Hugging Face's logo

jeiku
/
moondream2-onnx-bnb4

Image-Text-to-Text
Transformers.js
ONNX
moondream1
text-generation
custom_code
Model card Files Community
1
jeiku commited on
Commit
d5a1900
•
1 Parent(s): 7df796e

Upload 15 files

Browse files
Files changed (15) hide show
  1. .gitattributes +40 -35
  2. README.md +69 -0
  3. added_tokens.json +40 -0
  4. config.json +41 -0
  5. generation_config.json +6 -0
  6. merges.txt +0 -0
  7. onnx/decoder_model_merged_bnb4.onnx +3 -0
  8. onnx/embed_tokens_bnb4.onnx +3 -0
  9. onnx/vision_encoder_bnb4.onnx +3 -0
  10. preprocessor_config.json +23 -0
  11. quantize_config.json +329 -0
  12. special_tokens_map.json +23 -0
  13. tokenizer.json +0 -0
  14. tokenizer_config.json +331 -0
  15. vocab.json +0 -0
.gitattributes CHANGED
@@ -1,35 +1,40 @@
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
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ onnx/decoder_model.onnx_data filter=lfs diff=lfs merge=lfs -text
37
+ onnx/decoder_model_merged.onnx_data filter=lfs diff=lfs merge=lfs -text
38
+ onnx/decoder_with_past_model.onnx_data filter=lfs diff=lfs merge=lfs -text
39
+ onnx/decoder_model_merged_fp16.onnx_data filter=lfs diff=lfs merge=lfs -text
40
+ onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers.js
3
+ pipeline_tag: image-text-to-text
4
+ license: apache-2.0
5
+ ---
6
+
7
+ https://huggingface.co/vikhyatk/moondream2 with ONNX weights to be compatible with Transformers.js.
8
+
9
+
10
+ ## Usage (Transformers.js)
11
+
12
+ > [!IMPORTANT]
13
+ > NOTE: Moondream support is experimental and requires you to install Transformers.js [v3](https://github.com/xenova/transformers.js/tree/v3) from source.
14
+
15
+ If you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [GitHub](https://github.com/xenova/transformers.js/tree/v3) using:
16
+ ```bash
17
+ npm install xenova/transformers.js#v3
18
+ ```
19
+
20
+ **Example:**
21
+ ```js
22
+ import { AutoProcessor, AutoTokenizer, Moondream1ForConditionalGeneration, RawImage } from '@xenova/transformers';
23
+
24
+ // Load processor, tokenizer and model
25
+ const model_id = 'Xenova/moondream2';
26
+ const processor = await AutoProcessor.from_pretrained(model_id);
27
+ const tokenizer = await AutoTokenizer.from_pretrained(model_id);
28
+ const model = await Moondream1ForConditionalGeneration.from_pretrained(model_id, {
29
+ dtype: {
30
+ embed_tokens: 'fp16', // or 'fp32'
31
+ vision_encoder: 'fp16', // or 'q8'
32
+ decoder_model_merged: 'q4', // or 'q4f16' or 'q8'
33
+ },
34
+ device: 'webgpu',
35
+ });
36
+
37
+ // Prepare text inputs
38
+ const prompt = 'Describe this image.';
39
+ const text = `<image>\n\nQuestion: ${prompt}\n\nAnswer:`;
40
+ const text_inputs = tokenizer(text);
41
+
42
+ // Prepare vision inputs
43
+ const url = 'https://huggingface.co/vikhyatk/moondream1/resolve/main/assets/demo-1.jpg';
44
+ const image = await RawImage.fromURL(url);
45
+ const vision_inputs = await processor(image);
46
+
47
+ // Generate response
48
+ const output = await model.generate({
49
+ ...text_inputs,
50
+ ...vision_inputs,
51
+ do_sample: false,
52
+ max_new_tokens: 64,
53
+ });
54
+ const decoded = tokenizer.batch_decode(output, { skip_special_tokens: false });
55
+ console.log(decoded);
56
+ // [
57
+ // '<|endoftext|><image>\n\n' +
58
+ // 'Question: Describe this image.\n\n' +
59
+ // 'Answer: A hand is holding a white book titled "The Little Book of Deep Learning" against a backdrop of a balcony with a railing and a view of a building and trees.<|endoftext|>'
60
+ // ]
61
+ ```
62
+
63
+ We also released an online demo, which you can try yourself: https://huggingface.co/spaces/Xenova/experimental-moondream-webgpu
64
+
65
+ <video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/61b253b7ac5ecaae3d1efe0c/9q6LTQIYiI3qKrKfAb4D8.mp4"></video>
66
+
67
+ ---
68
+
69
+ Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).
