Upload model
Browse files- config.json +29 -0
- generation_config.json +4 -0
- pytorch_model.bin +3 -0
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"PerceiverCausalLanguageModel"
|
4 |
+
],
|
5 |
+
"is_decoder": true,
|
6 |
+
"model_config": {
|
7 |
+
"abs_pos_emb": false,
|
8 |
+
"activation_checkpointing": false,
|
9 |
+
"activation_offloading": false,
|
10 |
+
"cross_attention_dropout": 0.0,
|
11 |
+
"cross_attention_widening_factor": 4,
|
12 |
+
"init_scale": 0.02,
|
13 |
+
"max_heads_parallel": 2,
|
14 |
+
"max_latents": 512,
|
15 |
+
"max_seq_len": 1024,
|
16 |
+
"num_channels": 1280,
|
17 |
+
"num_heads": 10,
|
18 |
+
"num_self_attention_layers": 20,
|
19 |
+
"output_bias": false,
|
20 |
+
"output_norm": true,
|
21 |
+
"post_attention_dropout": 0.0,
|
22 |
+
"self_attention_widening_factor": 4,
|
23 |
+
"vocab_size": 32000
|
24 |
+
},
|
25 |
+
"model_type": "perceiver-ar-causal-language-model",
|
26 |
+
"tokenizer_class": "XLNetTokenizerFast",
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.28.0"
|
29 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"transformers_version": "4.28.0"
|
4 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aaa4e2ac321bcaf8080e1b086d62c484b644bf680a6f1c17618be591c23805c5
|
3 |
+
size 1815876273
|