[WIP] Upload folder using huggingface_hub (multi-commit e84e4c0e1545628a53c87bb7530949d52709740c1280014e278a91726016ea53)
#1
by
Goekdeniz-Guelmez
- opened
- README.md +0 -23
- config.json +0 -39
- model.safetensors +0 -3
- model.safetensors.index.json +0 -249
- special_tokens_map.json +0 -30
- tokenizer.json +0 -0
- tokenizer_config.json +0 -218
README.md
DELETED
@@ -1,23 +0,0 @@
|
|
1 |
-
---
|
2 |
-
library_name: transformers
|
3 |
-
tags:
|
4 |
-
- mlx
|
5 |
-
base_model: state-spaces/mamba-130m-hf
|
6 |
-
---
|
7 |
-
|
8 |
-
# mlx-community/mamba-130m-hf-f32
|
9 |
-
|
10 |
-
The Model [mlx-community/mamba-130m-hf-f32](https://huggingface.co/mlx-community/mamba-130m-hf-f32) was converted to MLX format from [state-spaces/mamba-130m-hf](https://huggingface.co/state-spaces/mamba-130m-hf) using mlx-lm version **0.18.1**.
|
11 |
-
|
12 |
-
## Use with mlx
|
13 |
-
|
14 |
-
```bash
|
15 |
-
pip install mlx-lm
|
16 |
-
```
|
17 |
-
|
18 |
-
```python
|
19 |
-
from mlx_lm import load, generate
|
20 |
-
|
21 |
-
model, tokenizer = load("mlx-community/mamba-130m-hf-f32")
|
22 |
-
response = generate(model, tokenizer, prompt="hello", verbose=True)
|
23 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
config.json
DELETED
@@ -1,39 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"architectures": [
|
3 |
-
"MambaForCausalLM"
|
4 |
-
],
|
5 |
-
"bos_token_id": 0,
|
6 |
-
"conv_kernel": 4,
|
7 |
-
"d_inner": 1536,
|
8 |
-
"d_model": 768,
|
9 |
-
"eos_token_id": 0,
|
10 |
-
"expand": 2,
|
11 |
-
"fused_add_norm": true,
|
12 |
-
"hidden_act": "silu",
|
13 |
-
"hidden_size": 768,
|
14 |
-
"initializer_range": 0.1,
|
15 |
-
"intermediate_size": 1536,
|
16 |
-
"layer_norm_epsilon": 1e-05,
|
17 |
-
"model_type": "mamba",
|
18 |
-
"n_layer": 24,
|
19 |
-
"num_hidden_layers": 24,
|
20 |
-
"pad_token_id": 0,
|
21 |
-
"pad_vocab_size_multiple": 8,
|
22 |
-
"rescale_prenorm_residual": false,
|
23 |
-
"residual_in_fp32": true,
|
24 |
-
"rms_norm": true,
|
25 |
-
"ssm_cfg": {},
|
26 |
-
"state_size": 16,
|
27 |
-
"time_step_floor": 0.0001,
|
28 |
-
"time_step_init_scheme": "random",
|
29 |
-
"time_step_max": 0.1,
|
30 |
-
"time_step_min": 0.001,
|
31 |
-
"time_step_rank": 48,
|
32 |
-
"time_step_scale": 1.0,
|
33 |
-
"torch_dtype": "float32",
|
34 |
-
"transformers_version": "4.39.0.dev0",
|
35 |
-
"use_bias": false,
|
36 |
-
"use_cache": true,
|
37 |
-
"use_conv_bias": true,
|
38 |
-
"vocab_size": 50280
|
39 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
model.safetensors
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:5b0c2400e3161bf9f12179770ff2c20db33e72f8678717a312e5eb2b2f341cbf
|
3 |
-
size 516567397
|
|
|
|
|
|
|
|
model.safetensors.index.json
DELETED
@@ -1,249 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"metadata": {
|
3 |
-
"total_size": 516541440
|
4 |
-
},
|
5 |
-
"weight_map": {
|
6 |
-
"backbone.embeddings.weight": "model.safetensors",
|
7 |
-
"backbone.layers.0.mixer.A_log": "model.safetensors",
|
8 |
-
"backbone.layers.0.mixer.D": "model.safetensors",
|
9 |
-
"backbone.layers.0.mixer.conv1d.bias": "model.safetensors",
|
10 |
-
"backbone.layers.0.mixer.conv1d.weight": "model.safetensors",
|
11 |
-
"backbone.layers.0.mixer.dt_proj.bias": "model.safetensors",
|
12 |
-
