random",
|
24 |
+
"time_step_max": 0.1,
|
25 |
+
"time_step_min": 0.001,
|
26 |
+
"time_step_rank": 256,
|
27 |
+
"time_step_scale": 1.0,
|
28 |
+
"torch_dtype": "bfloat16",
|
29 |
+
"transformers_version": "4.47.0",
|
30 |
+
"use_bias": false,
|
31 |
+
"use_cache": true,
|
32 |
+
"use_conv_bias": true,
|
33 |
+
"use_mambapy": false,
|
34 |
+
"vocab_size": 65024
|
35 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": [
|
5 |
+
10,
|
6 |
+
11
|
7 |
+
],
|
8 |
+
"pad_token_id": 0,
|
9 |
+
"transformers_version": "4.47.0"
|
10 |
+
}
|
model-00001-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:500dd14977bed48ef9d9221a781e1555b7da7d31a48cf128fc469767c7f87260
|
3 |
+
size 4956184024
|
model-00002-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33c6def23cf1f3f85791838409fda5e8a29fc1cb564071f0a795fa2378266825
|
3 |
+
size 4987536920
|
model-00003-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b7f1f26946f4aee515a476d51d829760862f2380da88b99e7d99313d2628606
|
3 |
+
size 4601680888
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,650 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 14545330176
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"backbone.embeddings.weight": "model-00001-of-00003.safetensors",
|
7 |
+
"backbone.layers.0.mixer.A_log": "model-00001-of-00003.safetensors",
|
8 |
+
"backbone.layers.0.mixer.D": "model-00001-of-00003.safetensors",
|
9 |
+
"backbone.layers.0.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
10 |
+
"backbone.layers.0.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
11 |
+
"backbone.layers.0.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
12 |
+
"backbone.layers.0.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
13 |
+
"backbone.layers.0.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
14 |
+
"backbone.layers.0.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
15 |
+
"backbone.layers.0.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
16 |
+
"backbone.layers.0.norm.weight": "model-00001-of-00003.safetensors",
|
17 |
+
"backbone.layers.1.mixer.A_log": "model-00001-of-00003.safetensors",
|
18 |
+
"backbone.layers.1.mixer.D": "model-00001-of-00003.safetensors",
|
19 |
+
"backbone.layers.1.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
20 |
+
"backbone.layers.1.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
21 |
+
"backbone.layers.1.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
22 |
+
"backbone.layers.1.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
23 |
+
"backbone.layers.1.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
24 |
+
"backbone.layers.1.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
25 |
+
"backbone.layers.1.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
26 |
+
"backbone.layers.1.norm.weight": "model-00001-of-00003.safetensors",
|
27 |
+
"backbone.layers.10.mixer.A_log": "model-00001-of-00003.safetensors",
|
28 |
+
"backbone.layers.10.mixer.D": "model-00001-of-00003.safetensors",
|
29 |
+
"backbone.layers.10.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
30 |
+
"backbone.layers.10.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
31 |
+
"backbone.layers.10.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
32 |
+
"backbone.layers.10.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
33 |
+
"backbone.layers.10.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
34 |
+
"backbone.layers.10.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
35 |
+
"backbone.layers.10.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
36 |
+
"backbone.layers.10.norm.weight": "model-00001-of-00003.safetensors",
|
37 |
+
"backbone.layers.11.mixer.A_log": "model-00001-of-00003.safetensors",
|
38 |
+
"backbone.layers.11.mixer.D": "model-00001-of-00003.safetensors",
|
39 |
+
"backbone.layers.11.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
40 |
+
"backbone.layers.11.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
41 |
+
"backbone.layers.11.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
42 |
+
"backbone.layers.11.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
43 |
+
"backbone.layers.11.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
44 |
+
"backbone.layers.11.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
45 |
+
"backbone.layers.11.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
46 |
+
"backbone.layers.11.norm.weight": "model-00001-of-00003.safetensors",
|
47 |
+
"backbone.layers.12.mixer.A_log": "model-00001-of-00003.safetensors",
|
48 |
+
"backbone.layers.12.mixer.D": "model-00001-of-00003.safetensors",
|
49 |
+
"backbone.layers.12.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
50 |
+
"backbone.layers.12.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
51 |
+
"backbone.layers.12.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
52 |
+
"backbone.layers.12.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
53 |
+
"backbone.layers.12.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
54 |
+
"backbone.layers.12.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
55 |
+
"backbone.layers.12.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
56 |
+
"backbone.layers.12.norm.weight": "model-00001-of-00003.safetensors",
|
57 |
+
"backbone.layers.13.mixer.A_log": "model-00001-of-00003.safetensors",
|
58 |
+
"backbone.layers.13.mixer.D": "model-00001-of-00003.safetensors",
|
59 |
+
"backbone.layers.13.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
60 |
+
"backbone.layers.13.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
61 |
+
"backbone.layers.13.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
62 |
+
"backbone.layers.13.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
63 |
+
"backbone.layers.13.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
64 |
+
"backbone.layers.13.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
65 |
+
"backbone.layers.13.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
66 |
+
"backbone.layers.13.norm.weight": "model-00001-of-00003.safetensors",
|
67 |
+
"backbone.layers.14.mixer.A_log": "model-00001-of-00003.safetensors",
|
68 |
+
"backbone.layers.14.mixer.D": "model-00001-of-00003.safetensors",
|
69 |
+
"backbone.layers.14.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
70 |
+
"backbone.layers.14.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
71 |
+
"backbone.layers.14.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
72 |
+
"backbone.layers.14.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
73 |
+
"backbone.layers.14.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
74 |
+
"backbone.layers.14.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
75 |
+
"backbone.layers.14.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
76 |
+
"backbone.layers.14.norm.weight": "model-00001-of-00003.safetensors",
|
77 |
+
"backbone.layers.15.mixer.A_log": "model-00001-of-00003.safetensors",
|
78 |
+
"backbone.layers.15.mixer.D": "model-00001-of-00003.safetensors",
|
79 |
+
"backbone.layers.15.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
