diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..40f7af3996c29b3c82feca30f2724698b6d74216 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +checkpoint-36/tokenizer.json filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..00526be7c37fd74f93c3aba3e61c5be580151ce2 --- /dev/null +++ b/README.md @@ -0,0 +1,129 @@ +--- +--- + +[Built with Axolotl](https://github.com/axolotl-ai-cloud/axolotl) +
See axolotl config + +axolotl version: `0.9.2` +```yaml +base_model: /capstor/scratch/cscs/bbernath/models/meditron-70B +chat_template: llama3 +bfloat16: true +output_dir: /capstor/store/cscs/swissai/a06/meditron/models/meditron_CHUV_2 #/capstor/scratch/cscs/bbernath/models/meditron_CHUV +dataset_prepared_path: /capstor/scratch/cscs/bbernath/dataset/ +# - path: /capstor/store/cscs/swissai/a06/meditron/datasets/masked/special_mixture/instruction_tuning_mixture.jsonl +# type: chat_template +# ds_type: json +# split: train +# field_messages: conversations +# message_field_role: from +# message_field_content: value +#pretraining_dataset: +# - path: json +# data_files: +# - /capstor/store/cscs/swissai/a06/meditron/datasets/pretrain/pubmed/pubmed_3B.jsonl +# - /capstor/store/cscs/swissai/a06/meditron/datasets/pretrain/fineweb/fineweb_400M_anglais.jsonl +# type: pretrain +datasets: + - path: /capstor/store/cscs/swissai/a06/meditron/datasets/masked/gemini/moove_gemini_2.jsonl + type: chat_template + ds_type: json + split: train + field_messages: conversations + message_field_role: from + message_field_content: value + +shuffle_merged_datasets: true +dataset_processes: 128 +# max_steps: 1500 +flash_attention: true +sequence_len: 8192 +gradient_accumulation_steps: 1 +micro_batch_size: 1 +train_on_inputs: false +group_by_length: false +pad_to_sequence_len: true +sample_packing: true +optimizer: adamw_torch +optim_args: + fused: true +cosine_min_lr_ratio: 0.1 +learning_rate: 5.0e-6 +warmup_ratio: 0 +weight_decay: 0.05 +gradient_checkpointing: true +gradient_checkpointing_kwargs: + use_reentrant: false +load_in_4bit: false +load_in_8bit: false +num_epochs: 1 +saves_per_epoch: 1 +# evals_per_epoch: 1 +eval_set_size: 0.0 +eval_table_size: null +lr_scheduler: cosine +max_grad_norm: 1.0 +resume_from_checkpoint: null +special_tokens: + pad_token: <|end_of_text|> +tf32: false +tokenizer_type: AutoTokenizer +type: LlamaForCausalLM +flash_attn_rms_norm: true +flash_attn_fuse_qkv: false +early_stopping_patience: 0 +wandb_entity: alexs-team +wandb_name: meditron-CHUV-llama-gemini +wandb_project: Meditron DDX +wandb_watch: gradients +xformers_attention: null +logging_steps: 1 +deepspeed: /capstor/users/cscs/bbernath/meditron/axolotl_config/deepspeed_new.json + +``` + +

+ +# capstor/store/cscs/swissai/a06/meditron/models/meditron_CHUV_2 + +This model was trained from scratch on the /capstor/store/cscs/swissai/a06/meditron/datasets/masked/gemini/moove_gemini_2.jsonl dataset. + +## Model description + +More information needed + +## Intended uses & limitations + +More information needed + +## Training and evaluation data + +More information needed + +## Training procedure + +### Training hyperparameters + +The following hyperparameters were used during training: +- learning_rate: 5e-06 +- train_batch_size: 1 +- eval_batch_size: 1 +- seed: 42 +- distributed_type: multi-GPU +- num_devices: 32 +- total_train_batch_size: 32 +- total_eval_batch_size: 32 +- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=fused=True +- lr_scheduler_type: cosine +- num_epochs: 1.0 + +### Training results + + + +### Framework versions + +- Transformers 4.51.3 +- Pytorch 2.7.0a0+79aa17489c.nv25.04 +- Datasets 3.6.0 +- Tokenizers 0.21.1 diff --git a/checkpoint-36/config.json b/checkpoint-36/config.json new file mode 100644 index 0000000000000000000000000000000000000000..4946add7353eabbc5791c753f11b44b5be1f89b9 --- /dev/null +++ b/checkpoint-36/config.json @@ -0,0 +1,35 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128009, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 8192, + "initializer_range": 0.02, + "intermediate_size": 28672, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 64, + "num_hidden_layers": 80, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.51.3", + "use_cache": false, + "vocab_size": 128256 +} diff --git a/checkpoint-36/generation_config.json b/checkpoint-36/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..cd28e19ed02358fd2089710dcd138907439c525b --- /dev/null +++ b/checkpoint-36/generation_config.json @@ -0,0 +1,8 @@ +{ + "_from_model_config": true, + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": 128009, + "transformers_version": "4.51.3", + "use_cache": false +} diff --git a/checkpoint-36/global_step36/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/checkpoint-36/global_step36/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ab20d02180d011251d89632bf7530fb356153d81 --- /dev/null +++ b/checkpoint-36/global_step36/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7ae6d478a48a04b829bdf309b2109104cd87bb05761d2569f66ed4d16d09c9f +size 26457647899 diff --git a/checkpoint-36/global_step36/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt b/checkpoint-36/global_step36/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a7d077968ccbd79a559c967d706480335150f4ab --- /dev/null +++ b/checkpoint-36/global_step36/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6fa76a3fd02bc15997d4f6e41df80985373c355d81bbe9a750d3d512d98c023 +size 26457647920 diff --git a/checkpoint-36/global_step36/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt b/checkpoint-36/global_step36/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1f98566c4efa4fea040a49d4bb8308e05d0cd828 --- /dev/null +++ b/checkpoint-36/global_step36/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6524c751c24ec6f0fa0b2306a3aed370117e5d77b4a938df76112b6f9833a6b3 +size 26457647920 diff --git a/checkpoint-36/global_step36/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt b/checkpoint-36/global_step36/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6d63babb7154f9cae5416197c0aa5184854e9426 --- /dev/null +++ b/checkpoint-36/global_step36/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed9e62f3fd69513940ce85849ed74cfdbca35f69a567d8cfc12d93da1be64286 +size 26457647920 diff --git a/checkpoint-36/global_step36/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt b/checkpoint-36/global_step36/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1961d71ee03701b3654e2b3ed2f0d6cdc86e3010 --- /dev/null +++ b/checkpoint-36/global_step36/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8e3639691f08a961e26f5bd61d5b51be5170a0340372fe35816e6d6f48522ca +size 26457647920 diff --git a/checkpoint-36/global_step36/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt b/checkpoint-36/global_step36/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4e8d37a7d185e2a2d45d0b55a0daa3ca1411b2af --- /dev/null +++ b/checkpoint-36/global_step36/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80827d2a7cd25ac5bf8b86b998115b1b1c10f4689e4665bec03ca4c009acc504 +size 26457647920 diff --git a/checkpoint-36/global_step36/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt b/checkpoint-36/global_step36/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0888e7bb7d0af9c2e5d8178522d14e29020cfd3e --- /dev/null +++ b/checkpoint-36/global_step36/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38f353a8c4c4143db58a72e2cbce430c5a4840d7809cf44a603bd32ac0bf0a34 +size 26457647899 diff --git a/checkpoint-36/global_step36/zero_pp_rank_0_mp_rank_00_model_states.pt b/checkpoint-36/global_step36/zero_pp_rank_0_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8f9406c1451049457b9ea6730d1e42b4dc32df02 --- /dev/null +++ b/checkpoint-36/global_step36/zero_pp_rank_0_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bae1f93932e95493b7252837c1d4637439f0a6b8671f2a7aab6451251e24ee53 +size 368825 diff --git a/checkpoint-36/global_step36/zero_pp_rank_10_mp_rank_00_model_states.pt b/checkpoint-36/global_step36/zero_pp_rank_10_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7887e47791f76494616236081fb53b24472bbcbb --- /dev/null +++ b/checkpoint-36/global_step36/zero_pp_rank_10_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a792d9f6f9186ae94097075f6cb897da42e5b4fc765000bded4cc4598cc4a153 +size 369553 diff --git a/checkpoint-36/global_step36/zero_pp_rank_11_mp_rank_00_model_states.pt b/checkpoint-36/global_step36/zero_pp_rank_11_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..537e692e95a1a8c6aee42e0212657f2ee45019b5 --- /dev/null +++ b/checkpoint-36/global_step36/zero_pp_rank_11_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1453c1d7975756e71e6d9bb93e0b047f1f9c5096ed28bd65bde30ab7912359db +size 369553 diff --git a/checkpoint-36/global_step36/zero_pp_rank_12_mp_rank_00_model_states.pt b/checkpoint-36/global_step36/zero_pp_rank_12_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1fcdb3668d5954d34a0640d208307feab09490ee --- /dev/null +++ b/checkpoint-36/global_step36/zero_pp_rank_12_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d85def5a04040f8ab38dfaea748ab029e7a19a9eda262e971a85c2f7de8fcf88 +size 369553 diff --git a/checkpoint-36/global_step36/zero_pp_rank_13_mp_rank_00_model_states.pt b/checkpoint-36/global_step36/zero_pp_rank_13_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..33cd38e1c15c5fb08a95a31235e2e21b866c083a --- /dev/null +++ b/checkpoint-36/global_step36/zero_pp_rank_13_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1302ef54cf0bf94ceceaceceb1efedfe340ccbf3a0d91435ebf35a40a4689c42 +size 369553 diff --git a/checkpoint-36/global_step36/zero_pp_rank_14_mp_rank_00_model_states.pt b/checkpoint-36/global_step36/zero_pp_rank_14_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..166d2e499ac609bf1b5f9aff34ffa7aeca080277 --- /dev/null +++ b/checkpoint-36/global_step36/zero_pp_rank_14_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b86c96aed22c2500ccb847daac820ee04f72845e6cc13a8ef16976283cde1cd5 +size 369553 diff --git a/checkpoint-36/global_step36/zero_pp_rank_15_mp_rank_00_model_states.pt b/checkpoint-36/global_step36/zero_pp_rank_15_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c0e4789e80c08ee14a4db6962362853465514c15 --- /dev/null +++ b/checkpoint-36/global_step36/zero_pp_rank_15_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3dab2319c9e13ceccd16423a62efe56ad37f283c05adbb87846797b8c8264e6 +size 369553 diff --git a/checkpoint-36/global_step36/zero_pp_rank_16_mp_rank_00_model_states.pt b/checkpoint-36/global_step36/zero_pp_rank_16_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3cb4ee03aec29bf143f865a1b824139f6f324e6d --- /dev/null +++ b/checkpoint-36/global_step36/zero_pp_rank_16_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d41103c9aedc28774a8a107f847709995c2e08aaca62fc927c6f786d9b8ccf2d +size 369553 diff --git a/checkpoint-36/global_step36/zero_pp_rank_17_mp_rank_00_model_states.pt b/checkpoint-36/global_step36/zero_pp_rank_17_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..494f886b97f2accc450cc318226eee7a086d552d --- /dev/null +++ b/checkpoint-36/global_step36/zero_pp_rank_17_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8933b76d538e3e20119faa4027be5064598ce3507d17b17ba48217ce7d2b5373 +size 369553 diff --git a/checkpoint-36/global_step36/zero_pp_rank_18_mp_rank_00_model_states.pt b/checkpoint-36/global_step36/zero_pp_rank_18_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bf57f237d31d79ae3da8b1f5fbe949270e287d57 --- /dev/null +++ b/checkpoint-36/global_step36/zero_pp_rank_18_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:319b3931bec6cf49afb98ce47bff0e0cf6f085b3fd8335372a14dbaf3d493a50 +size 369553 diff --git a/checkpoint-36/global_step36/zero_pp_rank_19_mp_rank_00_model_states.pt b/checkpoint-36/global_step36/zero_pp_rank_19_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..36d12b0f3c99dd704938648dd58e113c913c4801 --- /dev/null +++ b/checkpoint-36/global_step36/zero_pp_rank_19_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a44ddafab92a91dff54b730a33eca4f77ae283995d0a92c6dbc808a31a36857c +size 369553 diff --git a/checkpoint-36/global_step36/zero_pp_rank_1_mp_rank_00_model_states.pt b/checkpoint-36/global_step36/zero_pp_rank_1_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..525b1b948306a2be9968c4aaae02c60bab7c2a6f --- /dev/null +++ b/checkpoint-36/global_step36/zero_pp_rank_1_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf534431d2fbef15f117900c9e5c0e75db186219ac42541cb90dee5e0b7725ca +size 368825 diff --git a/checkpoint-36/global_step36/zero_pp_rank_20_mp_rank_00_model_states.pt b/checkpoint-36/global_step36/zero_pp_rank_20_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fa64811aaed7690a016ae69eb977805a07cd3c16 --- /dev/null +++ b/checkpoint-36/global_step36/zero_pp_rank_20_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f380e3fdf643afeb5fc621e57f723ef594e316d7c5f703f71f4cf2dab945ef2b +size 369553 diff --git a/checkpoint-36/global_step36/zero_pp_rank_21_mp_rank_00_model_states.pt b/checkpoint-36/global_step36/zero_pp_rank_21_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..43111c180a4ed3edd190d33e6dbf38231c5d10fd --- /dev/null +++ b/checkpoint-36/global_step36/zero_pp_rank_21_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d69de6226909b4ebff72bb00798f1774edf1a8c723d2692f9fa6d9b0d05d416 +size 369553 diff --git a/checkpoint-36/global_step36/zero_pp_rank_22_mp_rank_00_model_states.pt b/checkpoint-36/global_step36/zero_pp_rank_22_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ddf42315d310176ad61c1799e1606d4cbe976f1f --- /dev/null +++ b/checkpoint-36/global_step36/zero_pp_rank_22_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84f7e37e167b1f88de8cb6c7e2e6d275e1943ed99d8d4386a848114aabc97713 +size 369553 diff --git a/checkpoint-36/global_step36/zero_pp_rank_23_mp_rank_00_model_states.pt b/checkpoint-36/global_step36/zero_pp_rank_23_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8de4c114b22ef94bde388adf5fa384a1b458e6b1 --- /dev/null +++ b/checkpoint-36/global_step36/zero_pp_rank_23_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b65d408a5e14cee02057b858cca39662aa636ea4d2b20228913ea327e81aca34 +size 369553 diff --git a/checkpoint-36/global_step36/zero_pp_rank_24_mp_rank_00_model_states.pt b/checkpoint-36/global_step36/zero_pp_rank_24_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2ea3670bd0c679e96b1b3b9d1a3e0f4f6c0e2d38 --- /dev/null +++ b/checkpoint-36/global_step36/zero_pp_rank_24_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e71363f973b0416507bf87624cc8184e813d183f50d7481de1360d82b33c96f +size 369553 diff --git a/checkpoint-36/global_step36/zero_pp_rank_25_mp_rank_00_model_states.pt