"backbone.layers.0.mixer.dt_proj.weight": "model.safetensors",
|
13 |
-
"backbone.layers.0.mixer.in_proj.weight": "model.safetensors",
|
14 |
-
"backbone.layers.0.mixer.out_proj.weight": "model.safetensors",
|
15 |
-
"backbone.layers.0.mixer.x_proj.weight": "model.safetensors",
|
16 |
-
"backbone.layers.0.norm.weight": "model.safetensors",
|
17 |
-
"backbone.layers.1.mixer.A_log": "model.safetensors",
|
18 |
-
"backbone.layers.1.mixer.D": "model.safetensors",
|
19 |
-
"backbone.layers.1.mixer.conv1d.bias": "model.safetensors",
|
20 |
-
"backbone.layers.1.mixer.conv1d.weight": "model.safetensors",
|
21 |
-
"backbone.layers.1.mixer.dt_proj.bias": "model.safetensors",
|
22 |
-
"backbone.layers.1.mixer.dt_proj.weight": "model.safetensors",
|
23 |
-
"backbone.layers.1.mixer.in_proj.weight": "model.safetensors",
|
24 |
-
"backbone.layers.1.mixer.out_proj.weight": "model.safetensors",
|
25 |
-
"backbone.layers.1.mixer.x_proj.weight": "model.safetensors",
|
26 |
-
"backbone.layers.1.norm.weight": "model.safetensors",
|
27 |
-
"backbone.layers.10.mixer.A_log": "model.safetensors",
|
28 |
-
"backbone.layers.10.mixer.D": "model.safetensors",
|
29 |
-
"backbone.layers.10.mixer.conv1d.bias": "model.safetensors",
|
30 |
-
"backbone.layers.10.mixer.conv1d.weight": "model.safetensors",
|
31 |
-
"backbone.layers.10.mixer.dt_proj.bias": "model.safetensors",
|
32 |
-
"backbone.layers.10.mixer.dt_proj.weight": "model.safetensors",
|
33 |
-
"backbone.layers.10.mixer.in_proj.weight": "model.safetensors",
|
34 |
-
"backbone.layers.10.mixer.out_proj.weight": "model.safetensors",
|
35 |
-
"backbone.layers.10.mixer.x_proj.weight": "model.safetensors",
|
36 |
-
"backbone.layers.10.norm.weight": "model.safetensors",
|
37 |
-
"backbone.layers.11.mixer.A_log": "model.safetensors",
|
38 |
-
"backbone.layers.11.mixer.D": "model.safetensors",
|
39 |
-
"backbone.layers.11.mixer.conv1d.bias": "model.safetensors",
|
40 |
-
"backbone.layers.11.mixer.conv1d.weight": "model.safetensors",
|
41 |
-
"backbone.layers.11.mixer.dt_proj.bias": "model.safetensors",
|
42 |
-
"backbone.layers.11.mixer.dt_proj.weight": "model.safetensors",
|
43 |
-
"backbone.layers.11.mixer.in_proj.weight": "model.safetensors",
|
44 |
-
"backbone.layers.11.mixer.out_proj.weight": "model.safetensors",
|
45 |
-
"backbone.layers.11.mixer.x_proj.weight": "model.safetensors",
|
46 |
-
"backbone.layers.11.norm.weight": "model.safetensors",
|
47 |
-
"backbone.layers.12.mixer.A_log": "model.safetensors",
|
48 |
-
"backbone.layers.12.mixer.D": "model.safetensors",
|
49 |
-
"backbone.layers.12.mixer.conv1d.bias": "model.safetensors",
|
50 |
-
"backbone.layers.12.mixer.conv1d.weight": "model.safetensors",
|
51 |
-
"backbone.layers.12.mixer.dt_proj.bias": "model.safetensors",
|
52 |
-
"backbone.layers.12.mixer.dt_proj.weight": "model.safetensors",
|
53 |
-
"backbone.layers.12.mixer.in_proj.weight": "model.safetensors",
|
54 |
-
"backbone.layers.12.mixer.out_proj.weight": "model.safetensors",
|
55 |
-
"backbone.layers.12.mixer.x_proj.weight": "model.safetensors",
|
56 |
-
"backbone.layers.12.norm.weight": "model.safetensors",
|
57 |
-
"backbone.layers.13.mixer.A_log": "model.safetensors",
|
58 |
-
"backbone.layers.13.mixer.D": "model.safetensors",
|
59 |
-
"backbone.layers.13.mixer.conv1d.bias": "model.safetensors",