80 |
+
"backbone.layers.15.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
81 |
+
"backbone.layers.15.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
82 |
+
"backbone.layers.15.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
83 |
+
"backbone.layers.15.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
84 |
+
"backbone.layers.15.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
85 |
+
"backbone.layers.15.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
86 |
+
"backbone.layers.15.norm.weight": "model-00001-of-00003.safetensors",
|
87 |
+
"backbone.layers.16.mixer.A_log": "model-00001-of-00003.safetensors",
|
88 |
+
"backbone.layers.16.mixer.D": "model-00001-of-00003.safetensors",
|
89 |
+
"backbone.layers.16.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
90 |
+
"backbone.layers.16.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
91 |
+
"backbone.layers.16.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
92 |
+
"backbone.layers.16.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
93 |
+
"backbone.layers.16.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
94 |
+
"backbone.layers.16.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
95 |
+
"backbone.layers.16.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
96 |
+
"backbone.layers.16.norm.weight": "model-00001-of-00003.safetensors",
|
97 |
+
"backbone.layers.17.mixer.A_log": "model-00001-of-00003.safetensors",
|
98 |
+
"backbone.layers.17.mixer.D": "model-00001-of-00003.safetensors",
|
99 |
+
"backbone.layers.17.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
100 |
+
"backbone.layers.17.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
101 |
+
"backbone.layers.17.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
102 |
+
"backbone.layers.17.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
103 |
+
"backbone.layers.17.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
104 |
+
"backbone.layers.17.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
105 |
+
"backbone.layers.17.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
106 |
+
"backbone.layers.17.norm.weight": "model-00001-of-00003.safetensors",
|
107 |
+
"backbone.layers.18.mixer.A_log": "model-00001-of-00003.safetensors",
|
108 |
+
"backbone.layers.18.mixer.D": "model-00001-of-00003.safetensors",
|
109 |
+
"backbone.layers.18.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
110 |
+
"backbone.layers.18.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
111 |
+
"backbone.layers.18.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
112 |
+
"backbone.layers.18.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
113 |
+
"backbone.layers.18.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
114 |
+
"backbone.layers.18.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
115 |
+
"backbone.layers.18.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
116 |
+
"backbone.layers.18.norm.weight": "model-00001-of-00003.safetensors",
|
117 |
+
"backbone.layers.19.mixer.A_log": "model-00001-of-00003.safetensors",
|
118 |
+
"backbone.layers.19.mixer.D": "model-00001-of-00003.safetensors",
|
119 |
+
"backbone.layers.19.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
120 |
+
"backbone.layers.19.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
121 |
+
"backbone.layers.19.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
122 |
+
"backbone.layers.19.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
123 |
+
"backbone.layers.19.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
124 |
+
"backbone.layers.19.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
125 |
+
"backbone.layers.19.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
126 |
+
"backbone.layers.19.norm.weight": "model-00001-of-00003.safetensors",
|
127 |
+
"backbone.layers.2.mixer.A_log": "model-00001-of-00003.safetensors",
|
128 |
+
"backbone.layers.2.mixer.D": "model-00001-of-00003.safetensors",
|
129 |
+
"backbone.layers.2.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
130 |
+
"backbone.layers.2.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
131 |
+
"backbone.layers.2.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
132 |
+
"backbone.layers.2.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
133 |
+
"backbone.layers.2.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
134 |
+
"backbone.layers.2.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
135 |
+
"backbone.layers.2.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
136 |
+
"backbone.layers.2.norm.weight": "model-00001-of-00003.safetensors",
|
137 |
+
"backbone.layers.20.mixer.A_log": "model-00001-of-00003.safetensors",
|
138 |
+
"backbone.layers.20.mixer.D": "model-00001-of-00003.safetensors",
|
139 |
+
"backbone.layers.20.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
140 |
+
"backbone.layers.20.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
141 |
+
"backbone.layers.20.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
142 |
+
"backbone.layers.20.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
143 |
+
"backbone.layers.20.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
144 |
+
"backbone.layers.20.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
145 |
+
"backbone.layers.20.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
146 |
+
"backbone.layers.20.norm.weight": "model-00001-of-00003.safetensors",
|
147 |
+
"backbone.layers.21.mixer.A_log": "model-00001-of-00003.safetensors",
|
148 |
+
"backbone.layers.21.mixer.D": "model-00001-of-00003.safetensors",
|
149 |
+
"backbone.layers.21.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
150 |
+
"backbone.layers.21.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
151 |
+
"backbone.layers.21.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
152 |
+
"backbone.layers.21.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
153 |
+
"backbone.layers.21.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
154 |
+
"backbone.layers.21.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
155 |
+
"backbone.layers.21.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
156 |
+
"backbone.layers.21.norm.weight": "model-00001-of-00003.safetensors",
|
157 |
+
"backbone.layers.22.mixer.A_log": "model-00002-of-00003.safetensors",
|
158 |
+
"backbone.layers.22.mixer.D": "model-00002-of-00003.safetensors",
|
159 |
+
"backbone.layers.22.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
160 |
+
"backbone.layers.22.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
161 |
+
"backbone.layers.22.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
162 |
+
"backbone.layers.22.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
163 |
+
"backbone.layers.22.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
164 |
+
"backbone.layers.22.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
165 |
+
"backbone.layers.22.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
166 |
+
"backbone.layers.22.norm.weight": "model-00002-of-00003.safetensors",
|
167 |
+