b/checkpoint-36/global_step36/zero_pp_rank_25_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6b40e212c7907abadf46bdfc12f9d3d495523c13 --- /dev/null +++ b/checkpoint-36/global_step36/zero_pp_rank_25_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cdf3a013fb60e4a4c62ed3a8cf119d34cce70beab16feb38d3c3addfe228a3d +size 369553 diff --git a/checkpoint-36/global_step36/zero_pp_rank_26_mp_rank_00_model_states.pt b/checkpoint-36/global_step36/zero_pp_rank_26_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d789353a5f7ecb40c2b809ff75fc1d9e071edfdd --- /dev/null +++ b/checkpoint-36/global_step36/zero_pp_rank_26_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67ff0837d13ae22f4ef8e9e29a4135288dc04141df4558e8d785369b7d9d37f6 +size 369553 diff --git a/checkpoint-36/global_step36/zero_pp_rank_27_mp_rank_00_model_states.pt b/checkpoint-36/global_step36/zero_pp_rank_27_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..713efb3706889311bcd46395b52d006b3ca12164 --- /dev/null +++ b/checkpoint-36/global_step36/zero_pp_rank_27_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a38dd63881612bf78a6f35916bbe359eb4a286f60622dbe3ab0f1c74a4b6078 +size 369553 diff --git a/checkpoint-36/global_step36/zero_pp_rank_28_mp_rank_00_model_states.pt b/checkpoint-36/global_step36/zero_pp_rank_28_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a8924a81e93246d743f1d3af1caab6a78944a699 --- /dev/null +++ b/checkpoint-36/global_step36/zero_pp_rank_28_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d45b0b837f47572a7ea95937caddaae71866b1c29a225ba150191a9dcd6a0960 +size 369553 diff --git a/checkpoint-36/global_step36/zero_pp_rank_29_mp_rank_00_model_states.pt b/checkpoint-36/global_step36/zero_pp_rank_29_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..229071d5904355089775db529e922d241563c8e8 --- /dev/null +++ b/checkpoint-36/global_step36/zero_pp_rank_29_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ba15c637a97b79a7d20b322a57fed67203c8fad3064f248dc630711feef8bdd +size 369553 diff --git a/checkpoint-36/global_step36/zero_pp_rank_2_mp_rank_00_model_states.pt b/checkpoint-36/global_step36/zero_pp_rank_2_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3923cbe8cc254b26cbae39f462488f8f5f8966c7 --- /dev/null +++ b/checkpoint-36/global_step36/zero_pp_rank_2_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddbb8400389879accf364d0361a8e87fac639509ab92a294470da6c3bf92df73 +size 368825 diff --git a/checkpoint-36/global_step36/zero_pp_rank_30_mp_rank_00_model_states.pt b/checkpoint-36/global_step36/zero_pp_rank_30_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cecb57104672e3a3fa673ebab4c53d40bdec29bb --- /dev/null +++ b/checkpoint-36/global_step36/zero_pp_rank_30_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f94d9490207baafdd2240f6facf5bf4cee05eff2bbc4c07eef9d4199fa7a962c +size 369553 diff --git a/checkpoint-36/global_step36/zero_pp_rank_31_mp_rank_00_model_states.pt b/checkpoint-36/global_step36/zero_pp_rank_31_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f57c3bd2ed8f80a62b7bccfecf36e64980737615 --- /dev/null +++ b/checkpoint-36/global_step36/zero_pp_rank_31_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c15b47cd9758433b93bf043bea52912f0194b5387e57c21e236f92f26f48350e +size 369553 diff --git a/checkpoint-36/global_step36/zero_pp_rank_3_mp_rank_00_model_states.pt b/checkpoint-36/global_step36/zero_pp_rank_3_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b57a866aa8068d52ae9fc30c0469a9f491f15a4f --- /dev/null +++ b/checkpoint-36/global_step36/zero_pp_rank_3_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:014a2aba358672f2d0c456198e41691d89aa1f79fc0e27a31205d6c7b698c824 +size 368825 diff --git a/checkpoint-36/global_step36/zero_pp_rank_4_mp_rank_00_model_states.pt b/checkpoint-36/global_step36/zero_pp_rank_4_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..46dd291cb01bd4809156e39bb2dbdf95a7882b6c --- /dev/null +++ b/checkpoint-36/global_step36/zero_pp_rank_4_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5408b704557aacbf43c9caf0bf84765c342b337f7e7072276f593e5cb64190ac +size 368825 diff --git a/checkpoint-36/global_step36/zero_pp_rank_5_mp_rank_00_model_states.pt b/checkpoint-36/global_step36/zero_pp_rank_5_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..62b26dce6ce6d7e193bac0fcf28a61a4f9f283be --- /dev/null +++ b/checkpoint-36/global_step36/zero_pp_rank_5_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:376881b210f89c1a19d106b0673f057fb272d12dcbbcee4c41fb3bf20bd8391d +size 368825 diff --git a/checkpoint-36/global_step36/zero_pp_rank_6_mp_rank_00_model_states.pt b/checkpoint-36/global_step36/zero_pp_rank_6_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2cc630bff2a43518bd406e981e5178910b9e0442 --- /dev/null +++ b/checkpoint-36/global_step36/zero_pp_rank_6_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a75f2d192b3f128caaedd747e10b0024a0af50dfe5155c4402016357702e925 +size 368825 diff --git a/checkpoint-36/global_step36/zero_pp_rank_7_mp_rank_00_model_states.pt b/checkpoint-36/global_step36/zero_pp_rank_7_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0c8beff411cf3ac49840bbcb3eac70148f390cc7 --- /dev/null +++ b/checkpoint-36/global_step36/zero_pp_rank_7_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da265d76fa82e5eda92c28d4914332a1f0eaeb13540bd5312d805b00728326cf +size 368825 diff --git a/checkpoint-36/global_step36/zero_pp_rank_8_mp_rank_00_model_states.pt b/checkpoint-36/global_step36/zero_pp_rank_8_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0af1bf8e6e55962c965d83365baed7a1596961e1 --- /dev/null +++ b/checkpoint-36/global_step36/zero_pp_rank_8_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a00e4dea0649853fe5168359203ad013f85f3b740a31136ca595fed5d137f9af +size 368825 diff --git a/checkpoint-36/global_step36/zero_pp_rank_9_mp_rank_00_model_states.pt b/checkpoint-36/global_step36/zero_pp_rank_9_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..aab25707d15d6d8eb0832c4a140f4d03b29b96b2 --- /dev/null +++ b/checkpoint-36/global_step36/zero_pp_rank_9_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc83fec43838c8cf0785e8cff37959b7eadeab0eaecccbb294bfd0a24054cfaa +size 368825 diff --git a/checkpoint-36/latest b/checkpoint-36/latest new file mode 100644 index 0000000000000000000000000000000000000000..377336ce371ac0248aa71731610cacc22e84b848 --- /dev/null +++ b/checkpoint-36/latest @@ -0,0 +1 @@ +global_step36 \ No newline at end of file diff --git a/checkpoint-36/model-00001-of-00030.safetensors b/checkpoint-36/model-00001-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..033593d292ed2fcef62eb2e37f36218b92eac53d --- /dev/null +++ b/checkpoint-36/model-00001-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4cabb5d59084cfa0516e1ee9733929ab22844b6f28be8133e20a098dd1d40e1 +size 4584408808 diff --git a/checkpoint-36/model-00002-of-00030.safetensors b/checkpoint-36/model-00002-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..446e42a65a5f73bc5529b2a8c690902e576df3a0 --- /dev/null +++ b/checkpoint-36/model-00002-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ddc59c1cc80f904fc1987d24f0c421df9eefaf8074e787b0ee14b67b90a4f8b +size 4664167376 diff --git a/checkpoint-36/model-00003-of-00030.safetensors b/checkpoint-36/model-00003-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..71559b7831aad3c8b70f8c0824c5814a3d841844 --- /dev/null +++ b/checkpoint-36/model-00003-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22513694fe0f63a9a036561351b57c0cfae48fc00cf36c12b662649ce8cb078e +size 4999711704 diff --git a/checkpoint-36/model-00004-of-00030.safetensors b/checkpoint-36/model-00004-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bb62ce95c63f77b715a9ff87eef0e9dfc1ceee43 --- /dev/null +++ b/checkpoint-36/model-00004-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:691e9246e1d9092c75352c97f0eccb8dd02639553042f0f5a51db2531b6c74f3 +size 4966157032 diff --git a/checkpoint-36/model-00005-of-00030.safetensors b/checkpoint-36/model-00005-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9f842617523301d625fcc209775b9dc4ad793dc4 --- /dev/null +++ b/checkpoint-36/model-00005-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1e5a69ab2e16687429773b4b3f681852518869dbbcec8e61caa012064cf0f0a +size 4664134408 diff --git a/checkpoint-36/model-00006-of-00030.safetensors b/checkpoint-36/model-00006-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8984b19cd0deb7d687ca52345399b891a8fa8cea --- /dev/null +++ b/checkpoint-36/model-00006-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e3a1b59792281c7d8ae475ce26bf81cf057c68b243cb62946c97a07dc4594ee +size 4664167408 diff --git a/checkpoint-36/model-00007-of-00030.safetensors b/checkpoint-36/model-00007-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..147a1fb80453297df1f994aee9e7697b2980bec3 --- /dev/null +++ b/checkpoint-36/model-00007-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d748bcea229e07f1eb39f922e2722b88f64ed8b1c927d8468a5a7255722cc1f +size 4664167408 diff --git a/checkpoint-36/model-00008-of-00030.safetensors b/checkpoint-36/model-00008-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4d1ef19cb75adaabb878baa1eec5ab10d13cb697 --- /dev/null +++ b/checkpoint-36/model-00008-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e19bfcd9e549ef045b6f6c65da24295bc1d616fef032cfa3ed3d9d070c2e079 +size 4999711728 diff --git a/checkpoint-36/model-00009-of-00030.safetensors b/checkpoint-36/model-00009-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e9f0f96a980427add67024e806820e7b69527fc9 --- /dev/null +++ b/checkpoint-36/model-00009-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb099d9ff85178472649e0ff678c2c773ce39107fddb3eafaed71031499a2e9b +size 4966157056 diff --git a/checkpoint-36/model-00010-of-00030.safetensors b/checkpoint-36/model-00010-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8a43714c237c6900642f8480591d112ecd9b2a7e --- /dev/null +++ b/checkpoint-36/model-00010-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afbf674bac3fabfce368a362c07ce6657d0cba056611928f06589c35cce5f747 +size 4664134408 diff --git a/checkpoint-36/model-00011-of-00030.safetensors b/checkpoint-36/model-00011-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1f85a9ef08e7a95f94f930b46eaa0476b9e3cf92 --- /dev/null +++ b/checkpoint-36/model-00011-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e42f2db2ecfc3ee540cb85949151df7dbc675ca10fe9bd70937ad3ab97d7fd52 +size 4664167408 diff --git a/checkpoint-36/model-00012-of-00030.safetensors b/checkpoint-36/model-00012-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6f196eae0cd1c6e943bc388a4cb803eee86c1949 --- /dev/null +++ b/checkpoint-36/model-00012-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:677690d7c7590a54095252fe70aa438cbc8e237cf6af60da9069f733bf4ff4ce +size 4664167408 diff --git a/checkpoint-36/model-00013-of-00030.safetensors b/checkpoint-36/model-00013-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e7c9ffc9f09d43ca8ccd6a839008b246d96bf38d --- /dev/null +++ b/checkpoint-36/model-00013-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d703720cd04e2b35c0528029a2ece4a6d621ab43b075d39d929df54202a267ee +size 4999711728 diff --git a/checkpoint-36/model-00014-of-00030.safetensors b/checkpoint-36/model-00014-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7ab6485f7a376a23b8d9eaf1398946eb5e1b202a --- /dev/null +++ b/checkpoint-36/model-00014-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c63ae134dbaa344665789b8b0ef2697a4984bf2a4060b7e9b4d7d2202b5e4ade +size 4966157056 diff --git a/checkpoint-36/model-00015-of-00030.safetensors b/checkpoint-36/model-00015-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3a0af656a33007be9948cfd8d6e8b08520736eaa --- /dev/null +++ b/checkpoint-36/model-00015-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:960ae0a271bb777784dc8cdeb96bb88451e6d6620c1400073fe8d37552c74173 +size 4664134408 diff --git a/checkpoint-36/model-00016-of-00030.safetensors b/checkpoint-36/model-00016-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cad213e04f1b91bdd12b51e9917e5f43ac12aba8 --- /dev/null +++ b/checkpoint-36/model-00016-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44abb02c211d7aded70a0f23c996afdb4505a287155e5b344cb7b2a43ec8640b +size 4664167408 diff --git a/checkpoint-36/model-00017-of-00030.safetensors b/checkpoint-36/model-00017-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..42f81fcd692c27a534244a4e7b9d9915008c8685 --- /dev/null +++ b/checkpoint-36/model-00017-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22aeaf179ffde50a10aecbda803a140446fc76b609e42c05aae821a527dbca75 +size 4664167408 diff --git a/checkpoint-36/model-00018-of-00030.safetensors b/checkpoint-36/model-00018-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b9ceb087fa0864768d72f549d3e8967e6d2966ae --- /dev/null +++ b/checkpoint-36/model-00018-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2798d3191824f504e59750f67a75e4f620956610e79eb5451d32ea4addf2c7f3 +size 4999711728 diff --git a/checkpoint-36/model-00019-of-00030.safetensors b/checkpoint-36/model-00019-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..11f761a31b38f451644b476ed434c05b2b0d8a57 --- /dev/null +++ b/checkpoint-36/model-00019-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd045f6262276c5c417d6d381ea88c24ab7b506398d1172c8a06612eccc55640 +size 4966157056 diff --git a/checkpoint-36/model-00020-of-00030.safetensors b/checkpoint-36/model-00020-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4785512474540a8b10253806117ea6e210106d9b --- /dev/null +++ b/checkpoint-36/model-00020-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0048cf26d97567fac9f8c491373844b43fda8da0293f6eeccf4fb63e44bfea1 +size 4664134408 diff --git a/checkpoint-36/model-00021-of-00030.safetensors b/checkpoint-36/model-00021-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bc037f2544096a32cb33c50be7afb12bf071462a --- /dev/null +++ b/checkpoint-36/model-00021-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07330fd90ed976fb41f9ca657a413ed2d3444b8ed8a7fdca64838706e9834bad +size 4664167408 diff --git a/checkpoint-36/model-00022-of-00030.safetensors b/checkpoint-36/model-00022-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..90b9c987a0f69f89fefa37e4fa22cb55087cdac2 --- /dev/null +++ b/checkpoint-36/model-00022-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d3e63e361e2f21b9a8dc8a7c27a63384371427803ef8a96a6ea7d7c9fdf25bd +size 4664167408 diff --git a/checkpoint-36/model-00023-of-00030.safetensors b/checkpoint-36/model-00023-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..17c60a61d31b33f6907d523024ced7b5ecfd3d74 --- /dev/null +++ b/checkpoint-36/model-00023-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cdbb795719a187775a5edb2431d214e38882a8954d994d3d6fc921f817d2636 +size 4999711728 diff --git a/checkpoint-36/model-00024-of-00030.safetensors b/checkpoint-36/model-00024-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2bc3c5d0068473ef5aaaa61e30836eb91af7f059 --- /dev/null +++ b/checkpoint-36/model-00024-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:756d4e1a1fc22a9d38285c03568635c2a3440455047aa515d7653221f1fa0e18 +size 4966157056 diff --git a/checkpoint-36/model-00025-of-00030.safetensors b/checkpoint-36/model-00025-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5d1fb58abd6dc7b4c539f9cdf9c975cd6b0472b8 --- /dev/null +++ b/checkpoint-36/model-00025-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4b93c281b20705b010ed1af2fb461fae6317c6f3034fad649fde5fed3ac9e80 +size 4664134408 diff --git a/checkpoint-36/model-00026-of-00030.safetensors b/checkpoint-36/model-00026-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6d429b5614d0bea063a8a8679e104d9841cba596 --- /dev/null +++ b/checkpoint-36/model-00026-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cb003d2d89c383dcde824c418a1a832ff908f8ee2b98e8d27cbb3707e363cda +size 4664167408 diff --git a/checkpoint-36/model-00027-of-00030.safetensors b/checkpoint-36/model-00027-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5471659e734724652b85d5f8b4c2e932c466b3e9 --- /dev/null +++ b/checkpoint-36/model-00027-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:043f5027e70ee23b4d65d56106055018ab5746fdfbf856a4a5ca963bede6679b +size 4664167408 diff --git a/checkpoint-36/model-00028-of-00030.safetensors b/checkpoint-36/model-00028-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6e3b477a84e9e876cf7add95c8d6fb517b5cd89f --- /dev/null +++ b/checkpoint-36/model-00028-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08b1d835c29f3f1ed6fb37c22dd449cb0eb587373866a2009959c22d852f1824 +size 4999711728 diff --git a/checkpoint-36/model-00029-of-00030.safetensors b/checkpoint-36/model-00029-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..40657cd94cd7484bfe53de232c0b37f31c900862 --- /dev/null +++ b/checkpoint-36/model-00029-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b02c8b1e7875bd4be22db0d438e28a4ed47c4279914b5cf02200c5bdeccdb0c6 +size 4966173536 diff --git a/checkpoint-36/model-00030-of-00030.safetensors b/checkpoint-36/model-00030-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a92bae86487bffc2c07e97dd23d54198d8efe174 --- /dev/null +++ b/checkpoint-36/model-00030-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a200ab4a9f6e3c246058e2742fc5a09a7586ac85a2c7215aa5c42bb051df0b5 +size 2101346432 diff --git a/checkpoint-36/model.safetensors.index.json b/checkpoint-36/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..37b1afe63cadc4ddce30aaff1b149c2f3083650c --- /dev/null +++ b/checkpoint-36/model.safetensors.index.json @@ -0,0 +1,730 @@ +{ + "metadata": { + "total_size": 141107412992 + }, + "weight_map": { + "lm_head.weight": "model-00030-of-00030.safetensors", + "model.embed_tokens.weight": "model-00001-of-00030.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00030.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00030.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00030.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00030.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00030.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00030.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00030.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00030.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00030.safetensors", + "model.layers.1.input_layernorm.weight": "model-00002-of-00030.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00030.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00030.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00030.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00030.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00030.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00030.safetensors", + "model.layers.10.input_layernorm.weight": "model-00005-of-00030.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00030.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.11.input_layernorm.weight": "model-00005-of-00030.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00030.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.12.input_layernorm.weight": "model-00006-of-00030.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00030.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.13.input_layernorm.weight": "model-00006-of-00030.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00030.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.14.input_layernorm.weight": "model-00006-of-00030.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00030.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.15.input_layernorm.weight": "model-00007-of-00030.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00030.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.16.input_layernorm.weight": "model-00007-of-00030.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00030.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.17.input_layernorm.weight": "model-00007-of-00030.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00030.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.18.input_layernorm.weight": "model-00008-of-00030.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00030.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.19.input_layernorm.weight": "model-00008-of-00030.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00030.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.2.input_layernorm.weight": "model-00002-of-00030.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00030.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.20.input_layernorm.weight": "model-00008-of-00030.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00030.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.21.input_layernorm.weight": "model-00009-of-00030.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00030.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.22.input_layernorm.weight": "model-00009-of-00030.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00030.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.23.input_layernorm.weight": "model-00009-of-00030.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00030.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.24.input_layernorm.weight": "model-00010-of-00030.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00030.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.25.input_layernorm.weight": "model-00010-of-00030.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00030.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.26.input_layernorm.weight": "model-00011-of-00030.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00030.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.27.input_layernorm.weight": "model-00011-of-00030.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00030.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.28.input_layernorm.weight": "model-00011-of-00030.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00030.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.29.input_layernorm.weight": "model-00012-of-00030.