transformers-integration
#9
by
eustlb
HF Staff
- opened
- README.md +289 -0
- config.json +53 -0
- generation_config.json +6 -0
- model-00001-of-00011.safetensors +3 -0
- model-00002-of-00011.safetensors +3 -0
- model-00003-of-00011.safetensors +3 -0
- model-00004-of-00011.safetensors +3 -0
- model-00005-of-00011.safetensors +3 -0
- model-00006-of-00011.safetensors +3 -0
- model-00007-of-00011.safetensors +3 -0
- model-00008-of-00011.safetensors +3 -0
- model-00009-of-00011.safetensors +3 -0
- model-00010-of-00011.safetensors +3 -0
- model-00011-of-00011.safetensors +3 -0
- model.safetensors.index.json +860 -0
- preprocessor_config.json +15 -0
README.md
CHANGED
|
@@ -17,6 +17,8 @@ extra_gated_description: >-
|
|
| 17 |
If you want to learn more about how we process your personal data, please read
|
| 18 |
our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
|
| 19 |
pipeline_tag: audio-text-to-text
|
|
|
|
|
|
|
| 20 |
---
|
| 21 |
|
| 22 |
# Voxtral Small 1.0 (24B) - 2507
|
|
@@ -52,6 +54,7 @@ Average word error rate (WER) over the FLEURS, Mozilla Common Voice and Multilin
|
|
| 52 |
|
| 53 |
The model can be used with the following frameworks;
|
| 54 |
- [`vllm (recommended)`](https://github.com/vllm-project/vllm): See [here](#vllm-recommended)
|
|
|
|
| 55 |
|
| 56 |
**Notes**:
|
| 57 |
|
|
@@ -327,4 +330,290 @@ print(30 * "=" + "BOT 1" + 30 * "=")
|
|
| 327 |
print(response.choices[0].message.tool_calls)
|
| 328 |
print("\n\n")
|
| 329 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 330 |
</details>
|
|
|
|
| 17 |
If you want to learn more about how we process your personal data, please read
|
| 18 |
our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
|
| 19 |
pipeline_tag: audio-text-to-text
|
| 20 |
+
tags:
|
| 21 |
+
- transformers
|
| 22 |
---
|
| 23 |
|
| 24 |
# Voxtral Small 1.0 (24B) - 2507
|
|
|
|
| 54 |
|
| 55 |
The model can be used with the following frameworks;
|
| 56 |
- [`vllm (recommended)`](https://github.com/vllm-project/vllm): See [here](#vllm-recommended)
|
| 57 |
+
- [`Transformers` 🤗](https://github.com/huggingface/transformers): See [here](#transformers-🤗)
|
| 58 |
|
| 59 |
**Notes**:
|
| 60 |
|
|
|
|
| 330 |
print(response.choices[0].message.tool_calls)
|
| 331 |
print("\n\n")
|
| 332 |
```
|
| 333 |
+
</details>
|
| 334 |
+
|
| 335 |
+
### Transformers 🤗
|
| 336 |
+
|
| 337 |
+
Voxtral is supported in Transformers natively!
|
| 338 |
+
|
| 339 |
+
Install Transformers from source:
|
| 340 |
+
```bash
|
| 341 |
+
pip install git+https://github.com/huggingface/transformers
|
| 342 |
+
```
|
| 343 |
+
|
| 344 |
+
Make sure to have `mistral-common >= 1.8.1` installed with audio dependencies:
|
| 345 |
+
```bash
|
| 346 |
+
pip install --upgrade "mistral-common[audio]"
|
| 347 |
+
```
|
| 348 |
+
|
| 349 |
+
#### Audio Instruct
|
| 350 |
+
|
| 351 |
+
<details>
|
| 352 |
+
<summary>➡️ multi-audio + text instruction</summary>
|
| 353 |
+
|
| 354 |
+
```python
|
| 355 |
+
from transformers import VoxtralForConditionalGeneration, AutoProcessor
|
| 356 |
+
import torch
|
| 357 |
+
|
| 358 |
+
device = "cuda"
|
| 359 |
+
repo_id = "mistralai/Voxtral-Small-24B-2507"
|
| 360 |
+
|
| 361 |
+
processor = AutoProcessor.from_pretrained(repo_id)
|
| 362 |
+
model = VoxtralForConditionalGeneration.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map=device)
|
| 363 |
+
|
| 364 |
+
conversation = [
|
| 365 |
+
{
|
| 366 |
+
"role": "user",
|
| 367 |
+
"content": [
|
| 368 |
+
{
|
| 369 |
+
"type": "audio",
|
| 370 |
+
"path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/mary_had_lamb.mp3",
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"type": "audio",
|
| 374 |
+
"path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/winning_call.mp3",
|
| 375 |
+
},
|
| 376 |
+
{"type": "text", "text": "What sport and what nursery rhyme are referenced?"},
|
| 377 |
+
],
|
| 378 |
+
}
|
| 379 |
+
]
|
| 380 |
+
|
| 381 |
+
inputs = processor.apply_chat_template(conversation)
|
| 382 |
+
inputs = inputs.to(device, dtype=torch.bfloat16)
|
| 383 |
+
|
| 384 |
+
outputs = model.generate(**inputs, max_new_tokens=500)
|
| 385 |
+
decoded_outputs = processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)
|
| 386 |
+
|
| 387 |
+
print("\nGenerated response:")
|
| 388 |
+
print("=" * 80)
|
| 389 |
+
print(decoded_outputs[0])
|
| 390 |
+
print("=" * 80)
|
| 391 |
+
```
|
| 392 |
+
</details>
|
| 393 |
+
|
| 394 |
+
|
| 395 |
+
<details>
|
| 396 |
+
<summary>➡️ multi-turn</summary>
|
| 397 |
+
|
| 398 |
+
```python
|
| 399 |
+
from transformers import VoxtralForConditionalGeneration, AutoProcessor
|
| 400 |
+
import torch
|
| 401 |
+
|
| 402 |
+
device = "cuda"
|
| 403 |
+
repo_id = "mistralai/Voxtral-Small-24B-2507"
|
| 404 |
+
|
| 405 |
+
processor = AutoProcessor.from_pretrained(repo_id)
|
| 406 |
+
model = VoxtralForConditionalGeneration.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map=device)
|
| 407 |
+
|
| 408 |
+
conversation = [
|
| 409 |
+
{
|
| 410 |
+
"role": "user",
|
| 411 |
+
"content": [
|
| 412 |
+
{
|
| 413 |
+
"type": "audio",
|
| 414 |
+
"path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/obama.mp3",
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"type": "audio",
|
| 418 |
+
"path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/bcn_weather.mp3",
|
| 419 |
+
},
|
| 420 |
+
{"type": "text", "text": "Describe briefly what you can hear."},
|
| 421 |
+
],
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"role": "assistant",
|
| 425 |
+
"content": "The audio begins with the speaker delivering a farewell address in Chicago, reflecting on his eight years as president and expressing gratitude to the American people. The audio then transitions to a weather report, stating that it was 35 degrees in Barcelona the previous day, but the temperature would drop to minus 20 degrees the following day.",
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"role": "user",
|
| 429 |
+
"content": [
|
| 430 |
+
{
|
| 431 |
+
"type": "audio",
|
| 432 |
+
"path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/winning_call.mp3",
|
| 433 |
+
},
|
| 434 |
+
{"type": "text", "text": "Ok, now compare this new audio with the previous one."},
|
| 435 |
+
],
|
| 436 |
+
},
|
| 437 |
+
]
|
| 438 |
+
|
| 439 |
+
inputs = processor.apply_chat_template(conversation)
|
| 440 |
+
inputs = inputs.to(device, dtype=torch.bfloat16)
|
| 441 |
+
|
| 442 |
+
outputs = model.generate(**inputs, max_new_tokens=500)
|
| 443 |
+
decoded_outputs = processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)
|
| 444 |
+
|
| 445 |
+
print("\nGenerated response:")
|
| 446 |
+
print("=" * 80)
|
| 447 |
+
print(decoded_outputs[0])
|
| 448 |
+
print("=" * 80)
|
| 449 |
+
```
|
| 450 |
+
</details>
|
| 451 |
+
|
| 452 |
+
|
| 453 |
+
<details>
|
| 454 |
+
<summary>➡️ text only</summary>
|
| 455 |
+
|
| 456 |
+
```python
|
| 457 |
+
from transformers import VoxtralForConditionalGeneration, AutoProcessor
|
| 458 |
+
import torch
|
| 459 |
+
|
| 460 |
+
device = "cuda"
|
| 461 |
+
repo_id = "mistralai/Voxtral-Small-24B-2507"
|
| 462 |
+
|
| 463 |
+
processor = AutoProcessor.from_pretrained(repo_id)
|
| 464 |
+
model = VoxtralForConditionalGeneration.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map=device)
|
| 465 |
+
|
| 466 |
+
conversation = [
|
| 467 |
+
{
|
| 468 |
+
"role": "user",
|
| 469 |
+
"content": [
|
| 470 |
+
{
|
| 471 |
+
"type": "text",
|
| 472 |
+
"text": "Why should AI models be open-sourced?",
|
| 473 |
+
},
|
| 474 |
+
],
|
| 475 |
+
}
|
| 476 |
+
]
|
| 477 |
+
|
| 478 |
+
inputs = processor.apply_chat_template(conversation)
|
| 479 |
+
inputs = inputs.to(device, dtype=torch.bfloat16)
|
| 480 |
+
|
| 481 |
+
outputs = model.generate(**inputs, max_new_tokens=500)
|
| 482 |
+
decoded_outputs = processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)
|
| 483 |
+
|
| 484 |
+
print("\nGenerated response:")
|
| 485 |
+
print("=" * 80)
|
| 486 |
+
print(decoded_outputs[0])
|
| 487 |
+
print("=" * 80)
|
| 488 |
+
```
|
| 489 |
+
</details>
|
| 490 |
+
|
| 491 |
+
|
| 492 |
+
<details>
|
| 493 |
+
<summary>➡️ audio only</summary>
|
| 494 |
+
|
| 495 |
+
```python
|
| 496 |
+
from transformers import VoxtralForConditionalGeneration, AutoProcessor
|
| 497 |
+
import torch
|
| 498 |
+
|
| 499 |
+
device = "cuda"
|
| 500 |
+
repo_id = "mistralai/Voxtral-Small-24B-2507"
|
| 501 |
+
|
| 502 |
+
processor = AutoProcessor.from_pretrained(repo_id)
|
| 503 |
+
model = VoxtralForConditionalGeneration.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map=device)
|
| 504 |
+
|
| 505 |
+
conversation = [
|
| 506 |
+
{
|
| 507 |
+
"role": "user",
|
| 508 |
+
"content": [
|
| 509 |
+
{
|
| 510 |
+
"type": "audio",
|
| 511 |
+
"path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/winning_call.mp3",
|
| 512 |
+
},
|
| 513 |
+
],
|
| 514 |
+
}
|
| 515 |
+
]
|
| 516 |
+
|
| 517 |
+
inputs = processor.apply_chat_template(conversation)
|
| 518 |
+
inputs = inputs.to(device, dtype=torch.bfloat16)
|
| 519 |
+
|
| 520 |
+
outputs = model.generate(**inputs, max_new_tokens=500)
|
| 521 |
+
decoded_outputs = processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)
|
| 522 |
+
|
| 523 |
+
print("\nGenerated response:")
|
| 524 |
+
print("=" * 80)
|
| 525 |
+
print(decoded_outputs[0])
|
| 526 |
+
print("=" * 80)
|
| 527 |
+
```
|
| 528 |
+
</details>
|
| 529 |
+
|
| 530 |
+
|
| 531 |
+
<details>
|
| 532 |
+
<summary>➡️ batched inference</summary>
|
| 533 |
+
|
| 534 |
+
```python
|
| 535 |
+
from transformers import VoxtralForConditionalGeneration, AutoProcessor
|
| 536 |
+
import torch
|
| 537 |
+
|
| 538 |
+
device = "cuda"
|
| 539 |
+
repo_id = "mistralai/Voxtral-Small-24B-2507"
|
| 540 |
+
|
| 541 |
+
processor = AutoProcessor.from_pretrained(repo_id)
|
| 542 |
+
model = VoxtralForConditionalGeneration.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map=device)
|
| 543 |
+
|
| 544 |
+
conversations = [
|
| 545 |
+
[
|
| 546 |
+
{
|
| 547 |
+
"role": "user",
|
| 548 |
+
"content": [
|
| 549 |
+
{
|
| 550 |
+
"type": "audio",
|
| 551 |
+
"path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/obama.mp3",
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"type": "audio",
|
| 555 |
+
"path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/bcn_weather.mp3",
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"type": "text",
|
| 559 |
+
"text": "Who's speaking in the speach and what city's weather is being discussed?",
|
| 560 |
+
},
|
| 561 |
+
],
|
| 562 |
+
}
|
| 563 |
+
],
|
| 564 |
+
[
|
| 565 |
+
{
|
| 566 |
+
"role": "user",
|
| 567 |
+
"content": [
|
| 568 |
+
{
|
| 569 |
+
"type": "audio",
|
| 570 |
+
"path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/winning_call.mp3",
|
| 571 |
+
},
|
| 572 |
+
{"type": "text", "text": "What can you tell me about this audio?"},
|
| 573 |
+
],
|
| 574 |
+
}
|
| 575 |
+
],
|
| 576 |
+
]
|
| 577 |
+
|
| 578 |
+
inputs = processor.apply_chat_template(conversations)
|
| 579 |
+
inputs = inputs.to(device, dtype=torch.bfloat16)
|
| 580 |
+
|
| 581 |
+
outputs = model.generate(**inputs, max_new_tokens=500)
|
| 582 |
+
decoded_outputs = processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)
|
| 583 |
+
|
| 584 |
+
print("\nGenerated responses:")
|
| 585 |
+
print("=" * 80)
|
| 586 |
+
for decoded_output in decoded_outputs:
|
| 587 |
+
print(decoded_output)
|
| 588 |
+
print("=" * 80)
|
| 589 |
+
```
|
| 590 |
+
</details>
|
| 591 |
+
|
| 592 |
+
#### Transcription
|
| 593 |
+
|
| 594 |
+
<details>
|
| 595 |
+
<summary>➡️ transcribe</summary>
|
| 596 |