"backbone.layers.23.mixer.A_log": "model-00002-of-00003.safetensors",
|
168 |
+
"backbone.layers.23.mixer.D": "model-00002-of-00003.safetensors",
|
169 |
+
"backbone.layers.23.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
170 |
+
"backbone.layers.23.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
171 |
+
"backbone.layers.23.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
172 |
+
"backbone.layers.23.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
173 |
+
"backbone.layers.23.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
174 |
+
"backbone.layers.23.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
175 |
+
"backbone.layers.23.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
176 |
+
"backbone.layers.23.norm.weight": "model-00002-of-00003.safetensors",
|
177 |
+
"backbone.layers.24.mixer.A_log": "model-00002-of-00003.safetensors",
|
178 |
+
"backbone.layers.24.mixer.D": "model-00002-of-00003.safetensors",
|
179 |
+
"backbone.layers.24.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
180 |
+
"backbone.layers.24.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
181 |
+
"backbone.layers.24.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
182 |
+
"backbone.layers.24.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
183 |
+
"backbone.layers.24.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
184 |
+
"backbone.layers.24.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
185 |
+
"backbone.layers.24.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
186 |
+
"backbone.layers.24.norm.weight": "model-00002-of-00003.safetensors",
|
187 |
+
"backbone.layers.25.mixer.A_log": "model-00002-of-00003.safetensors",
|
188 |
+
"backbone.layers.25.mixer.D": "model-00002-of-00003.safetensors",
|
189 |
+
"backbone.layers.25.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
190 |
+
"backbone.layers.25.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
191 |
+
"backbone.layers.25.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
192 |
+
"backbone.layers.25.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
193 |
+
"backbone.layers.25.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
194 |
+
"backbone.layers.25.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
195 |
+
"backbone.layers.25.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
196 |
+
"backbone.layers.25.norm.weight": "model-00002-of-00003.safetensors",
|
197 |
+
"backbone.layers.26.mixer.A_log": "model-00002-of-00003.safetensors",
|
198 |
+
"backbone.layers.26.mixer.D": "model-00002-of-00003.safetensors",
|
199 |
+
"backbone.layers.26.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
200 |
+
"backbone.layers.26.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
201 |
+
"backbone.layers.26.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
202 |
+
"backbone.layers.26.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
203 |
+
"backbone.layers.26.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
204 |
+
"backbone.layers.26.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
205 |
+
"backbone.layers.26.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
206 |
+
"backbone.layers.26.norm.weight": "model-00002-of-00003.safetensors",
|
207 |
+
"backbone.layers.27.mixer.A_log": "model-00002-of-00003.safetensors",
|
208 |
+
"backbone.layers.27.mixer.D": "model-00002-of-00003.safetensors",
|
209 |
+
"backbone.layers.27.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
210 |
+
"backbone.layers.27.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
211 |
+
"backbone.layers.27.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
212 |
+
"backbone.layers.27.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
213 |
+
"backbone.layers.27.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
214 |
+
"backbone.layers.27.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
215 |
+
"backbone.layers.27.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
216 |
+
"backbone.layers.27.norm.weight": "model-00002-of-00003.safetensors",
|
217 |
+
"backbone.layers.28.mixer.A_log": "model-00002-of-00003.safetensors",
|
218 |
+
"backbone.layers.28.mixer.D": "model-00002-of-00003.safetensors",
|
219 |
+
"backbone.layers.28.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
220 |
+
"backbone.layers.28.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
221 |
+
"backbone.layers.28.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
222 |
+
"backbone.layers.28.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
223 |
+
"backbone.layers.28.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
224 |
+
"backbone.layers.28.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
225 |
+
"backbone.layers.28.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
226 |
+
"backbone.layers.28.norm.weight": "model-00002-of-00003.safetensors",
|
227 |
+
"backbone.layers.29.mixer.A_log": "model-00002-of-00003.safetensors",
|
228 |
+
"backbone.layers.29.mixer.D": "model-00002-of-00003.safetensors",
|
229 |
+
"backbone.layers.29.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
230 |
+
"backbone.layers.29.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
231 |
+
"backbone.layers.29.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
232 |
+
"backbone.layers.29.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
233 |
+
"backbone.layers.29.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
234 |
+
"backbone.layers.29.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
235 |
+
"backbone.layers.29.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
236 |
+
"backbone.layers.29.norm.weight": "model-00002-of-00003.safetensors",
|
237 |
+
"backbone.layers.3.mixer.A_log": "model-00001-of-00003.safetensors",
|
238 |
+
"backbone.layers.3.mixer.D": "model-00001-of-00003.safetensors",
|
239 |
+
"backbone.layers.3.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
240 |
+
"backbone.layers.3.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
241 |
+
"backbone.layers.3.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
242 |
+
"backbone.layers.3.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
243 |
+
"backbone.layers.3.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
244 |
+
"backbone.layers.3.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
245 |
+
"backbone.layers.3.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
246 |
+
"backbone.layers.3.norm.weight": "model-00001-of-00003.safetensors",
|
247 |
+
"backbone.layers.30.mixer.A_log": "model-00002-of-00003.safetensors",
|
248 |
+
"backbone.layers.30.mixer.D": "model-00002-of-00003.safetensors",
|
249 |
+
"backbone.layers.30.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
250 |
+
"backbone.layers.30.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
251 |
+
"backbone.layers.30.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
252 |
+
"backbone.layers.30.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
253 |
+
"backbone.layers.30.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
254 |
+
"backbone.layers.30.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
