Upload VoxtralForConditionalGeneration
Browse files- .gitattributes +1 -0
- README.md +9 -0
- config.json +54 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- preprocessor_config.json +15 -0
- tekken.json +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tekken.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
tags:
|
| 4 |
+
- trl
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
# Tiny VoxtralForConditionalGeneration
|
| 8 |
+
|
| 9 |
+
This is a minimal model built for unit tests in the [TRL](https://github.com/huggingface/trl) library.
|
config.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"VoxtralForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"audio_config": {
|
| 6 |
+
"activation_dropout": 0.0,
|
| 7 |
+
"activation_function": "gelu",
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"dropout": 0.0,
|
| 10 |
+
"head_dim": 64,
|
| 11 |
+
"hidden_size": 1280,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 5120,
|
| 14 |
+
"layerdrop": 0.0,
|
| 15 |
+
"max_source_positions": 1500,
|
| 16 |
+
"model_type": "voxtral_encoder",
|
| 17 |
+
"num_attention_heads": 20,
|
| 18 |
+
"num_hidden_layers": 32,
|
| 19 |
+
"num_key_value_heads": 20,
|
| 20 |
+
"num_mel_bins": 128,
|
| 21 |
+
"scale_embedding": false,
|
| 22 |
+
"vocab_size": 51866
|
| 23 |
+
},
|
| 24 |
+
"audio_token_id": 24,
|
| 25 |
+
"dtype": "bfloat16",
|
| 26 |
+
"hidden_size": 3072,
|
| 27 |
+
"model_type": "voxtral",
|
| 28 |
+
"projector_hidden_act": "gelu",
|
| 29 |
+
"text_config": {
|
| 30 |
+
"attention_bias": false,
|
| 31 |
+
"attention_dropout": 0.0,
|
| 32 |
+
"head_dim": 4,
|
| 33 |
+
"hidden_act": "silu",
|
| 34 |
+
"hidden_size": 16,
|
| 35 |
+
"initializer_range": 0.02,
|
| 36 |
+
"intermediate_size": 32,
|
| 37 |
+
"layer_types": null,
|
| 38 |
+
"max_position_embeddings": 131072,
|
| 39 |
+
"mlp_bias": false,
|
| 40 |
+
"model_type": "llama",
|
| 41 |
+
"num_attention_heads": 4,
|
| 42 |
+
"num_hidden_layers": 2,
|
| 43 |
+
"num_key_value_heads": 2,
|
| 44 |
+
"pretraining_tp": 1,
|
| 45 |
+
"rms_norm_eps": 1e-05,
|
| 46 |
+
"rope_scaling": null,
|
| 47 |
+
"rope_theta": 100000000.0,
|
| 48 |
+
"sliding_window": null,
|
| 49 |
+
"use_cache": true,
|
| 50 |
+
"vocab_size": 131072
|
| 51 |
+
},
|
| 52 |
+
"transformers_version": "4.56.2",
|
| 53 |
+
"vocab_size": 131072
|
| 54 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"eos_token_id": 2,
|
| 4 |
+
"pad_token_id": 11,
|
| 5 |
+
"transformers_version": "4.56.2"
|
| 6 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ccef54545a1e5b005e5d5332b169749da57017aa2de3017f85ffff5a7f552a1d
|
| 3 |
+
size 1282559192
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chunk_length": 30,
|
| 3 |
+
"dither": 0.0,
|
| 4 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
| 5 |
+
"feature_size": 128,
|
| 6 |
+
"hop_length": 160,
|
| 7 |
+
"n_fft": 400,
|
| 8 |
+
"n_samples": 480000,
|
| 9 |
+
"nb_max_frames": 3000,
|
| 10 |
+
"padding_side": "right",
|
| 11 |
+
"padding_value": 0.0,
|
| 12 |
+
"processor_class": "VoxtralProcessor",
|
| 13 |
+
"return_attention_mask": false,
|
| 14 |
+
"sampling_rate": 16000
|
| 15 |
+
}
|
tekken.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4aaf3836c2a5332f029ce85a7a62255c966f47b6797ef81dedd0ade9c862e4a8
|
| 3 |
+
size 14894206
|