added_tokens.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "\t\t": 50294,
3
+ "\t\t\t": 50293,
4
+ "\t\t\t\t": 50292,
5
+ "\t\t\t\t\t": 50291,
6
+ "\t\t\t\t\t\t": 50290,
7
+ "\t\t\t\t\t\t\t": 50289,
8
+ "\t\t\t\t\t\t\t\t": 50288,
9
+ "\t\t\t\t\t\t\t\t\t": 50287,
10
+ " ": 50286,
11
+ " ": 50285,
12
+ " ": 50284,
13
+ " ": 50283,
14
+ " ": 50282,
15
+ " ": 50281,
16
+ " ": 50280,
17
+ " ": 50279,
18
+ " ": 50278,
19
+ " ": 50277,
20
+ " ": 50276,
21
+ " ": 50275,
22
+ " ": 50274,
23
+ " ": 50273,
24
+ " ": 50272,
25
+ " ": 50271,
26
+ " ": 50270,
27
+ " ": 50269,
28
+ " ": 50268,
29
+ " ": 50267,
30
+ " ": 50266,
31
+ " ": 50265,
32
+ " ": 50264,
33
+ " ": 50263,
34
+ " ": 50262,
35
+ " ": 50261,
36
+ " ": 50260,
37
+ " ": 50259,
38
+ " ": 50258,
39
+ " ": 50257
40
+ }
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Moondream"
4
+ ],
5
+ "auto_map": {
6
+ "AutoConfig": "configuration_moondream.MoondreamConfig",
7
+ "AutoModelForCausalLM": "moondream.Moondream"
8
+ },
9
+ "model_type": "moondream1",
10
+ "phi_config": {
11
+ "architectures": [
12
+ "PhiForCausalLM"
13
+ ],
14
+ "attention_dropout": 0.0,
15
+ "bos_token_id": 50256,
16
+ "embd_pdrop": 0.0,
17
+ "eos_token_id": 50256,
18
+ "hidden_act": "gelu_new",
19
+ "hidden_size": 2048,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 8192,
22
+ "layer_norm_eps": 1e-05,
23
+ "max_position_embeddings": 2048,
24
+ "model_type": "phi",
25
+ "num_attention_heads": 32,
26
+ "num_hidden_layers": 24,
27
+ "num_key_value_heads": 32,
28
+ "partial_rotary_factor": 0.5,
29
+ "qk_layernorm": false,
30
+ "resid_pdrop": 0.0,
31
+ "rope_scaling": null,
32
+ "rope_theta": 10000.0,
33
+ "tie_word_embeddings": false,
34
+ "transformers_version": "4.38.2",
35
+ "use_cache": true,
36
+ "vocab_size": 51200
37
+ },
38
+ "torch_dtype": "float16",
39
+ "transformers_version": "4.38.2",
40
+ "image_token_index": -200
41
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.38.2"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
onnx/decoder_model_merged_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33a5b77971745a0cd7d926fadf805b18c027d3368a8ba469e3427fb3e45dc43a
3
+ size 742293206
onnx/embed_tokens_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e83c0024e7785c5946ecda27729cdb4d32d5e6b72d75bc58a155f3d7247967ef
3
+ size 419430658
onnx/vision_encoder_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16e58e62576028dd79b630744176b870adc455ed145b45a0524b6d45a6bfb048
3
+ size 251839217
preprocessor_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_rescale": true,
4
+ "do_resize": true,
5
+ "image_mean": [
6
+ 0.5,
7
+ 0.5,
8
+ 0.5
9
+ ],
10
+ "image_processor_type": "SiglipImageProcessor",
11
+ "image_std": [
12
+ 0.5,
13
+ 0.5,
14
+ 0.5
15
+ ],
16
+ "processor_class": "SiglipProcessor",
17
+ "resample": 3,
18
+ "rescale_factor": 0.00392156862745098,
19
+ "size": {
20
+ "height": 378,
21
+ "width": 378
22
+ }
23
+ }
quantize_config.json ADDED
@@ -0,0 +1,329 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "q8": {
3
+ "per_model_config": {
4
+ "decoder_with_past_model": {
5
+ "op_types": [
6
+ "Add",
7
+ "Cast",
8
+ "Concat",
9
+ "Constant",
10
+ "ConstantOfShape",
11
+ "Div",
12
+ "Equal",
13
+ "Expand",
14
+ "Gather",
15
+ "Identity",
16
+ "Less",
17
+ "MatMul",
18
+ "Mul",
19
+ "Neg",
20
+ "Pow",