255 |
+
"backbone.layers.30.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
256 |
+
"backbone.layers.30.norm.weight": "model-00002-of-00003.safetensors",
|
257 |
+
"backbone.layers.31.mixer.A_log": "model-00002-of-00003.safetensors",
|
258 |
+
"backbone.layers.31.mixer.D": "model-00002-of-00003.safetensors",
|
259 |
+
"backbone.layers.31.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
260 |
+
"backbone.layers.31.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
261 |
+
"backbone.layers.31.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
262 |
+
"backbone.layers.31.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
263 |
+
"backbone.layers.31.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
264 |
+
"backbone.layers.31.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
265 |
+
"backbone.layers.31.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
266 |
+
"backbone.layers.31.norm.weight": "model-00002-of-00003.safetensors",
|
267 |
+
"backbone.layers.32.mixer.A_log": "model-00002-of-00003.safetensors",
|
268 |
+
"backbone.layers.32.mixer.D": "model-00002-of-00003.safetensors",
|
269 |
+
"backbone.layers.32.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
270 |
+
"backbone.layers.32.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
271 |
+
"backbone.layers.32.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
272 |
+
"backbone.layers.32.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
273 |
+
"backbone.layers.32.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
274 |
+
"backbone.layers.32.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
275 |
+
"backbone.layers.32.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
276 |
+
"backbone.layers.32.norm.weight": "model-00002-of-00003.safetensors",
|
277 |
+
"backbone.layers.33.mixer.A_log": "model-00002-of-00003.safetensors",
|
278 |
+
"backbone.layers.33.mixer.D": "model-00002-of-00003.safetensors",
|
279 |
+
"backbone.layers.33.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
280 |
+
"backbone.layers.33.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
281 |
+
"backbone.layers.33.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
282 |
+
"backbone.layers.33.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
283 |
+
"backbone.layers.33.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
284 |
+
"backbone.layers.33.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
285 |
+
"backbone.layers.33.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
286 |
+
"backbone.layers.33.norm.weight": "model-00002-of-00003.safetensors",
|
287 |
+
"backbone.layers.34.mixer.A_log": "model-00002-of-00003.safetensors",
|
288 |
+
"backbone.layers.34.mixer.D": "model-00002-of-00003.safetensors",
|
289 |
+
"backbone.layers.34.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
290 |
+
"backbone.layers.34.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
291 |
+
"backbone.layers.34.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
292 |
+
"backbone.layers.34.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
293 |
+
"backbone.layers.34.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
294 |
+
"backbone.layers.34.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
295 |
+
"backbone.layers.34.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
296 |
+
"backbone.layers.34.norm.weight": "model-00002-of-00003.safetensors",
|
297 |
+
"backbone.layers.35.mixer.A_log": "model-00002-of-00003.safetensors",
|
298 |
+
"backbone.layers.35.mixer.D": "model-00002-of-00003.safetensors",
|
299 |
+
"backbone.layers.35.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
300 |
+
"backbone.layers.35.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
301 |
+
"backbone.layers.35.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
302 |
+
"backbone.layers.35.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
303 |
+
"backbone.layers.35.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
304 |
+
"backbone.layers.35.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
305 |
+
"backbone.layers.35.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
306 |
+
"backbone.layers.35.norm.weight": "model-00002-of-00003.safetensors",
|
307 |
+
"backbone.layers.36.mixer.A_log": "model-00002-of-00003.safetensors",
|
308 |
+
"backbone.layers.36.mixer.D": "model-00002-of-00003.safetensors",
|
309 |
+
"backbone.layers.36.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
310 |
+
"backbone.layers.36.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
311 |
+
"backbone.layers.36.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
312 |
+
"backbone.layers.36.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
313 |
+
"backbone.layers.36.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
314 |
+
"backbone.layers.36.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
315 |
+
"backbone.layers.36.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
316 |
+
"backbone.layers.36.norm.weight": "model-00002-of-00003.safetensors",
|
317 |
+
"backbone.layers.37.mixer.A_log": "model-00002-of-00003.safetensors",
|
318 |
+
"backbone.layers.37.mixer.D": "model-00002-of-00003.safetensors",
|
319 |
+
"backbone.layers.37.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
320 |
+
"backbone.layers.37.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
321 |
+
"backbone.layers.37.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
322 |
+
"backbone.layers.37.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
323 |
+
"backbone.layers.37.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
324 |
+
"backbone.layers.37.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
325 |
+
"backbone.layers.37.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
326 |
+
"backbone.layers.37.norm.weight": "model-00002-of-00003.safetensors",
|
327 |
+
"backbone.layers.38.mixer.A_log": "model-00002-of-00003.safetensors",
|
328 |
+
"backbone.layers.38.mixer.D": "model-00002-of-00003.safetensors",
|
329 |
+
"backbone.layers.38.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
330 |
+
"backbone.layers.38.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
331 |
+
"backbone.layers.38.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
332 |
+
"backbone.layers.38.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
333 |
+
"backbone.layers.38.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
334 |
+
"backbone.layers.38.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
335 |
+
"backbone.layers.38.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
336 |
+
"backbone.layers.38.norm.weight": "model-00002-of-00003.safetensors",
|
337 |
+
"backbone.layers.39.mixer.A_log": "model-00002-of-00003.safetensors",
|
338 |
+
"backbone.layers.39.mixer.D": "model-00002-of-00003.safetensors",
|
339 |
+
"backbone.layers.39.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
340 |
+
"backbone.layers.39.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
341 |
+
"backbone.layers.39.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