+
|
| 597 |
+
```python
|
| 598 |
+
from transformers import VoxtralForConditionalGeneration, AutoProcessor
|
| 599 |
+
import torch
|
| 600 |
+
|
| 601 |
+
device = "cuda"
|
| 602 |
+
repo_id = "mistralai/Voxtral-Small-24B-2507"
|
| 603 |
+
|
| 604 |
+
processor = AutoProcessor.from_pretrained(repo_id)
|
| 605 |
+
model = VoxtralForConditionalGeneration.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map=device)
|
| 606 |
+
|
| 607 |
+
inputs = processor.apply_transcrition_request(language="en", audio="https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/obama.mp3", model_id=repo_id)
|
| 608 |
+
inputs = inputs.to(device, dtype=torch.bfloat16)
|
| 609 |
+
|
| 610 |
+
outputs = model.generate(**inputs, max_new_tokens=500)
|
| 611 |
+
decoded_outputs = processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)
|
| 612 |
+
|
| 613 |
+
print("\nGenerated responses:")
|
| 614 |
+
print("=" * 80)
|
| 615 |
+
for decoded_output in decoded_outputs:
|
| 616 |
+
print(decoded_output)
|
| 617 |
+
print("=" * 80)
|
| 618 |
+
```
|
| 619 |
</details>
|
config.json
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"hidden_size": 5120,
|
| 26 |
+
"model_type": "voxtral",
|
| 27 |
+
"projector_hidden_act": "gelu",
|
| 28 |
+
"text_config": {
|
| 29 |
+
"attention_bias": false,
|
| 30 |
+
"attention_dropout": 0.0,
|
| 31 |
+
"head_dim": 128,
|
| 32 |
+
"hidden_act": "silu",
|
| 33 |
+
"hidden_size": 5120,
|
| 34 |
+
"initializer_range": 0.02,
|
| 35 |
+
"intermediate_size": 32768,
|
| 36 |
+
"max_position_embeddings": 131072,
|
| 37 |
+
"mlp_bias": false,
|
| 38 |
+
"model_type": "llama",
|
| 39 |
+
"num_attention_heads": 32,
|
| 40 |
+
"num_hidden_layers": 40,
|
| 41 |
+
"num_key_value_heads": 8,
|
| 42 |
+
"pretraining_tp": 1,
|
| 43 |
+
"rms_norm_eps": 1e-05,
|
| 44 |
+
"rope_scaling": null,
|
| 45 |
+
"rope_theta": 100000000.0,
|
| 46 |
+
"sliding_window": null,
|
| 47 |
+
"use_cache": true,
|
| 48 |
+
"vocab_size": 131072
|
| 49 |
+
},
|
| 50 |
+
"torch_dtype": "bfloat16",
|
| 51 |
+
"transformers_version": "4.54.0.dev0",
|
| 52 |
+
"vocab_size": 131072
|
| 53 |
+
}
|
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": "4.54.0.dev0"
|
| 6 |
+
}
|
model-00001-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e4c3fde4ef4a1141b4b06f2125c63bb2032f71a7985fafb4b3ae8243ca17be2
|
| 3 |
+
size 4947893992
|
model-00002-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6998429899fc08e533b7ef0bb65a66d0c744a490c31b5210ea5f61e62e8fb997
|
| 3 |
+
size 4781593336
|
model-00003-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b692e60c5d9acfd5b6e7fd2c0337349a421bb687c8cef14627469f744efa83df
|
| 3 |
+
size 4781593344
|
model-00004-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c34b0b04a59f62c3d1f320803f421c45d51dbf917f4e3f90eda957640ae85da
|
| 3 |
+
size 4886472248
|
model-00005-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bcea8514dd1330b2478deeff5b48b6788c1e6fbd1c6d5034faeeee5c066b6288
|
| 3 |
+
size 4781593376
|
model-00006-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e415b6a5cc6f266acdd8aeba526288abd8345ebaa4022ab0e26ea30eaaffa91
|
| 3 |
+
size 4781593368
|
model-00007-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:720bbe6314e0b69b97fd13e07ffdef4953dc5aec3b4b91c15a9c1d40d7b1c7fc
|
| 3 |
+
size 4886472248
|
model-00008-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85c590b7d4d6c843dc083b3048f5b00cda7ee7ddfeb18a3732ff2db65926a6eb
|
| 3 |
+
size 4781593376
|
model-00009-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc973532e7f8faea778ed22aac9867b84e1d4bb4ad9c9a50744fc1eeeb6c9115
|
| 3 |
+
size 4781593368
|
model-00010-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:365913969c7a5c93cc2d9e19b6f9d4128e675db8a1941c2436f0a2a2c64870e2
|
| 3 |
+
size 3670112232
|
model-00011-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2515d18911999b503000115208d6c5ae46777223227c18a170cbff3095aaf697
|
| 3 |
+
size 1447035256
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,860 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 24261800960,
|
| 4 |
+
"total_size": 48527441920
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"audio_tower.conv1.bias": "model-00001-of-00011.safetensors",
|
| 8 |
+
"audio_tower.conv1.weight": "model-00001-of-00011.safetensors",
|
| 9 |
+
"audio_tower.conv2.bias": "model-00001-of-00011.safetensors",
|
| 10 |
+
"audio_tower.conv2.weight": "model-00001-of-00011.safetensors",
|
| 11 |
+
"audio_tower.embed_positions.weight": "model-00001-of-00011.safetensors",
|
| 12 |
+
"audio_tower.layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 13 |
+
"audio_tower.layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 14 |
+
"audio_tower.layers.0.fc1.bias": "model-00001-of-00011.safetensors",
|
| 15 |
+
"audio_tower.layers.0.fc1.weight": "model-00001-of-00011.safetensors",
|
| 16 |
+
"audio_tower.layers.0.fc2.bias": "model-00001-of-00011.safetensors",
|
| 17 |
+
"audio_tower.layers.0.fc2.weight": "model-00001-of-00011.safetensors",
|
| 18 |
+
"audio_tower.layers.0.final_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 19 |
+
"audio_tower.layers.0.final_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 20 |
+
"audio_tower.layers.0.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 21 |
+
"audio_tower.layers.0.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
|
| 22 |
+
"audio_tower.layers.0.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 23 |
+
"audio_tower.layers.0.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
|
| 24 |
+
"audio_tower.layers.0.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 25 |
+
"audio_tower.layers.0.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
|
| 26 |
+
"audio_tower.layers.0.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 27 |
+
"audio_tower.layers.0.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 28 |
+
"audio_tower.layers.0.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 29 |
+
"audio_tower.layers.1.fc1.bias": "model-00001-of-00011.safetensors",
|
| 30 |
+
"audio_tower.layers.1.fc1.weight": "model-00001-of-00011.safetensors",
|
| 31 |
+
"audio_tower.layers.1.fc2.bias": "model-00001-of-00011.safetensors",
|
| 32 |
+
"audio_tower.layers.1.fc2.weight": "model-00001-of-00011.safetensors",
|
| 33 |
+
"audio_tower.layers.1.final_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 34 |
+
"audio_tower.layers.1.final_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 35 |
+
"audio_tower.layers.1.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 36 |
+
"audio_tower.layers.1.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
|
| 37 |
+
"audio_tower.layers.1.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 38 |
+
"audio_tower.layers.1.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
|
| 39 |
+
"audio_tower.layers.1.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 40 |
+
"audio_tower.layers.1.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
|
| 41 |
+
"audio_tower.layers.1.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 42 |
+
"audio_tower.layers.1.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 43 |
+
"audio_tower.layers.1.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 44 |
+
"audio_tower.layers.10.fc1.bias": "model-00001-of-00011.safetensors",
|
| 45 |
+
"audio_tower.layers.10.fc1.weight": "model-00001-of-00011.safetensors",
|
| 46 |
+
"audio_tower.layers.10.fc2.bias": "model-00001-of-00011.safetensors",
|
| 47 |
+
"audio_tower.layers.10.fc2.weight": "model-00001-of-00011.safetensors",
|
| 48 |
+
"audio_tower.layers.10.final_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 49 |
+
"audio_tower.layers.10.final_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 50 |
+
"audio_tower.layers.10.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 51 |
+
"audio_tower.layers.10.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
|
| 52 |
+
"audio_tower.layers.10.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 53 |
+
"audio_tower.layers.10.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
|
| 54 |
+
"audio_tower.layers.10.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 55 |
+
"audio_tower.layers.10.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
|
| 56 |
+
"audio_tower.layers.10.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 57 |
+
"audio_tower.layers.10.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 58 |
+
"audio_tower.layers.10.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 59 |
+
"audio_tower.layers.11.fc1.bias": "model-00001-of-00011.safetensors",
|
| 60 |
+
"audio_tower.layers.11.fc1.weight": "model-00001-of-00011.safetensors",
|
| 61 |
+
"audio_tower.layers.11.fc2.bias": "model-00001-of-00011.safetensors",
|
| 62 |
+
"audio_tower.layers.11.fc2.weight": "model-00001-of-00011.safetensors",
|
| 63 |
+
"audio_tower.layers.11.final_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 64 |
+
"audio_tower.layers.11.final_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 65 |
+
"audio_tower.layers.11.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 66 |
+
"audio_tower.layers.11.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
|
| 67 |
+
"audio_tower.layers.11.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 68 |
+
"audio_tower.layers.11.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
|
| 69 |
+
"audio_tower.layers.11.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 70 |
+
"audio_tower.layers.11.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
|
| 71 |
+
"audio_tower.layers.11.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 72 |
+
"audio_tower.layers.11.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 73 |
+
"audio_tower.layers.11.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 74 |
+
"audio_tower.layers.12.fc1.bias": "model-00001-of-00011.safetensors",
|
| 75 |
+
"audio_tower.layers.12.fc1.weight": "model-00001-of-00011.safetensors",
|
| 76 |
+
"audio_tower.layers.12.fc2.bias": "model-00001-of-00011.safetensors",
|
| 77 |
+
"audio_tower.layers.12.fc2.weight": "model-00001-of-00011.safetensors",
|
| 78 |
+
"audio_tower.layers.12.final_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 79 |
+
"audio_tower.layers.12.final_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 80 |
+
"audio_tower.layers.12.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 81 |
+
"audio_tower.layers.12.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
|
| 82 |
+
"audio_tower.layers.12.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 83 |
+
"audio_tower.layers.12.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
|
| 84 |
+
"audio_tower.layers.12.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 85 |
+
"audio_tower.layers.12.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
|
| 86 |
+
"audio_tower.layers.12.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 87 |
+
"audio_tower.layers.12.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 88 |
+
"audio_tower.layers.12.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 89 |
+
"audio_tower.layers.13.fc1.bias": "model-00001-of-00011.safetensors",
|
| 90 |
+
"audio_tower.layers.13.fc1.weight": "model-00001-of-00011.safetensors",
|
| 91 |
+
"audio_tower.layers.13.fc2.bias": "model-00001-of-00011.safetensors",
|
| 92 |
+
"audio_tower.layers.13.fc2.weight": "model-00001-of-00011.safetensors",
|
| 93 |
+
"audio_tower.layers.13.final_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 94 |
+
"audio_tower.layers.13.final_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 95 |
+