|
60 |
-
"backbone.layers.13.mixer.conv1d.weight": "model.safetensors",
|
61 |
-
"backbone.layers.13.mixer.dt_proj.bias": "model.safetensors",
|
62 |
-
"backbone.layers.13.mixer.dt_proj.weight": "model.safetensors",
|
63 |
-
"backbone.layers.13.mixer.in_proj.weight": "model.safetensors",
|
64 |
-
"backbone.layers.13.mixer.out_proj.weight": "model.safetensors",
|
65 |
-
"backbone.layers.13.mixer.x_proj.weight": "model.safetensors",
|
66 |
-
"backbone.layers.13.norm.weight": "model.safetensors",
|
67 |
-
"backbone.layers.14.mixer.A_log": "model.safetensors",
|
68 |
-
"backbone.layers.14.mixer.D": "model.safetensors",
|
69 |
-
"backbone.layers.14.mixer.conv1d.bias": "model.safetensors",
|
70 |
-
"backbone.layers.14.mixer.conv1d.weight": "model.safetensors",
|
71 |
-
"backbone.layers.14.mixer.dt_proj.bias": "model.safetensors",
|
72 |
-
"backbone.layers.14.mixer.dt_proj.weight": "model.safetensors",
|
73 |
-
"backbone.layers.14.mixer.in_proj.weight": "model.safetensors",
|
74 |
-
"backbone.layers.14.mixer.out_proj.weight": "model.safetensors",
|
75 |
-
"backbone.layers.14.mixer.x_proj.weight": "model.safetensors",
|
76 |
-
"backbone.layers.14.norm.weight": "model.safetensors",
|
77 |
-
"backbone.layers.15.mixer.A_log": "model.safetensors",
|
78 |
-
"backbone.layers.15.mixer.D": "model.safetensors",
|
79 |
-
"backbone.layers.15.mixer.conv1d.bias": "model.safetensors",
|
80 |
-
"backbone.layers.15.mixer.conv1d.weight": "model.safetensors",
|
81 |
-
"backbone.layers.15.mixer.dt_proj.bias": "model.safetensors",
|
82 |
-
"backbone.layers.15.mixer.dt_proj.weight": "model.safetensors",
|
83 |
-
"backbone.layers.15.mixer.in_proj.weight": "model.safetensors",
|
84 |
-
"backbone.layers.15.mixer.out_proj.weight": "model.safetensors",
|
85 |
-
"backbone.layers.15.mixer.x_proj.weight": "model.safetensors",
|
86 |
-
"backbone.layers.15.norm.weight": "model.safetensors",
|
87 |
-
"backbone.layers.16.mixer.A_log": "model.safetensors",
|
88 |
-
"backbone.layers.16.mixer.D": "model.safetensors",
|
89 |
-
"backbone.layers.16.mixer.conv1d.bias": "model.safetensors",
|
90 |
-
"backbone.layers.16.mixer.conv1d.weight": "model.safetensors",
|
91 |
-
"backbone.layers.16.mixer.dt_proj.bias": "model.safetensors",
|
92 |
-
"backbone.layers.16.mixer.dt_proj.weight": "model.safetensors",
|
93 |
-
"backbone.layers.16.mixer.in_proj.weight": "model.safetensors",
|
94 |
-
"backbone.layers.16.mixer.out_proj.weight": "model.safetensors",
|
95 |
-
"backbone.layers.16.mixer.x_proj.weight": "model.safetensors",
|
96 |
-
"backbone.layers.16.norm.weight": "model.safetensors",
|
97 |
-
"backbone.layers.17.mixer.A_log": "model.safetensors",
|
98 |
-
"backbone.layers.17.mixer.D": "model.safetensors",
|
99 |
-
"backbone.layers.17.mixer.conv1d.bias": "model.safetensors",
|
100 |
-
"backbone.layers.17.mixer.conv1d.weight": "model.safetensors",
|
101 |
-
"backbone.layers.17.mixer.dt_proj.bias": "model.safetensors",
|
102 |
-
"backbone.layers.17.mixer.dt_proj.weight": "model.safetensors",
|
103 |
-
"backbone.layers.17.mixer.in_proj.weight": "model.safetensors",
|
104 |
-
"backbone.layers.17.mixer.out_proj.weight": "model.safetensors",
|
105 |
-
"backbone.layers.17.mixer.x_proj.weight": "model.safetensors",
|
106 |
-
"backbone.layers.17.norm.weight": "model.safetensors",
