Upload PerceiverTextClassifier
Browse files- config.json +58 -0
- pytorch_model.bin +3 -0
config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"PerceiverTextClassifier"
|
4 |
+
],
|
5 |
+
"id2label": {
|
6 |
+
"0": "NEGATIVE",
|
7 |
+
"1": "POSITIVE"
|
8 |
+
},
|
9 |
+
"label2id": {
|
10 |
+
"NEGATIVE": 0,
|
11 |
+
"POSITIVE": 1
|
12 |
+
},
|
13 |
+
"model_config": {
|
14 |
+
"activation_checkpointing": true,
|
15 |
+
"activation_offloading": false,
|
16 |
+
"decoder": {
|
17 |
+
"cross_attention_residual": true,
|
18 |
+
"cross_attention_widening_factor": 1,
|
19 |
+
"dropout": 0.1,
|
20 |
+
"freeze": false,
|
21 |
+
"init_scale": 0.02,
|
22 |
+
"num_classes": 2,
|
23 |
+
"num_cross_attention_heads": 1,
|
24 |
+
"num_cross_attention_qk_channels": null,
|
25 |
+
"num_cross_attention_v_channels": null,
|
26 |
+
"num_output_queries": 1,
|
27 |
+
"num_output_query_channels": 768
|
28 |
+
},
|
29 |
+
"encoder": {
|
30 |
+
"cross_attention_widening_factor": 1,
|
31 |
+
"dropout": 0.1,
|
32 |
+
"first_cross_attention_layer_shared": false,
|
33 |
+
"first_self_attention_block_shared": true,
|
34 |
+
"freeze": false,
|
35 |
+
"init_scale": 0.02,
|
36 |
+
"max_seq_len": 2048,
|
37 |
+
"num_cross_attention_heads": 8,
|
38 |
+
"num_cross_attention_layers": 1,
|
39 |
+
"num_cross_attention_qk_channels": 256,
|
40 |
+
"num_cross_attention_v_channels": 1280,
|
41 |
+
"num_input_channels": 768,
|
42 |
+
"num_self_attention_blocks": 1,
|
43 |
+
"num_self_attention_heads": 8,
|
44 |
+
"num_self_attention_layers_per_block": 26,
|
45 |
+
"num_self_attention_qk_channels": 256,
|
46 |
+
"num_self_attention_v_channels": 1280,
|
47 |
+
"params": null,
|
48 |
+
"self_attention_widening_factor": 1,
|
49 |
+
"vocab_size": 262
|
50 |
+
},
|
51 |
+
"num_latent_channels": 1280,
|
52 |
+
"num_latents": 256
|
53 |
+
},
|
54 |
+
"model_type": "perceiver-io-text-classifier",
|
55 |
+
"tokenizer_class": "PerceiverTokenizer",
|
56 |
+
"torch_dtype": "float32",
|
57 |
+
"transformers_version": "4.28.0"
|
58 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa90be50862ac411d7170c02dc8210680b2b119aaacf0f99e053700cd63d48ae
|
3 |
+
size 802502005
|