ml233 commited on
Commit
ff6ff65
·
verified ·
1 Parent(s): cfefd61

Push model using huggingface_hub.

Browse files
Files changed (3) hide show
  1. README.md +9 -0
  2. config.json +39 -0
  3. model.safetensors +3 -0
README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - model_hub_mixin
4
+ - pytorch_model_hub_mixin
5
+ ---
6
+
7
+ This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
8
+ - Library: [More Information Needed]
9
+ - Docs: [More Information Needed]
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "d_model": null,
3
+ "device": "cpu",
4
+ "model_kwargs": {},
5
+ "model_name": "MOMENT",
6
+ "patch_len": 8,
7
+ "patch_stride_len": 8,
8
+ "seq_len": 512,
9
+ "t5_config": {
10
+ "architectures": [
11
+ "T5ForConditionalGeneration"
12
+ ],
13
+ "d_ff": 2816,
14
+ "d_kv": 64,
15
+ "d_model": 1024,
16
+ "decoder_start_token_id": 0,
17
+ "dropout_rate": 0.1,
18
+ "eos_token_id": 1,
19
+ "feed_forward_proj": "gated-gelu",
20
+ "initializer_factor": 1.0,
21
+ "is_encoder_decoder": true,
22
+ "layer_norm_epsilon": 1e-06,
23
+ "model_type": "t5",
24
+ "n_positions": 512,
25
+ "num_decoder_layers": 24,
26
+ "num_heads": 16,
27
+ "num_layers": 24,
28
+ "output_past": true,
29
+ "pad_token_id": 0,
30
+ "relative_attention_max_distance": 128,
31
+ "relative_attention_num_buckets": 32,
32
+ "tie_word_embeddings": false,
33
+ "use_cache": true,
34
+ "vocab_size": 32128
35
+ },
36
+ "task_name": "reconstruction",
37
+ "transformer_backbone": "google/flan-t5-large",
38
+ "transformer_type": "encoder_only"
39
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8894f32351ef3855d7d86e274367c0cc11790086b54a325c50bced8bab599fc0
3
+ size 1412765008