342 |
+
"backbone.layers.39.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
343 |
+
"backbone.layers.39.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
344 |
+
"backbone.layers.39.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
345 |
+
"backbone.layers.39.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
346 |
+
"backbone.layers.39.norm.weight": "model-00002-of-00003.safetensors",
|
347 |
+
"backbone.layers.4.mixer.A_log": "model-00001-of-00003.safetensors",
|
348 |
+
"backbone.layers.4.mixer.D": "model-00001-of-00003.safetensors",
|
349 |
+
"backbone.layers.4.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
350 |
+
"backbone.layers.4.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
351 |
+
"backbone.layers.4.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
352 |
+
"backbone.layers.4.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
353 |
+
"backbone.layers.4.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
354 |
+
"backbone.layers.4.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
355 |
+
"backbone.layers.4.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
356 |
+
"backbone.layers.4.norm.weight": "model-00001-of-00003.safetensors",
|
357 |
+
"backbone.layers.40.mixer.A_log": "model-00002-of-00003.safetensors",
|
358 |
+
"backbone.layers.40.mixer.D": "model-00002-of-00003.safetensors",
|
359 |
+
"backbone.layers.40.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
360 |
+
"backbone.layers.40.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
361 |
+
"backbone.layers.40.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
362 |
+
"backbone.layers.40.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
363 |
+
"backbone.layers.40.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
364 |
+
"backbone.layers.40.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
365 |
+
"backbone.layers.40.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
366 |
+
"backbone.layers.40.norm.weight": "model-00002-of-00003.safetensors",
|
367 |
+
"backbone.layers.41.mixer.A_log": "model-00002-of-00003.safetensors",
|
368 |
+
"backbone.layers.41.mixer.D": "model-00002-of-00003.safetensors",
|
369 |
+
"backbone.layers.41.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
370 |
+
"backbone.layers.41.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
371 |
+
"backbone.layers.41.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
372 |
+
"backbone.layers.41.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
373 |
+
"backbone.layers.41.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
374 |
+
"backbone.layers.41.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
375 |
+
"backbone.layers.41.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
376 |
+
"backbone.layers.41.norm.weight": "model-00002-of-00003.safetensors",
|
377 |
+
"backbone.layers.42.mixer.A_log": "model-00002-of-00003.safetensors",
|
378 |
+
"backbone.layers.42.mixer.D": "model-00002-of-00003.safetensors",
|
379 |
+
"backbone.layers.42.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
380 |
+
"backbone.layers.42.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
381 |
+
"backbone.layers.42.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
382 |
+
"backbone.layers.42.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
383 |
+
"backbone.layers.42.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
384 |
+
"backbone.layers.42.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
385 |
+
"backbone.layers.42.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
386 |
+
"backbone.layers.42.norm.weight": "model-00002-of-00003.safetensors",
|
387 |
+
"backbone.layers.43.mixer.A_log": "model-00002-of-00003.safetensors",
|
388 |
+
"backbone.layers.43.mixer.D": "model-00002-of-00003.safetensors",
|
389 |
+
"backbone.layers.43.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
390 |
+
"backbone.layers.43.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
391 |
+
"backbone.layers.43.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
392 |
+
"backbone.layers.43.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
393 |
+
"backbone.layers.43.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
394 |
+
"backbone.layers.43.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
395 |
+
"backbone.layers.43.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
396 |
+
"backbone.layers.43.norm.weight": "model-00002-of-00003.safetensors",
|
397 |
+
"backbone.layers.44.mixer.A_log": "model-00002-of-00003.safetensors",
|
398 |
+
"backbone.layers.44.mixer.D": "model-00002-of-00003.safetensors",
|
399 |
+
"backbone.layers.44.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
400 |
+
"backbone.layers.44.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
401 |
+
"backbone.layers.44.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
402 |
+
"backbone.layers.44.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
403 |
+
"backbone.layers.44.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
404 |
+
"backbone.layers.44.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
405 |
+
"backbone.layers.44.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
406 |
+
"backbone.layers.44.norm.weight": "model-00002-of-00003.safetensors",
|
407 |
+
"backbone.layers.45.mixer.A_log": "model-00003-of-00003.safetensors",
|
408 |
+
"backbone.layers.45.mixer.D": "model-00003-of-00003.safetensors",
|
409 |
+
"backbone.layers.45.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
410 |
+
"backbone.layers.45.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
411 |
+
"backbone.layers.45.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
412 |
+
"backbone.layers.45.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
413 |
+
"backbone.layers.45.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
414 |
+
"backbone.layers.45.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
415 |
+
"backbone.layers.45.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
416 |
+
"backbone.layers.45.norm.weight": "model-00003-of-00003.safetensors",
|
417 |
+
"backbone.layers.46.mixer.A_log": "model-00003-of-00003.safetensors",
|
418 |
+
"backbone.layers.46.mixer.D": "model-00003-of-00003.safetensors",
|
419 |
+
"backbone.layers.46.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
420 |
+
"backbone.layers.46.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
421 |
+
"backbone.layers.46.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
422 |
+
"backbone.layers.46.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
423 |
+
"backbone.layers.46.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
424 |
+
"backbone.layers.46.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
425 |
+
"backbone.layers.46.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
426 |
+
"backbone.layers.46.norm.weight": "model-00003-of-00003.safetensors",
|
427 |
+
"backbone.layers.47.mixer.A_log": "model-00003-of-00003.safetensors",
|
428 |
+
"backbone.layers.47.mixer.D": "model-00003-of-00003.safetensors",
|
