Feature Extraction
Transformers
Safetensors
liquid_codec
liquid
lfm3
audio
audio-codec
speech
streaming
edge
multilingual
custom_code
Instructions to use eustlb/Liquid-Codec with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use eustlb/Liquid-Codec with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="eustlb/Liquid-Codec", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("eustlb/Liquid-Codec", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Rename config keys: quantization_levels, quantization_dim, embedder_hidden_size, embedder_hidden_act
Browse files- config.json +10 -10
config.json
CHANGED
|
@@ -30,7 +30,7 @@
|
|
| 30 |
"num_attention_heads": 8,
|
| 31 |
"num_hidden_layers": 8,
|
| 32 |
"num_key_value_heads": 2,
|
| 33 |
-
"
|
| 34 |
"rope_parameters": {
|
| 35 |
"sliding_attention": {
|
| 36 |
"partial_rotary_factor": 1.0,
|
|
@@ -50,10 +50,10 @@
|
|
| 50 |
"attention_dropout": 0.0,
|
| 51 |
"conv_L_cache": 7,
|
| 52 |
"conv_bias": false,
|
| 53 |
-
"
|
|
|
|
| 54 |
"frame_stack": 6,
|
| 55 |
"head_dim": 64,
|
| 56 |
-
"hidden_act": "silu",
|
| 57 |
"hidden_size": 512,
|
| 58 |
"initializer_range": 0.02,
|
| 59 |
"intermediate_size": 2304,
|
|
@@ -74,7 +74,7 @@
|
|
| 74 |
"num_attention_heads": 8,
|
| 75 |
"num_hidden_layers": 8,
|
| 76 |
"num_key_value_heads": 2,
|
| 77 |
-
"
|
| 78 |
"rope_parameters": {
|
| 79 |
"full_attention": {
|
| 80 |
"partial_rotary_factor": 1.0,
|
|
@@ -87,16 +87,16 @@
|
|
| 87 |
"use_cache": false,
|
| 88 |
"use_sandwich_norm": true
|
| 89 |
},
|
| 90 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 91 |
8,
|
| 92 |
7,
|
| 93 |
6,
|
| 94 |
6
|
| 95 |
],
|
| 96 |
-
"initializer_range": 0.02,
|
| 97 |
-
"model_type": "liquid_codec",
|
| 98 |
-
"num_quantizers": 12,
|
| 99 |
-
"quantizer_dim": 256,
|
| 100 |
"sampling_rate": 24000,
|
| 101 |
-
"transformers_version": "5.
|
| 102 |
}
|
|
|
|
| 30 |
"num_attention_heads": 8,
|
| 31 |
"num_hidden_layers": 8,
|
| 32 |
"num_key_value_heads": 2,
|
| 33 |
+
"quantization_dim": 256,
|
| 34 |
"rope_parameters": {
|
| 35 |
"sliding_attention": {
|
| 36 |
"partial_rotary_factor": 1.0,
|
|
|
|
| 50 |
"attention_dropout": 0.0,
|
| 51 |
"conv_L_cache": 7,
|
| 52 |
"conv_bias": false,
|
| 53 |
+
"embedder_hidden_act": "silu",
|
| 54 |
+
"embedder_hidden_size": 256,
|
| 55 |
"frame_stack": 6,
|
| 56 |
"head_dim": 64,
|
|
|
|
| 57 |
"hidden_size": 512,
|
| 58 |
"initializer_range": 0.02,
|
| 59 |
"intermediate_size": 2304,
|
|
|
|
| 74 |
"num_attention_heads": 8,
|
| 75 |
"num_hidden_layers": 8,
|
| 76 |
"num_key_value_heads": 2,
|
| 77 |
+
"quantization_dim": 256,
|
| 78 |
"rope_parameters": {
|
| 79 |
"full_attention": {
|
| 80 |
"partial_rotary_factor": 1.0,
|
|
|
|
| 87 |
"use_cache": false,
|
| 88 |
"use_sandwich_norm": true
|
| 89 |
},
|
| 90 |
+
"initializer_range": 0.02,
|
| 91 |
+
"model_type": "liquid_codec",
|
| 92 |
+
"num_quantizers": 12,
|
| 93 |
+
"quantization_dim": 256,
|
| 94 |
+
"quantization_levels": [
|
| 95 |
8,
|
| 96 |
7,
|
| 97 |
6,
|
| 98 |
6
|
| 99 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
| 100 |
"sampling_rate": 24000,
|
| 101 |
+
"transformers_version": "5.24.0.dev0"
|
| 102 |
}
|