|
107 |
-
"backbone.layers.18.mixer.A_log": "model.safetensors",
|
108 |
-
"backbone.layers.18.mixer.D": "model.safetensors",
|
109 |
-
"backbone.layers.18.mixer.conv1d.bias": "model.safetensors",
|
110 |
-
"backbone.layers.18.mixer.conv1d.weight": "model.safetensors",
|
111 |
-
"backbone.layers.18.mixer.dt_proj.bias": "model.safetensors",
|
112 |
-
"backbone.layers.18.mixer.dt_proj.weight": "model.safetensors",
|
113 |
-
"backbone.layers.18.mixer.in_proj.weight": "model.safetensors",
|
114 |
-
"backbone.layers.18.mixer.out_proj.weight": "model.safetensors",
|
115 |
-
"backbone.layers.18.mixer.x_proj.weight": "model.safetensors",
|
116 |
-
"backbone.layers.18.norm.weight": "model.safetensors",
|
117 |
-
"backbone.layers.19.mixer.A_log": "model.safetensors",
|
118 |
-
"backbone.layers.19.mixer.D": "model.safetensors",
|
119 |
-
"backbone.layers.19.mixer.conv1d.bias": "model.safetensors",
|
120 |
-
"backbone.layers.19.mixer.conv1d.weight": "model.safetensors",
|
121 |
-
"backbone.layers.19.mixer.dt_proj.bias": "model.safetensors",
|
122 |
-
"backbone.layers.19.mixer.dt_proj.weight": "model.safetensors",
|
123 |
-
"backbone.layers.19.mixer.in_proj.weight": "model.safetensors",
|
124 |
-
"backbone.layers.19.mixer.out_proj.weight": "model.safetensors",
|
125 |
-
"backbone.layers.19.mixer.x_proj.weight": "model.safetensors",
|
126 |
-
"backbone.layers.19.norm.weight": "model.safetensors",
|
127 |
-
"backbone.layers.2.mixer.A_log": "model.safetensors",
|
128 |
-
"backbone.layers.2.mixer.D": "model.safetensors",
|
129 |
-
"backbone.layers.2.mixer.conv1d.bias": "model.safetensors",
|
130 |
-
"backbone.layers.2.mixer.conv1d.weight": "model.safetensors",
|
131 |
-
"backbone.layers.2.mixer.dt_proj.bias": "model.safetensors",
|
132 |
-
"backbone.layers.2.mixer.dt_proj.weight": "model.safetensors",
|
133 |
-
"backbone.layers.2.mixer.in_proj.weight": "model.safetensors",
|
134 |
-
"backbone.layers.2.mixer.out_proj.weight": "model.safetensors",
|
135 |
-
"backbone.layers.2.mixer.x_proj.weight": "model.safetensors",
|
136 |
-
"backbone.layers.2.norm.weight": "model.safetensors",
|
137 |
-
"backbone.layers.20.mixer.A_log": "model.safetensors",
|
138 |
-
"backbone.layers.20.mixer.D": "model.safetensors",
|
139 |
-
"backbone.layers.20.mixer.conv1d.bias": "model.safetensors",
|
140 |
-
"backbone.layers.20.mixer.conv1d.weight": "model.safetensors",
|
141 |
-
"backbone.layers.20.mixer.dt_proj.bias": "model.safetensors",
|
142 |
-
"backbone.layers.20.mixer.dt_proj.weight": "model.safetensors",
|
143 |
-
"backbone.layers.20.mixer.in_proj.weight": "model.safetensors",
|
144 |
-
"backbone.layers.20.mixer.out_proj.weight": "model.safetensors",
|
145 |
-
"backbone.layers.20.mixer.x_proj.weight": "model.safetensors",
|
146 |
-
"backbone.layers.20.norm.weight": "model.safetensors",
|
147 |
-
"backbone.layers.21.mixer.A_log": "model.safetensors",
|
148 |
-
"backbone.layers.21.mixer.D": "model.safetensors",
|
149 |
-
"backbone.layers.21.mixer.conv1d.bias": "model.safetensors",
|
150 |
-
"backbone.layers.21.mixer.conv1d.weight": "model.safetensors",
|
151 |
-
"backbone.layers.21.mixer.dt_proj.bias": "model.safetensors",
|
152 |
-
"backbone.layers.21.mixer.dt_proj.weight": "model.safetensors",
|
153 |
-