"audio_tower.layers.13.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 96 |
+
"audio_tower.layers.13.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
|
| 97 |
+
"audio_tower.layers.13.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 98 |
+
"audio_tower.layers.13.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
|
| 99 |
+
"audio_tower.layers.13.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 100 |
+
"audio_tower.layers.13.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
|
| 101 |
+
"audio_tower.layers.13.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 102 |
+
"audio_tower.layers.13.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 103 |
+
"audio_tower.layers.13.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 104 |
+
"audio_tower.layers.14.fc1.bias": "model-00001-of-00011.safetensors",
|
| 105 |
+
"audio_tower.layers.14.fc1.weight": "model-00001-of-00011.safetensors",
|
| 106 |
+
"audio_tower.layers.14.fc2.bias": "model-00001-of-00011.safetensors",
|
| 107 |
+
"audio_tower.layers.14.fc2.weight": "model-00001-of-00011.safetensors",
|
| 108 |
+
"audio_tower.layers.14.final_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 109 |
+
"audio_tower.layers.14.final_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 110 |
+
"audio_tower.layers.14.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 111 |
+
"audio_tower.layers.14.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
|
| 112 |
+
"audio_tower.layers.14.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 113 |
+
"audio_tower.layers.14.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
|
| 114 |
+
"audio_tower.layers.14.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 115 |
+
"audio_tower.layers.14.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
|
| 116 |
+
"audio_tower.layers.14.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 117 |
+
"audio_tower.layers.14.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 118 |
+
"audio_tower.layers.14.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 119 |
+
"audio_tower.layers.15.fc1.bias": "model-00001-of-00011.safetensors",
|
| 120 |
+
"audio_tower.layers.15.fc1.weight": "model-00001-of-00011.safetensors",
|
| 121 |
+
"audio_tower.layers.15.fc2.bias": "model-00001-of-00011.safetensors",
|
| 122 |
+
"audio_tower.layers.15.fc2.weight": "model-00001-of-00011.safetensors",
|
| 123 |
+
"audio_tower.layers.15.final_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 124 |
+
"audio_tower.layers.15.final_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 125 |
+
"audio_tower.layers.15.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 126 |
+
"audio_tower.layers.15.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
|
| 127 |
+
"audio_tower.layers.15.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 128 |
+
"audio_tower.layers.15.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
|
| 129 |
+
"audio_tower.layers.15.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 130 |
+
"audio_tower.layers.15.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
|
| 131 |
+
"audio_tower.layers.15.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 132 |
+
"audio_tower.layers.15.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 133 |
+
"audio_tower.layers.15.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 134 |
+
"audio_tower.layers.16.fc1.bias": "model-00001-of-00011.safetensors",
|
| 135 |
+
"audio_tower.layers.16.fc1.weight": "model-00001-of-00011.safetensors",
|
| 136 |
+
"audio_tower.layers.16.fc2.bias": "model-00001-of-00011.safetensors",
|
| 137 |
+
"audio_tower.layers.16.fc2.weight": "model-00001-of-00011.safetensors",
|
| 138 |
+
"audio_tower.layers.16.final_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 139 |
+
"audio_tower.layers.16.final_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 140 |
+
"audio_tower.layers.16.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 141 |
+
"audio_tower.layers.16.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
|
| 142 |
+
"audio_tower.layers.16.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 143 |
+
"audio_tower.layers.16.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
|
| 144 |
+
"audio_tower.layers.16.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 145 |
+
"audio_tower.layers.16.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
|
| 146 |
+
"audio_tower.layers.16.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 147 |
+
"audio_tower.layers.16.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 148 |
+
"audio_tower.layers.16.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 149 |
+
"audio_tower.layers.17.fc1.bias": "model-00001-of-00011.safetensors",
|
| 150 |
+
"audio_tower.layers.17.fc1.weight": "model-00001-of-00011.safetensors",
|
| 151 |
+
"audio_tower.layers.17.fc2.bias": "model-00001-of-00011.safetensors",
|
| 152 |
+
"audio_tower.layers.17.fc2.weight": "model-00001-of-00011.safetensors",
|
| 153 |
+
"audio_tower.layers.17.final_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 154 |
+
"audio_tower.layers.17.final_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 155 |
+
"audio_tower.layers.17.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 156 |
+
"audio_tower.layers.17.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
|
| 157 |
+
"audio_tower.layers.17.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 158 |
+
"audio_tower.layers.17.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
|
| 159 |
+
"audio_tower.layers.17.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 160 |
+
"audio_tower.layers.17.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
|
| 161 |
+
"audio_tower.layers.17.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 162 |
+
"audio_tower.layers.17.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 163 |
+
"audio_tower.layers.17.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 164 |
+
"audio_tower.layers.18.fc1.bias": "model-00001-of-00011.safetensors",
|
| 165 |
+
"audio_tower.layers.18.fc1.weight": "model-00001-of-00011.safetensors",
|
| 166 |
+
"audio_tower.layers.18.fc2.bias": "model-00001-of-00011.safetensors",
|
| 167 |
+
"audio_tower.layers.18.fc2.weight": "model-00001-of-00011.safetensors",
|
| 168 |
+
"audio_tower.layers.18.final_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 169 |
+
"audio_tower.layers.18.final_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 170 |
+
"audio_tower.layers.18.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 171 |
+
"audio_tower.layers.18.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
|
| 172 |
+
"audio_tower.layers.18.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 173 |
+
"audio_tower.layers.18.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
|
| 174 |
+
"audio_tower.layers.18.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 175 |
+
"audio_tower.layers.18.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
|
| 176 |
+
"audio_tower.layers.18.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 177 |
+
"audio_tower.layers.18.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 178 |
+
"audio_tower.layers.18.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 179 |
+
"audio_tower.layers.19.fc1.bias": "model-00001-of-00011.safetensors",
|
| 180 |
+
"audio_tower.layers.19.fc1.weight": "model-00001-of-00011.safetensors",
|
| 181 |
+
"audio_tower.layers.19.fc2.bias": "model-00001-of-00011.safetensors",
|
| 182 |
+
"audio_tower.layers.19.fc2.weight": "model-00001-of-00011.safetensors",
|
| 183 |
+
"audio_tower.layers.19.final_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 184 |
+
"audio_tower.layers.19.final_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 185 |
+
"audio_tower.layers.19.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 186 |
+
"audio_tower.layers.19.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
|
| 187 |
+
"audio_tower.layers.19.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 188 |
+
"audio_tower.layers.19.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
|
| 189 |
+
"audio_tower.layers.19.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 190 |
+
"audio_tower.layers.19.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
|
| 191 |
+
"audio_tower.layers.19.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 192 |
+
"audio_tower.layers.19.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 193 |
+
"audio_tower.layers.19.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 194 |
+
"audio_tower.layers.2.fc1.bias": "model-00001-of-00011.safetensors",
|
| 195 |
+
"audio_tower.layers.2.fc1.weight": "model-00001-of-00011.safetensors",
|
| 196 |
+
"audio_tower.layers.2.fc2.bias": "model-00001-of-00011.safetensors",
|
| 197 |
+
"audio_tower.layers.2.fc2.weight": "model-00001-of-00011.safetensors",
|
| 198 |
+
"audio_tower.layers.2.final_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 199 |
+
"audio_tower.layers.2.final_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 200 |
+
"audio_tower.layers.2.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 201 |
+
"audio_tower.layers.2.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
|
| 202 |
+
"audio_tower.layers.2.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 203 |
+
"audio_tower.layers.2.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
|
| 204 |
+
"audio_tower.layers.2.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 205 |
+
"audio_tower.layers.2.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
|
| 206 |
+
"audio_tower.layers.2.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 207 |
+
"audio_tower.layers.2.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 208 |
+
"audio_tower.layers.2.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 209 |
+
"audio_tower.layers.20.fc1.bias": "model-00001-of-00011.safetensors",
|
| 210 |
+
"audio_tower.layers.20.fc1.weight": "model-00001-of-00011.safetensors",
|
| 211 |
+
"audio_tower.layers.20.fc2.bias": "model-00001-of-00011.safetensors",
|
| 212 |
+
"audio_tower.layers.20.fc2.weight": "model-00001-of-00011.safetensors",
|
| 213 |
+
"audio_tower.layers.20.final_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 214 |
+
"audio_tower.layers.20.final_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 215 |
+
"audio_tower.layers.20.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 216 |
+
"audio_tower.layers.20.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
|
| 217 |
+
"audio_tower.layers.20.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 218 |
+
"audio_tower.layers.20.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
|
| 219 |
+
"audio_tower.layers.20.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 220 |
+
"audio_tower.layers.20.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
|
| 221 |
+
"audio_tower.layers.20.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 222 |
+
"audio_tower.layers.20.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 223 |
+
"audio_tower.layers.20.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 224 |
+
"audio_tower.layers.21.fc1.bias": "model-00001-of-00011.safetensors",
|
| 225 |
+
"audio_tower.layers.21.fc1.weight": "model-00001-of-00011.safetensors",
|
| 226 |
+
"audio_tower.layers.21.fc2.bias": "model-00001-of-00011.safetensors",
|
| 227 |
+
"audio_tower.layers.21.fc2.weight": "model-00001-of-00011.safetensors",
|
| 228 |
+
"audio_tower.layers.21.final_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 229 |
+
"audio_tower.layers.21.final_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 230 |
+
"audio_tower.layers.21.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 231 |
+
"audio_tower.layers.21.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
|
| 232 |
+
"audio_tower.layers.21.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 233 |
+
"audio_tower.layers.21.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
|
| 234 |
+
"audio_tower.layers.21.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 235 |
+
"audio_tower.layers.21.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
|
| 236 |
+
"audio_tower.layers.21.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 237 |
+
"audio_tower.layers.21.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 238 |
+
"audio_tower.layers.21.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 239 |
+
"audio_tower.layers.22.fc1.bias": "model-00001-of-00011.safetensors",
|
| 240 |
+
"audio_tower.layers.22.fc1.weight": "model-00001-of-00011.safetensors",
|
| 241 |
+
"audio_tower.layers.22.fc2.bias": "model-00001-of-00011.safetensors",
|
| 242 |
+
"audio_tower.layers.22.fc2.weight": "model-00001-of-00011.safetensors",
|
| 243 |
+
"audio_tower.layers.22.final_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 244 |
+
"audio_tower.layers.22.final_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 245 |
+
"audio_tower.layers.22.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 246 |
+
"audio_tower.layers.22.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
|
| 247 |
+
"audio_tower.layers.22.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 248 |
+
"audio_tower.layers.22.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
|
| 249 |
+
"audio_tower.layers.22.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 250 |
+
"audio_tower.layers.22.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
|
| 251 |
+
"audio_tower.layers.22.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 252 |
+
"audio_tower.layers.22.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 253 |
+
"audio_tower.layers.22.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 254 |
+
"audio_tower.layers.23.fc1.bias": "model-00001-of-00011.safetensors",
|
| 255 |
+
"audio_tower.layers.23.fc1.weight": "model-00001-of-00011.safetensors",
|
| 256 |
+
"audio_tower.layers.23.fc2.bias": "model-00001-of-00011.safetensors",
|
| 257 |
+
"audio_tower.layers.23.fc2.weight": "model-00001-of-00011.safetensors",
|
| 258 |
+
"audio_tower.layers.23.final_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 259 |
+
"audio_tower.layers.23.final_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 260 |
+
"audio_tower.layers.23.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 261 |
+
"audio_tower.layers.23.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
|
| 262 |
+
"audio_tower.layers.23.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 263 |
+
"audio_tower.layers.23.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
|
| 264 |
+
"audio_tower.layers.23.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 265 |
+
"audio_tower.layers.23.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
|
| 266 |
+
"audio_tower.layers.23.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 267 |
+
"audio_tower.layers.23.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 268 |
+
"audio_tower.layers.23.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 269 |
+
"audio_tower.layers.24.fc1.bias": "model-00001-of-00011.safetensors",
|
| 270 |
+
"audio_tower.layers.24.fc1.weight": "model-00001-of-00011.safetensors",
|
| 271 |
+
"audio_tower.layers.24.fc2.bias": "model-00001-of-00011.safetensors",
|
| 272 |
+
"audio_tower.layers.24.fc2.weight": "model-00001-of-00011.safetensors",
|
| 273 |
+
"audio_tower.layers.24.final_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 274 |
+
"audio_tower.layers.24.final_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 275 |
+
"audio_tower.layers.24.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 276 |
+
"audio_tower.layers.24.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
|
| 277 |
+
"audio_tower.layers.24.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 278 |
+
"audio_tower.layers.24.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
|
| 279 |
+
"audio_tower.layers.24.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 280 |
+
"audio_tower.layers.24.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
|
| 281 |
+
"audio_tower.layers.24.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 282 |
+
"audio_tower.layers.24.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 283 |
+
"audio_tower.layers.24.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 284 |
+
"audio_tower.layers.25.fc1.bias": "model-00001-of-00011.safetensors",
|
| 285 |
+
"audio_tower.layers.25.fc1.weight": "model-00001-of-00011.safetensors",
|
| 286 |
+
"audio_tower.layers.25.fc2.bias": "model-00001-of-00011.safetensors",
|
| 287 |
+
"audio_tower.layers.25.fc2.weight": "model-00001-of-00011.safetensors",
|
| 288 |
+
"audio_tower.layers.25.final_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 289 |
+
"audio_tower.layers.25.final_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 290 |
+
"audio_tower.layers.25.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 291 |
+
"audio_tower.layers.25.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
|
| 292 |
+
"audio_tower.layers.25.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 293 |
+
"audio_tower.layers.25.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
|
| 294 |
+
"audio_tower.layers.25.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 295 |
+
"audio_tower.layers.25.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
|
| 296 |
+
"audio_tower.layers.25.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 297 |
+
"audio_tower.layers.25.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 298 |
+
"audio_tower.layers.25.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 299 |
+
"audio_tower.layers.26.fc1.bias": "model-00001-of-00011.safetensors",
|
| 300 |
+
"audio_tower.layers.26.fc1.weight": "model-00001-of-00011.safetensors",
|
| 301 |
+
"audio_tower.layers.26.fc2.bias": "model-00001-of-00011.safetensors",
|
| 302 |
+
"audio_tower.layers.26.fc2.weight": "model-00001-of-00011.safetensors",
|
| 303 |
+
"audio_tower.layers.26.final_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 304 |
+
"audio_tower.layers.26.final_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 305 |
+
"audio_tower.layers.26.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 306 |
+
"audio_tower.layers.26.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
|
| 307 |
+
"audio_tower.layers.26.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 308 |
+
"audio_tower.layers.26.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
|
| 309 |
+
"audio_tower.layers.26.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 310 |
+
"audio_tower.layers.26.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
|
| 311 |
+
"audio_tower.layers.26.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 312 |
+
"audio_tower.layers.26.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 313 |
+
"audio_tower.layers.26.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 314 |
+
"audio_tower.layers.27.fc1.bias": "model-00001-of-00011.safetensors",
|
| 315 |
+
"audio_tower.layers.27.fc1.weight": "model-00001-of-00011.safetensors",
|
| 316 |
+
"audio_tower.layers.27.fc2.bias": "model-00001-of-00011.safetensors",
|
| 317 |
+
"audio_tower.layers.27.fc2.weight": "model-00001-of-00011.safetensors",
|
| 318 |
+
"audio_tower.layers.27.final_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 319 |
+
"audio_tower.layers.27.final_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 320 |
+
"audio_tower.layers.27.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 321 |
+
"audio_tower.layers.27.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
|
| 322 |
+
"audio_tower.layers.27.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 323 |
+
"audio_tower.layers.27.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
|
| 324 |
+
"audio_tower.layers.27.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 325 |
+
"audio_tower.layers.27.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
|
| 326 |
+
"audio_tower.layers.27.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 327 |
+
"audio_tower.layers.27.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 328 |
+
"audio_tower.layers.27.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 329 |
+
"audio_tower.layers.28.fc1.bias": "model-00001-of-00011.safetensors",
|
| 330 |
+
"audio_tower.layers.28.fc1.weight": "model-00001-of-00011.safetensors",
|
| 331 |
+
"audio_tower.layers.28.fc2.bias": "model-00001-of-00011.safetensors",
|
| 332 |
+
"audio_tower.layers.28.fc2.weight": "model-00001-of-00011.safetensors",
|
| 333 |
+
"audio_tower.layers.28.final_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 334 |
+
"audio_tower.layers.28.final_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 335 |
+
"audio_tower.layers.28.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 336 |
+
"audio_tower.layers.28.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
|
| 337 |
+
"audio_tower.layers.28.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 338 |
+
"audio_tower.layers.28.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
|
| 339 |
+
"audio_tower.layers.28.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 340 |
+
"audio_tower.layers.28.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
|
| 341 |
+
"audio_tower.layers.28.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 342 |
+
"audio_tower.layers.28.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 343 |
+
"audio_tower.layers.28.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 344 |
+
"audio_tower.layers.29.fc1.bias": "model-00001-of-00011.safetensors",
|
| 345 |
+
"audio_tower.layers.29.fc1.weight": "model-00001-of-00011.safetensors",
|
| 346 |
+
"audio_tower.layers.29.fc2.bias": "model-00001-of-00011.safetensors",
|
| 347 |
+
"audio_tower.layers.29.fc2.weight": "model-00001-of-00011.safetensors",
|
| 348 |
+
"audio_tower.layers.29.final_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 349 |
+
"audio_tower.layers.29.final_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 350 |
+
"audio_tower.layers.29.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 351 |
+
"audio_tower.layers.29.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
|
| 352 |
+
"audio_tower.layers.29.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 353 |
+
"audio_tower.layers.29.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
|
| 354 |
+
"audio_tower.layers.29.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 355 |
+
"audio_tower.layers.29.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
|
| 356 |
+
"audio_tower.layers.29.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 357 |
+
"audio_tower.layers.29.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 358 |
+
"audio_tower.layers.29.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 359 |
+
"audio_tower.layers.3.fc1.bias": "model-00001-of-00011.safetensors",
|
| 360 |
+
"audio_tower.layers.3.fc1.weight": "model-00001-of-00011.safetensors",
|
| 361 |
+
"audio_tower.layers.3.fc2.bias": "model-00001-of-00011.safetensors",
|
| 362 |
+
"audio_tower.layers.3.fc2.weight": "model-00001-of-00011.safetensors",
|
| 363 |
+
"audio_tower.layers.3.final_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 364 |
+
"audio_tower.layers.3.final_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 365 |
+
"audio_tower.layers.3.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 366 |
+
"audio_tower.layers.3.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
|
| 367 |
+
"audio_tower.layers.3.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 368 |
+
"audio_tower.layers.3.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
|
| 369 |
+
"audio_tower.layers.3.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 370 |
+
"audio_tower.layers.3.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
|
| 371 |
+
"audio_tower.layers.3.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 372 |
+
"audio_tower.layers.3.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 373 |
+
"audio_tower.layers.3.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 374 |
+
"audio_tower.layers.30.fc1.bias": "model-00001-of-00011.safetensors",
|
| 375 |
+
"audio_tower.layers.30.fc1.weight": "model-00001-of-00011.safetensors",
|
| 376 |
+
"audio_tower.layers.30.fc2.bias": "model-00001-of-00011.safetensors",
|
| 377 |
+
"audio_tower.layers.30.fc2.weight": "model-00001-of-00011.safetensors",
|
| 378 |
+
"audio_tower.layers.30.final_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 379 |
+
"audio_tower.layers.30.final_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 380 |
+
"audio_tower.layers.30.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 381 |
+
"audio_tower.layers.30.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
|
| 382 |
+
"audio_tower.layers.30.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 383 |
+
"audio_tower.layers.30.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
|
| 384 |
+
"audio_tower.layers.30.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 385 |
+
"audio_tower.layers.30.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
|
| 386 |
+
"audio_tower.layers.30.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 387 |
+
"audio_tower.layers.30.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 388 |
+
"audio_tower.layers.30.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 389 |
+
"audio_tower.layers.31.fc1.bias": "model-00001-of-00011.safetensors",
|
| 390 |
+
"audio_tower.layers.31.fc1.weight": "model-00001-of-00011.safetensors",
|
| 391 |
+
"audio_tower.layers.31.fc2.bias": "model-00001-of-00011.safetensors",
|
| 392 |
+
"audio_tower.layers.31.fc2.weight": "model-00001-of-00011.safetensors",
|
| 393 |
+
"audio_tower.layers.31.final_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 394 |
+
"audio_tower.layers.31.final_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 395 |
+
"audio_tower.layers.31.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 396 |
+
"audio_tower.layers.31.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
|
| 397 |
+
"audio_tower.layers.31.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 398 |
+
"audio_tower.layers.31.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
|
| 399 |
+
"audio_tower.layers.31.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 400 |
+
"audio_tower.layers.31.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
|
| 401 |
+
"audio_tower.layers.31.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 402 |
+
"audio_tower.layers.31.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 403 |
+
"audio_tower.layers.31.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 404 |
+
"audio_tower.layers.4.fc1.bias": "model-00001-of-00011.safetensors",
|
| 405 |
+
"audio_tower.layers.4.fc1.weight": "model-00001-of-00011.safetensors",
|
| 406 |
+
"audio_tower.layers.4.fc2.bias": "model-00001-of-00011.safetensors",
|
| 407 |
+
"audio_tower.layers.4.fc2.weight": "model-00001-of-00011.safetensors",
|
| 408 |
+
"audio_tower.layers.4.final_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 409 |
+
"audio_tower.layers.4.final_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 410 |
+
"audio_tower.layers.4.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 411 |
+
"audio_tower.layers.4.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
|
| 412 |
+
"audio_tower.layers.4.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 413 |
+
"audio_tower.layers.4.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
|
| 414 |
+
"audio_tower.layers.4.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 415 |
+
"audio_tower.layers.4.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
|
| 416 |
+
"audio_tower.layers.4.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 417 |
+
"audio_tower.layers.4.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 418 |
+
"audio_tower.layers.4.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 419 |
+
"audio_tower.layers.5.fc1.bias": "model-00001-of-00011.safetensors",
|
| 420 |
+
"audio_tower.layers.5.fc1.weight": "model-00001-of-00011.safetensors",
|
| 421 |
+
"audio_tower.layers.5.fc2.bias": "model-00001-of-00011.safetensors",
|
| 422 |
+
"audio_tower.layers.5.fc2.weight": "model-00001-of-00011.safetensors",
|
| 423 |
+
"audio_tower.layers.5.final_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 424 |
+
"audio_tower.layers.5.final_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 425 |
+
"audio_tower.layers.5.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 426 |
+
"audio_tower.layers.5.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
|
| 427 |
+
"audio_tower.layers.5.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 428 |
+
"audio_tower.layers.5.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
|
| 429 |
+
"audio_tower.layers.5.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 430 |
+
"audio_tower.layers.5.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
|
| 431 |
+
"audio_tower.layers.5.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 432 |
+
"audio_tower.layers.5.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 433 |
+
"audio_tower.layers.5.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 434 |
+
"audio_tower.layers.6.fc1.bias": "model-00001-of-00011.safetensors",
|
| 435 |
+
"audio_tower.layers.6.fc1.weight": "model-00001-of-00011.safetensors",
|
| 436 |
+
"audio_tower.layers.6.fc2.bias": "model-00001-of-00011.safetensors",
|
| 437 |
+
"audio_tower.layers.6.fc2.weight": "model-00001-of-00011.safetensors",
|
| 438 |
+
"audio_tower.layers.6.final_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 439 |
+
"audio_tower.layers.6.final_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 440 |
+
"audio_tower.layers.6.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 441 |
+
"audio_tower.layers.6.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
|
| 442 |
+
"audio_tower.layers.6.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 443 |
+
"audio_tower.layers.6.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
|
| 444 |
+
"audio_tower.layers.6.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 445 |
+
"audio_tower.layers.6.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
|
| 446 |
+
"audio_tower.layers.6.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 447 |
+
"audio_tower.layers.6.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 448 |
+
"audio_tower.layers.6.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 449 |
+
"audio_tower.layers.7.fc1.bias": "model-00001-of-00011.safetensors",
|
| 450 |
+
"audio_tower.layers.7.fc1.weight": "model-00001-of-00011.safetensors",
|
| 451 |
+
"audio_tower.layers.7.fc2.bias": "model-00001-of-00011.safetensors",
|
| 452 |
+
"audio_tower.layers.7.fc2.weight": "model-00001-of-00011.safetensors",
|
| 453 |
+
"audio_tower.layers.7.final_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 454 |
+
"audio_tower.layers.7.final_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 455 |
+
"audio_tower.layers.7.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 456 |
+
"audio_tower.layers.7.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
|
| 457 |
+
"audio_tower.layers.7.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 458 |
+
"audio_tower.layers.7.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
|
| 459 |
+
"audio_tower.layers.7.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 460 |
+
"audio_tower.layers.7.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
|
| 461 |
+
"audio_tower.layers.7.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 462 |
+
"audio_tower.layers.7.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 463 |
+
"audio_tower.layers.7.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 464 |
+
"audio_tower.layers.8.fc1.bias": "model-00001-of-00011.safetensors",
|
| 465 |
+
"audio_tower.layers.8.fc1.weight": "model-00001-of-00011.safetensors",
|
| 466 |
+
"audio_tower.layers.8.fc2.bias": "model-00001-of-00011.safetensors",
|
| 467 |
+
"audio_tower.layers.8.fc2.weight": "model-00001-of-00011.safetensors",
|
| 468 |
+
"audio_tower.layers.8.final_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 469 |
+
"audio_tower.layers.8.final_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 470 |
+
"audio_tower.layers.8.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 471 |
+
"audio_tower.layers.8.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
|
| 472 |
+
"audio_tower.layers.8.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 473 |
+
"audio_tower.layers.8.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
|
| 474 |
+
"audio_tower.layers.8.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 475 |
+
"audio_tower.layers.8.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
|
| 476 |
+
"audio_tower.layers.8.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 477 |
+
"audio_tower.layers.8.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 478 |
+
"audio_tower.layers.8.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 479 |
+
"audio_tower.layers.9.fc1.bias": "model-00001-of-00011.safetensors",
|
| 480 |
+
"audio_tower.layers.9.fc1.weight": "model-00001-of-00011.safetensors",
|
| 481 |
+
"audio_tower.layers.9.fc2.bias": "model-00001-of-00011.safetensors",
|
| 482 |
+
"audio_tower.layers.9.fc2.weight": "model-00001-of-00011.safetensors",
|
| 483 |
+
"audio_tower.layers.9.final_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 484 |
+
"audio_tower.layers.9.final_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 485 |
+
"audio_tower.layers.9.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 486 |
+
"audio_tower.layers.9.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
|
| 487 |
+
"audio_tower.layers.9.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
|
| 488 |
+
"audio_tower.layers.9.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
|
| 489 |
+
"audio_tower.layers.9.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 490 |
+
"audio_tower.layers.9.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
|
| 491 |
+
"audio_tower.layers.9.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 492 |
+
"audio_tower.layers.9.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
|
| 493 |
+
"audio_tower.layers.9.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
|
| 494 |
+
"language_model.lm_head.weight": "model-00011-of-00011.safetensors",
|
| 495 |
+
"language_model.model.embed_tokens.weight": "model-00001-of-00011.safetensors",
|
| 496 |
+
"language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors",
|
| 497 |
+
"language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
|
| 498 |
+
"language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
|
| 499 |
+
"language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
|
| 500 |
+
"language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
|
| 501 |
+
"language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 502 |
+
"language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
|
| 503 |
+
"language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 504 |
+
"language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 505 |
+
"language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00011.safetensors",
|
| 506 |
+
"language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
|
| 507 |
+
"language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
|
| 508 |
+
"language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
|
| 509 |
+
"language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
|
| 510 |
+
"language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 511 |
+
"language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
|
| 512 |
+
"language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 513 |
+
"language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 514 |
+
"language_model.model.layers.10.input_layernorm.weight": "model-00004-of-00011.safetensors",
|
| 515 |
+
"language_model.model.layers.10.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
|
| 516 |
+
"language_model.model.layers.10.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
|
| 517 |
+
"language_model.model.layers.10.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
|
| 518 |
+
"language_model.model.layers.10.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
|
| 519 |
+
"language_model.model.layers.10.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
|
| 520 |
+
"language_model.model.layers.10.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
|
| 521 |
+
"language_model.model.layers.10.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
|
| 522 |
+
"language_model.model.layers.10.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
|
| 523 |
+
"language_model.model.layers.11.input_layernorm.weight": "model-00004-of-00011.safetensors",
|
| 524 |
+
"language_model.model.layers.11.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
|
| 525 |
+
"language_model.model.layers.11.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
|
| 526 |
+
"language_model.model.layers.11.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
|
| 527 |
+
"language_model.model.layers.11.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
|
| 528 |
+
"language_model.model.layers.11.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
|
| 529 |
+
"language_model.model.layers.11.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
|
| 530 |
+
"language_model.model.layers.11.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
|
| 531 |
+
"language_model.model.layers.11.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
|
| 532 |
+
"language_model.model.layers.12.input_layernorm.weight": "model-00004-of-00011.safetensors",
|
| 533 |
+
"language_model.model.layers.12.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
|
| 534 |
+
"language_model.model.layers.12.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
|
| 535 |
+
"language_model.model.layers.12.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
|
| 536 |
+
"language_model.model.layers.12.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
|
| 537 |
+
"language_model.model.layers.12.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
|
| 538 |
+
"language_model.model.layers.12.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
|
| 539 |
+
"language_model.model.layers.12.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
|
| 540 |
+
"language_model.model.layers.12.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
|
| 541 |
+
"language_model.model.layers.13.input_layernorm.weight": "model-00004-of-00011.safetensors",
|
| 542 |
+
"language_model.model.layers.13.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
|
| 543 |
+
"language_model.model.layers.13.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
|
| 544 |
+
"language_model.model.layers.13.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
|
| 545 |
+
"language_model.model.layers.13.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
|
| 546 |
+
"language_model.model.layers.13.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
|
| 547 |
+
"language_model.model.layers.13.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
|
| 548 |
+
"language_model.model.layers.13.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
|
| 549 |
+
"language_model.model.layers.13.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
|
| 550 |
+
"language_model.model.layers.14.input_layernorm.weight": "model-00004-of-00011.safetensors",
|
| 551 |
+
"language_model.model.layers.14.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
|
| 552 |
+
"language_model.model.layers.14.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
|
| 553 |
+
"language_model.model.layers.14.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
|
| 554 |
+
"language_model.model.layers.14.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
|
| 555 |
+
"language_model.model.layers.14.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
|
| 556 |
+
"language_model.model.layers.14.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
|
| 557 |
+
"language_model.model.layers.14.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
|
| 558 |
+
"language_model.model.layers.14.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
|
| 559 |
+
"language_model.model.layers.15.input_layernorm.weight": "model-00005-of-00011.safetensors",
|
| 560 |
+
"language_model.model.layers.15.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
|
| 561 |
+
"language_model.model.layers.15.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
|
| 562 |
+
"language_model.model.layers.15.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
|
| 563 |
+
"language_model.model.layers.15.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
|
| 564 |
+
"language_model.model.layers.15.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
|
| 565 |
+
"language_model.model.layers.15.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
|
| 566 |
+
"language_model.model.layers.15.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
|
| 567 |
+
"language_model.model.layers.15.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
|
| 568 |
+
"language_model.model.layers.16.input_layernorm.weight": "model-00005-of-00011.safetensors",
|
| 569 |
+
"language_model.model.layers.16.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
|
| 570 |
+
"language_model.model.layers.16.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
|
| 571 |
+
"language_model.model.layers.16.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
|
| 572 |
+
"language_model.model.layers.16.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
|
| 573 |
+
"language_model.model.layers.16.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
|
| 574 |
+
"language_model.model.layers.16.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
|
| 575 |
+
"language_model.model.layers.16.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
|
| 576 |
+
"language_model.model.layers.16.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
|
| 577 |
+
"language_model.model.layers.17.input_layernorm.weight": "model-00005-of-00011.safetensors",
|
| 578 |
+
"language_model.model.layers.17.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
|
| 579 |
+
"language_model.model.layers.17.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
|
| 580 |
+
"language_model.model.layers.17.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
|
| 581 |
+
"language_model.model.layers.17.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
|
| 582 |
+
"language_model.model.layers.17.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
|
| 583 |
+
"language_model.model.layers.17.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
|
| 584 |
+
"language_model.model.layers.17.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
|
| 585 |
+
"language_model.model.layers.17.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
|
| 586 |
+
"language_model.model.layers.18.input_layernorm.weight": "model-00005-of-00011.safetensors",
|
| 587 |
+
"language_model.model.layers.18.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
|
| 588 |
+
"language_model.model.layers.18.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
|
| 589 |
+
"language_model.model.layers.18.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
|
| 590 |
+
"language_model.model.layers.18.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
|
| 591 |
+
"language_model.model.layers.18.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
|
| 592 |
+
"language_model.model.layers.18.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
|
| 593 |
+
"language_model.model.layers.18.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
|
| 594 |
+
"language_model.model.layers.18.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
|
| 595 |
+
"language_model.model.layers.19.input_layernorm.weight": "model-00006-of-00011.safetensors",
|
| 596 |
+
"language_model.model.layers.19.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
|
| 597 |
+
"language_model.model.layers.19.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
|
| 598 |
+
"language_model.model.layers.19.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
|
| 599 |
+
"language_model.model.layers.19.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
|
| 600 |
+
"language_model.model.layers.19.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
|
| 601 |
+
"language_model.model.layers.19.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
|
| 602 |
+
"language_model.model.layers.19.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
|
| 603 |
+
"language_model.model.layers.19.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
|
| 604 |
+
"language_model.model.layers.2.input_layernorm.weight": "model-00002-of-00011.safetensors",
|
| 605 |
+
"language_model.model.layers.2.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
|
| 606 |
+
"language_model.model.layers.2.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
|
| 607 |
+
"language_model.model.layers.2.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
|
| 608 |
+
"language_model.model.layers.2.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
|
| 609 |
+
"language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
| 610 |
+
"language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
|
| 611 |
+
"language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
| 612 |
+
"language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
| 613 |
+
"language_model.model.layers.20.input_layernorm.weight": "model-00006-of-00011.safetensors",
|
| 614 |
+
"language_model.model.layers.20.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
|
| 615 |
+
"language_model.model.layers.20.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
|
| 616 |
+
"language_model.model.layers.20.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
|
| 617 |
+
"language_model.model.layers.20.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
|
| 618 |
+
"language_model.model.layers.20.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
|
| 619 |
+
"language_model.model.layers.20.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
|
| 620 |
+
"language_model.model.layers.20.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
|
| 621 |
+
"language_model.model.layers.20.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
|
| 622 |
+
"language_model.model.layers.21.input_layernorm.weight": "model-00006-of-00011.safetensors",
|
| 623 |
+
"language_model.model.layers.21.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
|
| 624 |
+
"language_model.model.layers.21.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
|
| 625 |
+
"language_model.model.layers.21.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
|
| 626 |
+
"language_model.model.layers.21.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
|
| 627 |
+
"language_model.model.layers.21.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
|
| 628 |
+
"language_model.model.layers.21.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
|
| 629 |
+
"language_model.model.layers.21.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
|
| 630 |
+
"language_model.model.layers.21.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
|
| 631 |
+
"language_model.model.layers.22.input_layernorm.weight": "model-00006-of-00011.safetensors",
|
| 632 |
+
"language_model.model.layers.22.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
|
| 633 |
+
"language_model.model.layers.22.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
|
| 634 |
+
"language_model.model.layers.22.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
|
| 635 |
+
"language_model.model.layers.22.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
|
| 636 |
+
"language_model.model.layers.22.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
|
| 637 |
+
"language_model.model.layers.22.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
|
| 638 |
+
"language_model.model.layers.22.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
|
| 639 |
+
"language_model.model.layers.22.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
|
| 640 |
+
"language_model.model.layers.23.input_layernorm.weight": "model-00007-of-00011.safetensors",
|
| 641 |
+
"language_model.model.layers.23.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
|
| 642 |
+
"language_model.model.layers.23.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
|
| 643 |
+
"language_model.model.layers.23.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
|
| 644 |
+
"language_model.model.layers.23.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
|
| 645 |
+
"language_model.model.layers.23.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
|
| 646 |
+
"language_model.model.layers.23.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
|
| 647 |
+
"language_model.model.layers.23.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
|
| 648 |
+
"language_model.model.layers.23.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
|
| 649 |
+
"language_model.model.layers.24.input_layernorm.weight": "model-00007-of-00011.safetensors",
|
| 650 |
+
"language_model.model.layers.24.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
|
| 651 |
+
"language_model.model.layers.24.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
|
| 652 |
+
"language_model.model.layers.24.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
|
| 653 |
+
"language_model.model.layers.24.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
|
| 654 |
+
"language_model.model.layers.24.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
|
| 655 |
+
"language_model.model.layers.24.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
|
| 656 |
+
"language_model.model.layers.24.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
|
| 657 |
+
"language_model.model.layers.24.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
|
| 658 |
+
"language_model.model.layers.25.input_layernorm.weight": "model-00007-of-00011.safetensors",
|
| 659 |
+
"language_model.model.layers.25.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
|
| 660 |
+
"language_model.model.layers.25.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
|
| 661 |
+
"language_model.model.layers.25.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
|
| 662 |
+
"language_model.model.layers.25.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
|
| 663 |
+
"language_model.model.layers.25.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
|
| 664 |
+
"language_model.model.layers.25.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
|
| 665 |
+
"language_model.model.layers.25.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
|
| 666 |
+
"language_model.model.layers.25.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
|
| 667 |
+
"language_model.model.layers.26.input_layernorm.weight": "model-00007-of-00011.safetensors",
|
| 668 |
+
"language_model.model.layers.26.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
|
| 669 |
+
"language_model.model.layers.26.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
|
| 670 |
+
"language_model.model.layers.26.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
|
| 671 |
+
"language_model.model.layers.26.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
|
| 672 |
+
"language_model.model.layers.26.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
|
| 673 |
+
"language_model.model.layers.26.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
|
| 674 |
+
"language_model.model.layers.26.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
|
| 675 |
+
"language_model.model.layers.26.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
|
| 676 |
+
"language_model.model.layers.27.input_layernorm.weight": "model-00007-of-00011.safetensors",
|
| 677 |
+
"language_model.model.layers.27.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
|
| 678 |
+
"language_model.model.layers.27.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
|
| 679 |
+
"language_model.model.layers.27.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
|
| 680 |
+
"language_model.model.layers.27.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
|
| 681 |
+
"language_model.model.layers.27.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
|
| 682 |
+
"language_model.model.layers.27.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
|
| 683 |
+
"language_model.model.layers.27.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
|
| 684 |
+
"language_model.model.layers.27.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
|
| 685 |
+
"language_model.model.layers.28.input_layernorm.weight": "model-00008-of-00011.safetensors",
|
| 686 |
+
"language_model.model.layers.28.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
|
| 687 |
+
"language_model.model.layers.28.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
|
| 688 |
+
"language_model.model.layers.28.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
|
| 689 |
+
"language_model.model.layers.28.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
|
| 690 |
+
"language_model.model.layers.28.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
|
| 691 |
+
"language_model.model.layers.28.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
|
| 692 |
+
"language_model.model.layers.28.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
|
| 693 |
+
"language_model.model.layers.28.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
|
| 694 |
+
"language_model.model.layers.29.input_layernorm.weight": "model-00008-of-00011.safetensors",
|
| 695 |
+
"language_model.model.layers.29.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
|
| 696 |
+
"language_model.model.layers.29.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
|
| 697 |
+
"language_model.model.layers.29.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
|
| 698 |
+
"language_model.model.layers.29.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
|
| 699 |
+
"language_model.model.layers.29.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
|
| 700 |
+
"language_model.model.layers.29.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
|
| 701 |
+
"language_model.model.layers.29.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
|
| 702 |
+
"language_model.model.layers.29.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
|
| 703 |
+
"language_model.model.layers.3.input_layernorm.weight": "model-00002-of-00011.safetensors",
|
| 704 |
+
"language_model.model.layers.3.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
|
| 705 |
+
"language_model.model.layers.3.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
|
| 706 |
+
"language_model.model.layers.3.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
|
| 707 |
+
"language_model.model.layers.3.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
|
| 708 |
+
"language_model.model.layers.3.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
|
| 709 |
+
"language_model.model.layers.3.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
|
| 710 |
+
"language_model.model.layers.3.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
|
| 711 |
+
"language_model.model.layers.3.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
|
| 712 |
+
"language_model.model.layers.30.input_layernorm.weight": "model-00008-of-00011.safetensors",
|
| 713 |
+
"language_model.model.layers.30.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
|
| 714 |
+
"language_model.model.layers.30.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
|
| 715 |
+
"language_model.model.layers.30.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
|
| 716 |
+
"language_model.model.layers.30.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
|
| 717 |
+
"language_model.model.layers.30.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
|
| 718 |
+
"language_model.model.layers.30.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
|
| 719 |
+
"language_model.model.layers.30.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
|
| 720 |
+
"language_model.model.layers.30.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
|
| 721 |
+
"language_model.model.layers.31.input_layernorm.weight": "model-00008-of-00011.safetensors",
|
| 722 |
+
"language_model.model.layers.31.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
|
| 723 |
+
"language_model.model.layers.31.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
|
| 724 |
+
"language_model.model.layers.31.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
|
| 725 |
+
"language_model.model.layers.31.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
|
| 726 |
+
"language_model.model.layers.31.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
|
| 727 |
+
"language_model.model.layers.31.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
|
| 728 |
+
"language_model.model.layers.31.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
|
| 729 |
+
"language_model.model.layers.31.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
|
| 730 |
+
"language_model.model.layers.32.input_layernorm.weight": "model-00009-of-00011.safetensors",
|
| 731 |
+
"language_model.model.layers.32.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
|
| 732 |
+
"language_model.model.layers.32.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
|
| 733 |
+
"language_model.model.layers.32.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
|
| 734 |
+
"language_model.model.layers.32.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
|
| 735 |
+
"language_model.model.layers.32.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
|
| 736 |
+
"language_model.model.layers.32.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
|
| 737 |
+
"language_model.model.layers.32.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
|
| 738 |
+
"language_model.model.layers.32.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
|
| 739 |
+
"language_model.model.layers.33.input_layernorm.weight": "model-00009-of-00011.safetensors",
|
| 740 |
+
"language_model.model.layers.33.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
|
| 741 |
+
"language_model.model.layers.33.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
|
| 742 |
+
"language_model.model.layers.33.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
|
| 743 |
+
"language_model.model.layers.33.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
|
| 744 |
+
"language_model.model.layers.33.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
|
| 745 |
+
"language_model.model.layers.33.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
|
| 746 |
+
"language_model.model.layers.33.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
|
| 747 |
+
"language_model.model.layers.33.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
|
| 748 |
+
"language_model.model.layers.34.input_layernorm.weight": "model-00009-of-00011.safetensors",
|
| 749 |
+
"language_model.model.layers.34.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
|
| 750 |
+
"language_model.model.layers.34.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
|
| 751 |
+
"language_model.model.layers.34.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
|
| 752 |
+
"language_model.model.layers.34.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
|
| 753 |
+
"language_model.model.layers.34.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
|
| 754 |
+
"language_model.model.layers.34.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
|
| 755 |
+
"language_model.model.layers.34.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
|
| 756 |
+
"language_model.model.layers.34.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
|
| 757 |
+
"language_model.model.layers.35.input_layernorm.weight": "model-00009-of-00011.safetensors",
|
| 758 |
+
"language_model.model.layers.35.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
|
| 759 |
+
"language_model.model.layers.35.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
|
| 760 |
+
"language_model.model.layers.35.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
|
| 761 |
+
"language_model.model.layers.35.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
|
| 762 |
+
"language_model.model.layers.35.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
|
| 763 |
+
"language_model.model.layers.35.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
|
| 764 |
+
"language_model.model.layers.35.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
|
| 765 |
+
"language_model.model.layers.35.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
|
| 766 |
+
"language_model.model.layers.36.input_layernorm.weight": "model-00010-of-00011.safetensors",
|
| 767 |
+
"language_model.model.layers.36.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
|
| 768 |
+
"language_model.model.layers.36.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
|
| 769 |
+
"language_model.model.layers.36.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
|
| 770 |
+
"language_model.model.layers.36.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
|
| 771 |
+
"language_model.model.layers.36.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
|
| 772 |
+
"language_model.model.layers.36.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
|
| 773 |
+
"language_model.model.layers.36.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
|
| 774 |
+
"language_model.model.layers.36.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
|
| 775 |
+
"language_model.model.layers.37.input_layernorm.weight": "model-00010-of-00011.safetensors",
|
| 776 |
+
"language_model.model.layers.37.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
|
| 777 |
+
"language_model.model.layers.37.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
|
| 778 |
+
"language_model.model.layers.37.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
|
| 779 |
+
"language_model.model.layers.37.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
|
| 780 |
+
"language_model.model.layers.37.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
|
| 781 |
+
"language_model.model.layers.37.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
|
| 782 |
+
"language_model.model.layers.37.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
|
| 783 |
+
"language_model.model.layers.37.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
|
| 784 |
+
"language_model.model.layers.38.input_layernorm.weight": "model-00010-of-00011.safetensors",
|
| 785 |
+
"language_model.model.layers.38.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
|
| 786 |
+
"language_model.model.layers.38.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
|
| 787 |
+
"language_model.model.layers.38.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
|
| 788 |
+
"language_model.model.layers.38.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
|
| 789 |
+
"language_model.model.layers.38.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
|
| 790 |
+
"language_model.model.layers.38.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
|
| 791 |
+
"language_model.model.layers.38.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
|
| 792 |
+
"language_model.model.layers.38.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
|
| 793 |
+
"language_model.model.layers.39.input_layernorm.weight": "model-00010-of-00011.safetensors",
|
| 794 |
+
"language_model.model.layers.39.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
|
| 795 |
+
"language_model.model.layers.39.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
|
| 796 |
+
"language_model.model.layers.39.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
|
| 797 |
+
"language_model.model.layers.39.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
|
| 798 |
+
"language_model.model.layers.39.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
|
| 799 |
+
"language_model.model.layers.39.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
|
| 800 |
+
"language_model.model.layers.39.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
|
| 801 |
+
"language_model.model.layers.39.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
|
| 802 |
+
"language_model.model.layers.4.input_layernorm.weight": "model-00002-of-00011.safetensors",
|
| 803 |
+
"language_model.model.layers.4.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
|
| 804 |
+
"language_model.model.layers.4.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
|
| 805 |
+
"language_model.model.layers.4.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
|
| 806 |
+
"language_model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
|
| 807 |
+
"language_model.model.layers.4.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
|
| 808 |
+
"language_model.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
|
| 809 |
+
"language_model.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
|
| 810 |
+
"language_model.model.layers.4.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
|
| 811 |
+
"language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00011.safetensors",
|
| 812 |
+
"language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
|
| 813 |
+
"language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
|
| 814 |
+
"language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
|
| 815 |
+
"language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
|
| 816 |
+
"language_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
|
| 817 |
+
"language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
|
| 818 |
+
"language_model.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
|
| 819 |
+
"language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
|
| 820 |
+
"language_model.model.layers.6.input_layernorm.weight": "model-00003-of-00011.safetensors",
|
| 821 |
+
"language_model.model.layers.6.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
|
| 822 |
+
"language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
|
| 823 |
+
"language_model.model.layers.6.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
|
| 824 |
+
"language_model.model.layers.6.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
|
| 825 |
+
"language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
|
| 826 |
+
"language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
|
| 827 |
+
"language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
|
| 828 |
+
"language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
|
| 829 |
+
"language_model.model.layers.7.input_layernorm.weight": "model-00003-of-00011.safetensors",
|
| 830 |
+
"language_model.model.layers.7.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
|
| 831 |
+
"language_model.model.layers.7.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
|
| 832 |
+
"language_model.model.layers.7.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
|
| 833 |
+
"language_model.model.layers.7.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
|
| 834 |
+
"language_model.model.layers.7.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
|
| 835 |
+
"language_model.model.layers.7.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
|
| 836 |
+
"language_model.model.layers.7.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
|
| 837 |
+
"language_model.model.layers.7.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
|
| 838 |
+
"language_model.model.layers.8.input_layernorm.weight": "model-00003-of-00011.safetensors",
|
| 839 |
+
"language_model.model.layers.8.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
|
| 840 |
+
"language_model.model.layers.8.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
|
| 841 |
+
"language_model.model.layers.8.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
|
| 842 |
+
"language_model.model.layers.8.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
|
| 843 |
+
"language_model.model.layers.8.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
|
| 844 |
+
"language_model.model.layers.8.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
|
| 845 |
+
"language_model.model.layers.8.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
|
| 846 |
+
"language_model.model.layers.8.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
|
| 847 |
+
"language_model.model.layers.9.input_layernorm.weight": "model-00003-of-00011.safetensors",
|
| 848 |
+
"language_model.model.layers.9.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
|
| 849 |
+
"language_model.model.layers.9.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
|
| 850 |
+
"language_model.model.layers.9.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
|
| 851 |
+
"language_model.model.layers.9.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
|
| 852 |
+
"language_model.model.layers.9.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
|
| 853 |
+
"language_model.model.layers.9.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
|
| 854 |
+
"language_model.model.layers.9.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
|
| 855 |
+
"language_model.model.layers.9.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
|
| 856 |
+
"language_model.model.norm.weight": "model-00010-of-00011.safetensors",
|
| 857 |
+
"multi_modal_projector.linear_1.weight": "model-00011-of-00011.safetensors",
|
| 858 |
+
"multi_modal_projector.linear_2.weight": "model-00011-of-00011.safetensors"
|
| 859 |
+
}
|
| 860 |
+
}
|
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 |
+
}
|