21
+ "Range",
22
+ "ReduceMean",
23
+ "Reshape",
24
+ "Shape",
25
+ "Slice",
26
+ "Softmax",
27
+ "Sqrt",
28
+ "Squeeze",
29
+ "Sub",
30
+ "Tanh",
31
+ "Transpose",
32
+ "Unsqueeze",
33
+ "Where"
34
+ ],
35
+ "weight_type": "QInt8"
36
+ },
37
+ "decoder_model": {
38
+ "op_types": [
39
+ "Add",
40
+ "Cast",
41
+ "Concat",
42
+ "Constant",
43
+ "ConstantOfShape",
44
+ "Div",
45
+ "Equal",
46
+ "Expand",
47
+ "Gather",
48
+ "Identity",
49
+ "Less",
50
+ "MatMul",
51
+ "Mul",
52
+ "Neg",
53
+ "Pow",
54
+ "Range",
55
+ "ReduceMean",
56
+ "Reshape",
57
+ "Shape",
58
+ "Slice",
59
+ "Softmax",
60
+ "Sqrt",
61
+ "Squeeze",
62
+ "Sub",
63
+ "Tanh",
64
+ "Transpose",
65
+ "Unsqueeze",
66
+ "Where"
67
+ ],
68
+ "weight_type": "QInt8"
69
+ },
70
+ "decoder_model_merged": {
71
+ "op_types": [
72
+ "Add",
73
+ "Cast",
74
+ "Concat",
75
+ "Constant",
76
+ "ConstantOfShape",
77
+ "Div",
78
+ "Equal",
79
+ "Expand",
80
+ "Gather",
81
+ "Identity",
82
+ "If",
83
+ "Less",
84
+ "MatMul",
85
+ "Mul",
86
+ "Neg",
87
+ "Pow",
88
+ "Range",
89
+ "ReduceMean",
90
+ "Reshape",
91
+ "Shape",
92
+ "Slice",
93
+ "Softmax",
94
+ "Sqrt",
95
+ "Squeeze",
96
+ "Sub",
97
+ "Tanh",
98
+ "Transpose",
99
+ "Unsqueeze",
100
+ "Where"
101
+ ],
102
+ "weight_type": "QInt8"
103
+ }
104
+ },
105
+ "per_channel": false,
106
+ "reduce_range": false
107
+ },
108
+ "int8": {
109
+ "per_model_config": {
110
+ "decoder_with_past_model": {
111
+ "op_types": [
112
+ "Add",
113
+ "Cast",
114
+ "Concat",
115
+ "Constant",
116
+ "ConstantOfShape",
117
+ "Div",
118
+ "Equal",
119
+ "Expand",
120
+ "Gather",
121
+ "Identity",
122
+ "Less",
123
+ "MatMul",
124
+ "Mul",
125
+ "Neg",
126
+ "Pow",
127
+ "Range",
128
+ "ReduceMean",
129
+ "Reshape",
130
+ "Shape",
131
+ "Slice",
132
+ "Softmax",
133
+ "Sqrt",
134
+ "Squeeze",
135
+ "Sub",
136
+ "Tanh",
137
+ "Transpose",
138
+ "Unsqueeze",
139
+ "Where"
140
+ ],
141
+ "weight_type": "QInt8"
142
+ },
143
+ "decoder_model": {
144
+ "op_types": [
145
+ "Add",
146
+ "Cast",
147
+ "Concat",
148
+ "Constant",
149
+ "ConstantOfShape",
150
+ "Div",
151
+ "Equal",
152
+ "Expand",
153
+ "Gather",
154
+ "Identity",
155
+ "Less",
156
+ "MatMul",
157
+ "Mul",
158
+ "Neg",
159
+ "Pow",
160
+ "Range",
161
+ "ReduceMean",
162
+ "Reshape",
163
+ "Shape",
164
+ "Slice",
165
+ "Softmax",
166
+ "Sqrt",
167
+ "Squeeze",
168
+ "Sub",
169
+ "Tanh",
170
+ "Transpose",
171
+ "Unsqueeze",
172
+ "Where"
173
+ ],
174
+ "weight_type": "QInt8"
175
+ },
176
+ "decoder_model_merged": {
177
+ "op_types": [
178
+ "Add",
179
+ "Cast",
180
+ "Concat",
181
+ "Constant",
182
+ "ConstantOfShape",
183
+ "Div",
184
+ "Equal",
185
+ "Expand",
186
+ "Gather",
187
+ "Identity",
188
+ "If",
189
+ "Less",
190
+ "MatMul",
191
+ "Mul",
192
+ "Neg",
193
+ "Pow",
194
+ "Range",
195
+ "ReduceMean",
196
+ "Reshape",
197
+ "Shape",
198
+ "Slice",
199
+ "Softmax",
200
+ "Sqrt",
201
+ "Squeeze",
202
+ "Sub",
203
+ "Tanh",
204
+ "Transpose",
205
+ "Unsqueeze",
206
+ "Where"
207
+ ],
208
+ "weight_type": "QInt8"
209
+ }
210
+ },
211
+ "per_channel": false,
212
+ "reduce_range": false
213
+ },
214
+ "uint8": {
215
+ "per_model_config": {
216
+ "decoder_with_past_model": {
217
+ "op_types": [
218
+ "Add",
219
+ "Cast",
220
+ "Concat",
221
+ "Constant",
222
+ "ConstantOfShape",
223
+ "Div",
224
+ "Equal",
225
+ "Expand",