"backbone.layers.21.mixer.in_proj.weight": "model.safetensors",
|
154 |
-
"backbone.layers.21.mixer.out_proj.weight": "model.safetensors",
|
155 |
-
"backbone.layers.21.mixer.x_proj.weight": "model.safetensors",
|
156 |
-
"backbone.layers.21.norm.weight": "model.safetensors",
|
157 |
-
"backbone.layers.22.mixer.A_log": "model.safetensors",
|
158 |
-
"backbone.layers.22.mixer.D": "model.safetensors",
|
159 |
-
"backbone.layers.22.mixer.conv1d.bias": "model.safetensors",
|
160 |
-
"backbone.layers.22.mixer.conv1d.weight": "model.safetensors",
|
161 |
-
"backbone.layers.22.mixer.dt_proj.bias": "model.safetensors",
|
162 |
-
"backbone.layers.22.mixer.dt_proj.weight": "model.safetensors",
|
163 |
-
"backbone.layers.22.mixer.in_proj.weight": "model.safetensors",
|
164 |
-
"backbone.layers.22.mixer.out_proj.weight": "model.safetensors",
|
165 |
-
"backbone.layers.22.mixer.x_proj.weight": "model.safetensors",
|
166 |
-
"backbone.layers.22.norm.weight": "model.safetensors",
|
167 |
-
"backbone.layers.23.mixer.A_log": "model.safetensors",
|
168 |
-
"backbone.layers.23.mixer.D": "model.safetensors",
|
169 |
-
"backbone.layers.23.mixer.conv1d.bias": "model.safetensors",
|
170 |
-
"backbone.layers.23.mixer.conv1d.weight": "model.safetensors",
|
171 |
-
"backbone.layers.23.mixer.dt_proj.bias": "model.safetensors",
|
172 |
-
"backbone.layers.23.mixer.dt_proj.weight": "model.safetensors",
|
173 |
-
"backbone.layers.23.mixer.in_proj.weight": "model.safetensors",
|
174 |
-
"backbone.layers.23.mixer.out_proj.weight": "model.safetensors",
|
175 |
-
"backbone.layers.23.mixer.x_proj.weight": "model.safetensors",
|
176 |
-
"backbone.layers.23.norm.weight": "model.safetensors",
|
177 |
-
"backbone.layers.3.mixer.A_log": "model.safetensors",
|
178 |
-
"backbone.layers.3.mixer.D": "model.safetensors",
|
179 |
-
"backbone.layers.3.mixer.conv1d.bias": "model.safetensors",
|
180 |
-
"backbone.layers.3.mixer.conv1d.weight": "model.safetensors",
|
181 |
-
"backbone.layers.3.mixer.dt_proj.bias": "model.safetensors",
|
182 |
-
"backbone.layers.3.mixer.dt_proj.weight": "model.safetensors",
|
183 |
-
"backbone.layers.3.mixer.in_proj.weight": "model.safetensors",
|
184 |
-
"backbone.layers.3.mixer.out_proj.weight": "model.safetensors",
|
185 |
-
"backbone.layers.3.mixer.x_proj.weight": "model.safetensors",
|
186 |
-
"backbone.layers.3.norm.weight": "model.safetensors",
|
187 |
-
"backbone.layers.4.mixer.A_log": "model.safetensors",
|
188 |
-
"backbone.layers.4.mixer.D": "model.safetensors",
|
189 |
-
"backbone.layers.4.mixer.conv1d.bias": "model.safetensors",
|
190 |
-
"backbone.layers.4.mixer.conv1d.weight": "model.safetensors",
|
191 |
-
"backbone.layers.4.mixer.dt_proj.bias": "model.safetensors",
|
192 |
-
"backbone.layers.4.mixer.dt_proj.weight": "model.safetensors",
|
193 |
-
"backbone.layers.4.mixer.in_proj.weight": "model.safetensors",
|
194 |
-
"backbone.layers.4.mixer.out_proj.weight": "model.safetensors",
|
195 |
-
"backbone.layers.4.mixer.x_proj.weight": "model.safetensors",
|
196 |
-
"backbone.layers.4.norm.weight": "model.safetensors",
|
197 |
-
"backbone.layers.5.mixer.A_log": "model.safetensors",
|
198 |
-
"backbone.layers.5.mixer.D": "model.safetensors",
|
199 |
-
"backbone.layers.5.mixer.conv1d.bias": "model.safetensors",
|
200 |
-