429 |
+
"backbone.layers.47.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
430 |
+
"backbone.layers.47.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
431 |
+
"backbone.layers.47.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
432 |
+
"backbone.layers.47.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
433 |
+
"backbone.layers.47.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
434 |
+
"backbone.layers.47.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
435 |
+
"backbone.layers.47.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
436 |
+
"backbone.layers.47.norm.weight": "model-00003-of-00003.safetensors",
|
437 |
+
"backbone.layers.48.mixer.A_log": "model-00003-of-00003.safetensors",
|
438 |
+
"backbone.layers.48.mixer.D": "model-00003-of-00003.safetensors",
|
439 |
+
"backbone.layers.48.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
440 |
+
"backbone.layers.48.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
441 |
+
"backbone.layers.48.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
442 |
+
"backbone.layers.48.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
443 |
+
"backbone.layers.48.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
444 |
+
"backbone.layers.48.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
445 |
+
"backbone.layers.48.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
446 |
+
"backbone.layers.48.norm.weight": "model-00003-of-00003.safetensors",
|
447 |
+
"backbone.layers.49.mixer.A_log": "model-00003-of-00003.safetensors",
|
448 |
+
"backbone.layers.49.mixer.D": "model-00003-of-00003.safetensors",
|
449 |
+
"backbone.layers.49.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
450 |
+
"backbone.layers.49.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
451 |
+
"backbone.layers.49.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
452 |
+
"backbone.layers.49.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
453 |
+
"backbone.layers.49.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
454 |
+
"backbone.layers.49.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
455 |
+
"backbone.layers.49.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
456 |
+
"backbone.layers.49.norm.weight": "model-00003-of-00003.safetensors",
|
457 |
+
"backbone.layers.5.mixer.A_log": "model-00001-of-00003.safetensors",
|
458 |
+
"backbone.layers.5.mixer.D": "model-00001-of-00003.safetensors",
|
459 |
+
"backbone.layers.5.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
460 |
+
"backbone.layers.5.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
461 |
+
"backbone.layers.5.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
462 |
+
"backbone.layers.5.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
463 |
+
"backbone.layers.5.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
464 |
+
"backbone.layers.5.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
465 |
+
"backbone.layers.5.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
466 |
+
"backbone.layers.5.norm.weight": "model-00001-of-00003.safetensors",
|
467 |
+
"backbone.layers.50.mixer.A_log": "model-00003-of-00003.safetensors",
|
468 |
+
"backbone.layers.50.mixer.D": "model-00003-of-00003.safetensors",
|
469 |
+
"backbone.layers.50.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
470 |
+
"backbone.layers.50.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
471 |
+
"backbone.layers.50.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
472 |
+
"backbone.layers.50.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
473 |
+
"backbone.layers.50.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
474 |
+
"backbone.layers.50.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
475 |
+
"backbone.layers.50.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
476 |
+
"backbone.layers.50.norm.weight": "model-00003-of-00003.safetensors",
|
477 |
+
"backbone.layers.51.mixer.A_log": "model-00003-of-00003.safetensors",
|
478 |
+
"backbone.layers.51.mixer.D": "model-00003-of-00003.safetensors",
|
479 |
+
"backbone.layers.51.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
480 |
+
"backbone.layers.51.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
481 |
+
"backbone.layers.51.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
482 |
+
"backbone.layers.51.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
483 |
+
"backbone.layers.51.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
484 |
+
"backbone.layers.51.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
485 |
+
"backbone.layers.51.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
486 |
+
"backbone.layers.51.norm.weight": "model-00003-of-00003.safetensors",
|
487 |
+
"backbone.layers.52.mixer.A_log": "model-00003-of-00003.safetensors",
|
488 |
+
"backbone.layers.52.mixer.D": "model-00003-of-00003.safetensors",
|
489 |
+
"backbone.layers.52.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
490 |
+
"backbone.layers.52.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
491 |
+
"backbone.layers.52.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
492 |
+
"backbone.layers.52.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
493 |
+
"backbone.layers.52.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
494 |
+
"backbone.layers.52.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
495 |
+
"backbone.layers.52.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
496 |
+
"backbone.layers.52.norm.weight": "model-00003-of-00003.safetensors",
|
497 |
+
"backbone.layers.53.mixer.A_log": "model-00003-of-00003.safetensors",
|
498 |
+
"backbone.layers.53.mixer.D": "model-00003-of-00003.safetensors",
|
499 |
+
"backbone.layers.53.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
500 |
+
"backbone.layers.53.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
501 |
+
"backbone.layers.53.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
502 |
+
"backbone.layers.53.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
503 |
+
"backbone.layers.53.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
504 |
+
"backbone.layers.53.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
505 |
+
"backbone.layers.53.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
506 |
+
"backbone.layers.53.norm.weight": "model-00003-of-00003.safetensors",
|
507 |
+
"backbone.layers.54.mixer.A_log": "model-00003-of-00003.safetensors",
|
508 |
+
"backbone.layers.54.mixer.D": "model-00003-of-00003.safetensors",
|
509 |
+
"backbone.layers.54.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
510 |
+
"backbone.layers.54.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
511 |
+
"backbone.layers.54.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
512 |
+
"backbone.layers.54.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
513 |
+
"backbone.layers.54.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
514 |
+
"backbone.layers.54.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
515 |
+
"backbone.layers.54.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
516 |
+