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00012-of-00030.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.3.input_layernorm.weight": "model-00002-of-00030.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00030.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.30.input_layernorm.weight": "model-00012-of-00030.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00030.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.31.input_layernorm.weight": "model-00012-of-00030.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00030.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.32.input_layernorm.weight": "model-00013-of-00030.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00013-of-00030.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.33.input_layernorm.weight": "model-00013-of-00030.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00013-of-00030.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.34.input_layernorm.weight": "model-00013-of-00030.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00013-of-00030.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.35.input_layernorm.weight": "model-00014-of-00030.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00014-of-00030.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.36.input_layernorm.weight": "model-00014-of-00030.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00014-of-00030.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.37.input_layernorm.weight": "model-00014-of-00030.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00014-of-00030.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.38.input_layernorm.weight": "model-00015-of-00030.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00015-of-00030.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.39.input_layernorm.weight": "model-00015-of-00030.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00015-of-00030.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.4.input_layernorm.weight": "model-00003-of-00030.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00030.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.40.input_layernorm.weight": "model-00016-of-00030.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00016-of-00030.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.41.input_layernorm.weight": "model-00016-of-00030.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00016-of-00030.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.42.input_layernorm.weight": "model-00016-of-00030.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00016-of-00030.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.43.input_layernorm.weight": "model-00017-of-00030.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00017-of-00030.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.44.input_layernorm.weight": "model-00017-of-00030.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00017-of-00030.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.45.input_layernorm.weight": "model-00017-of-00030.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00017-of-00030.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.46.input_layernorm.weight": "model-00018-of-00030.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00018-of-00030.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.47.input_layernorm.weight": "model-00018-of-00030.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00018-of-00030.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.48.input_layernorm.weight": "model-00018-of-00030.safetensors", + "model.layers.48.mlp.down_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.48.mlp.gate_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.48.mlp.up_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00018-of-00030.safetensors", + "model.layers.48.self_attn.k_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.48.self_attn.q_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.48.self_attn.v_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.49.input_layernorm.weight": "model-00019-of-00030.safetensors", + "model.layers.49.mlp.down_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.49.mlp.gate_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.49.mlp.up_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00019-of-00030.safetensors", + "model.layers.49.self_attn.k_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.49.self_attn.o_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.49.self_attn.q_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.49.self_attn.v_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.5.input_layernorm.weight": "model-00003-of-00030.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00030.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.50.input_layernorm.weight": "model-00019-of-00030.safetensors", + "model.layers.50.mlp.down_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.50.mlp.gate_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.50.mlp.up_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00019-of-00030.safetensors", + "model.layers.50.self_attn.k_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.50.self_attn.o_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.50.self_attn.q_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.50.self_attn.v_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.51.input_layernorm.weight": "model-00019-of-00030.safetensors", + "model.layers.51.mlp.down_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.51.mlp.gate_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.51.mlp.up_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00019-of-00030.safetensors", + "model.layers.51.self_attn.k_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.51.self_attn.o_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.51.self_attn.q_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.51.self_attn.v_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.52.input_layernorm.weight": "model-00020-of-00030.safetensors", + "model.layers.52.mlp.down_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.52.mlp.gate_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.52.mlp.up_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00020-of-00030.safetensors", + "model.layers.52.self_attn.k_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.52.self_attn.o_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.52.self_attn.q_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.52.self_attn.v_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.53.input_layernorm.weight": "model-00020-of-00030.safetensors", + "model.layers.53.mlp.down_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.53.mlp.gate_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.53.mlp.up_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00020-of-00030.safetensors", + "model.layers.53.self_attn.k_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.53.self_attn.o_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.53.self_attn.q_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.53.self_attn.v_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.54.input_layernorm.weight": "model-00021-of-00030.safetensors", + "model.layers.54.mlp.down_