Upload Florence2ForConditionalGeneration
Browse files- README.md +3 -0
- config.json +19 -19
- generation_config.json +0 -9
- model.safetensors +2 -2
README.md
CHANGED
@@ -1,3 +1,6 @@
|
|
|
|
|
|
|
|
1 |
```
|
2 |
import os
|
3 |
|
|
|
1 |
+
---
|
2 |
+
{}
|
3 |
+
---
|
4 |
```
|
5 |
import os
|
6 |
|
config.json
CHANGED
@@ -1,11 +1,11 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"Florence2ForConditionalGeneration"
|
5 |
],
|
6 |
"auto_map": {
|
7 |
-
"AutoConfig": "configuration_florence2.Florence2Config",
|
8 |
-
"AutoModelForCausalLM": "modeling_florence2.Florence2ForConditionalGeneration"
|
9 |
},
|
10 |
"bos_token_id": 2,
|
11 |
"eos_token_id": 1,
|
@@ -13,7 +13,7 @@
|
|
13 |
"is_encoder_decoder": true,
|
14 |
"model_type": "florence2",
|
15 |
"pad_token_id": 0,
|
16 |
-
"projection_dim":
|
17 |
"text_config": {
|
18 |
"_name_or_path": "",
|
19 |
"activation_dropout": 0.1,
|
@@ -30,20 +30,20 @@
|
|
30 |
"classif_dropout": 0.1,
|
31 |
"classifier_dropout": 0.0,
|
32 |
"cross_attention_hidden_size": null,
|
33 |
-
"d_model":
|
34 |
-
"decoder_attention_heads":
|
35 |
-
"decoder_ffn_dim":
|
36 |
"decoder_layerdrop": 0.0,
|
37 |
-
"decoder_layers":
|
38 |
"decoder_start_token_id": 2,
|
39 |
"diversity_penalty": 0.0,
|
40 |
"do_sample": false,
|
41 |
"dropout": 0.1,
|
42 |
"early_stopping": true,
|
43 |
-
"encoder_attention_heads":
|
44 |
-
"encoder_ffn_dim":
|
45 |
"encoder_layerdrop": 0.0,
|
46 |
-
"encoder_layers":
|
47 |
"encoder_no_repeat_ngram_size": 0,
|
48 |
"eos_token_id": 2,
|
49 |
"exponential_decay_length_penalty": null,
|
@@ -73,7 +73,7 @@
|
|
73 |
"normalize_before": false,
|
74 |
"num_beam_groups": 1,
|
75 |
"num_beams": 3,
|
76 |
-
"num_hidden_layers":
|
77 |
"num_return_sequences": 1,
|
78 |
"output_attentions": false,
|
79 |
"output_hidden_states": false,
|
@@ -123,10 +123,10 @@
|
|
123 |
1
|
124 |
],
|
125 |
"dim_embed": [
|
126 |
-
128,
|
127 |
256,
|
128 |
512,
|
129 |
-
1024
|
|
|
130 |
],
|
131 |
"diversity_penalty": 0.0,
|
132 |
"do_sample": false,
|
@@ -165,16 +165,16 @@
|
|
165 |
"num_beam_groups": 1,
|
166 |
"num_beams": 1,
|
167 |
"num_groups": [
|
168 |
-
4,
|
169 |
8,
|
170 |
16,
|
171 |
-
32
|
|
|
172 |
],
|
173 |
"num_heads": [
|
174 |
-
4,
|
175 |
8,
|
176 |
16,
|
177 |
-
32
|
|
|
178 |
],
|
179 |
"num_return_sequences": 1,
|
180 |
"output_attentions": false,
|
@@ -207,7 +207,7 @@
|
|
207 |
],
|
208 |
"prefix": null,
|
209 |
"problem_type": null,
|
210 |
-
"projection_dim":
|
211 |
"pruned_heads": {},
|
212 |
"remove_invalid_values": false,
|
213 |
"repetition_penalty": 1.0,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "microsoft/Florence-2-large-ft",
|
3 |
"architectures": [
|
4 |
"Florence2ForConditionalGeneration"
|
5 |
],
|
6 |
"auto_map": {
|
7 |
+