226
+ "Gather",
227
+ "Identity",
228
+ "Less",
229
+ "MatMul",
230
+ "Mul",
231
+ "Neg",
232
+ "Pow",
233
+ "Range",
234
+ "ReduceMean",
235
+ "Reshape",
236
+ "Shape",
237
+ "Slice",
238
+ "Softmax",
239
+ "Sqrt",
240
+ "Squeeze",
241
+ "Sub",
242
+ "Tanh",
243
+ "Transpose",
244
+ "Unsqueeze",
245
+ "Where"
246
+ ],
247
+ "weight_type": "QUInt8"
248
+ },
249
+ "decoder_model": {
250
+ "op_types": [
251
+ "Add",
252
+ "Cast",
253
+ "Concat",
254
+ "Constant",
255
+ "ConstantOfShape",
256
+ "Div",
257
+ "Equal",
258
+ "Expand",
259
+ "Gather",
260
+ "Identity",
261
+ "Less",
262
+ "MatMul",
263
+ "Mul",
264
+ "Neg",
265
+ "Pow",
266
+ "Range",
267
+ "ReduceMean",
268
+ "Reshape",
269
+ "Shape",
270
+ "Slice",
271
+ "Softmax",
272
+ "Sqrt",
273
+ "Squeeze",
274
+ "Sub",
275
+ "Tanh",
276
+ "Transpose",
277
+ "Unsqueeze",
278
+ "Where"
279
+ ],
280
+ "weight_type": "QUInt8"
281
+ },
282
+ "decoder_model_merged": {
283
+ "op_types": [
284
+ "Add",
285
+ "Cast",
286
+ "Concat",
287
+ "Constant",
288
+ "ConstantOfShape",
289
+ "Div",
290
+ "Equal",
291
+ "Expand",
292
+ "Gather",
293
+ "Identity",
294
+ "If",
295
+ "Less",
296
+ "MatMul",
297
+ "Mul",
298
+ "Neg",
299
+ "Pow",
300
+ "Range",
301
+ "ReduceMean",
302
+ "Reshape",
303
+ "Shape",
304
+ "Slice",
305
+ "Softmax",
306
+ "Sqrt",
307
+ "Squeeze",
308
+ "Sub",
309
+ "Tanh",
310
+ "Transpose",
311
+ "Unsqueeze",
312
+ "Where"
313
+ ],
314
+ "weight_type": "QUInt8"
315
+ }
316
+ },
317
+ "per_channel": false,
318
+ "reduce_range": false
319
+ },
320
+ "q4": {
321
+ "block_size": 32,
322
+ "is_symmetric": true,
323
+ "accuracy_level": null
324
+ },
325
+ "bnb4": {
326
+ "block_size": 64,
327
+ "quant_type": 1
328
+ }
329
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "unk_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,331 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "-200": {
5
+ "content": "<image>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50256": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "50257": {
21
+ "content": " ",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ },
28
+ "50258": {
29
+ "content": " ",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "50259": {
37
+ "content": " ",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "50260": {
45
+ "content": " ",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50261": {
53
+ "content": " ",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50262": {
61
+ "content": " ",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "50263": {
69
+ "content": " ",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "50264": {
77
+ "content": " ",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "50265": {
85
+ "content": " ",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "50266": {
93
+ "content": " ",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "50267": {
101
+ "content": " ",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "50268": {
109
+ "content": " ",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "50269": {
117
+ "content": " ",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "50270": {
125
+ "content": " ",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "50271": {
133
+ "content": " ",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "50272": {
141
