diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..00cb85cd31717154ba4f79efddb4d263e61431e6 --- /dev/null +++ b/config.json @@ -0,0 +1,163 @@ +{ + "_frozen": true, + "_n_gpu": 1, + "adafactor": false, + "adam_beta1": 0.9, + "adam_beta2": 0.999, + "adam_epsilon": 1e-06, + "architectures": [ + "InversionFromLogitsEmbModel" + ], + "auto_find_batch_size": false, + "bf16": true, + "bf16_full_eval": false, + "cache_dir": null, + "cheat_on_train_hypotheses": false, + "config_name": null, + "config_overrides": null, + "corrector_ignore_hypothesis_embedding": false, + "corrector_model_alias": null, + "corrector_model_from_pretrained": null, + "data_seed": null, + "dataloader_drop_last": false, + "dataloader_num_workers": 0, + "dataloader_pin_memory": true, + "dataset_name": "one_million_instructions", + "ddp_backend": null, + "ddp_broadcast_buffers": null, + "ddp_bucket_cap_mb": null, + "ddp_find_unused_parameters": true, + "ddp_timeout": 1800, + "debug": [], + "decoder_dropout_disabled": false, + "deepspeed": null, + "deepspeed_plugin": null, + "disable_tqdm": true, + "dispatch_batches": null, + "do_eval": false, + "do_predict": false, + "do_train": false, + "embedder_fake_with_zeros": false, + "embedder_model_api": null, + "embedder_model_name": "meta-llama/Llama-2-7b-chat-hf", + "embedder_no_grad": true, + "embedder_torch_dtype": "bfloat16", + "embedding_transform_strategy": "repeat", + "embedding_zero_except_topk": null, + "embeddings_from_layer_n": null, + "encoder_dropout_disabled": false, + "eval_accumulation_steps": null, + "eval_delay": 0, + "eval_steps": 3125, + "evaluation_strategy": "steps", + "exp_group_name": "", + "exp_name": "", + "experiment": "inversion_from_logits_emb", + "fp16": false, + "fp16_backend": "auto", + "fp16_full_eval": false, + "fp16_opt_level": "O1", + "freeze_strategy": "none", + "fsdp": [], + "fsdp_config": { + "min_num_params": 0, + "xla": false, + "xla_fsdp_grad_ckpt": false + }, + "fsdp_min_num_params": 0, + "fsdp_transformer_layer_cls_to_wrap": null, + "full_determinism": false, + "gradient_accumulation_steps": 1, + "gradient_checkpointing": false, + "gradient_checkpointing_kwargs": null, + "greater_is_better": false, + "group_by_length": true, + "half_precision_backend": "auto", + "hub_always_push": false, + "hub_model_id": null, + "hub_private_repo": false, + "hub_strategy": "every_save", + "hub_token": null, + "ignore_data_skip": false, + "include_inputs_for_metrics": true, + "include_tokens_per_second": false, + "jit_mode_eval": false, + "label_names": null, + "label_smoothing_factor": 0.0, + "learning_rate": 0.0002, + "length_column_name": "length", + "load_best_model_at_end": true, + "local_rank": 0, + "log_level": "passive", + "log_level_replica": "warning", + "log_on_each_node": true, + "logging_dir": "saves/llama-align-3/runs/Nov15_09-18-58_mosaic-cirrascale-35.reviz.ai2.in", + "logging_first_step": false, + "logging_nan_inf_filter": true, + "logging_steps": 50, + "logging_strategy": "steps", + "lr_scheduler_type": "constant_with_warmup", + "max_eval_samples": 500, + "max_grad_norm": 1.0, + "max_seq_length": 64, + "max_steps": -1, + "metric_for_best_model": "one_million_instructions_loss", + "mock_embedder": false, + "model_name_or_path": "t5-base", + "model_revision": "main", + "mp_parameters": "", + "neftune_noise_alpha": null, + "no_cuda": true, + "num_repeat_tokens": 16, + "num_train_epochs": 200.0, + "optim": "adamw_torch", + "optim_args": null, + "output_dir": "saves/llama-align-3", + "overwrite_output_dir": false, + "past_index": -1, + "per_device_eval_batch_size": 256, + "per_device_train_batch_size": 256, + "per_gpu_eval_batch_size": null, + "per_gpu_train_batch_size": null, + "prediction_loss_only": false, + "push_to_hub": false, + "push_to_hub_model_id": null, + "push_to_hub_organization": null, + "push_to_hub_token": null, + "ray_scope": "last", + "remove_unused_columns": false, + "report_to": [], + "resume_from_checkpoint": null, + "run_name": "saves/llama-align-3", + "save_on_each_node": false, + "save_safetensors": true, + "save_steps": 500, + "save_strategy": "steps", + "save_total_limit": 2, + "seed": 42, + "skip_memory_metrics": true, + "split_batches": false, + "steps_per_epoch": 500000, + "suffix_conditioning": false, + "tf32": null, + "tokenizer_name": null, + "torch_compile": false, + "torch_compile_backend": null, + "torch_compile_mode": null, + "torch_dtype": "float32", + "torchdynamo": null, + "tpu_metrics_debug": false, + "tpu_num_cores": null, + "transformers_version": "4.35.0", + "use_cpu": false, + "use_frozen_embeddings_as_input": true, + "use_ipex": false, + "use_legacy_prediction_loop": false, + "use_less_data": -1, + "use_lora": false, + "use_mps_device": false, + "use_wandb": false, + "warmup_ratio": 0.0, + "warmup_steps": 12500, + "weight_decay": 0.0 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1a4f6ced0c038e73e672c9dd3ac9e1d4a831447c --- /dev/null +++ b/generation_config.json @@ -0,0 +1,4 @@ +{ + "_from_model_config": true, + "transformers_version": "4.35.0" +} diff --git a/model-00001-of-00089.safetensors b/model-00001-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..06fde0075737c46d7157492319575254075e1f57 --- /dev/null +++ b/model-00001-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e47495756fb0e28709106b8b94a454c5290baa976b0bee36e8108bd3f7cbb7d +size 197916456 diff --git a/model-00002-of-00089.safetensors b/model-00002-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..eb1a4c9292d995b5c3c41c87b7e932db67e8e931 --- /dev/null +++ b/model-00002-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce88da202886a0b63dbcec124e744cee8562f0d739b5924cdbd374d440c29747 +size 193096216 diff --git a/model-00003-of-00089.safetensors b/model-00003-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ea35b27f97c5a83c580bb74b0bfe3be3ef35cab8 --- /dev/null +++ b/model-00003-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ca383cebdece77de778cfadad829c95b3b945f8ea3361d1e0c8fcd32d8bc1f5 +size 198231376 diff --git a/model-00004-of-00089.safetensors b/model-00004-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1a57d3bbdeadc6942031be076d1f17764e9c4d14 --- /dev/null +++ b/model-00004-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1566221415fabb636784ff5dd623062948fbd836c0f2ae16c549a5226c1382d +size 198240288 diff --git a/model-00005-of-00089.safetensors b/model-00005-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c8280e80b33c8f08e0f0731f3842da477dee5d0c --- /dev/null +++ b/model-00005-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6f0cd1c0609e41468f389eeafead24e36288b12435f62263f65cd499280c337 +size 198239416 diff --git a/model-00006-of-00089.safetensors b/model-00006-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1393fb72874222f8626b545626521422bba5e156 --- /dev/null +++ b/model-00006-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb6a5138b7935be091e562543bcda7aa0ff24b07c248e82738615777919ed1c1 +size 129027064 diff --git a/model-00007-of-00089.safetensors b/model-00007-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d67a042f7e6f064d9aeb5346449eec0c032388ad --- /dev/null +++ b/model-00007-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7fdd68c8d6848e0da73d524479f5aca838ad3a3754958d5d53d19c2d29f52b5 +size 262144144 diff --git a/model-00008-of-00089.safetensors b/model-00008-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0108a4a505844b0b61a18e3c3b222007d13d3a42 --- /dev/null +++ b/model-00008-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0f059e563c55b8acbfc558848a9faf7d7b61675319d60a707db16250dd7a62e +size 134218256 diff --git a/model-00009-of-00089.safetensors b/model-00009-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6c43d6aa80e21939af32b18f5c4f5c9e18c5cb8d --- /dev/null +++ b/model-00009-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ff8700a1e5e34372788c728b1b65607825ddcc20f790d5da105e5b8d98ca144 +size 180355344 diff --git a/model-00010-of-00089.safetensors b/model-00010-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3a2ecbeb85897d2bcf73028474c229060863e309 --- /dev/null +++ b/model-00010-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe1507b2316b8203604f6f19537e7132e55bc1bd48360461988fb11aa1b77c47 +size 190857976 diff --git a/model-00011-of-00089.safetensors b/model-00011-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f57b5bc822c4b704e4eed2f44b9b518f52d1cab7 --- /dev/null +++ b/model-00011-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b79c6d1197eef9104c651e22de7ddd0f2f9788e9b783c7e552201da060c83f8c +size 123732248 diff --git a/model-00012-of-00089.safetensors b/model-00012-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..804a3ebdaf061639194c038c80a1bbb08e7f232d --- /dev/null +++ b/model-00012-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ec241d862369109d71ef527496fd8bba349de5bfd050b879aa3d44f085970ee +size 180371968 diff --git a/model-00013-of-00089.safetensors b/model-00013-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..79bb505a519891cac4a250524f79a7521323c050 --- /dev/null +++ b/model-00013-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57d49c7e35ac6a6d157d35c2ac23ba50185b40cc8bcfbbc0a6dcbd4e05c410e0 +size 134218256 diff --git a/model-00014-of-00089.safetensors b/model-00014-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4ff1ae27c8b1adb3017a458e30d662e1d06306ec --- /dev/null +++ b/model-00014-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:441dfa3ea97617c8f8919c35f2eda30419bdd73ec0edf1c358ebb4684f382fc3 +size 180355344 diff --git a/model-00015-of-00089.safetensors b/model-00015-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c7eb2cc48ee696c579964fa45349327a91a76c53 --- /dev/null +++ b/model-00015-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83d692f3c7902fa011c341ca0d31bbc999257b2ee2bb011d423440a0d690ea8c +size 190857976 diff --git a/model-00016-of-00089.safetensors b/model-00016-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7272084da52cdb4a1ad213c2bb0b1e97061cff69 --- /dev/null +++ b/model-00016-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7642f519bc1aadb5b47597c52f8ea004fec7030e60f69ef1b4044113c8101149 +size 123732248 diff --git a/model-00017-of-00089.safetensors b/model-00017-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ec552cff05dc214b2a031502a6d54864bd166cd6 --- /dev/null +++ b/model-00017-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2190531b0cda5c4f7241152ad8860ee076b871f834897bf286383b9c140a00fe +size 180371968 diff --git a/model-00018-of-00089.safetensors b/model-00018-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..77caa2083b3f4165ad3a60303280bb89dc0b1389 --- /dev/null +++ b/model-00018-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8747288747f93b4f293382452f96b7db00ad6564c06040aac9c6d5e82753943d +size 134218256 diff --git a/model-00019-of-00089.safetensors b/model-00019-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d4eb52752a4efcfb2a3be4a10d67d749ad526d2a --- /dev/null +++ b/model-00019-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c881d847db54d7e27a3b42ec5ade1296dea55b975161ac64ef09f5fea624a8e0 +size 180355344 diff --git a/model-00020-of-00089.safetensors b/model-00020-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..afbb2e3aba15b6c113fe63c0c665b71518dc4dd3 --- /dev/null +++ b/model-00020-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2699fe914b5b810cd6c7ff01aad3db1589ab2eac8ac5170470cff9ab454dec8 +size 190857976 diff --git a/model-00021-of-00089.safetensors b/model-00021-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..90a413afe41c79060267fc608d728f1f410881d2 --- /dev/null +++ b/model-00021-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a560bef7ae77dde68c53c9fe3b7fb6a9386214647236a5ff27872b6d352adc1e +size 123732248 diff --git a/model-00022-of-00089.safetensors b/model-00022-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..52f3dd4f0a32270280ae126ec0ea4d9d6c011f09 --- /dev/null +++ b/model-00022-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bab35b116b45d46c37e9db84dd53894b52a5219ba4d85ddf3d08f39991879c3 +size 180371968 diff --git a/model-00023-of-00089.safetensors b/model-00023-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2da14ec49edb0aa388add21ae2acab5bf841434c --- /dev/null +++ b/model-00023-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94b18c2f7b8cdfef685cd3cecba97eaf49e4cbbf8f22248351c5ea887368694d +size 134218256 diff --git a/model-00024-of-00089.safetensors b/model-00024-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c43b16dc8ce9db1da70e4ae163262ceb42ad1ff8 --- /dev/null +++ b/model-00024-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ac8e34b86279af79fe10b6ed5e3ce112b9ae6e672eb37e5a79705d75b768b70 +size 180355344 diff --git a/model-00025-of-00089.safetensors b/model-00025-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2b8882d830aab2f84ca3f168719eb5470da63133 --- /dev/null +++ b/model-00025-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75a33e771b9dd45e0155be1cd75f45f6fb100a61c19c8d3d74a6a803a241d15e +size 190857976 diff --git a/model-00026-of-00089.safetensors b/model-00026-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f776e417d59773a601c72fa13d485c6a484b384c --- /dev/null +++ b/model-00026-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03903628ddeae4e87443cf0f21f521354742a0ef513ec410c360bb617f5a94cd +size 123732248 diff --git a/model-00027-of-00089.safetensors b/model-00027-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..468b4ff1ac39476fac1f13ed9ae8ed0ca1efd89e --- /dev/null +++ b/model-00027-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c954a75c014339c16af6f103927225b294f44e5403654bc6307fc787f0837d7d +size 180371968 diff --git a/model-00028-of-00089.safetensors b/model-00028-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..adf7ff67895af72b7d1c1033388b47223dd17b6f --- /dev/null +++ b/model-00028-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76017740a5cf623497d012bec949ad577715346907afdb9468b62cb2d1dd6329 +size 134218256 diff --git a/model-00029-of-00089.safetensors b/model-00029-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..62e3f3d91fe43e3b25296b1e021e76179cba6d1e --- /dev/null +++ b/model-00029-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94083115a4cdeb323098d4d586daae1c154c81a1b14b907688ad2d60cadc0902 +size 180355344 diff --git a/model-00030-of-00089.safetensors b/model-00030-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c48aaa84fd53076766bfa5ae5190dce19a65db5f --- /dev/null +++ b/model-00030-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c5b67846c7e15dc4d6c76b9738ec4deb57834c7aa6ee46f69742e264748a9f2 +size 190857976 diff --git a/model-00031-of-00089.safetensors b/model-00031-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cd813494a98ffb09b58ef217ec26f17b98146491 --- /dev/null +++ b/model-00031-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edbbcd3bd14aab97b15f7447c74a3bf2fafc13fc199294d0a442d6b4242d1456 +size 123732248 diff --git a/model-00032-of-00089.safetensors b/model-00032-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fc68788300a1691a42ab07cac5727be4309bd1fd --- /dev/null +++ b/model-00032-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85d679ba84b28a8e3f270dcbc620b1579482a2e00dc251e73956da003928b6f6 +size 180371968 diff --git a/model-00033-of-00089.safetensors b/model-00033-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9b84e9747ecb6da60b88e4d250ad91d5e9da7ea3 --- /dev/null +++ b/model-00033-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a7cbcbccc5b4660c27d5881da718f490ba2ede568f299b3f4eb840f0514a890 +size 134218256 diff --git a/model-00034-of-00089.safetensors b/model-00034-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2ee7109e19fdcfd76062f3a92245a9ddd249eace --- /dev/null +++ b/model-00034-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e951f92ec9fac91e51095a1d1a45338a000d523284b831074cb7046c61d3db9a +size 180355352 diff --git a/model-00035-of-00089.safetensors b/model-00035-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..445c080e4e76cf693dfdefcb502223167841b8b0 --- /dev/null +++ b/model-00035-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a03f8a797ed1f732d2142b0212e75e423c38e8ac5c54b910161c7c04a469d2da +size 190857984 diff --git a/model-00036-of-00089.safetensors b/model-00036-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8f1a10a243d51c37522ce1596eb0599052dcfb40 --- /dev/null +++ b/model-00036-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09f99e17a5f44384955d83bb111f66689d8edd732d7111080251a2e0f361586e +size 123732248 diff --git a/model-00037-of-00089.safetensors b/model-00037-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4e381ff6ce9bad8d434da39536f4746e3eb3b0cf --- /dev/null +++ b/model-00037-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ffee844d2f71b64418f29231bed699a2dab6a172286a2cd9c4529b761095cb0 +size 180371968 diff --git a/model-00038-of-00089.safetensors b/model-00038-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bfd8481443212389095b48dfbecd6fdc382b9654 --- /dev/null +++ b/model-00038-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:780da4a4b51e82996999d3a23a86d33feda70eec62a10780c7f2a5d203e49b4f +size 134218256 diff --git a/model-00039-of-00089.safetensors b/model-00039-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6347afdce989d686ac0dccc83cb32d4b937c2d01 --- /dev/null +++ b/model-00039-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:378ce3204d2115325bc085c279dcde6e99826dc6dc45674c9e86f716c15a9b3a +size 180355352 diff --git a/model-00040-of-00089.safetensors b/model-00040-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b9d9505b7be482c0f0355fe8b2d0b4160e0252c9 --- /dev/null +++ b/model-00040-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8f3cf6fba1bdfea966347a5a1c826ffbc93136d2330743437e0143eaa3b0e18 +size 190857984 diff --git a/model-00041-of-00089.safetensors b/model-00041-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7841b3600de6cb0e2cccf301b222ff93d8c55880 --- /dev/null +++ b/model-00041-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02607ed3920f51c3c9ff431ca0e386664a02a7f707bd3c22bd0e0a91f645d882 +size 123732248 diff --git a/model-00042-of-00089.safetensors b/model-00042-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2624e4008157562d49080cc7cddb41a0bc4783c9 --- /dev/null +++ b/model-00042-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3291498c3e81c458e4208b6a8b76fe8647836be5cb4e6307e650d9c343ea2b4c +size 180371968 diff --git a/model-00043-of-00089.safetensors b/model-00043-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e1326a40fc47a7448a703f5c089ebdd4d1ce193c --- /dev/null +++ b/model-00043-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9f93d71691be499d5ea7604b127cc56103038a9de89fefe0eb9751fa117d618 +size 134218256 diff --git a/model-00044-of-00089.safetensors b/model-00044-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8855c1944665f5e00f59a13319f40b267f685af9 --- /dev/null +++ b/model-00044-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d2c4ddbc97657ca53478f2be00e6e93d2c45d50bbbbd42ccc4bb76f6087edc0 +size 180355352 diff --git a/model-00045-of-00089.safetensors b/model-00045-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..945ca157cf12da12e303fdca3b46858461607ecd --- /dev/null +++ b/model-00045-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b319777bd5daf807a8227b5d090f069345757efc686b5d5bb1c89ae096176ec +size 190857984 diff --git a/model-00046-of-00089.safetensors b/model-00046-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a2fd375a99510b89becfb869fa294e55a187a6f8 --- /dev/null +++ b/model-00046-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:388e3ae20b316691ee054ac3707c5a6c3c0b2c700ffa3edf48f9c035b4b28398 +size 123732248 diff --git a/model-00047-of-00089.safetensors b/model-00047-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7e99ffc0b9913f455fcc764594b568f6624e664d --- /dev/null +++ b/model-00047-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4311e9cbf45bbbabffdab57e974c3481db9e946d1e1562fb98aca74359a012c8 +size 180371968 diff --git a/model-00048-of-00089.safetensors b/model-00048-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0248dc3ac25bf9d5e828b69228ac1c1a49d5eb52 --- /dev/null +++ b/model-00048-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0175a98f75ffce3df77d16a164c487f183b1775d8783fc68b3df68e2539eb98c +size 134218256 diff --git a/model-00049-of-00089.safetensors b/model-00049-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f7a3aa3813251f8156c94857822218afd7cb8022 --- /dev/null +++ b/model-00049-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ef433e064005b414538d6d40273cf2b2ab26c5136b36b8453bab191d7472bdf +size 180355352 diff --git a/model-00050-of-00089.safetensors b/model-00050-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8183a1d391e39147c4f2d2296e3a56517bce4f93 --- /dev/null +++ b/model-00050-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75b1b5452fa9b293968eb4ca8174ab3f497845e073f996d98d8fdda642c8a0f0 +size 190857984 diff --git a/model-00051-of-00089.safetensors b/model-00051-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..26beaeefcc7394ad17fdfc5620c30da00bc793fd --- /dev/null +++ b/model-00051-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e852577e264de2ad79db925612553f3a170c0a5d737d8c11e1d386e1d90ffed +size 123732248 diff --git a/model-00052-of-00089.safetensors b/model-00052-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e7ad253235588a968e5ad26653a91101aeaf25c6 --- /dev/null +++ b/model-00052-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c07986df9488f3679380d5148be89906d3653828a4f37e1a68441e6141fdcbc +size 180371968 diff --git a/model-00053-of-00089.safetensors b/model-00053-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f0411ea0d91b6d7dc31bee5cd280ee31bddf0ea1 --- /dev/null +++ b/model-00053-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d4ef23f31cb94478af8f7e1abe5972581567ca2429b9f1e3bb554f7d2ed1aa2 +size 134218256 diff --git a/model-00054-of-00089.safetensors b/model-00054-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ed53344cf3747119134922319f7c057536c865f4 --- /dev/null +++ b/model-00054-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce9ebf30b9e89ffac0b7178351b7b37779eb77a7e1e7dad3c43d818c7f170aba +size 180355352 diff --git a/model-00055-of-00089.safetensors b/model-00055-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e264a5462efe86067d02e95a6b3a7ab9b6497bda --- /dev/null +++ b/model-00055-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ba009d2615267f140499ad3cbcbb673a0d3285f75a09939216b9742363bf2cb +size 190857984 diff --git a/model-00056-of-00089.safetensors b/model-00056-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..319506ca45a948b3f0825c9ccdd4d22243a8b932 --- /dev/null +++ b/model-00056-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:551fc02621477afd913188b0bd828baad231da7fd389da9b81c2b47e9ab73764 +size 123732248 diff --git a/model-00057-of-00089.safetensors b/model-00057-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..eefc44532f21c216ca7755d397a014d0b8885267 --- /dev/null +++ b/model-00057-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:937e4067ad0cdc7f2635c24db9b84ff342e0ed56d07614f92fdecb6a18e26307 +size 180371968 diff --git a/model-00058-of-00089.safetensors b/model-00058-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b24bf97e987dc86a33480f88d2fe5ee5d116d51d --- /dev/null +++ b/model-00058-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d678af9d4568441f86b1d38e1a14035eacd7c4a123ff0e96ec212235dbff3b4 +size 134218256 diff --git a/model-00059-of-00089.safetensors b/model-00059-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bac5ff394d347b942a16ef7f01760d7892ced9e3 --- /dev/null +++ b/model-00059-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e37e82034f2122a0605b316c737f390a860d10cd6a29a0ae6076011482fb9e4e +size 180355352 diff --git a/model-00060-of-00089.safetensors b/model-00060-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ad423c3f0d04e49f4d76646a99f50d80bde89060 --- /dev/null +++ b/model-00060-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c631efba2fefc370af104718a8656b59184ce3946a1c6fecc0268cc804c3a27 +size 190857984 diff --git a/model-00061-of-00089.safetensors b/model-00061-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3630cf92f7bf033d57eac2d21e3201e8d199a9f6 --- /dev/null +++ b/model-00061-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7a407a64284ddb38a618e9b50c9e41f25054272070f855b67dde82f61275db3 +size 123732248 diff --git a/model-00062-of-00089.safetensors b/model-00062-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7b103465601374c6cf7d0083bf309aa11ce10cf7 --- /dev/null +++ b/model-00062-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25b4ca9c2057b06696f51ca087ad13e4df81352691ca04aab241a9ab912f44e7 +size 180371968 diff --git a/model-00063-of-00089.safetensors b/model-00063-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3fb94c2922de1e2d2cca96bbbf7e725d1e7767f2 --- /dev/null +++ b/model-00063-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cde6ff151bb432b1b5a1a983d10e1e9554cd0a4a2c1e9d8b4fb336a049f04e06 +size 134218256 diff --git a/model-00064-of-00089.safetensors b/model-00064-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ef3f2df4e52cbdd003f3ef38aea82f905d44e1d5 --- /dev/null +++ b/model-00064-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:631aa19b7fb81a44ac5e04b5ee0b57c038b04833c5cc20d996150f735b3603c6 +size 180355352 diff --git a/model-00065-of-00089.safetensors b/model-00065-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..66f3c14e9f8c5fc4751776f12ba8330c97100a6f --- /dev/null +++ b/model-00065-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9cd29439f14451159e2cb18052b54e70e17febb602f48e847753e66e2220d7d +size 190857984 diff --git a/model-00066-of-00089.safetensors b/model-00066-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6eef15899e27c51f1f10d0073b7661a8e82b2be2 --- /dev/null +++ b/model-00066-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb5813a487d01465b55008236de7da22f78d9fa47a24d970f1750c080fd25ded +size 123732248 diff --git a/model-00067-of-00089.safetensors b/model-00067-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c138bca9d0b4ebd150c5183135293a68d39aa8df --- /dev/null +++ b/model-00067-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bd78db1b487709c540b02191c3f0e347bc1592bb70b15f3c1864e2465647705 +size 180371968 diff --git a/model-00068-of-00089.safetensors b/model-00068-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..123a9b33bf0e8fe64a532cd43f84f3364d6e4932 --- /dev/null +++ b/model-00068-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a85c2795e2e6c7b725969f1d62dc336e6e58f47ce2a0d9d11bf56b0d23b103f1 +size 134218256 diff --git a/model-00069-of-00089.safetensors b/model-00069-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3ac79bee54030ca7551c043a9c9ad8281fe6aed3 --- /dev/null +++ b/model-00069-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57626fa0e3bfe17f06c5be057f13af019bc0b516fde709b8e97b52f607f1b427 +size 180355352 diff --git a/model-00070-of-00089.safetensors b/model-00070-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..93c3add73646b31551ca6adfd3f67aa26afbedb1 --- /dev/null +++ b/model-00070-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69825d8478099c0d9dc4873070b2f50ea01d50d1fa5167978a95269f1e0c3314 +size 190857984 diff --git a/model-00071-of-00089.safetensors b/model-00071-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1f94d058770077b58ca7caf24b0c3a61e918c69e --- /dev/null +++ b/model-00071-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a2e802f6e0dc28553dea77a50645e39977c38693a5a3a76fa4d2467a5114114 +size 123732248 diff --git a/model-00072-of-00089.safetensors b/model-00072-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..246fe8a17fb28a428cdbcfcded0d15c45ae7a773 --- /dev/null +++ b/model-00072-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2e8d760522dbc76abe2f5e1e662789ee1a107b41af8e555fe504c849dce16d7 +size 180371968 diff --git a/model-00073-of-00089.safetensors b/model-00073-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b9d365c58cca68aef3fa6939d46bb0dc541b8b06 --- /dev/null +++ b/model-00073-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cc0312b40f45a57088fbc1c41f27a4fab11aaec768fdd6cd35f7b8d012dabb7 +size 134218256 diff --git a/model-00074-of-00089.safetensors b/model-00074-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b22444b03caff54c5bee1afc7558f028b6fcd4b2 --- /dev/null +++ b/model-00074-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00d889cd04e7b3e5737f4122e2e6cf1064e54a679454f1fb0e708b5cfbeb8792 +size 180355352 diff --git a/model-00075-of-00089.safetensors b/model-00075-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1afaf1bbd08713a7ec87ec22c0730f4421312746 --- /dev/null +++ b/model-00075-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7a7b4ad218491dada536d2f56c89f31f0d3bb861637d96dcd1d345f69e0c608 +size 190857984 diff --git a/model-00076-of-00089.safetensors b/model-00076-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..42d621512e186331a96b9461ccfd5ed58970d9c8 --- /dev/null +++ b/model-00076-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccc85c553e8476ae2be74b9a03f793ec50fd00f120f9e5a403cc05d20333500b +size 123732248 diff --git a/model-00077-of-00089.safetensors b/model-00077-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4be143f4a65ecd3f3ef3744f4cd42a07e3b72e55 --- /dev/null +++ b/model-00077-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:673586c7a1f84ffde9859b29483ea45fb0c793a602b338335f7fe98663f92cf9 +size 180371968 diff --git a/model-00078-of-00089.safetensors b/model-00078-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f3f4d7c45ce9865383409dc4017fc341660d404c --- /dev/null +++ b/model-00078-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f89bb3dba1a0c4937ac8e3ed88cb3f42061ff1a7abd2cc2e98dcc3eae538535 +size 134218256 diff --git a/model-00079-of-00089.safetensors b/model-00079-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9d7343a81f8489540f7312063b0a313a124d05a2 --- /dev/null +++ b/model-00079-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d12e2e7360094049b1a82bbe3945fed69fcd567b1b312b6f5ac9f6fbb94c8ac +size 180355352 diff --git a/model-00080-of-00089.safetensors b/model-00080-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d63cb063259b32047f94fb5c74532dde01ae5f47 --- /dev/null +++ b/model-00080-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a089ffa54c4b991857558f551ea4c6672370c4c9fb469a2d5b65690d4e88efb3 +size 190857984 diff --git a/model-00081-of-00089.safetensors b/model-00081-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f836cd0a9e03c14bdb63aeb9009568bce8a20d13 --- /dev/null +++ b/model-00081-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77da35dd67ab49e426a31be18396d44318794d69dd5a4ca251546a920d3abd1f +size 123732248 diff --git a/model-00082-of-00089.safetensors b/model-00082-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fbcec3a80af3abd8685481bfb181f182404a93bb --- /dev/null +++ b/model-00082-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bcd8976aadd3437339b7541b3c7268c864363e9a11d0f235ac7c3fbf00dda10 +size 180371968 diff --git a/model-00083-of-00089.safetensors b/model-00083-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ad9a017937c783c61ed4555f5474a155749f4086 --- /dev/null +++ b/model-00083-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:737b9cba175c3801a89f26ac004f221633dbf52c0f020891923372541be90e3a +size 134218256 diff --git a/model-00084-of-00089.safetensors b/model-00084-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2854bc631013b3df43e4074eb61a21815df9686c --- /dev/null +++ b/model-00084-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ce3f2b80157c247d4743b8d98fabacaa6170d3fff07ad76f392d4eb5eaed43f +size 180355352 diff --git a/model-00085-of-00089.safetensors b/model-00085-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e0d799df67da8fd02825a739dd3a347c388ede08 --- /dev/null +++ b/model-00085-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf5a1eb4a2c022af10515e350d9e0a3c10df0c4e7a95a199f522e8c9e93e7d2a +size 190857984 diff --git a/model-00086-of-00089.safetensors b/model-00086-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..53ce1207f94a8612f082781cf0bcd49199353bd8 --- /dev/null +++ b/model-00086-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:713f27e2b0a81a8c4f764821c29522aadbab69f9718149a98c2a3bc6eeb4a08e +size 123732248 diff --git a/model-00087-of-00089.safetensors b/model-00087-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7c211e28bd154fa588593a7357524dc20939b02d --- /dev/null +++ b/model-00087-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0703219889b54dd388c24e50ad02ce3335774ed4e338082a038a141d985b7f8 +size 180380264 diff --git a/model-00088-of-00089.safetensors b/model-00088-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..aea4d5780fa6630d24f0550856f0a84eec3c813e --- /dev/null +++ b/model-00088-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c698ab7127f0974d2d661a6f68c522ead9488b70f19e1a7ca0af49b9c6fc36b +size 262144136 diff --git a/model-00089-of-00089.safetensors b/model-00089-of-00089.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..79d0b166ce5845033959b15ffb87c20cbc1b3c95 --- /dev/null +++ b/model-00089-of-00089.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:195225444caa0fe5b95ab4b6546fd2916b3d28457d438f7741245949abf6ff2f +size 25185680 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..bcea67412fa381b53ff8ce691939eb816e0e5113 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,566 @@ +{ + "metadata": { + "total_size": 14616732160 + }, + "weight_map": { + "embedder.lm_head.weight": "model-00088-of-00089.safetensors", + "embedder.model.embed_tokens.weight": "model-00007-of-00089.safetensors", + "embedder.model.layers.0.input_layernorm.weight": "model-00010-of-00089.safetensors", + "embedder.model.layers.0.mlp.down_proj.weight": "model-00010-of-00089.safetensors", + "embedder.model.layers.0.mlp.gate_proj.weight": "model-00009-of-00089.safetensors", + "embedder.model.layers.0.mlp.up_proj.weight": "model-00009-of-00089.safetensors", + "embedder.model.layers.0.post_attention_layernorm.weight": "model-00010-of-00089.safetensors", + "embedder.model.layers.0.self_attn.k_proj.weight": "model-00008-of-00089.safetensors", + "embedder.model.layers.0.self_attn.o_proj.weight": "model-00008-of-00089.safetensors", + "embedder.model.layers.0.self_attn.q_proj.weight": "model-00008-of-00089.safetensors", + "embedder.model.layers.0.self_attn.v_proj.weight": "model-00008-of-00089.safetensors", + "embedder.model.layers.1.input_layernorm.weight": "model-00012-of-00089.safetensors", + "embedder.model.layers.1.mlp.down_proj.weight": "model-00012-of-00089.safetensors", + "embedder.model.layers.1.mlp.gate_proj.weight": "model-00011-of-00089.safetensors", + "embedder.model.layers.1.mlp.up_proj.weight": "model-00012-of-00089.safetensors", + "embedder.model.layers.1.post_attention_layernorm.weight": "model-00012-of-00089.safetensors", + "embedder.model.layers.1.self_attn.k_proj.weight": "model-00010-of-00089.safetensors", + "embedder.model.layers.1.self_attn.o_proj.weight": "model-00011-of-00089.safetensors", + "embedder.model.layers.1.self_attn.q_proj.weight": "model-00010-of-00089.safetensors", + "embedder.model.layers.1.self_attn.v_proj.weight": "model-00010-of-00089.safetensors", + "embedder.model.layers.10.input_layernorm.weight": "model-00035-of-00089.safetensors", + "embedder.model.layers.10.mlp.down_proj.weight": "model-00035-of-00089.safetensors", + "embedder.model.layers.10.mlp.gate_proj.weight": "model-00034-of-00089.safetensors", + "embedder.model.layers.10.mlp.up_proj.weight": "model-00034-of-00089.safetensors", + "embedder.model.layers.10.post_attention_layernorm.weight": "model-00035-of-00089.safetensors", + "embedder.model.layers.10.self_attn.k_proj.weight": "model-00033-of-00089.safetensors", + "embedder.model.layers.10.self_attn.o_proj.weight": "model-00033-of-00089.safetensors", + "embedder.model.layers.10.self_attn.q_proj.weight": "model-00033-of-00089.safetensors", + "embedder.model.layers.10.self_attn.v_proj.weight": "model-00033-of-00089.safetensors", + "embedder.model.layers.11.input_layernorm.weight": "model-00037-of-00089.safetensors", + "embedder.model.layers.11.mlp.down_proj.weight": "model-00037-of-00089.safetensors", + "embedder.model.layers.11.mlp.gate_proj.weight": "model-00036-of-00089.safetensors", + "embedder.model.layers.11.mlp.up_proj.weight": "model-00037-of-00089.safetensors", + "embedder.model.layers.11.post_attention_layernorm.weight": "model-00037-of-00089.safetensors", + "embedder.model.layers.11.self_attn.k_proj.weight": "model-00035-of-00089.safetensors", + "embedder.model.layers.11.self_attn.o_proj.weight": "model-00036-of-00089.safetensors", + "embedder.model.layers.11.self_attn.q_proj.weight": "model-00035-of-00089.safetensors", + "embedder.model.layers.11.self_attn.v_proj.weight": "model-00035-of-00089.safetensors", + "embedder.model.layers.12.input_layernorm.weight": "model-00040-of-00089.safetensors", + "embedder.model.layers.12.mlp.down_proj.weight": "model-00040-of-00089.safetensors", + "embedder.model.layers.12.mlp.gate_proj.weight": "model-00039-of-00089.safetensors", + "embedder.model.layers.12.mlp.up_proj.weight": "model-00039-of-00089.safetensors", + "embedder.model.layers.12.post_attention_layernorm.weight": "model-00040-of-00089.safetensors", + "embedder.model.layers.12.self_attn.k_proj.weight": "model-00038-of-00089.safetensors", + "embedder.model.layers.12.self_attn.o_proj.weight": "model-00038-of-00089.safetensors", + "embedder.model.layers.12.self_attn.q_proj.weight": "model-00038-of-00089.safetensors", + "embedder.model.layers.12.self_attn.v_proj.weight": "model-00038-of-00089.safetensors", + "embedder.model.layers.13.input_layernorm.weight": "model-00042-of-00089.safetensors", + "embedder.model.layers.13.mlp.down_proj.weight": "model-00042-of-00089.safetensors", + "embedder.model.layers.13.mlp.gate_proj.weight": "model-00041-of-00089.safetensors", + "embedder.model.layers.13.mlp.up_proj.weight": "model-00042-of-00089.safetensors", + "embedder.model.layers.13.post_attention_layernorm.weight": "model-00042-of-00089.safetensors", + "embedder.model.layers.13.self_attn.k_proj.weight": "model-00040-of-00089.safetensors", + "embedder.model.layers.13.self_attn.o_proj.weight": "model-00041-of-00089.safetensors", + "embedder.model.layers.13.self_attn.q_proj.weight": "model-00040-of-00089.safetensors", + "embedder.model.layers.13.self_attn.v_proj.weight": "model-00040-of-00089.safetensors", + "embedder.model.layers.14.input_layernorm.weight": "model-00045-of-00089.safetensors", + "embedder.model.layers.14.mlp.down_proj.weight": "model-00045-of-00089.safetensors", + "embedder.model.layers.14.mlp.gate_proj.weight": "model-00044-of-00089.safetensors", + "embedder.model.layers.14.mlp.up_proj.weight": "model-00044-of-00089.safetensors", + "embedder.model.layers.14.post_attention_layernorm.weight": "model-00045-of-00089.safetensors", + "embedder.model.layers.14.self_attn.k_proj.weight": "model-00043-of-00089.safetensors", + "embedder.model.layers.14.self_attn.o_proj.weight": "model-00043-of-00089.safetensors", + "embedder.model.layers.14.self_attn.q_proj.weight": "model-00043-of-00089.safetensors", + "embedder.model.layers.14.self_attn.v_proj.weight": "model-00043-of-00089.safetensors", + "embedder.model.layers.15.input_layernorm.weight": "model-00047-of-00089.safetensors", + "embedder.model.layers.15.mlp.down_proj.weight": "model-00047-of-00089.safetensors", + "embedder.model.layers.15.mlp.gate_proj.weight": "model-00046-of-00089.safetensors", + "embedder.model.layers.15.mlp.up_proj.weight": "model-00047-of-00089.safetensors", + "embedder.model.layers.15.post_attention_layernorm.weight": "model-00047-of-00089.safetensors", + "embedder.model.layers.15.self_attn.k_proj.weight": "model-00045-of-00089.safetensors", + "embedder.model.layers.15.self_attn.o_proj.weight": "model-00046-of-00089.safetensors", + "embedder.model.layers.15.self_attn.q_proj.weight": "model-00045-of-00089.safetensors", + "embedder.model.layers.15.self_attn.v_proj.weight": "model-00045-of-00089.safetensors", + "embedder.model.layers.16.input_layernorm.weight": "model-00050-of-00089.safetensors", + "embedder.model.layers.16.mlp.down_proj.weight": "model-00050-of-00089.safetensors", + "embedder.model.layers.16.mlp.gate_proj.weight": "model