"AutoConfig": "microsoft/Florence-2-large-ft--configuration_florence2.Florence2Config",
|
8 |
+
"AutoModelForCausalLM": "microsoft/Florence-2-large-ft--modeling_florence2.Florence2ForConditionalGeneration"
|
9 |
},
|
10 |
"bos_token_id": 2,
|
11 |
"eos_token_id": 1,
|
|
|
13 |
"is_encoder_decoder": true,
|
14 |
"model_type": "florence2",
|
15 |
"pad_token_id": 0,
|
16 |
+
"projection_dim": 1024,
|
17 |
"text_config": {
|
18 |
"_name_or_path": "",
|
19 |
"activation_dropout": 0.1,
|
|
|
30 |
"classif_dropout": 0.1,
|
31 |
"classifier_dropout": 0.0,
|
32 |
"cross_attention_hidden_size": null,
|
33 |
+
"d_model": 1024,
|
34 |
+
"decoder_attention_heads": 16,
|
35 |
+
"decoder_ffn_dim": 4096,
|
36 |
"decoder_layerdrop": 0.0,
|
37 |
+
"decoder_layers": 12,
|
38 |
"decoder_start_token_id": 2,
|
39 |
"diversity_penalty": 0.0,
|
40 |
"do_sample": false,
|
41 |
"dropout": 0.1,
|
42 |
"early_stopping": true,
|
43 |
+
"encoder_attention_heads": 16,
|
44 |
+
"encoder_ffn_dim": 4096,
|
45 |
"encoder_layerdrop": 0.0,
|
46 |
+
"encoder_layers": 12,
|
47 |
"encoder_no_repeat_ngram_size": 0,
|
48 |
"eos_token_id": 2,
|
49 |
"exponential_decay_length_penalty": null,
|
|
|
73 |
"normalize_before": false,
|
74 |
"num_beam_groups": 1,
|
75 |
"num_beams": 3,
|
76 |
+
"num_hidden_layers": 12,
|
77 |
"num_return_sequences": 1,
|
78 |
"output_attentions": false,
|
79 |
"output_hidden_states": false,
|
|
|
123 |
1
|
124 |
],
|
125 |
"dim_embed": [
|
|
|
126 |
256,
|
127 |
512,
|
128 |
+
1024,
|
129 |
+
2048
|
130 |
],
|
131 |
"diversity_penalty": 0.0,
|
132 |
"do_sample": false,
|
|
|
165 |
"num_beam_groups": 1,
|
166 |
"num_beams": 1,
|
167 |
"num_groups": [
|
|
|
168 |
8,
|
169 |
16,
|
170 |
+
32,
|
171 |
+
64
|
172 |
],
|
173 |
"num_heads": [
|
|
|
174 |
8,
|
175 |
16,
|
176 |
+
32,
|
177 |
+
64
|
178 |
],
|
179 |
"num_return_sequences": 1,
|
180 |
"output_attentions": false,
|
|
|
207 |
],
|
208 |
"prefix": null,
|
209 |
"problem_type": null,
|
210 |
+
"projection_dim": 1024,
|
211 |
"pruned_heads": {},
|
212 |
"remove_invalid_values": false,
|
213 |
"repetition_penalty": 1.0,
|
generation_config.json
CHANGED
@@ -1,13 +1,4 @@
|
|
1 |
{
|
2 |
-
"_from_model_config": true,
|
3 |
-
"bos_token_id": 2,
|
4 |
-
"decoder_start_token_id": 2,
|
5 |
-
"early_stopping": true,
|
6 |
-
"eos_token_id": 1,
|
7 |
-
"forced_bos_token_id": 0,
|
8 |
-
"forced_eos_token_id": 2,
|
9 |
-
"no_repeat_ngram_size": 3,
|
10 |
"num_beams": 3,
|
11 |
-
"pad_token_id": 0,
|
12 |
"transformers_version": "4.41.2"
|
13 |
}
|
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"num_beams": 3,
|
|
|
3 |
"transformers_version": "4.41.2"
|
4 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22b6e4524ea080b9f7f2a07bd316c2917ad5934b05a11048063fa4279cc4b82b
|
3 |
+
size 3291921348
|