"backbone.layers.5.mixer.conv1d.weight": "model.safetensors",
|
201 |
-
"backbone.layers.5.mixer.dt_proj.bias": "model.safetensors",
|
202 |
-
"backbone.layers.5.mixer.dt_proj.weight": "model.safetensors",
|
203 |
-
"backbone.layers.5.mixer.in_proj.weight": "model.safetensors",
|
204 |
-
"backbone.layers.5.mixer.out_proj.weight": "model.safetensors",
|
205 |
-
"backbone.layers.5.mixer.x_proj.weight": "model.safetensors",
|
206 |
-
"backbone.layers.5.norm.weight": "model.safetensors",
|
207 |
-
"backbone.layers.6.mixer.A_log": "model.safetensors",
|
208 |
-
"backbone.layers.6.mixer.D": "model.safetensors",
|
209 |
-
"backbone.layers.6.mixer.conv1d.bias": "model.safetensors",
|
210 |
-
"backbone.layers.6.mixer.conv1d.weight": "model.safetensors",
|
211 |
-
"backbone.layers.6.mixer.dt_proj.bias": "model.safetensors",
|
212 |
-
"backbone.layers.6.mixer.dt_proj.weight": "model.safetensors",
|
213 |
-
"backbone.layers.6.mixer.in_proj.weight": "model.safetensors",
|
214 |
-
"backbone.layers.6.mixer.out_proj.weight": "model.safetensors",
|
215 |
-
"backbone.layers.6.mixer.x_proj.weight": "model.safetensors",
|
216 |
-
"backbone.layers.6.norm.weight": "model.safetensors",
|
217 |
-
"backbone.layers.7.mixer.A_log": "model.safetensors",
|
218 |
-
"backbone.layers.7.mixer.D": "model.safetensors",
|
219 |
-
"backbone.layers.7.mixer.conv1d.bias": "model.safetensors",
|
220 |
-
"backbone.layers.7.mixer.conv1d.weight": "model.safetensors",
|
221 |
-
"backbone.layers.7.mixer.dt_proj.bias": "model.safetensors",
|
222 |
-
"backbone.layers.7.mixer.dt_proj.weight": "model.safetensors",
|
223 |
-
"backbone.layers.7.mixer.in_proj.weight": "model.safetensors",
|
224 |
-
"backbone.layers.7.mixer.out_proj.weight": "model.safetensors",
|
225 |
-
"backbone.layers.7.mixer.x_proj.weight": "model.safetensors",
|
226 |
-
"backbone.layers.7.norm.weight": "model.safetensors",
|
227 |
-
"backbone.layers.8.mixer.A_log": "model.safetensors",
|
228 |
-
"backbone.layers.8.mixer.D": "model.safetensors",
|
229 |
-
"backbone.layers.8.mixer.conv1d.bias": "model.safetensors",
|
230 |
-
"backbone.layers.8.mixer.conv1d.weight": "model.safetensors",
|
231 |
-
"backbone.layers.8.mixer.dt_proj.bias": "model.safetensors",
|
232 |
-
"backbone.layers.8.mixer.dt_proj.weight": "model.safetensors",
|
233 |
-
"backbone.layers.8.mixer.in_proj.weight": "model.safetensors",
|
234 |
-
"backbone.layers.8.mixer.out_proj.weight": "model.safetensors",
|
235 |
-
"backbone.layers.8.mixer.x_proj.weight": "model.safetensors",
|
236 |
-
"backbone.layers.8.norm.weight": "model.safetensors",
|
237 |
-
"backbone.layers.9.mixer.A_log": "model.safetensors",
|
238 |
-
"backbone.layers.9.mixer.D": "model.safetensors",
|
239 |
-
"backbone.layers.9.mixer.conv1d.bias": "model.safetensors",
|
240 |
-
"backbone.layers.9.mixer.conv1d.weight": "model.safetensors",
|
241 |
-
"backbone.layers.9.mixer.dt_proj.bias": "model.safetensors",
|
242 |
-
"backbone.layers.9.mixer.dt_proj.weight": "model.safetensors",
|
243 |
-
"backbone.layers.9.mixer.in_proj.weight": "model.safetensors",
|
244 |
-
"backbone.layers.9.mixer.out_proj.weight": "model.safetensors",
|
245 |
-
"backbone.layers.9.mixer.x_proj.weight": "model.safetensors",
|
246 |
-
"backbone.layers.9.norm.weight": "model.safetensors",
|
247 |
-