-00049-of-00089.safetensors", + "embedder.model.layers.16.mlp.up_proj.weight": "model-00049-of-00089.safetensors", + "embedder.model.layers.16.post_attention_layernorm.weight": "model-00050-of-00089.safetensors", + "embedder.model.layers.16.self_attn.k_proj.weight": "model-00048-of-00089.safetensors", + "embedder.model.layers.16.self_attn.o_proj.weight": "model-00048-of-00089.safetensors", + "embedder.model.layers.16.self_attn.q_proj.weight": "model-00048-of-00089.safetensors", + "embedder.model.layers.16.self_attn.v_proj.weight": "model-00048-of-00089.safetensors", + "embedder.model.layers.17.input_layernorm.weight": "model-00052-of-00089.safetensors", + "embedder.model.layers.17.mlp.down_proj.weight": "model-00052-of-00089.safetensors", + "embedder.model.layers.17.mlp.gate_proj.weight": "model-00051-of-00089.safetensors", + "embedder.model.layers.17.mlp.up_proj.weight": "model-00052-of-00089.safetensors", + "embedder.model.layers.17.post_attention_layernorm.weight": "model-00052-of-00089.safetensors", + "embedder.model.layers.17.self_attn.k_proj.weight": "model-00050-of-00089.safetensors", + "embedder.model.layers.17.self_attn.o_proj.weight": "model-00051-of-00089.safetensors", + "embedder.model.layers.17.self_attn.q_proj.weight": "model-00050-of-00089.safetensors", + "embedder.model.layers.17.self_attn.v_proj.weight": "model-00050-of-00089.safetensors", + "embedder.model.layers.18.input_layernorm.weight": "model-00055-of-00089.safetensors", + "embedder.model.layers.18.mlp.down_proj.weight": "model-00055-of-00089.safetensors", + "embedder.model.layers.18.mlp.gate_proj.weight": "model-00054-of-00089.safetensors", + "embedder.model.layers.18.mlp.up_proj.weight": "model-00054-of-00089.safetensors", + "embedder.model.layers.18.post_attention_layernorm.weight": "model-00055-of-00089.safetensors", + "embedder.model.layers.18.self_attn.k_proj.weight": "model-00053-of-00089.safetensors", + "embedder.model.layers.18.self_attn.o_proj.weight": "model-00053-of-00089.safetensors", + "embedder.model.layers.18.self_attn.q_proj.weight": "model-00053-of-00089.safetensors", + "embedder.model.layers.18.self_attn.v_proj.weight": "model-00053-of-00089.safetensors", + "embedder.model.layers.19.input_layernorm.weight": "model-00057-of-00089.safetensors", + "embedder.model.layers.19.mlp.down_proj.weight": "model-00057-of-00089.safetensors", + "embedder.model.layers.19.mlp.gate_proj.weight": "model-00056-of-00089.safetensors", + "embedder.model.layers.19.mlp.up_proj.weight": "model-00057-of-00089.safetensors", + "embedder.model.layers.19.post_attention_layernorm.weight": "model-00057-of-00089.safetensors", + "embedder.model.layers.19.self_attn.k_proj.weight": "model-00055-of-00089.safetensors", + "embedder.model.layers.19.self_attn.o_proj.weight": "model-00056-of-00089.safetensors", + "embedder.model.layers.19.self_attn.q_proj.weight": "model-00055-of-00089.safetensors", + "embedder.model.layers.19.self_attn.v_proj.weight": "model-00055-of-00089.safetensors", + "embedder.model.layers.2.input_layernorm.weight": "model-00015-of-00089.safetensors", + "embedder.model.layers.2.mlp.down_proj.weight": "model-00015-of-00089.safetensors", + "embedder.model.layers.2.mlp.gate_proj.weight": "model-00014-of-00089.safetensors", + "embedder.model.layers.2.mlp.up_proj.weight": "model-00014-of-00089.safetensors", + "embedder.model.layers.2.post_attention_layernorm.weight": "model-00015-of-00089.safetensors", + "embedder.model.layers.2.self_attn.k_proj.weight": "model-00013-of-00089.safetensors", + "embedder.model.layers.2.self_attn.o_proj.weight": "model-00013-of-00089.safetensors", + "embedder.model.layers.2.self_attn.q_proj.weight": "model-00013-of-00089.safetensors", + "embedder.model.layers.2.self_attn.v_proj.weight": "model-00013-of-00089.safetensors", + "embedder.model.layers.20.input_layernorm.weight": "model-00060-of-00089.safetensors", + "embedder.model.layers.20.mlp.down_proj.weight": "model-00060-of-00089.safetensors", + "embedder.model.layers.20.mlp.gate_proj.weight": "model-00059-of-00089.safetensors", + "embedder.model.layers.20.mlp.up_proj.weight": "model-00059-of-00089.safetensors", + "embedder.model.layers.20.post_attention_layernorm.weight": "model-00060-of-00089.safetensors", + "embedder.model.layers.20.self_attn.k_proj.weight": "model-00058-of-00089.safetensors", + "embedder.model.layers.20.self_attn.o_proj.weight": "model-00058-of-00089.safetensors", + "embedder.model.layers.20.self_attn.q_proj.weight": "model-00058-of-00089.safetensors", + "embedder.model.layers.20.self_attn.v_proj.weight": "model-00058-of-00089.safetensors", + "embedder.model.layers.21.input_layernorm.weight": "model-00062-of-00089.safetensors", + "embedder.model.layers.21.mlp.down_proj.weight": "model-00062-of-00089.safetensors", + "embedder.model.layers.21.mlp.gate_proj.weight": "model-00061-of-00089.safetensors", + "embedder.model.layers.21.mlp.up_proj.weight": "model-00062-of-00089.safetensors", + "embedder.model.layers.21.post_attention_layernorm.weight": "model-00062-of-00089.safetensors", + "embedder.model.layers.21.self_attn.k_proj.weight": "model-00060-of-00089.safetensors", + "embedder.model.layers.21.self_attn.o_proj.weight": "model-00061-of-00089.safetensors", + "embedder.model.layers.21.self_attn.q_proj.weight": "model-00060-of-00089.safetensors", + "embedder.model.layers.21.self_attn.v_proj.weight": "model-00060-of-00089.safetensors", + "embedder.model.layers.22.input_layernorm.weight": "model-00065-of-00089.safetensors", + "embedder.model.layers.22.mlp.down_proj.weight": "model-00065-of-00089.safetensors", + "embedder.model.layers.22.mlp.gate_proj.weight": "model-00064-of-00089.safetensors", + "embedder.model.layers.22.mlp.up_proj.weight": "model-00064-of-00089.safetensors", + "embedder.model.layers.22.post_attention_layernorm.weight": "model-00065-of-00089.safetensors", + "embedder.model.layers.22.self_attn.k_proj.weight": "model-00063-of-00089.safetensors", + "embedder.model.layers.22.self_attn.o_proj.weight": "model-00063-of-00089.safetensors", + "embedder.model.layers.22.self_attn.q_proj.weight": "model-00063-of-00089.safetensors", + "embedder.model.layers.22.self_attn.v_proj.weight": "model-00063-of-00089.safetensors", + "embedder.model.layers.23.input_layernorm.weight": "model-00067-of-00089.safetensors", + "embedder.model.layers.23.mlp.down_proj.weight": "model-00067-of-00089.safetensors", + "embedder.model.layers.23.mlp.gate_proj.weight": "model-00066-of-00089.safetensors", + "embedder.model.layers.23.mlp.up_proj.weight": "model-00067-of-00089.safetensors", + "embedder.model.layers.23.post_attention_layernorm.weight": "model-00067-of-00089.safetensors", + "embedder.model.layers.23.self_attn.k_proj.weight": "model-00065-of-00089.safetensors", + "embedder.model.layers.23.self_attn.o_proj.weight": "model-00066-of-00089.safetensors", + "embedder.model.layers.23.self_attn.q_proj.weight": "model-00065-of-00089.safetensors", + "embedder.model.layers.23.self_attn.v_proj.weight": "model-00065-of-00089.safetensors", + "embedder.model.layers.24.input_layernorm.weight": "model-00070-of-00089.safetensors", + "embedder.model.layers.24.mlp.down_proj.weight": "model-00070-of-00089.safetensors", + "embedder.model.layers.24.mlp.gate_proj.weight": "model-00069-of-00089.safetensors", + "embedder.model.layers.24.mlp.up_proj.weight": "model-00069-of-00089.safetensors", + "embedder.model.layers.24.post_attention_layernorm.weight": "model-00070-of-00089.safetensors", + "embedder.model.layers.24.self_attn.k_proj.weight": "model-00068-of-00089.safetensors", + "embedder.model.layers.24.self_attn.o_proj.weight": "model-00068-of-00089.safetensors", + "embedder.model.layers.24.self_attn.q_proj.weight": "model-00068-of-00089.safetensors", + "embedder.model.layers.24.self_attn.v_proj.weight": "model-00068-of-00089.safetensors", + "embedder.model.layers.25.input_layernorm.weight": "model-00072-of-00089.safetensors", + "embedder.model.layers.25.mlp.down_proj.weight": "model-00072-of-00089.safetensors", + "embedder.model.layers.25.mlp.gate_proj.weight": "model-00071-of-00089.safetensors", + "embedder.model.layers.25.mlp.up_proj.weight": "model-00072-of-00089.safetensors", + "embedder.model.layers.25.post_attention_layernorm.weight": "model-00072-of-00089.safetensors", + "embedder.model.layers.25.self_attn.k_proj.weight": "model-00070-of-00089.safetensors", + "embedder.model.layers.25.self_attn.o_proj.weight": "model-00071-of-00089.safetensors", + "embedder.model.layers.25.self_attn.q_proj.weight": "model-00070-of-00089.safetensors", + "embedder.model.layers.25.self_attn.v_proj.weight": "model-00070-of-00089.safetensors", + "embedder.model.layers.26.input_layernorm.weight": "model-00075-of-00089.safetensors", + "embedder.model.layers.26.mlp.down_proj.weight": "model-00075-of-00089.safetensors", + "embedder.model.layers.26.mlp.gate_proj.weight": "model-00074-of-00089.safetensors", + "embedder.model.layers.26.mlp.up_proj.weight": "model-00074-of-00089.safetensors", + "embedder.model.layers.26.post_attention_layernorm.weight": "model-00075-of-00089.safetensors", + "embedder.model.layers.26.self_attn.k_proj.weight": "model-00073-of-00089.safetensors", + "embedder.model.layers.26.self_attn.o_proj.weight": "model-00073-of-00089.safetensors", + "embedder.model.layers.26.self_attn.q_proj.weight": "model-00073-of-00089.safetensors", + "embedder.model.layers.26.self_attn.v_proj.weight": "model-00073-of-00089.safetensors", + "embedder.model.layers.27.input_layernorm.weight": "model-00077-of-00089.safetensors", + "embedder.model.layers.27.mlp.down_proj.weight": "model-00077-of-00089.safetensors", + "embedder.model.layers.27.mlp.gate_proj.weight": "model-00076-of-00089.safetensors", + "embedder.model.layers.27.mlp.up_proj.weight": "model-00077-of-00089.safetensors", + "embedder.model.layers.27.post_attention_layernorm.weight": "model-00077-of-00089.safetensors", + "embedder.model.layers.27.self_attn.k_proj.weight": "model-00075-of-00089.safetensors", + "embedder.model.layers.27.self_attn.o_proj.weight": "model-00076-of-00089.safetensors", + "embedder.model.layers.27.self_attn.q_proj.weight": "model-00075-of-00089.safetensors", + "embedder.model.layers.27.self_attn.v_proj.weight": "model-00075-of-00089.safetensors", + "embedder.model.layers.28.input_layernorm.weight": "model-00080-of-00089.safetensors", + "embedder.model.layers.28.mlp.down_proj.weight": "model-00080-of-00089.safetensors", + "embedder.model.layers.28.mlp.gate_proj.weight": "model-00079-of-00089.safetensors", + "embedder.model.layers.28.mlp.up_proj.weight": "model-00079-of-00089.safetensors", + "embedder.model.layers.28.post_attention_layernorm.weight": "model-00080-of-00089.safetensors", + "embedder.model.layers.28.self_attn.k_proj.weight": "model-00078-of-00089.safetensors", + "embedder.model.layers.28.self_attn.o_proj.weight": "model-00078-of-00089.safetensors", + "embedder.model.layers.28.self_attn.q_proj.weight": "model-00078-of-00089.safetensors", + "embedder.model.layers.28.self_attn.v_proj.weight": "model-00078-of-00089.safetensors", + "embedder.model.layers.29.input_layernorm.weight": "model-00082-of-00089.safetensors", + "embedder.model.layers.29.mlp.down_proj.weight": "model-00082-of-00089.safetensors", + "embedder.model.layers.29.mlp.gate_proj.weight": "model-00081-of-00089.safetensors", + "embedder.model.layers.29.mlp.up_proj.weight": "model-00082-of-00089.safetensors", + "embedder.model.layers.29.post_attention_layernorm.weight": "model-00082-of-00089.safetensors", + "embedder.model.layers.29.self_attn.k_proj.weight": "model-00080-of-00089.safetensors", + "embedder.model.layers.29.self_attn.o_proj.weight": "model-00081-of-00089.safetensors", + "embedder.model.layers.29.self_attn.q_proj.weight": "model-00080-of-00089.safetensors", + "embedder.model.layers.29.self_attn.v_proj.weight": "model-00080-of-00089.safetensors", + "embedder.model.layers.3.input_layernorm.weight": "model-00017-of-00089.safetensors", + "embedder.model.layers.3.mlp.down_proj.weight": "model-00017-of-00089.safetensors", + "embedder.model.layers.3.mlp.gate_proj.weight": "model-00016-of-00089.safetensors", + "embedder.model.layers.3.mlp.up_proj.weight": "model-00017-of-00089.safetensors", + "embedder.model.layers.3.post_attention_layernorm.weight": "model-00017-of-00089.safetensors", + "embedder.model.layers.3.self_attn.k_proj.weight": "model-00015-of-00089.safetensors", + "embedder.model.layers.3.self_attn.o_proj.weight": "model-00016-of-00089.safetensors", + "embedder.model.layers.3.self_attn.q_proj.weight": "model-00015-of-00089.safetensors", + "embedder.model.layers.3.self_attn.v_proj.weight": "model-00015-of-00089.safetensors", + "embedder.model.layers.30.input_layernorm.weight": "model-00085-of-00089.safetensors", + "embedder.model.layers.30.mlp.down_proj.weight": "model-00085-of-00089.safetensors", + "embedder.model.layers.30.mlp.gate_proj.weight": "model-00084-of-00089.safetensors", + "embedder.model.layers.30.mlp.up_proj.weight": "model-00084-of-00089.safetensors", + "embedder.model.layers.30.post_attention_layernorm.weight": "model-00085-of-00089.safetensors", + "embedder.model.layers.30.self_attn.k_proj.weight": "model-00083-of-00089.safetensors", + "embedder.model.layers.30.self_attn.o_proj.weight": "model-00083-of-00089.safetensors", + "embedder.model.layers.30.self_attn.q_proj.weight": "model-00083-of-00089.safetensors", + "embedder.model.layers.30.self_attn.v_proj.weight": "model-00083-of-00089.safetensors", + "embedder.model.layers.31.input_layernorm.weight": "model-00087-of-00089.safetensors", + "embedder.model.layers.31.mlp.down_proj.weight": "model-00087-of-00089.safetensors", + "embedder.model.layers.31.mlp.gate_proj.weight": "model-00086-of-00089.safetensors", + "embedder.model.layers.31.mlp.up_proj.weight": "model-00087-of-00089.safetensors", + "embedder.model.layers.31.post_attention_layernorm.weight": "model-00087-of-00089.safetensors", + "embedder.model.layers.31.self_attn.k_proj.weight": "model-00085-of-00089.safetensors", + "embedder.model.layers.31.self_attn.o_proj.weight": "model-00086-of-00089.safetensors", + "embedder.model.layers.31.self_attn.q_proj.weight": "model-00085-of-00089.safetensors", + "embedder.model.layers.31.self_attn.v_proj.weight": "model-00085-of-00089.safetensors", + "embedder.model.layers.4.input_layernorm.weight": "model-00020-of-00089.safetensors", + "embedder.model.layers.4.mlp.down_proj.weight": "model-00020-of-00089.safetensors", + "embedder.model.layers.4.mlp.gate_proj.weight": "model-00019-of-00089.safetensors", + "embedder.model.layers.4.mlp.up_proj.weight": "model-00019-of-00089.safetensors", + "embedder.model.layers.4.post_attention_layernorm.weight": "model-00020-of-00089.safetensors", + "embedder.model.layers.4.self_attn.k_proj.weight": "model-00018-of-00089.safetensors", + "embedder.model.layers.4.self_attn.o_proj.weight": "model-00018-of-00089.safetensors", + "embedder.model.layers.4.self_attn.q_proj.weight": "model-00018-of-00089.safetensors", + "embedder.model.layers.4.self_attn.v_proj.weight": "model-00018-of-00089.safetensors", + "embedder.model.layers.5.input_layernorm.weight": "model-00022-of-00089.safetensors", + "embedder.model.layers.5.mlp.down_proj.weight": "model-00022-of-00089.safetensors", + "embedder.model.layers.5.mlp.gate_proj.weight": "model-00021-of-00089.safetensors", + "embedder.model.layers.5.mlp.up_proj.weight": "model-00022-of-00089.safetensors", + "embedder.model.layers.5.post_attention_layernorm.weight": "model-00022-of-00089.safetensors", + "embedder.model.layers.5.self_attn.k_proj.weight": "model-00020-of-00089.safetensors", + "embedder.model.layers.5.self_attn.o_proj.weight": "model-00021-of-00089.safetensors", + "embedder.model.layers.5.self_attn.q_proj.weight": "model-00020-of-00089.safetensors", + "embedder.model.layers.5.self_attn.v_proj.weight": "model-00020-of-00089.safetensors", + "embedder.model.layers.6.input_layernorm.weight": "model-00025-of-00089.safetensors", + "embedder.model.layers.6.mlp.down_proj.weight": "model-00025-of-00089.safetensors", + "embedder.model.layers.6.mlp.gate_proj.weight": "model-00024-of-00089.safetensors", + "embedder.model.layers.6.mlp.up_proj.weight": "model-00024-of-00089.safetensors", + "embedder.model.layers.6.post_attention_layernorm.weight": "model-00025-of-00089.safetensors", + "embedder.model.layers.6.self_attn.k_proj.weight": "model-00023-of-00089.safetensors", + "embedder.model.layers.6.self_attn.o_proj.weight": "model-00023-of-00089.safetensors", + "embedder.model.layers.6.self_attn.q_proj.weight": "model-00023-of-00089.safetensors", + "embedder.model.layers.6.self_attn.v_proj.weight": "model-00023-of-00089.safetensors", + "embedder.model.layers.7.input_layernorm.weight": "model-00027-of-00089.safetensors", + "embedder.model.layers.7.mlp.down_proj.weight": "model-00027-of-00089.safetensors", + "embedder.model.layers.7.mlp.gate_proj.weight": "model-00026-of-00089.safetensors", + "embedder.model.layers.7.mlp.up_proj.weight": "model-00027-of-00089.safetensors", + "embedder.model.layers.7.post_attention_layernorm.weight": "model-00027-of-00089.safetensors", + "embedder.model.layers.7.self_attn.k_proj.weight": "model-00025-of-00089.safetensors", + "embedder.model.layers.7.self_attn.o_proj.weight": "model-00026-of-00089.safetensors", + "embedder.model.layers.7.self_attn.q_proj.weight": "model-00025-of-00089.safetensors", + "embedder.model.layers.7.self_attn.v_proj.weight": "model-00025-of-00089.safetensors", + "embedder.model.layers.8.input_layernorm.weight": "model-00030-of-00089.safetensors", + "embedder.model.layers.8.mlp.down_proj.weight": "model-00030-of-00089.safetensors", + "embedder.model.layers.8.mlp.gate_proj.weight": "model-00029-of-00089.safetensors", + "embedder.model.layers.8.mlp.up_proj.weight": "model-00029-of-00089.safetensors", + "embedder.model.layers.8.post_attention_layernorm.weight": "model-00030-of-00089.safetensors", + "embedder.model.layers.8.self_attn.k_proj.weight": "model-00028-of-00089.safetensors", + "embedder.model.layers.8.self_attn.o_proj.weight": "model-00028-of-00089.safetensors", + "embedder.model.layers.8.self_attn.q_proj.weight": "model-00028-of-00089.safetensors", + "embedder.model.layers.8.self_attn.v_proj.weight": "model-00028-of-00089.safetensors", + "embedder.model.layers.9.input_layernorm.weight": "model-00032-of-00089.safetensors", + "embedder.model.layers.9.mlp.down_proj.weight": "model-00032-of-00089.safetensors", + "embedder.model.layers.9.mlp.gate_proj.weight": "model-00031-of-00089.safetensors", + "embedder.model.layers.9.mlp.up_proj.weight": "model-00032-of-00089.safetensors", + "embedder.model.layers.9.post_attention_layernorm.weight": "model-00032-of-00089.safetensors", + "embedder.model.layers.9.self_attn.k_proj.weight": "model-00030-of-00089.safetensors", + "embedder.model.layers.9.self_attn.o_proj.weight": "model-00031-of-00089.safetensors", + "embedder.model.layers.9.self_attn.q_proj.weight": "model-00030-of-00089.safetensors", + "embedder.model.layers.9.self_attn.v_proj.weight": "model-00030-of-00089.safetensors", + "embedder.model.norm.weight": "model-00087-of-00089.safetensors", + "embedding_proj.0.bias": "model-00089-of-00089.safetensors", + "embedding_proj.0.weight": "model-00089-of-00089.safetensors", + "embedding_proj.2.bias": "model-00089-of-00089.safetensors", + "embedding_proj.2.weight": "model-00089-of-00089.safetensors", + "embedding_transform.0.bias": "model-00006-of-00089.safetensors", + "embedding_transform.0.weight": "model-00006-of-00089.safetensors", + "embedding_transform.3.bias": "model-00006-of-00089.safetensors", + "embedding_transform.3.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.block.0.layer.0.SelfAttention.k.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.0.layer.0.SelfAttention.o.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.0.layer.0.SelfAttention.q.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.0.layer.0.SelfAttention.v.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.0.layer.0.layer_norm.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.0.layer.1.EncDecAttention.k.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.0.layer.1.EncDecAttention.o.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.0.layer.1.EncDecAttention.q.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.0.layer.1.EncDecAttention.v.