Upload 3 files
Browse files- conditioning.json +32 -0
- config.json +7 -0
- model.safetensors +3 -0
conditioning.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"format": "m5-caption-accent-speaker-lang-v3",
|
| 3 |
+
"field_order": [
|
| 4 |
+
"caption",
|
| 5 |
+
"accent",
|
| 6 |
+
"speaker",
|
| 7 |
+
"lang",
|
| 8 |
+
"text"
|
| 9 |
+
],
|
| 10 |
+
"missing_condition": {
|
| 11 |
+
"caption": "empty_between_delimiters",
|
| 12 |
+
"accent": "empty_between_delimiters",
|
| 13 |
+
"speaker": "literal_None",
|
| 14 |
+
"lang": "empty_between_delimiters"
|
| 15 |
+
},
|
| 16 |
+
"base_vocab_size": 129984,
|
| 17 |
+
"vocab_size": 129992,
|
| 18 |
+
"control_token_ids": {
|
| 19 |
+
"<|caption_begin|>": 129984,
|
| 20 |
+
"<|caption_end|>": 129985,
|
| 21 |
+
"<|lang_begin|>": 129986,
|
| 22 |
+
"<|lang_end|>": 129987,
|
| 23 |
+
"<|accent_begin|>": 129988,
|
| 24 |
+
"<|accent_end|>": 129989,
|
| 25 |
+
"<|speaker_start|>": 129990,
|
| 26 |
+
"<|speaker_end|>": 129991
|
| 27 |
+
},
|
| 28 |
+
"vocab_sha256": "05fd46dd14d5234c102aba957794a1e3a308fc86dc1c96be13db71cec4a5dbfe",
|
| 29 |
+
"tokenizer_pipeline_sha256": "a0a37555c0450564e132336a43e26b0989900268b72fb74eb64a9a079dd91fbc",
|
| 30 |
+
"bos_token_id": 128000,
|
| 31 |
+
"eos_token_id": 128001
|
| 32 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backbone_flavor": "llama-30M",
|
| 3 |
+
"decoder_flavor": "llama-20M",
|
| 4 |
+
"audio_vocab_size": 2051,
|
| 5 |
+
"audio_num_codebooks": 16,
|
| 6 |
+
"use_codebooks": 16
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:faf964d33ff0e02f5a319914980b00abd1eed56c79bc27df56b543a38eab0b90
|
| 3 |
+
size 599414424
|