"backbone.norm_f.weight": "model.safetensors"
|
248 |
-
}
|
249 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
special_tokens_map.json
DELETED
@@ -1,30 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"bos_token": {
|
3 |
-
"content": "<|endoftext|>",
|
4 |
-
"lstrip": false,
|
5 |
-
"normalized": false,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"eos_token": {
|
10 |
-
"content": "<|endoftext|>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"pad_token": {
|
17 |
-
"content": "<|endoftext|>",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
-
"unk_token": {
|
24 |
-
"content": "<|endoftext|>",
|
25 |
-
"lstrip": false,
|
26 |
-
"normalized": false,
|
27 |
-
"rstrip": false,
|
28 |
-
"single_word": false
|
29 |
-
}
|
30 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
DELETED
@@ -1,218 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"add_bos_token": false,
|
3 |
-
"add_eos_token": false,
|
4 |
-
"add_prefix_space": false,
|
5 |
-
"added_tokens_decoder": {
|
6 |
-
"0": {
|
7 |
-
"content": "<|endoftext|>",
|
8 |
-
"lstrip": false,
|
9 |
-
"normalized": false,
|
10 |
-
"rstrip": false,
|
11 |
-
"single_word": false,
|
12 |
-
"special": true
|
13 |
-
},
|
14 |
-
"1": {
|
15 |
-
"content": "<|padding|>",
|
16 |
-
"lstrip": false,
|
17 |
-
"normalized": false,
|
18 |
-
"rstrip": false,
|
19 |
-
"single_word": false,
|
20 |
-
"special": true
|
21 |
-
},
|
22 |
-
"50254": {
|
23 |
-
"content": " ",
|
24 |
-
"lstrip": false,
|
25 |
-
"normalized": true,
|
26 |
-
"rstrip": false,
|
27 |
-
"single_word": false,
|
28 |
-
"special": false
|
29 |
-
},
|
30 |
-
"50255": {
|
31 |
-
"content": " ",
|
32 |
-
"lstrip": false,
|
33 |
-
"normalized": true,
|
34 |
-
"rstrip": false,
|
35 |
-
"single_word": false,
|
36 |
-
"special": false
|
37 |
-
},
|
38 |
-
"50256": {
|
39 |
-
"content": " ",
|
40 |
-
"lstrip": false,
|
41 |
-
"normalized": true,
|
42 |
-
"rstrip": false,
|
43 |
-
"single_word": false,
|
44 |
-
"special": false
|
45 |
-
},
|
46 |
-
"50257": {
|
47 |
-
"content": " ",
|
48 |
-
"lstrip": false,
|
49 |
-
"normalized": true,
|
50 |
-
"rstrip": false,
|
51 |
-
"single_word": false,
|
52 |
-
"special": false
|
53 |
-
},
|
54 |
-
"50258": {
|
55 |
-
"content": " ",
|
56 |
-
"lstrip": false,
|
57 |
-
"normalized": true,
|
58 |
-
"rstrip": false,
|
59 |
-
"single_word": false,
|
60 |
-
"special": false
|
61 |
-
},
|
62 |
-
"50259": {
|
63 |
-
"content": " ",
|
64 |
-
"lstrip": false,
|
65 |
-
"normalized": true,
|
66 |
-
"rstrip": false,
|
67 |
-
"single_word": false,
|
68 |
-
"special": false
|
69 |
-
},
|
70 |
-
"50260": {
|
71 |
-
"content": " ",
|
72 |
-
"lstrip": false,
|
73 |
-
"normalized": true,
|
74 |
-
"rstrip": false,
|
75 |
-
"single_word": false,
|
76 |
-
"special": false
|
77 |
-
},
|
78 |
-
"50261": {
|
79 |
-
"content": " ",
|
80 |
-
"lstrip": false,
|
81 |
-
"normalized": true,
|
82 |
-
"rstrip": false,
|
83 |
-
"single_word": false,
|
84 |
-
"special": false
|
85 |
-
},
|
86 |
-
"50262": {
|
87 |
-
"content": " ",
|
88 |
-
"lstrip": false,
|
89 |
-
"normalized": true,
|
90 |
-
"rstrip": false,
|
91 |
-
"single_word": false,
|
92 |
-
"special": false
|
93 |
-
},
|
94 |
-
"50263": {
|
95 |
-
"content": " ",
|
96 |
-
"lstrip": false,
|
97 |
-
"normalized": true,
|
