vijaye12
commited on
Commit
•
bac72b9
1
Parent(s):
1fe1a51
adding 512 model with freq tuning
Browse files- config.json +57 -0
- generation_config.json +4 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"adaptive_patching_levels": 3,
|
3 |
+
"architectures": [
|
4 |
+
"TinyTimeMixerForPrediction"
|
5 |
+
],
|
6 |
+
"categorical_vocab_size_list": null,
|
7 |
+
"context_length": 512,
|
8 |
+
"d_model": 192,
|
9 |
+
"d_model_scale": 3,
|
10 |
+
"decoder_adaptive_patching_levels": 0,
|
11 |
+
"decoder_d_model": 128,
|
12 |
+
"decoder_d_model_scale": 2,
|
13 |
+
"decoder_mode": "common_channel",
|
14 |
+
"decoder_num_layers": 2,
|
15 |
+
"decoder_raw_residual": false,
|
16 |
+
"distribution_output": "student_t",
|
17 |
+
"dropout": 0.4,
|
18 |
+
"enable_forecast_channel_mixing": false,
|
19 |
+
"exogenous_channel_indices": null,
|
20 |
+
"expansion_factor": 2,
|
21 |
+
"fcm_context_length": 1,
|
22 |
+
"fcm_gated_attn": true,
|
23 |
+
"fcm_mix_layers": 3,
|
24 |
+
"fcm_prepend_past": true,
|
25 |
+
"fcm_use_mixer": true,
|
26 |
+
"frequency_token_vocab_size": 8,
|
27 |
+
"gated_attn": true,
|
28 |
+
"head_dropout": 0.4,
|
29 |
+
"init_processing": true,
|
30 |
+
"init_std": 0.02,
|
31 |
+
"loss": "mse",
|
32 |
+
"mode": "common_channel",
|
33 |
+
"model_type": "tinytimemixer",
|
34 |
+
"norm_eps": 1e-05,
|
35 |
+
"norm_mlp": "LayerNorm",
|
36 |
+
"num_input_channels": 1,
|
37 |
+
"num_layers": 2,
|
38 |
+
"num_parallel_samples": 100,
|
39 |
+
"num_patches": 9,
|
40 |
+
"patch_last": true,
|
41 |
+
"patch_length": 64,
|
42 |
+
"patch_stride": 64,
|
43 |
+
"positional_encoding_type": "sincos",
|
44 |
+
"post_init": false,
|
45 |
+
"prediction_channel_indices": null,
|
46 |
+
"prediction_filter_length": null,
|
47 |
+
"prediction_length": 96,
|
48 |
+
"resolution_prefix_tuning": true,
|
49 |
+
"scaling": "std",
|
50 |
+
"self_attn": false,
|
51 |
+
"self_attn_heads": 1,
|
52 |
+
"stride_ratio": 1,
|
53 |
+
"torch_dtype": "float32",
|
54 |
+
"transformers_version": "4.37.2",
|
55 |
+
"use_decoder": true,
|
56 |
+
"use_positional_encoding": false
|
57 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"transformers_version": "4.37.2"
|
4 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:105777859c941765e4f5f3de2d577a95ce40c2d3a6e8b7ac7721c356751d93c5
|
3 |
+
size 3439896
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3fd0d2a38092a6c70bc07a578dd8425674131c1fda4e49a24748117190b053aa
|
3 |
+
size 4856
|