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.54.mlp.gate_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.54.mlp.up_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00021-of-00030.safetensors", + "model.layers.54.self_attn.k_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.54.self_attn.o_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.54.self_attn.q_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.54.self_attn.v_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.55.input_layernorm.weight": "model-00021-of-00030.safetensors", + "model.layers.55.mlp.down_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.55.mlp.gate_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.55.mlp.up_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00021-of-00030.safetensors", + "model.layers.55.self_attn.k_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.55.self_attn.o_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.55.self_attn.q_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.55.self_attn.v_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.56.input_layernorm.weight": "model-00021-of-00030.safetensors", + "model.layers.56.mlp.down_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.56.mlp.gate_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.56.mlp.up_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00021-of-00030.safetensors", + "model.layers.56.self_attn.k_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.56.self_attn.o_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.56.self_attn.q_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.56.self_attn.v_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.57.input_layernorm.weight": "model-00022-of-00030.safetensors", + "model.layers.57.mlp.down_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.57.mlp.gate_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.57.mlp.up_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00022-of-00030.safetensors", + "model.layers.57.self_attn.k_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.57.self_attn.o_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.57.self_attn.q_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.57.self_attn.v_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.58.input_layernorm.weight": "model-00022-of-00030.safetensors", + "model.layers.58.mlp.down_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.58.mlp.gate_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.58.mlp.up_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00022-of-00030.safetensors", + "model.layers.58.self_attn.k_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.58.self_attn.o_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.58.self_attn.q_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.58.self_attn.v_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.59.input_layernorm.weight": "model-00022-of-00030.safetensors", + "model.layers.59.mlp.down_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.59.mlp.gate_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.59.mlp.up_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00022-of-00030.safetensors", + "model.layers.59.self_attn.k_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.59.self_attn.o_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.59.self_attn.q_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.59.self_attn.v_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.6.input_layernorm.weight": "model-00003-of-00030.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00030.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.60.input_layernorm.weight": "model-00023-of-00030.safetensors", + "model.layers.60.mlp.down_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.60.mlp.gate_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.60.mlp.up_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.60.post_attention_layernorm.weight": "model-00023-of-00030.safetensors", + "model.layers.60.self_attn.k_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.60.self_attn.o_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.60.self_attn.q_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.60.self_attn.v_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.61.input_layernorm.weight": "model-00023-of-00030.safetensors", + "model.layers.61.mlp.down_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.61.mlp.gate_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.61.mlp.up_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.61.post_attention_layernorm.weight": "model-00023-of-00030.safetensors", + "model.layers.61.self_attn.k_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.61.self_attn.o_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.61.self_attn.q_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.61.self_attn.v_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.62.input_layernorm.weight": "model-00023-of-00030.safetensors", + "model.layers.62.mlp.down_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.62.mlp.gate_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.62.mlp.up_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.62.post_attention_layernorm.weight": "model-00023-of-00030.safetensors", + "model.layers.62.self_attn.k_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.62.self_attn.o_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.62.self_attn.q_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.62.self_attn.v_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.63.input_layernorm.weight": "model-00024-of-00030.safetensors", + "model.layers.63.mlp.down_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.63.mlp.gate_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.63.mlp.up_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.63.post_attention_layernorm.weight": "model-00024-of-00030.safetensors", + "model.layers.63.self_attn.k_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.63.self_attn.o_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.63.self_attn.q_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.63.self_attn.v_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.64.input_layernorm.weight": "model-00024-of-00030.safetensors", + "model.layers.64.mlp.down_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.64.mlp.gate_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.64.mlp.up_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.64.post_attention_layernorm.weight": "model-00024-of-00030.safetensors", + "model.layers.64.self_attn.k_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.64.self_attn.o_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.64.self_attn.q_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.64.self_attn.v_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.65.input_layernorm.weight": "model-00024-of-00030.safetensors", + "model.layers.65.mlp.down_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.65.mlp.gate_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.65.mlp.up_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.65.post_attention_layernorm.weight": "model-00024-of-00030.safetensors", + "model.layers.65.self_attn.k_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.65.self_attn.o_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