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.0.layer.1.layer_norm.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.0.layer.2.DenseReluDense.wi.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.0.layer.2.DenseReluDense.wo.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.0.layer.2.layer_norm.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.1.layer.0.SelfAttention.k.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.1.layer.0.SelfAttention.o.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.1.layer.0.SelfAttention.q.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.1.layer.0.SelfAttention.v.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.1.layer.0.layer_norm.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.1.layer.1.EncDecAttention.k.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.1.layer.1.EncDecAttention.o.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.1.layer.1.EncDecAttention.q.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.1.layer.1.EncDecAttention.v.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.1.layer.1.layer_norm.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.1.layer.2.DenseReluDense.wi.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.1.layer.2.DenseReluDense.wo.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.1.layer.2.layer_norm.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.10.layer.0.SelfAttention.k.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.block.10.layer.0.SelfAttention.o.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.block.10.layer.0.SelfAttention.q.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.block.10.layer.0.SelfAttention.v.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.block.10.layer.0.layer_norm.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.block.10.layer.1.EncDecAttention.k.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.block.10.layer.1.EncDecAttention.o.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.block.10.layer.1.EncDecAttention.q.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.block.10.layer.1.EncDecAttention.v.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.block.10.layer.1.layer_norm.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.block.10.layer.2.DenseReluDense.wi.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.block.10.layer.2.DenseReluDense.wo.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.block.10.layer.2.layer_norm.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.block.11.layer.0.SelfAttention.k.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.block.11.layer.0.SelfAttention.o.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.block.11.layer.0.SelfAttention.q.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.block.11.layer.0.SelfAttention.v.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.block.11.layer.0.layer_norm.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.block.11.layer.1.EncDecAttention.k.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.block.11.layer.1.EncDecAttention.o.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.block.11.layer.1.EncDecAttention.q.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.block.11.layer.1.EncDecAttention.v.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.block.11.layer.1.layer_norm.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.block.11.layer.2.DenseReluDense.wi.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.block.11.layer.2.DenseReluDense.wo.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.block.11.layer.2.layer_norm.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.block.2.layer.0.SelfAttention.k.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.2.layer.0.SelfAttention.o.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.2.layer.0.SelfAttention.q.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.2.layer.0.SelfAttention.v.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.2.layer.0.layer_norm.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.2.layer.1.EncDecAttention.k.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.2.layer.1.EncDecAttention.o.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.2.layer.1.EncDecAttention.q.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.2.layer.1.EncDecAttention.v.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.2.layer.1.layer_norm.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.2.layer.2.DenseReluDense.wi.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.2.layer.2.DenseReluDense.wo.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.2.layer.2.layer_norm.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.3.layer.0.SelfAttention.k.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.3.layer.0.SelfAttention.o.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.3.layer.0.SelfAttention.q.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.3.layer.0.SelfAttention.v.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.3.layer.0.layer_norm.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.3.layer.1.EncDecAttention.k.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.3.layer.1.EncDecAttention.o.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.3.layer.1.EncDecAttention.q.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.3.layer.1.EncDecAttention.v.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.3.layer.1.layer_norm.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.3.layer.2.DenseReluDense.wi.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.3.layer.2.DenseReluDense.wo.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.3.layer.2.layer_norm.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.decoder.block.4.layer.0.SelfAttention.k.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.4.layer.0.SelfAttention.o.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.4.layer.0.SelfAttention.q.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.4.layer.0.SelfAttention.v.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.4.layer.0.layer_norm.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.4.layer.1.EncDecAttention.k.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.4.layer.1.EncDecAttention.o.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.4.layer.1.EncDecAttention.q.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.4.layer.1.EncDecAttention.v.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.4.layer.1.layer_norm.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.4.layer.2.DenseReluDense.wi.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.4.layer.2.DenseReluDense.wo.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.4.layer.2.layer_norm.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.5.layer.0.SelfAttention.k.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.5.layer.0.SelfAttention.o.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.5.layer.0.SelfAttention.q.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.5.layer.0.SelfAttention.v.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.5.layer.0.layer_norm.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.5.layer.1.EncDecAttention.k.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.5.layer.1.EncDecAttention.o.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.5.layer.1.EncDecAttention.q.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.5.layer.1.EncDecAttention.v.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.5.layer.1.layer_norm.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.5.layer.2.DenseReluDense.wi.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.5.layer.2.DenseReluDense.wo.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.5.layer.2.layer_norm.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.6.layer.0.SelfAttention.k.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.6.layer.0.SelfAttention.o.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.6.layer.0.SelfAttention.q.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.6.layer.0.SelfAttention.v.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.6.layer.0.layer_norm.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.6.layer.1.EncDecAttention.k.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.6.layer.1.EncDecAttention.o.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.6.layer.1.EncDecAttention.q.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.6.layer.1.EncDecAttention.v.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.6.layer.1.layer_norm.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.6.layer.2.DenseReluDense.wi.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.6.layer.2.DenseReluDense.wo.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.6.layer.2.layer_norm.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.7.layer.0.SelfAttention.k.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.7.layer.0.SelfAttention.o.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.7.layer.0.SelfAttention.q.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.7.layer.0.SelfAttention.v.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.7.layer.0.layer_norm.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.7.layer.1.EncDecAttention.k.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.7.layer.1.EncDecAttention.o.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.7.layer.1.EncDecAttention.q.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.7.layer.1.EncDecAttention.v.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.7.layer.1.layer_norm.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.7.layer.2.DenseReluDense.wi.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.7.layer.2.DenseReluDense.wo.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.7.layer.2.layer_norm.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.8.layer.0.SelfAttention.k.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.8.layer.0.SelfAttention.o.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.8.layer.0.SelfAttention.q.