"backbone.layers.54.norm.weight": "model-00003-of-00003.safetensors",
|
517 |
+
"backbone.layers.55.mixer.A_log": "model-00003-of-00003.safetensors",
|
518 |
+
"backbone.layers.55.mixer.D": "model-00003-of-00003.safetensors",
|
519 |
+
"backbone.layers.55.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
520 |
+
"backbone.layers.55.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
521 |
+
"backbone.layers.55.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
522 |
+
"backbone.layers.55.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
523 |
+
"backbone.layers.55.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
524 |
+
"backbone.layers.55.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
525 |
+
"backbone.layers.55.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
526 |
+
"backbone.layers.55.norm.weight": "model-00003-of-00003.safetensors",
|
527 |
+
"backbone.layers.56.mixer.A_log": "model-00003-of-00003.safetensors",
|
528 |
+
"backbone.layers.56.mixer.D": "model-00003-of-00003.safetensors",
|
529 |
+
"backbone.layers.56.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
530 |
+
"backbone.layers.56.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
531 |
+
"backbone.layers.56.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
532 |
+
"backbone.layers.56.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
533 |
+
"backbone.layers.56.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
534 |
+
"backbone.layers.56.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
535 |
+
"backbone.layers.56.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
536 |
+
"backbone.layers.56.norm.weight": "model-00003-of-00003.safetensors",
|
537 |
+
"backbone.layers.57.mixer.A_log": "model-00003-of-00003.safetensors",
|
538 |
+
"backbone.layers.57.mixer.D": "model-00003-of-00003.safetensors",
|
539 |
+
"backbone.layers.57.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
540 |
+
"backbone.layers.57.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
541 |
+
"backbone.layers.57.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
542 |
+
"backbone.layers.57.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
543 |
+
"backbone.layers.57.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
544 |
+
"backbone.layers.57.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
545 |
+
"backbone.layers.57.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
546 |
+
"backbone.layers.57.norm.weight": "model-00003-of-00003.safetensors",
|
547 |
+
"backbone.layers.58.mixer.A_log": "model-00003-of-00003.safetensors",
|
548 |
+
"backbone.layers.58.mixer.D": "model-00003-of-00003.safetensors",
|
549 |
+
"backbone.layers.58.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
550 |
+
"backbone.layers.58.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
551 |
+
"backbone.layers.58.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
552 |
+
"backbone.layers.58.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
553 |
+
"backbone.layers.58.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
554 |
+
"backbone.layers.58.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
555 |
+
"backbone.layers.58.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
556 |
+
"backbone.layers.58.norm.weight": "model-00003-of-00003.safetensors",
|
557 |
+
"backbone.layers.59.mixer.A_log": "model-00003-of-00003.safetensors",
|
558 |
+
"backbone.layers.59.mixer.D": "model-00003-of-00003.safetensors",
|
559 |
+
"backbone.layers.59.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
560 |
+
"backbone.layers.59.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
561 |
+
"backbone.layers.59.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
562 |
+
"backbone.layers.59.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
563 |
+
"backbone.layers.59.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
564 |
+
"backbone.layers.59.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
565 |
+
"backbone.layers.59.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
566 |
+
"backbone.layers.59.norm.weight": "model-00003-of-00003.safetensors",
|
567 |
+
"backbone.layers.6.mixer.A_log": "model-00001-of-00003.safetensors",
|
568 |
+
"backbone.layers.6.mixer.D": "model-00001-of-00003.safetensors",
|
569 |
+
"backbone.layers.6.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
570 |
+
"backbone.layers.6.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
571 |
+
"backbone.layers.6.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
572 |
+
"backbone.layers.6.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
573 |
+
"backbone.layers.6.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
574 |
+
"backbone.layers.6.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
575 |
+
"backbone.layers.6.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
576 |
+
"backbone.layers.6.norm.weight": "model-00001-of-00003.safetensors",
|
577 |
+
"backbone.layers.60.mixer.A_log": "model-00003-of-00003.safetensors",
|
578 |
+
"backbone.layers.60.mixer.D": "model-00003-of-00003.safetensors",
|
579 |
+
"backbone.layers.60.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
580 |
+
"backbone.layers.60.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
581 |
+
"backbone.layers.60.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
582 |
+
"backbone.layers.60.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
583 |
+
"backbone.layers.60.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
584 |
+
"backbone.layers.60.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
585 |
+
"backbone.layers.60.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
586 |
+
"backbone.layers.60.norm.weight": "model-00003-of-00003.safetensors",
|
587 |
+
"backbone.layers.61.mixer.A_log": "model-00003-of-00003.safetensors",
|
588 |
+
"backbone.layers.61.mixer.D": "model-00003-of-00003.safetensors",
|
589 |
+
"backbone.layers.61.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
590 |
+
"backbone.layers.61.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
591 |
+
"backbone.layers.61.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
592 |
+
"backbone.layers.61.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
593 |
+
"backbone.layers.61.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
594 |
+
"backbone.layers.61.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
595 |
+
"backbone.layers.61.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
596 |
+
"backbone.layers.61.norm.weight": "model-00003-of-00003.safetensors",
|
597 |
+
"backbone.layers.62.mixer.A_log": "model-00003-of-00003.safetensors",
|
598 |
+
"backbone.layers.62.mixer.D": "model-00003-of-00003.safetensors",
|
599 |
+
"backbone.layers.62.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
600 |
+
"backbone.layers.62.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
601 |
+
"backbone.layers.62.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
602 |
+
"backbone.layers.62.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
603 |
+