98 |
-
"rstrip": false,
|
99 |
-
"single_word": false,
|
100 |
-
"special": false
|
101 |
-
},
|
102 |
-
"50264": {
|
103 |
-
"content": " ",
|
104 |
-
"lstrip": false,
|
105 |
-
"normalized": true,
|
106 |
-
"rstrip": false,
|
107 |
-
"single_word": false,
|
108 |
-
"special": false
|
109 |
-
},
|
110 |
-
"50265": {
|
111 |
-
"content": " ",
|
112 |
-
"lstrip": false,
|
113 |
-
"normalized": true,
|
114 |
-
"rstrip": false,
|
115 |
-
"single_word": false,
|
116 |
-
"special": false
|
117 |
-
},
|
118 |
-
"50266": {
|
119 |
-
"content": " ",
|
120 |
-
"lstrip": false,
|
121 |
-
"normalized": true,
|
122 |
-
"rstrip": false,
|
123 |
-
"single_word": false,
|
124 |
-
"special": false
|
125 |
-
},
|
126 |
-
"50267": {
|
127 |
-
"content": " ",
|
128 |
-
"lstrip": false,
|
129 |
-
"normalized": true,
|
130 |
-
"rstrip": false,
|
131 |
-
"single_word": false,
|
132 |
-
"special": false
|
133 |
-
},
|
134 |
-
"50268": {
|
135 |
-
"content": " ",
|
136 |
-
"lstrip": false,
|
137 |
-
"normalized": true,
|
138 |
-
"rstrip": false,
|
139 |
-
"single_word": false,
|
140 |
-
"special": false
|
141 |
-
},
|
142 |
-
"50269": {
|
143 |
-
"content": " ",
|
144 |
-
"lstrip": false,
|
145 |
-
"normalized": true,
|
146 |
-
"rstrip": false,
|
147 |
-
"single_word": false,
|
148 |
-
"special": false
|
149 |
-
},
|
150 |
-
"50270": {
|
151 |
-
"content": " ",
|
152 |
-
"lstrip": false,
|
153 |
-
"normalized": true,
|
154 |
-
"rstrip": false,
|
155 |
-
"single_word": false,
|
156 |
-
"special": false
|
157 |
-
},
|
158 |
-
"50271": {
|
159 |
-
"content": " ",
|
160 |
-
"lstrip": false,
|
161 |
-
"normalized": true,
|
162 |
-
"rstrip": false,
|
163 |
-
"single_word": false,
|
164 |
-
"special": false
|
165 |
-
},
|
166 |
-
"50272": {
|
167 |
-
"content": " ",
|
168 |
-
"lstrip": false,
|
169 |
-
"normalized": true,
|
170 |
-
"rstrip": false,
|
171 |
-
"single_word": false,
|
172 |
-
"special": false
|
173 |
-
},
|
174 |
-
"50273": {
|
175 |
-
"content": " ",
|
176 |
-
"lstrip": false,
|
177 |
-
"normalized": true,
|
178 |
-
"rstrip": false,
|
179 |
-
"single_word": false,
|
180 |
-
"special": false
|
181 |
-
},
|
182 |
-
"50274": {
|
183 |
-
"content": " ",
|
184 |
-
"lstrip": false,
|
185 |
-
"normalized": true,
|
186 |
-
"rstrip": false,
|
187 |
-
"single_word": false,
|
188 |
-
"special": false
|
189 |
-
},
|
190 |
-
"50275": {
|
191 |
-
"content": " ",
|
192 |
-
"lstrip": false,
|
193 |
-
"normalized": true,
|
194 |
-
"rstrip": false,
|
195 |
-
"single_word": false,
|
196 |
-
"special": false
|
197 |
-
},
|
198 |
-
"50276": {
|
199 |
-
"content": " ",
|
200 |
-
"lstrip": false,
|
201 |
-
"normalized": true,
|
202 |
-
"rstrip": false,
|
203 |
-
"single_word": false,
|
204 |
-
"special": false
|
205 |
-
}
|
206 |
-
},
|
207 |
-
"bos_token": "<|endoftext|>",
|
208 |
-
"clean_up_tokenization_spaces": true,
|
209 |
-
"eos_token": "<|endoftext|>",
|
210 |
-
"max_length": 1024,
|
211 |
-
"model_max_length": 1000000000000000019884624838656,
|
212 |
-
"pad_token": "<|endoftext|>",
|
213 |
-
"stride": 0,
|
214 |
-
"tokenizer_class": "GPTNeoXTokenizer",
|
215 |
-
"truncation_side": "right",
|
216 |
-
"truncation_strategy": "longest_first",
|
217 |
-
"unk_token": "<|endoftext|>"
|
218 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|