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.8.layer.0.SelfAttention.v.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.8.layer.0.layer_norm.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.8.layer.1.EncDecAttention.k.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.8.layer.1.EncDecAttention.o.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.8.layer.1.EncDecAttention.q.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.8.layer.1.EncDecAttention.v.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.8.layer.1.layer_norm.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.8.layer.2.DenseReluDense.wi.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.8.layer.2.DenseReluDense.wo.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.8.layer.2.layer_norm.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.9.layer.0.SelfAttention.k.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.9.layer.0.SelfAttention.o.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.9.layer.0.SelfAttention.q.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.9.layer.0.SelfAttention.v.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.9.layer.0.layer_norm.weight": "model-00005-of-00089.safetensors", + "encoder_decoder.decoder.block.9.layer.1.EncDecAttention.k.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.block.9.layer.1.EncDecAttention.o.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.block.9.layer.1.EncDecAttention.q.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.block.9.layer.1.EncDecAttention.v.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.block.9.layer.1.layer_norm.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.block.9.layer.2.DenseReluDense.wi.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.block.9.layer.2.DenseReluDense.wo.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.block.9.layer.2.layer_norm.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.decoder.final_layer_norm.weight": "model-00006-of-00089.safetensors", + "encoder_decoder.encoder.block.0.layer.0.SelfAttention.k.weight": "model-00002-of-00089.safetensors", + "encoder_decoder.encoder.block.0.layer.0.SelfAttention.o.weight": "model-00002-of-00089.safetensors", + "encoder_decoder.encoder.block.0.layer.0.SelfAttention.q.weight": "model-00002-of-00089.safetensors", + "encoder_decoder.encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00089.safetensors", + "encoder_decoder.encoder.block.0.layer.0.SelfAttention.v.weight": "model-00002-of-00089.safetensors", + "encoder_decoder.encoder.block.0.layer.0.layer_norm.weight": "model-00002-of-00089.safetensors", + "encoder_decoder.encoder.block.0.layer.1.DenseReluDense.wi.weight": "model-00002-of-00089.safetensors", + "encoder_decoder.encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00002-of-00089.safetensors", + "encoder_decoder.encoder.block.0.layer.1.layer_norm.weight": "model-00002-of-00089.safetensors", + "encoder_decoder.encoder.block.1.layer.0.SelfAttention.k.weight": "model-00002-of-00089.safetensors", + "encoder_decoder.encoder.block.1.layer.0.SelfAttention.o.weight": "model-00002-of-00089.safetensors", + "encoder_decoder.encoder.block.1.layer.0.SelfAttention.q.weight": "model-00002-of-00089.safetensors", + "encoder_decoder.encoder.block.1.layer.0.SelfAttention.v.weight": "model-00002-of-00089.safetensors", + "encoder_decoder.encoder.block.1.layer.0.layer_norm.weight": "model-00002-of-00089.safetensors", + "encoder_decoder.encoder.block.1.layer.1.DenseReluDense.wi.weight": "model-00002-of-00089.safetensors", + "encoder_decoder.encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00002-of-00089.safetensors", + "encoder_decoder.encoder.block.1.layer.1.layer_norm.weight": "model-00002-of-00089.safetensors", + "encoder_decoder.encoder.block.10.layer.0.SelfAttention.k.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.10.layer.0.SelfAttention.o.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.10.layer.0.SelfAttention.q.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.10.layer.0.SelfAttention.v.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.10.layer.0.layer_norm.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.10.layer.1.DenseReluDense.wi.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.encoder.block.10.layer.1.layer_norm.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.encoder.block.11.layer.0.SelfAttention.k.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.encoder.block.11.layer.0.SelfAttention.o.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.encoder.block.11.layer.0.SelfAttention.q.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.encoder.block.11.layer.0.SelfAttention.v.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.encoder.block.11.layer.0.layer_norm.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.encoder.block.11.layer.1.DenseReluDense.wi.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.encoder.block.11.layer.1.layer_norm.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.encoder.block.2.layer.0.SelfAttention.k.weight": "model-00002-of-00089.safetensors", + "encoder_decoder.encoder.block.2.layer.0.SelfAttention.o.weight": "model-00002-of-00089.safetensors", + "encoder_decoder.encoder.block.2.layer.0.SelfAttention.q.weight": "model-00002-of-00089.safetensors", + "encoder_decoder.encoder.block.2.layer.0.SelfAttention.v.weight": "model-00002-of-00089.safetensors", + "encoder_decoder.encoder.block.2.layer.0.layer_norm.weight": "model-00002-of-00089.safetensors", + "encoder_decoder.encoder.block.2.layer.1.DenseReluDense.wi.weight": "model-00002-of-00089.safetensors", + "encoder_decoder.encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00002-of-00089.safetensors", + "encoder_decoder.encoder.block.2.layer.1.layer_norm.weight": "model-00002-of-00089.safetensors", + "encoder_decoder.encoder.block.3.layer.0.SelfAttention.k.weight": "model-00002-of-00089.safetensors", + "encoder_decoder.encoder.block.3.layer.0.SelfAttention.o.weight": "model-00002-of-00089.safetensors", + "encoder_decoder.encoder.block.3.layer.0.SelfAttention.q.weight": "model-00002-of-00089.safetensors", + "encoder_decoder.encoder.block.3.layer.0.SelfAttention.v.weight": "model-00002-of-00089.safetensors", + "encoder_decoder.encoder.block.3.layer.0.layer_norm.weight": "model-00002-of-00089.safetensors", + "encoder_decoder.encoder.block.3.layer.1.DenseReluDense.wi.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.3.layer.1.layer_norm.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.4.layer.0.SelfAttention.k.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.4.layer.0.SelfAttention.o.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.4.layer.0.SelfAttention.q.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.4.layer.0.SelfAttention.v.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.4.layer.0.layer_norm.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.4.layer.1.DenseReluDense.wi.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.4.layer.1.layer_norm.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.5.layer.0.SelfAttention.k.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.5.layer.0.SelfAttention.o.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.5.layer.0.SelfAttention.q.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.5.layer.0.SelfAttention.v.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.5.layer.0.layer_norm.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.5.layer.1.DenseReluDense.wi.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.5.layer.1.layer_norm.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.6.layer.0.SelfAttention.k.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.6.layer.0.SelfAttention.o.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.6.layer.0.SelfAttention.q.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.6.layer.0.SelfAttention.v.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.6.layer.0.layer_norm.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.6.layer.1.DenseReluDense.wi.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.6.layer.1.layer_norm.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.7.layer.0.SelfAttention.k.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.7.layer.0.SelfAttention.o.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.7.layer.0.SelfAttention.q.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.7.layer.0.SelfAttention.v.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.7.layer.0.layer_norm.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.7.layer.1.DenseReluDense.wi.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.7.layer.1.layer_norm.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.8.layer.0.SelfAttention.k.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.8.layer.0.SelfAttention.o.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.8.layer.0.SelfAttention.q.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.8.layer.0.SelfAttention.v.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.8.layer.0.layer_norm.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.8.layer.1.DenseReluDense.wi.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.8.layer.1.layer_norm.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.9.layer.0.SelfAttention.k.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.9.layer.0.SelfAttention.o.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.9.layer.0.SelfAttention.q.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.9.layer.0.SelfAttention.v.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.9.layer.0.layer_norm.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.9.layer.1.DenseReluDense.wi.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.block.9.layer.1.layer_norm.weight": "model-00003-of-00089.safetensors", + "encoder_decoder.encoder.final_layer_norm.weight": "model-00004-of-00089.safetensors", + "encoder_decoder.shared.weight": "model-00002-of-00089.safetensors", + "sequence_weights": "model-00001-of-00089.safetensors", + "unigram": "model-00001-of-00089.safetensors", + "word_embeddings": "model-00001-of-00089.safetensors" + } +}