"backbone.layers.62.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
604 |
+
"backbone.layers.62.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
605 |
+
"backbone.layers.62.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
606 |
+
"backbone.layers.62.norm.weight": "model-00003-of-00003.safetensors",
|
607 |
+
"backbone.layers.63.mixer.A_log": "model-00003-of-00003.safetensors",
|
608 |
+
"backbone.layers.63.mixer.D": "model-00003-of-00003.safetensors",
|
609 |
+
"backbone.layers.63.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
610 |
+
"backbone.layers.63.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
611 |
+
"backbone.layers.63.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
612 |
+
"backbone.layers.63.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
613 |
+
"backbone.layers.63.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
614 |
+
"backbone.layers.63.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
615 |
+
"backbone.layers.63.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
616 |
+
"backbone.layers.63.norm.weight": "model-00003-of-00003.safetensors",
|
617 |
+
"backbone.layers.7.mixer.A_log": "model-00001-of-00003.safetensors",
|
618 |
+
"backbone.layers.7.mixer.D": "model-00001-of-00003.safetensors",
|
619 |
+
"backbone.layers.7.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
620 |
+
"backbone.layers.7.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
621 |
+
"backbone.layers.7.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
622 |
+
"backbone.layers.7.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
623 |
+
"backbone.layers.7.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
624 |
+
"backbone.layers.7.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
625 |
+
"backbone.layers.7.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
626 |
+
"backbone.layers.7.norm.weight": "model-00001-of-00003.safetensors",
|
627 |
+
"backbone.layers.8.mixer.A_log": "model-00001-of-00003.safetensors",
|
628 |
+
"backbone.layers.8.mixer.D": "model-00001-of-00003.safetensors",
|
629 |
+
"backbone.layers.8.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
630 |
+
"backbone.layers.8.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
631 |
+
"backbone.layers.8.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
632 |
+
"backbone.layers.8.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
633 |
+
"backbone.layers.8.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
634 |
+
"backbone.layers.8.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
635 |
+
"backbone.layers.8.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
636 |
+
"backbone.layers.8.norm.weight": "model-00001-of-00003.safetensors",
|
637 |
+
"backbone.layers.9.mixer.A_log": "model-00001-of-00003.safetensors",
|
638 |
+
"backbone.layers.9.mixer.D": "model-00001-of-00003.safetensors",
|
639 |
+
"backbone.layers.9.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
640 |
+
"backbone.layers.9.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
641 |
+
"backbone.layers.9.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
642 |
+
"backbone.layers.9.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
643 |
+
"backbone.layers.9.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
644 |
+
"backbone.layers.9.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
645 |
+
"backbone.layers.9.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
646 |
+
"backbone.layers.9.norm.weight": "model-00001-of-00003.safetensors",
|
647 |
+
"backbone.norm_f.weight": "model-00003-of-00003.safetensors",
|
648 |
+
"lm_head.weight": "model-00003-of-00003.safetensors"
|
649 |
+
}
|
650 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
">>TITLE<<",
|
4 |
+
">>ABSTRACT<<",
|
5 |
+
">>INTRODUCTION<<",
|
6 |
+
">>SUMMARY<<",
|
7 |
+
">>COMMENT<<",
|
8 |
+
">>ANSWER<<",
|
9 |
+
">>QUESTION<<",
|
10 |
+
"assistant",
|
11 |
+
"<|begin_of_text|>",
|
12 |
+
"<|im_start|>",
|
13 |
+
"<|im_end|>"
|
14 |
+
],
|
15 |
+
"bos_token": {
|
16 |
+
"content": "<|begin_of_text|>",
|
17 |
+
"lstrip": false,
|
18 |
+
"normalized": false,
|
19 |
+
"rstrip": false,
|
20 |
+
"single_word": false
|
21 |
+
},
|
22 |
+
"eos_token": {
|
23 |
+
"content": "<|end_of_text|>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false
|
28 |
+
},
|
29 |
+
"pad_token": {
|
30 |
+
"content": ">>TITLE<<",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false
|
35 |
+
}
|
36 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": ">>TITLE<<",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": ">>ABSTRACT<<",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": ">>INTRODUCTION<<",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": ">>SUMMARY<<",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"4": {
|
37 |
+
"content": ">>COMMENT<<",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
},
|
44 |
+
"5": {
|
45 |
+
"content": ">>ANSWER<<",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": true
|
51 |
+
},
|
52 |
+
"6": {
|
53 |
+
"content": ">>QUESTION<<",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": true
|
59 |
+
},
|
60 |
+
"7": {
|
61 |
+
"content": "assistant",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": false,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": true
|
67 |
+
},
|
68 |
+
"8": {
|
69 |
+
"content": "<|begin_of_text|>",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": false,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": true
|
75 |
+
},
|
76 |
+
"9": {
|
77 |
+
"content": "<|im_start|>",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": false,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": true
|
83 |
+
},
|
84 |
+
"10": {
|
85 |
+
"content": "<|im_end|>",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": false,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": true
|
91 |
+
},
|
92 |
+
"11": {
|
93 |
+
"content": "<|end_of_text|>",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": false,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": true
|
99 |
+
}
|
100 |
+
},
|
101 |
+
"additional_special_tokens": [
|
102 |
+
">>TITLE<<",
|
103 |
+
">>ABSTRACT<<",
|
104 |
+
">>INTRODUCTION<<",
|
105 |
+
">>SUMMARY<<",
|
106 |
+
">>COMMENT<<",
|
107 |
+
">>ANSWER<<",
|
108 |
+
">>QUESTION<<",
|
109 |
+
"assistant",
|
110 |
+
"<|begin_of_text|>",
|
111 |
+
"<|im_start|>",
|
112 |
+
"<|im_end|>"
|
113 |
+
],
|
114 |
+
"bos_token": "<|begin_of_text|>",
|
115 |
+
"chat_template": "{{bos_token}}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
116 |
+
"clean_up_tokenization_spaces": true,
|
117 |
+
"eos_token": "<|end_of_text|>",
|
118 |
+
"extra_special_tokens": {},
|
119 |
+
"max_length": null,
|
120 |
+
"model_input_names": [
|
121 |
+
"input_ids",
|
122 |
+
"attention_mask"
|
123 |
+
],
|
124 |
+
"model_max_length": 1000000000000000019884624838656,
|
125 |
+
"pad_to_multiple_of": null,
|
126 |
+
"pad_token": ">>TITLE<<",
|
127 |
+
"pad_token_type_id": 0,
|
128 |
+
"padding_side": "left",
|
129 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
130 |
+
}
|