nthngdy commited on
Commit
59d4c00
1 Parent(s): 5b6f75f

bs1024 version

Browse files
Files changed (3) hide show
  1. config.json +38 -0
  2. generation_config.json +6 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MantaForConditionalGeneration"
4
+ ],
5
+ "byte_embedding_dim": 128,
6
+ "d_ff": 2048,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "dense_act_fn": "gelu_new",
10
+ "dropout_rate": 0.1,
11
+ "eos_token_id": 1,
12
+ "feed_forward_proj": "gated-gelu",
13
+ "frontier_predictor_attention_window": 16,
14
+ "frontier_predictor_num_attention_heads": 8,
15
+ "frontier_predictor_num_layers": 2,
16
+ "initializer_factor": 1.0,
17
+ "is_encoder_decoder": true,
18
+ "is_gated_act": true,
19
+ "layer_norm_epsilon": 1e-06,
20
+ "max_length_encoder_decoder": 256,
21
+ "max_length_inputs": 2048,
22
+ "model_type": "manta",
23
+ "num_decoder_layers": 12,
24
+ "num_heads": 12,
25
+ "num_layers": 12,
26
+ "pad_token_id": 0,
27
+ "pooling_depthwise_convolution": true,
28
+ "pooling_kernel_size": 3,
29
+ "pooling_mean_pool": false,
30
+ "pooling_variance_regularization": 1e-06,
31
+ "relative_attention_max_distance": 128,
32
+ "relative_attention_num_buckets": 32,
33
+ "tie_word_embeddings": false,
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.29.2",
36
+ "use_cache": true,
37
+ "vocab_size": 384
38
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.29.2"
6
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5956d10734fc88ffbafc89ad81b371b3be9201e0b25de9818040e4314a9e3a1
3
+ size 797912349