+ "content": " ",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "50273": {
149
+ "content": " ",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "50274": {
157
+ "content": " ",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "50275": {
165
+ "content": " ",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "50276": {
173
+ "content": " ",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "50277": {
181
+ "content": " ",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "50278": {
189
+ "content": " ",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "50279": {
197
+ "content": " ",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "50280": {
205
+ "content": " ",
206
+ "lstrip": false,
207
+ "normalized": true,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "50281": {
213
+ "content": " ",
214
+ "lstrip": false,
215
+ "normalized": true,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": false
219
+ },
220
+ "50282": {
221
+ "content": " ",
222
+ "lstrip": false,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": false
227
+ },
228
+ "50283": {
229
+ "content": " ",
230
+ "lstrip": false,
231
+ "normalized": true,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": false
235
+ },
236
+ "50284": {
237
+ "content": " ",
238
+ "lstrip": false,
239
+ "normalized": true,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": false
243
+ },
244
+ "50285": {
245
+ "content": " ",
246
+ "lstrip": false,
247
+ "normalized": true,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": false
251
+ },
252
+ "50286": {
253
+ "content": " ",
254
+ "lstrip": false,
255
+ "normalized": true,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": false
259
+ },
260
+ "50287": {
261
+ "content": "\t\t\t\t\t\t\t\t\t",
262
+ "lstrip": false,
263
+ "normalized": true,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": false
267
+ },
268
+ "50288": {
269
+ "content": "\t\t\t\t\t\t\t\t",
270
+ "lstrip": false,
271
+ "normalized": true,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": false
275
+ },
276
+ "50289": {
277
+ "content": "\t\t\t\t\t\t\t",
278
+ "lstrip": false,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": false
283
+ },
284
+ "50290": {
285
+ "content": "\t\t\t\t\t\t",
286
+ "lstrip": false,
287
+ "normalized": true,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": false
291
+ },
292
+ "50291": {
293
+ "content": "\t\t\t\t\t",
294
+ "lstrip": false,
295
+ "normalized": true,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": false
299
+ },
300
+ "50292": {
301
+ "content": "\t\t\t\t",
302
+ "lstrip": false,
303
+ "normalized": true,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": false
307
+ },
308
+ "50293": {
309
+ "content": "\t\t\t",
310
+ "lstrip": false,
311
+ "normalized": true,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": false
315
+ },
316
+ "50294": {
317
+ "content": "\t\t",
318
+ "lstrip": false,
319
+ "normalized": true,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": false
323
+ }
324
+ },
325
+ "bos_token": "<|endoftext|>",
326
+ "clean_up_tokenization_spaces": true,
327
+ "eos_token": "<|endoftext|>",
328
+ "model_max_length": 2048,
329
+ "tokenizer_class": "CodeGenTokenizer",
330
+ "unk_token": "<|endoftext|>"
331
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff