Merged lora checkpoint
Browse files- config.json +6 -1
- model-00001-of-00002.safetensors +2 -2
- model-00002-of-00002.safetensors +2 -2
- model.py +2 -1
- model.safetensors.index.json +202 -510
config.json
CHANGED
|
@@ -1,13 +1,18 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
| 2 |
"audio_enc_dim": 1024,
|
| 3 |
"audio_encoder_name": "microsoft/wavlm-large",
|
| 4 |
"audio_processor_name": "microsoft/wavlm-base",
|
| 5 |
"auto_map": {
|
| 6 |
-
"AutoConfig": "config.SpeechLLMModelConfig"
|
|
|
|
| 7 |
},
|
| 8 |
"llm_dim": 2048,
|
| 9 |
"llm_model_checkpoint": "hf_repo/llm_model_checkpoint",
|
| 10 |
"llm_model_name": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
|
| 11 |
"model_type": "custom_model",
|
|
|
|
| 12 |
"transformers_version": "4.41.2"
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"SpeechLLMModel"
|
| 4 |
+
],
|
| 5 |
"audio_enc_dim": 1024,
|
| 6 |
"audio_encoder_name": "microsoft/wavlm-large",
|
| 7 |
"audio_processor_name": "microsoft/wavlm-base",
|
| 8 |
"auto_map": {
|
| 9 |
+
"AutoConfig": "config.SpeechLLMModelConfig",
|
| 10 |
+
"AutoModel": "model.SpeechLLMModel"
|
| 11 |
},
|
| 12 |
"llm_dim": 2048,
|
| 13 |
"llm_model_checkpoint": "hf_repo/llm_model_checkpoint",
|
| 14 |
"llm_model_name": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
|
| 15 |
"model_type": "custom_model",
|
| 16 |
+
"torch_dtype": "float32",
|
| 17 |
"transformers_version": "4.41.2"
|
| 18 |
}
|
model-00001-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca3b8867386b18c6aadb0499a682799dcbd76a573769d4bd28e3b3db0637d34c
|
| 3 |
+
size 4972078744
|
model-00002-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c276e96e5b2bf5bc6824b157179f3cb4304de0e674ffbb793cc2cb62b8dd1cd6
|
| 3 |
+
size 836841304
|
model.py
CHANGED
|
@@ -58,6 +58,7 @@ class SpeechLLMModel(PreTrainedModel):
|
|
| 58 |
task_type="CAUSAL_LM",
|
| 59 |
)
|
| 60 |
self.llm_model = get_peft_model(self.llm_model, peft_config)
|
|
|
|
| 61 |
|
| 62 |
def encode(self, mel, pre_tokenized_ids, post_tokenized_ids, output_tokenized_ids):
|
| 63 |
batch_size = mel.shape[0]
|
|
@@ -66,7 +67,7 @@ class SpeechLLMModel(PreTrainedModel):
|
|
| 66 |
speech_embeds = self.audio_encoder(mel)
|
| 67 |
speech_embeds = self.connector(speech_embeds)
|
| 68 |
|
| 69 |
-
embedder = self.llm_model.model.
|
| 70 |
pre_prompt_embeds = embedder(pre_tokenized_ids)
|
| 71 |
post_prompt_embeds = embedder(post_tokenized_ids)
|
| 72 |
output_prompt_embeds = embedder(output_tokenized_ids)
|
|
|
|
| 58 |
task_type="CAUSAL_LM",
|
| 59 |
)
|
| 60 |
self.llm_model = get_peft_model(self.llm_model, peft_config)
|
| 61 |
+
self.llm_model = self.llm_model.merge_and_unload()
|
| 62 |
|
| 63 |
def encode(self, mel, pre_tokenized_ids, post_tokenized_ids, output_tokenized_ids):
|
| 64 |
batch_size = mel.shape[0]
|
|
|
|
| 67 |
speech_embeds = self.audio_encoder(mel)
|
| 68 |
speech_embeds = self.connector(speech_embeds)
|
| 69 |
|
| 70 |
+
embedder = self.llm_model.model.embed_tokens
|
| 71 |
pre_prompt_embeds = embedder(pre_tokenized_ids)
|
| 72 |
post_prompt_embeds = embedder(post_tokenized_ids)
|
| 73 |
output_prompt_embeds = embedder(output_tokenized_ids)
|
model.safetensors.index.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"audio_encoder.encoder.encoder.layer_norm.bias": "model-00001-of-00002.safetensors",
|
|
@@ -497,514 +497,206 @@
|
|
| 497 |
"connector.layer.3.weight": "model-00001-of-00002.safetensors",
|
| 498 |
"connector.layer.5.bias": "model-00001-of-00002.safetensors",
|
| 499 |
"connector.layer.5.weight": "model-00001-of-00002.safetensors",
|
| 500 |
-
"llm_model.
|
| 501 |
-
"llm_model.
|
| 502 |
-
"llm_model.
|
| 503 |
-
"llm_model.
|
| 504 |
-
"llm_model.
|
| 505 |
-
"llm_model.
|
| 506 |
-
"llm_model.
|
| 507 |
-
"llm_model.
|
| 508 |
-
"llm_model.
|
| 509 |
-
"llm_model.
|
| 510 |
-
"llm_model.
|
| 511 |
-
"llm_model.
|
| 512 |
-
"llm_model.
|
| 513 |
-
"llm_model.
|
| 514 |
-
"llm_model.
|
| 515 |
-
"llm_model.
|
| 516 |
-
"llm_model.
|
| 517 |
-
"llm_model.
|
| 518 |
-
"llm_model.
|
| 519 |
-
"llm_model.
|
| 520 |
-
"llm_model.
|
| 521 |
-
"llm_model.
|
| 522 |
-
"llm_model.
|
| 523 |
-
"llm_model.
|
| 524 |
-
"llm_model.
|
| 525 |
-
"llm_model.
|
| 526 |
-
"llm_model.
|
| 527 |
-
"llm_model.
|
| 528 |
-
"llm_model.
|
| 529 |
-
"llm_model.
|
| 530 |
-
"llm_model.
|
| 531 |
-
"llm_model.
|
| 532 |
-
"llm_model.
|
| 533 |
-
"llm_model.
|
| 534 |
-
"llm_model.
|
| 535 |
-
"llm_model.
|
| 536 |
-
"llm_model.
|
| 537 |
-
"llm_model.
|
| 538 |
-
"llm_model.
|
| 539 |
-
"llm_model.
|
| 540 |
-
"llm_model.
|
| 541 |
-
"llm_model.
|
| 542 |
-
"llm_model.
|
| 543 |
-
"llm_model.
|
| 544 |
-
"llm_model.
|
| 545 |
-
"llm_model.
|
| 546 |
-
"llm_model.
|
| 547 |
-
"llm_model.
|
| 548 |
-
"llm_model.
|
| 549 |
-
"llm_model.
|
| 550 |
-
"llm_model.
|
| 551 |
-
"llm_model.
|
| 552 |
-
"llm_model.
|
| 553 |
-
"llm_model.
|
| 554 |
-
"llm_model.
|
| 555 |
-
"llm_model.
|
| 556 |
-
"llm_model.
|
| 557 |
-
"llm_model.
|
| 558 |
-
"llm_model.
|
| 559 |
-
"llm_model.
|
| 560 |
-
"llm_model.
|
| 561 |
-
"llm_model.
|
| 562 |
-
"llm_model.
|
| 563 |
-
"llm_model.
|
| 564 |
-
"llm_model.
|
| 565 |
-
"llm_model.
|
| 566 |
-
"llm_model.
|
| 567 |
-
"llm_model.
|
| 568 |
-
"llm_model.
|
| 569 |
-
"llm_model.
|
| 570 |
-
"llm_model.
|
| 571 |
-
"llm_model.
|
| 572 |
-
"llm_model.
|
| 573 |
-
"llm_model.
|
| 574 |
-
"llm_model.
|
| 575 |
-
"llm_model.
|
| 576 |
-
"llm_model.
|
| 577 |
-
"llm_model.
|
| 578 |
-
"llm_model.
|
| 579 |
-
"llm_model.
|
| 580 |
-
"llm_model.
|
| 581 |
-
"llm_model.
|
| 582 |
-
"llm_model.
|
| 583 |
-
"llm_model.
|
| 584 |
-
"llm_model.
|
| 585 |
-
"llm_model.
|
| 586 |
-
"llm_model.
|
| 587 |
-
"llm_model.
|
| 588 |
-
"llm_model.
|
| 589 |
-
"llm_model.
|
| 590 |
-
"llm_model.
|
| 591 |
-
"llm_model.
|
| 592 |
-
"llm_model.
|
| 593 |
-
"llm_model.
|
| 594 |
-
"llm_model.
|
| 595 |
-
"llm_model.
|
| 596 |
-
"llm_model.
|
| 597 |
-
"llm_model.
|
| 598 |
-
"llm_model.
|
| 599 |
-
"llm_model.
|
| 600 |
-
"llm_model.
|
| 601 |
-
"llm_model.
|
| 602 |
-
"llm_model.
|
| 603 |
-
"llm_model.
|
| 604 |
-
"llm_model.
|
| 605 |
-
"llm_model.
|
| 606 |
-
"llm_model.
|
| 607 |
-
"llm_model.
|
| 608 |
-
"llm_model.
|
| 609 |
-
"llm_model.
|
| 610 |
-
"llm_model.
|
| 611 |
-
"llm_model.
|
| 612 |
-
"llm_model.
|
| 613 |
-
"llm_model.
|
| 614 |
-
"llm_model.
|
| 615 |
-
"llm_model.
|
| 616 |
-
"llm_model.
|
| 617 |
-
"llm_model.
|
| 618 |
-
"llm_model.
|
| 619 |
-
"llm_model.
|
| 620 |
-
"llm_model.
|
| 621 |
-
"llm_model.
|
| 622 |
-
"llm_model.
|
| 623 |
-
"llm_model.
|
| 624 |
-
"llm_model.
|
| 625 |
-
"llm_model.
|
| 626 |
-
"llm_model.
|
| 627 |
-
"llm_model.
|
| 628 |
-
"llm_model.
|
| 629 |
-
"llm_model.
|
| 630 |
-
"llm_model.
|
| 631 |
-
"llm_model.
|
| 632 |
-
"llm_model.
|
| 633 |
-
"llm_model.
|
| 634 |
-
"llm_model.
|
| 635 |
-
"llm_model.
|
| 636 |
-
"llm_model.
|
| 637 |
-
"llm_model.
|
| 638 |
-
"llm_model.
|
| 639 |
-
"llm_model.
|
| 640 |
-
"llm_model.
|
| 641 |
-
"llm_model.
|
| 642 |
-
"llm_model.
|
| 643 |
-
"llm_model.
|
| 644 |
-
"llm_model.
|
| 645 |
-
"llm_model.
|
| 646 |
-
"llm_model.
|
| 647 |
-
"llm_model.
|
| 648 |
-
"llm_model.
|
| 649 |
-
"llm_model.
|
| 650 |
-
"llm_model.
|
| 651 |
-
"llm_model.
|
| 652 |
-
"llm_model.
|
| 653 |
-
"llm_model.
|
| 654 |
-
"llm_model.
|
| 655 |
-
"llm_model.
|
| 656 |
-
"llm_model.
|
| 657 |
-
"llm_model.
|
| 658 |
-
"llm_model.
|
| 659 |
-
"llm_model.
|
| 660 |
-
"llm_model.
|
| 661 |
-
"llm_model.
|
| 662 |
-
"llm_model.
|
| 663 |
-
"llm_model.
|
| 664 |
-
"llm_model.
|
| 665 |
-
"llm_model.
|
| 666 |
-
"llm_model.
|
| 667 |
-
"llm_model.
|
| 668 |
-
"llm_model.
|
| 669 |
-
"llm_model.
|
| 670 |
-
"llm_model.
|
| 671 |
-
"llm_model.
|
| 672 |
-
"llm_model.
|
| 673 |
-
"llm_model.
|
| 674 |
-
"llm_model.
|
| 675 |
-
"llm_model.
|
| 676 |
-
"llm_model.
|
| 677 |
-
"llm_model.
|
| 678 |
-
"llm_model.
|
| 679 |
-
"llm_model.
|
| 680 |
-
"llm_model.
|
| 681 |
-
"llm_model.
|
| 682 |
-
"llm_model.
|
| 683 |
-
"llm_model.
|
| 684 |
-
"llm_model.
|
| 685 |
-
"llm_model.
|
| 686 |
-
"llm_model.
|
| 687 |
-
"llm_model.
|
| 688 |
-
"llm_model.
|
| 689 |
-
"llm_model.
|
| 690 |
-
"llm_model.
|
| 691 |
-
"llm_model.
|
| 692 |
-
"llm_model.
|
| 693 |
-
"llm_model.
|
| 694 |
-
"llm_model.
|
| 695 |
-
"llm_model.
|
| 696 |
-
"llm_model.
|
| 697 |
-
"llm_model.
|
| 698 |
-
"llm_model.
|
| 699 |
-
"llm_model.
|
| 700 |
-
"llm_model.
|
| 701 |
-
"llm_model.base_model.model.model.layers.16.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 702 |
-
"llm_model.base_model.model.model.layers.16.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 703 |
-
"llm_model.base_model.model.model.layers.16.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 704 |
-
"llm_model.base_model.model.model.layers.16.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 705 |
-
"llm_model.base_model.model.model.layers.16.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 706 |
-
"llm_model.base_model.model.model.layers.16.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 707 |
-
"llm_model.base_model.model.model.layers.16.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 708 |
-
"llm_model.base_model.model.model.layers.16.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 709 |
-
"llm_model.base_model.model.model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 710 |
-
"llm_model.base_model.model.model.layers.17.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 711 |
-
"llm_model.base_model.model.model.layers.17.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 712 |
-
"llm_model.base_model.model.model.layers.17.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 713 |
-
"llm_model.base_model.model.model.layers.17.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 714 |
-
"llm_model.base_model.model.model.layers.17.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 715 |
-
"llm_model.base_model.model.model.layers.17.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 716 |
-
"llm_model.base_model.model.model.layers.17.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 717 |
-
"llm_model.base_model.model.model.layers.17.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 718 |
-
"llm_model.base_model.model.model.layers.17.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 719 |
-
"llm_model.base_model.model.model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 720 |
-
"llm_model.base_model.model.model.layers.17.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 721 |
-
"llm_model.base_model.model.model.layers.17.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 722 |
-
"llm_model.base_model.model.model.layers.17.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 723 |
-
"llm_model.base_model.model.model.layers.17.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 724 |
-
"llm_model.base_model.model.model.layers.17.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 725 |
-
"llm_model.base_model.model.model.layers.17.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 726 |
-
"llm_model.base_model.model.model.layers.17.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 727 |
-
"llm_model.base_model.model.model.layers.17.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 728 |
-
"llm_model.base_model.model.model.layers.17.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 729 |
-
"llm_model.base_model.model.model.layers.17.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 730 |
-
"llm_model.base_model.model.model.layers.17.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 731 |
-
"llm_model.base_model.model.model.layers.17.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 732 |
-
"llm_model.base_model.model.model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 733 |
-
"llm_model.base_model.model.model.layers.18.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
|
| 734 |
-
"llm_model.base_model.model.model.layers.18.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
|
| 735 |
-
"llm_model.base_model.model.model.layers.18.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
|
| 736 |
-
"llm_model.base_model.model.model.layers.18.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 737 |
-
"llm_model.base_model.model.model.layers.18.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 738 |
-
"llm_model.base_model.model.model.layers.18.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 739 |
-
"llm_model.base_model.model.model.layers.18.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 740 |
-
"llm_model.base_model.model.model.layers.18.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 741 |
-
"llm_model.base_model.model.model.layers.18.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 742 |
-
"llm_model.base_model.model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 743 |
-
"llm_model.base_model.model.model.layers.18.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 744 |
-
"llm_model.base_model.model.model.layers.18.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 745 |
-
"llm_model.base_model.model.model.layers.18.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 746 |
-
"llm_model.base_model.model.model.layers.18.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 747 |
-
"llm_model.base_model.model.model.layers.18.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 748 |
-
"llm_model.base_model.model.model.layers.18.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 749 |
-
"llm_model.base_model.model.model.layers.18.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 750 |
-
"llm_model.base_model.model.model.layers.18.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 751 |
-
"llm_model.base_model.model.model.layers.18.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 752 |
-
"llm_model.base_model.model.model.layers.18.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 753 |
-
"llm_model.base_model.model.model.layers.18.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 754 |
-
"llm_model.base_model.model.model.layers.18.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 755 |
-
"llm_model.base_model.model.model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 756 |
-
"llm_model.base_model.model.model.layers.19.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
|
| 757 |
-
"llm_model.base_model.model.model.layers.19.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
|
| 758 |
-
"llm_model.base_model.model.model.layers.19.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
|
| 759 |
-
"llm_model.base_model.model.model.layers.19.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
|
| 760 |
-
"llm_model.base_model.model.model.layers.19.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
|
| 761 |
-
"llm_model.base_model.model.model.layers.19.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
|
| 762 |
-
"llm_model.base_model.model.model.layers.19.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
|
| 763 |
-
"llm_model.base_model.model.model.layers.19.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
|
| 764 |
-
"llm_model.base_model.model.model.layers.19.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
|
| 765 |
-
"llm_model.base_model.model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 766 |
-
"llm_model.base_model.model.model.layers.19.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
|
| 767 |
-
"llm_model.base_model.model.model.layers.19.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
|
| 768 |
-
"llm_model.base_model.model.model.layers.19.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
|
| 769 |
-
"llm_model.base_model.model.model.layers.19.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
|
| 770 |
-
"llm_model.base_model.model.model.layers.19.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
|
| 771 |
-
"llm_model.base_model.model.model.layers.19.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
|
| 772 |
-
"llm_model.base_model.model.model.layers.19.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
|
| 773 |
-
"llm_model.base_model.model.model.layers.19.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
|
| 774 |
-
"llm_model.base_model.model.model.layers.19.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
|
| 775 |
-
"llm_model.base_model.model.model.layers.19.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
|
| 776 |
-
"llm_model.base_model.model.model.layers.19.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
|
| 777 |
-
"llm_model.base_model.model.model.layers.19.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
|
| 778 |
-
"llm_model.base_model.model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 779 |
-
"llm_model.base_model.model.model.layers.2.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 780 |
-
"llm_model.base_model.model.model.layers.2.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 781 |
-
"llm_model.base_model.model.model.layers.2.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 782 |
-
"llm_model.base_model.model.model.layers.2.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 783 |
-
"llm_model.base_model.model.model.layers.2.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 784 |
-
"llm_model.base_model.model.model.layers.2.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 785 |
-
"llm_model.base_model.model.model.layers.2.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 786 |
-
"llm_model.base_model.model.model.layers.2.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 787 |
-
"llm_model.base_model.model.model.layers.2.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 788 |
-
"llm_model.base_model.model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 789 |
-
"llm_model.base_model.model.model.layers.2.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 790 |
-
"llm_model.base_model.model.model.layers.2.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 791 |
-
"llm_model.base_model.model.model.layers.2.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 792 |
-
"llm_model.base_model.model.model.layers.2.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 793 |
-
"llm_model.base_model.model.model.layers.2.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 794 |
-
"llm_model.base_model.model.model.layers.2.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 795 |
-
"llm_model.base_model.model.model.layers.2.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 796 |
-
"llm_model.base_model.model.model.layers.2.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 797 |
-
"llm_model.base_model.model.model.layers.2.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 798 |
-
"llm_model.base_model.model.model.layers.2.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 799 |
-
"llm_model.base_model.model.model.layers.2.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 800 |
-
"llm_model.base_model.model.model.layers.2.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 801 |
-
"llm_model.base_model.model.model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 802 |
-
"llm_model.base_model.model.model.layers.20.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
|
| 803 |
-
"llm_model.base_model.model.model.layers.20.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
|
| 804 |
-
"llm_model.base_model.model.model.layers.20.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
|
| 805 |
-
"llm_model.base_model.model.model.layers.20.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
|
| 806 |
-
"llm_model.base_model.model.model.layers.20.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
|
| 807 |
-
"llm_model.base_model.model.model.layers.20.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
|
| 808 |
-
"llm_model.base_model.model.model.layers.20.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
|
| 809 |
-
"llm_model.base_model.model.model.layers.20.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
|
| 810 |
-
"llm_model.base_model.model.model.layers.20.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
|
| 811 |
-
"llm_model.base_model.model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 812 |
-
"llm_model.base_model.model.model.layers.20.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
|
| 813 |
-
"llm_model.base_model.model.model.layers.20.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
|
| 814 |
-
"llm_model.base_model.model.model.layers.20.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
|
| 815 |
-
"llm_model.base_model.model.model.layers.20.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
|
| 816 |
-
"llm_model.base_model.model.model.layers.20.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
|
| 817 |
-
"llm_model.base_model.model.model.layers.20.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
|
| 818 |
-
"llm_model.base_model.model.model.layers.20.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
|
| 819 |
-
"llm_model.base_model.model.model.layers.20.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
|
| 820 |
-
"llm_model.base_model.model.model.layers.20.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
|
| 821 |
-
"llm_model.base_model.model.model.layers.20.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
|
| 822 |
-
"llm_model.base_model.model.model.layers.20.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
|
| 823 |
-
"llm_model.base_model.model.model.layers.20.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
|
| 824 |
-
"llm_model.base_model.model.model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 825 |
-
"llm_model.base_model.model.model.layers.21.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
|
| 826 |
-
"llm_model.base_model.model.model.layers.21.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
|
| 827 |
-
"llm_model.base_model.model.model.layers.21.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
|
| 828 |
-
"llm_model.base_model.model.model.layers.21.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
|
| 829 |
-
"llm_model.base_model.model.model.layers.21.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
|
| 830 |
-
"llm_model.base_model.model.model.layers.21.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
|
| 831 |
-
"llm_model.base_model.model.model.layers.21.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
|
| 832 |
-
"llm_model.base_model.model.model.layers.21.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
|
| 833 |
-
"llm_model.base_model.model.model.layers.21.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
|
| 834 |
-
"llm_model.base_model.model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 835 |
-
"llm_model.base_model.model.model.layers.21.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
|
| 836 |
-
"llm_model.base_model.model.model.layers.21.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
|
| 837 |
-
"llm_model.base_model.model.model.layers.21.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
|
| 838 |
-
"llm_model.base_model.model.model.layers.21.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
|
| 839 |
-
"llm_model.base_model.model.model.layers.21.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
|
| 840 |
-
"llm_model.base_model.model.model.layers.21.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
|
| 841 |
-
"llm_model.base_model.model.model.layers.21.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
|
| 842 |
-
"llm_model.base_model.model.model.layers.21.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
|
| 843 |
-
"llm_model.base_model.model.model.layers.21.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
|
| 844 |
-
"llm_model.base_model.model.model.layers.21.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
|
| 845 |
-
"llm_model.base_model.model.model.layers.21.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
|
| 846 |
-
"llm_model.base_model.model.model.layers.21.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
|
| 847 |
-
"llm_model.base_model.model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 848 |
-
"llm_model.base_model.model.model.layers.3.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 849 |
-
"llm_model.base_model.model.model.layers.3.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 850 |
-
"llm_model.base_model.model.model.layers.3.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 851 |
-
"llm_model.base_model.model.model.layers.3.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 852 |
-
"llm_model.base_model.model.model.layers.3.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 853 |
-
"llm_model.base_model.model.model.layers.3.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 854 |
-
"llm_model.base_model.model.model.layers.3.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 855 |
-
"llm_model.base_model.model.model.layers.3.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 856 |
-
"llm_model.base_model.model.model.layers.3.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 857 |
-
"llm_model.base_model.model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 858 |
-
"llm_model.base_model.model.model.layers.3.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 859 |
-
"llm_model.base_model.model.model.layers.3.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 860 |
-
"llm_model.base_model.model.model.layers.3.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 861 |
-
"llm_model.base_model.model.model.layers.3.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 862 |
-
"llm_model.base_model.model.model.layers.3.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 863 |
-
"llm_model.base_model.model.model.layers.3.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 864 |
-
"llm_model.base_model.model.model.layers.3.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 865 |
-
"llm_model.base_model.model.model.layers.3.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 866 |
-
"llm_model.base_model.model.model.layers.3.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 867 |
-
"llm_model.base_model.model.model.layers.3.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 868 |
-
"llm_model.base_model.model.model.layers.3.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 869 |
-
"llm_model.base_model.model.model.layers.3.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 870 |
-
"llm_model.base_model.model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 871 |
-
"llm_model.base_model.model.model.layers.4.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 872 |
-
"llm_model.base_model.model.model.layers.4.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 873 |
-
"llm_model.base_model.model.model.layers.4.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 874 |
-
"llm_model.base_model.model.model.layers.4.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 875 |
-
"llm_model.base_model.model.model.layers.4.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 876 |
-
"llm_model.base_model.model.model.layers.4.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 877 |
-
"llm_model.base_model.model.model.layers.4.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 878 |
-
"llm_model.base_model.model.model.layers.4.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 879 |
-
"llm_model.base_model.model.model.layers.4.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 880 |
-
"llm_model.base_model.model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 881 |
-
"llm_model.base_model.model.model.layers.4.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 882 |
-
"llm_model.base_model.model.model.layers.4.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 883 |
-
"llm_model.base_model.model.model.layers.4.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 884 |
-
"llm_model.base_model.model.model.layers.4.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 885 |
-
"llm_model.base_model.model.model.layers.4.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 886 |
-
"llm_model.base_model.model.model.layers.4.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 887 |
-
"llm_model.base_model.model.model.layers.4.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 888 |
-
"llm_model.base_model.model.model.layers.4.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 889 |
-
"llm_model.base_model.model.model.layers.4.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 890 |
-
"llm_model.base_model.model.model.layers.4.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 891 |
-
"llm_model.base_model.model.model.layers.4.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 892 |
-
"llm_model.base_model.model.model.layers.4.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 893 |
-
"llm_model.base_model.model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 894 |
-
"llm_model.base_model.model.model.layers.5.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 895 |
-
"llm_model.base_model.model.model.layers.5.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 896 |
-
"llm_model.base_model.model.model.layers.5.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 897 |
-
"llm_model.base_model.model.model.layers.5.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 898 |
-
"llm_model.base_model.model.model.layers.5.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 899 |
-
"llm_model.base_model.model.model.layers.5.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 900 |
-
"llm_model.base_model.model.model.layers.5.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 901 |
-
"llm_model.base_model.model.model.layers.5.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 902 |
-
"llm_model.base_model.model.model.layers.5.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 903 |
-
"llm_model.base_model.model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 904 |
-
"llm_model.base_model.model.model.layers.5.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 905 |
-
"llm_model.base_model.model.model.layers.5.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 906 |
-
"llm_model.base_model.model.model.layers.5.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 907 |
-
"llm_model.base_model.model.model.layers.5.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 908 |
-
"llm_model.base_model.model.model.layers.5.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 909 |
-
"llm_model.base_model.model.model.layers.5.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 910 |
-
"llm_model.base_model.model.model.layers.5.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 911 |
-
"llm_model.base_model.model.model.layers.5.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 912 |
-
"llm_model.base_model.model.model.layers.5.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 913 |
-
"llm_model.base_model.model.model.layers.5.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 914 |
-
"llm_model.base_model.model.model.layers.5.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 915 |
-
"llm_model.base_model.model.model.layers.5.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 916 |
-
"llm_model.base_model.model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 917 |
-
"llm_model.base_model.model.model.layers.6.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 918 |
-
"llm_model.base_model.model.model.layers.6.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 919 |
-
"llm_model.base_model.model.model.layers.6.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 920 |
-
"llm_model.base_model.model.model.layers.6.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 921 |
-
"llm_model.base_model.model.model.layers.6.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 922 |
-
"llm_model.base_model.model.model.layers.6.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 923 |
-
"llm_model.base_model.model.model.layers.6.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 924 |
-
"llm_model.base_model.model.model.layers.6.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 925 |
-
"llm_model.base_model.model.model.layers.6.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 926 |
-
"llm_model.base_model.model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 927 |
-
"llm_model.base_model.model.model.layers.6.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 928 |
-
"llm_model.base_model.model.model.layers.6.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 929 |
-
"llm_model.base_model.model.model.layers.6.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 930 |
-
"llm_model.base_model.model.model.layers.6.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 931 |
-
"llm_model.base_model.model.model.layers.6.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 932 |
-
"llm_model.base_model.model.model.layers.6.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 933 |
-
"llm_model.base_model.model.model.layers.6.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 934 |
-
"llm_model.base_model.model.model.layers.6.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 935 |
-
"llm_model.base_model.model.model.layers.6.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 936 |
-
"llm_model.base_model.model.model.layers.6.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 937 |
-
"llm_model.base_model.model.model.layers.6.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 938 |
-
"llm_model.base_model.model.model.layers.6.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 939 |
-
"llm_model.base_model.model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 940 |
-
"llm_model.base_model.model.model.layers.7.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 941 |
-
"llm_model.base_model.model.model.layers.7.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 942 |
-
"llm_model.base_model.model.model.layers.7.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 943 |
-
"llm_model.base_model.model.model.layers.7.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 944 |
-
"llm_model.base_model.model.model.layers.7.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 945 |
-
"llm_model.base_model.model.model.layers.7.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 946 |
-
"llm_model.base_model.model.model.layers.7.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 947 |
-
"llm_model.base_model.model.model.layers.7.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 948 |
-
"llm_model.base_model.model.model.layers.7.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 949 |
-
"llm_model.base_model.model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 950 |
-
"llm_model.base_model.model.model.layers.7.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 951 |
-
"llm_model.base_model.model.model.layers.7.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 952 |
-
"llm_model.base_model.model.model.layers.7.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 953 |
-
"llm_model.base_model.model.model.layers.7.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 954 |
-
"llm_model.base_model.model.model.layers.7.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 955 |
-
"llm_model.base_model.model.model.layers.7.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 956 |
-
"llm_model.base_model.model.model.layers.7.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 957 |
-
"llm_model.base_model.model.model.layers.7.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 958 |
-
"llm_model.base_model.model.model.layers.7.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 959 |
-
"llm_model.base_model.model.model.layers.7.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 960 |
-
"llm_model.base_model.model.model.layers.7.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 961 |
-
"llm_model.base_model.model.model.layers.7.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 962 |
-
"llm_model.base_model.model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 963 |
-
"llm_model.base_model.model.model.layers.8.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 964 |
-
"llm_model.base_model.model.model.layers.8.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 965 |
-
"llm_model.base_model.model.model.layers.8.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 966 |
-
"llm_model.base_model.model.model.layers.8.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 967 |
-
"llm_model.base_model.model.model.layers.8.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 968 |
-
"llm_model.base_model.model.model.layers.8.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 969 |
-
"llm_model.base_model.model.model.layers.8.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 970 |
-
"llm_model.base_model.model.model.layers.8.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 971 |
-
"llm_model.base_model.model.model.layers.8.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 972 |
-
"llm_model.base_model.model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 973 |
-
"llm_model.base_model.model.model.layers.8.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 974 |
-
"llm_model.base_model.model.model.layers.8.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 975 |
-
"llm_model.base_model.model.model.layers.8.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 976 |
-
"llm_model.base_model.model.model.layers.8.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 977 |
-
"llm_model.base_model.model.model.layers.8.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 978 |
-
"llm_model.base_model.model.model.layers.8.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 979 |
-
"llm_model.base_model.model.model.layers.8.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 980 |
-
"llm_model.base_model.model.model.layers.8.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 981 |
-
"llm_model.base_model.model.model.layers.8.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 982 |
-
"llm_model.base_model.model.model.layers.8.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 983 |
-
"llm_model.base_model.model.model.layers.8.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 984 |
-
"llm_model.base_model.model.model.layers.8.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 985 |
-
"llm_model.base_model.model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 986 |
-
"llm_model.base_model.model.model.layers.9.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 987 |
-
"llm_model.base_model.model.model.layers.9.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 988 |
-
"llm_model.base_model.model.model.layers.9.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 989 |
-
"llm_model.base_model.model.model.layers.9.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 990 |
-
"llm_model.base_model.model.model.layers.9.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 991 |
-
"llm_model.base_model.model.model.layers.9.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 992 |
-
"llm_model.base_model.model.model.layers.9.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 993 |
-
"llm_model.base_model.model.model.layers.9.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 994 |
-
"llm_model.base_model.model.model.layers.9.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 995 |
-
"llm_model.base_model.model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 996 |
-
"llm_model.base_model.model.model.layers.9.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 997 |
-
"llm_model.base_model.model.model.layers.9.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 998 |
-
"llm_model.base_model.model.model.layers.9.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 999 |
-
"llm_model.base_model.model.model.layers.9.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 1000 |
-
"llm_model.base_model.model.model.layers.9.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 1001 |
-
"llm_model.base_model.model.model.layers.9.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 1002 |
-
"llm_model.base_model.model.model.layers.9.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 1003 |
-
"llm_model.base_model.model.model.layers.9.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 1004 |
-
"llm_model.base_model.model.model.layers.9.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 1005 |
-
"llm_model.base_model.model.model.layers.9.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
|
| 1006 |
-
"llm_model.base_model.model.model.layers.9.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
|
| 1007 |
-
"llm_model.base_model.model.model.layers.9.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
|
| 1008 |
-
"llm_model.base_model.model.model.norm.weight": "model-00002-of-00002.safetensors"
|
| 1009 |
}
|
| 1010 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 5808827136
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"audio_encoder.encoder.encoder.layer_norm.bias": "model-00001-of-00002.safetensors",
|
|
|
|
| 497 |
"connector.layer.3.weight": "model-00001-of-00002.safetensors",
|
| 498 |
"connector.layer.5.bias": "model-00001-of-00002.safetensors",
|
| 499 |
"connector.layer.5.weight": "model-00001-of-00002.safetensors",
|
| 500 |
+
"llm_model.lm_head.weight": "model-00002-of-00002.safetensors",
|
| 501 |
+
"llm_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 502 |
+
"llm_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 503 |
+
"llm_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 504 |
+
"llm_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 505 |
+
"llm_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 506 |
+
"llm_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 507 |
+
"llm_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 508 |
+
"llm_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 509 |
+
"llm_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 510 |
+
"llm_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 511 |
+
"llm_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 512 |
+
"llm_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 513 |
+
"llm_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 514 |
+
"llm_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 515 |
+
"llm_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 516 |
+
"llm_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 517 |
+
"llm_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 518 |
+
"llm_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 519 |
+
"llm_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 520 |
+
"llm_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 521 |
+
"llm_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 522 |
+
"llm_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 523 |
+
"llm_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 524 |
+
"llm_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 525 |
+
"llm_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 526 |
+
"llm_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 527 |
+
"llm_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 528 |
+
"llm_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 529 |
+
"llm_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 530 |
+
"llm_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 531 |
+
"llm_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 532 |
+
"llm_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 533 |
+
"llm_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 534 |
+
"llm_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 535 |
+
"llm_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 536 |
+
"llm_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 537 |
+
"llm_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 538 |
+
"llm_model.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 539 |
+
"llm_model.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 540 |
+
"llm_model.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 541 |
+
"llm_model.model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 542 |
+
"llm_model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 543 |
+
"llm_model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 544 |
+
"llm_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 545 |
+
"llm_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 546 |
+
"llm_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 547 |
+
"llm_model.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 548 |
+
"llm_model.model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 549 |
+
"llm_model.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 550 |
+
"llm_model.model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 551 |
+
"llm_model.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 552 |
+
"llm_model.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 553 |
+
"llm_model.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 554 |
+
"llm_model.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 555 |
+
"llm_model.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 556 |
+
"llm_model.model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 557 |
+
"llm_model.model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 558 |
+
"llm_model.model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 559 |
+
"llm_model.model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 560 |
+
"llm_model.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 561 |
+
"llm_model.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 562 |
+
"llm_model.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 563 |
+
"llm_model.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 564 |
+
"llm_model.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 565 |
+
"llm_model.model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 566 |
+
"llm_model.model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 567 |
+
"llm_model.model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 568 |
+
"llm_model.model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 569 |
+
"llm_model.model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 570 |
+
"llm_model.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 571 |
+
"llm_model.model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 572 |
+
"llm_model.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 573 |
+
"llm_model.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 574 |
+
"llm_model.model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 575 |
+
"llm_model.model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 576 |
+
"llm_model.model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 577 |
+
"llm_model.model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 578 |
+
"llm_model.model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 579 |
+
"llm_model.model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 580 |
+
"llm_model.model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 581 |
+
"llm_model.model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 582 |
+
"llm_model.model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 583 |
+
"llm_model.model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 584 |
+
"llm_model.model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 585 |
+
"llm_model.model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 586 |
+
"llm_model.model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 587 |
+
"llm_model.model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 588 |
+
"llm_model.model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 589 |
+
"llm_model.model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 590 |
+
"llm_model.model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 591 |
+
"llm_model.model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 592 |
+
"llm_model.model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 593 |
+
"llm_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 594 |
+
"llm_model.model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 595 |
+
"llm_model.model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 596 |
+
"llm_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 597 |
+
"llm_model.model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 598 |
+
"llm_model.model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 599 |
+
"llm_model.model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 600 |
+
"llm_model.model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 601 |
+
"llm_model.model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 602 |
+
"llm_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 603 |
+
"llm_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 604 |
+
"llm_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 605 |
+
"llm_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 606 |
+
"llm_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 607 |
+
"llm_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 608 |
+
"llm_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 609 |
+
"llm_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 610 |
+
"llm_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 611 |
+
"llm_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 612 |
+
"llm_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 613 |
+
"llm_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 614 |
+
"llm_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 615 |
+
"llm_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 616 |
+
"llm_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 617 |
+
"llm_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 618 |
+
"llm_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 619 |
+
"llm_model.model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 620 |
+
"llm_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 621 |
+
"llm_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 622 |
+
"llm_model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 623 |
+
"llm_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 624 |
+
"llm_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 625 |
+
"llm_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 626 |
+
"llm_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 627 |
+
"llm_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 628 |
+
"llm_model.model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 629 |
+
"llm_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 630 |
+
"llm_model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 631 |
+
"llm_model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 632 |
+
"llm_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 633 |
+
"llm_model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 634 |
+
"llm_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 635 |
+
"llm_model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 636 |
+
"llm_model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 637 |
+
"llm_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 638 |
+
"llm_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 639 |
+
"llm_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 640 |
+
"llm_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 641 |
+
"llm_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 642 |
+
"llm_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 643 |
+
"llm_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 644 |
+
"llm_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 645 |
+
"llm_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 646 |
+
"llm_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 647 |
+
"llm_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 648 |
+
"llm_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 649 |
+
"llm_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 650 |
+
"llm_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 651 |
+
"llm_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 652 |
+
"llm_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 653 |
+
"llm_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 654 |
+
"llm_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 655 |
+
"llm_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 656 |
+
"llm_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 657 |
+
"llm_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 658 |
+
"llm_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 659 |
+
"llm_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 660 |
+
"llm_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 661 |
+
"llm_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 662 |
+
"llm_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 663 |
+
"llm_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 664 |
+
"llm_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 665 |
+
"llm_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 666 |
+
"llm_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 667 |
+
"llm_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 668 |
+
"llm_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 669 |
+
"llm_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 670 |
+
"llm_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 671 |
+
"llm_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 672 |
+
"llm_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 673 |
+
"llm_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 674 |
+
"llm_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 675 |
+
"llm_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 676 |
+
"llm_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 677 |
+
"llm_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 678 |
+
"llm_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 679 |
+
"llm_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 680 |
+
"llm_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 681 |
+
"llm_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 682 |
+
"llm_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 683 |
+
"llm_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 684 |
+
"llm_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 685 |
+
"llm_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 686 |
+
"llm_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 687 |
+
"llm_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 688 |
+
"llm_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 689 |
+
"llm_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 690 |
+
"llm_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 691 |
+
"llm_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 692 |
+
"llm_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 693 |
+
"llm_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 694 |
+
"llm_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 695 |
+
"llm_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 696 |
+
"llm_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 697 |
+
"llm_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 698 |
+
"llm_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 699 |
+
"llm_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 700 |
+
"llm_model.model.norm.weight": "model-00002-of-00002.safetensors"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 701 |
}
|
| 702 |
}
|