Push model using huggingface_hub.
Browse files- README.md +12 -0
- config.json +62 -0
- model.safetensors +3 -0
README.md
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
pipeline_tag: text-to-speech
|
| 4 |
+
tags:
|
| 5 |
+
- model_hub_mixin
|
| 6 |
+
- pytorch_model_hub_mixin
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
|
| 10 |
+
- Code: https://github.com/nari-labs/dia
|
| 11 |
+
- Paper: [More Information Needed]
|
| 12 |
+
- Docs: [More Information Needed]
|
config.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DiaForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"bos_token_id": 1026,
|
| 6 |
+
"decoder_config": {
|
| 7 |
+
"cross_head_dim": 128,
|
| 8 |
+
"cross_hidden_size": 1024,
|
| 9 |
+
"cross_num_attention_heads": 16,
|
| 10 |
+
"cross_num_key_value_heads": 16,
|
| 11 |
+
"head_dim": 128,
|
| 12 |
+
"hidden_act": "silu",
|
| 13 |
+
"hidden_size": 2048,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 8192,
|
| 16 |
+
"max_position_embeddings": 3072,
|
| 17 |
+
"model_type": "dia_decoder",
|
| 18 |
+
"norm_eps": 1e-05,
|
| 19 |
+
"num_attention_heads": 16,
|
| 20 |
+
"num_channels": 9,
|
| 21 |
+
"num_hidden_layers": 18,
|
| 22 |
+
"num_key_value_heads": 4,
|
| 23 |
+
"rope_scaling": null,
|
| 24 |
+
"rope_theta": 10000.0,
|
| 25 |
+
"vocab_size": 1028
|
| 26 |
+
},
|
| 27 |
+
"delay_pattern": [
|
| 28 |
+
0,
|
| 29 |
+
8,
|
| 30 |
+
9,
|
| 31 |
+
10,
|
| 32 |
+
11,
|
| 33 |
+
12,
|
| 34 |
+
13,
|
| 35 |
+
14,
|
| 36 |
+
15
|
| 37 |
+
],
|
| 38 |
+
"encoder_config": {
|
| 39 |
+
"head_dim": 128,
|
| 40 |
+
"hidden_act": "silu",
|
| 41 |
+
"hidden_size": 1024,
|
| 42 |
+
"initializer_range": 0.02,
|
| 43 |
+
"intermediate_size": 4096,
|
| 44 |
+
"max_position_embeddings": 1024,
|
| 45 |
+
"model_type": "dia_encoder",
|
| 46 |
+
"norm_eps": 1e-05,
|
| 47 |
+
"num_attention_heads": 16,
|
| 48 |
+
"num_hidden_layers": 12,
|
| 49 |
+
"num_key_value_heads": 16,
|
| 50 |
+
"rope_scaling": null,
|
| 51 |
+
"rope_theta": 10000.0,
|
| 52 |
+
"vocab_size": 256
|
| 53 |
+
},
|
| 54 |
+
"eos_token_id": 1024,
|
| 55 |
+
"initializer_range": 0.02,
|
| 56 |
+
"is_encoder_decoder": true,
|
| 57 |
+
"model_type": "dia",
|
| 58 |
+
"norm_eps": 1e-05,
|
| 59 |
+
"pad_token_id": 1025,
|
| 60 |
+
"torch_dtype": "float32",
|
| 61 |
+
"transformers_version": "4.53.0.dev0"
|
| 62 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e8ce7bb02603a7b36ff4dc263fc19823378eae528ee1b11f32bfa981d46be05
|
| 3 |
+
size 3222637464
|