.65.self_attn.q_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.65.self_attn.v_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.66.input_layernorm.weight": "model-00025-of-00030.safetensors", + "model.layers.66.mlp.down_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.66.mlp.gate_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.66.mlp.up_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.66.post_attention_layernorm.weight": "model-00025-of-00030.safetensors", + "model.layers.66.self_attn.k_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.66.self_attn.o_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.66.self_attn.q_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.66.self_attn.v_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.67.input_layernorm.weight": "model-00025-of-00030.safetensors", + "model.layers.67.mlp.down_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.67.mlp.gate_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.67.mlp.up_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.67.post_attention_layernorm.weight": "model-00025-of-00030.safetensors", + "model.layers.67.self_attn.k_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.67.self_attn.o_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.67.self_attn.q_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.67.self_attn.v_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.68.input_layernorm.weight": "model-00026-of-00030.safetensors", + "model.layers.68.mlp.down_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.68.mlp.gate_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.68.mlp.up_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.68.post_attention_layernorm.weight": "model-00026-of-00030.safetensors", + "model.layers.68.self_attn.k_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.68.self_attn.o_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.68.self_attn.q_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.68.self_attn.v_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.69.input_layernorm.weight": "model-00026-of-00030.safetensors", + "model.layers.69.mlp.down_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.69.mlp.gate_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.69.mlp.up_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.69.post_attention_layernorm.weight": "model-00026-of-00030.safetensors", + "model.layers.69.self_attn.k_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.69.self_attn.o_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.69.self_attn.q_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.69.self_attn.v_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.7.input_layernorm.weight": "model-00004-of-00030.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00004-of-00030.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00030.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00004-of-00030.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00030.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00030.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.70.input_layernorm.weight": "model-00026-of-00030.safetensors", + "model.layers.70.mlp.down_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.70.mlp.gate_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.70.mlp.up_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.70.post_attention_layernorm.weight": "model-00026-of-00030.safetensors", + "model.layers.70.self_attn.k_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.70.self_attn.o_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.70.self_attn.q_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.70.self_attn.v_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.71.input_layernorm.weight": "model-00027-of-00030.safetensors", + "model.layers.71.mlp.down_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.71.mlp.gate_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.71.mlp.up_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.71.post_attention_layernorm.weight": "model-00027-of-00030.safetensors", + "model.layers.71.self_attn.k_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.71.self_attn.o_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.71.self_attn.q_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.71.self_attn.v_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.72.input_layernorm.weight": "model-00027-of-00030.safetensors", + "model.layers.72.mlp.down_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.72.mlp.gate_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.72.mlp.up_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.72.post_attention_layernorm.weight": "model-00027-of-00030.safetensors", + "model.layers.72.self_attn.k_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.72.self_attn.o_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.72.self_attn.q_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.72.self_attn.v_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.73.input_layernorm.weight": "model-00027-of-00030.safetensors", + "model.layers.73.mlp.down_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.73.mlp.gate_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.73.mlp.up_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.73.post_attention_layernorm.weight": "model-00027-of-00030.safetensors", + "model.layers.73.self_attn.k_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.73.self_attn.o_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.73.self_attn.q_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.73.self_attn.v_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.74.input_layernorm.weight": "model-00028-of-00030.safetensors", + "model.layers.74.mlp.down_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.74.mlp.gate_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.74.mlp.up_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.74.post_attention_layernorm.weight": "model-00028-of-00030.safetensors", + "model.layers.74.self_attn.k_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.74.self_attn.o_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.74.self_attn.q_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.74.self_attn.v_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.75.input_layernorm.weight": "model-00028-of-00030.safetensors", + "model.layers.75.mlp.down_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.75.mlp.gate_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.75.mlp.up_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.75.post_attention_layernorm.weight": "model-00028-of-00030.safetensors", + "model.layers.75.self_attn.k_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.75.self_attn.o_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.75.self_attn.q_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.75.self_attn.v_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.76.input_layernorm.weight": "model-00028-of-00030.safetensors", + "model.layers.76.mlp.down_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.76.mlp.gate_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.76.mlp.up_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.76.post_attention_layernorm.weight": "model-00028-of-00030.safetensors", + "model.layers.76.self_attn.k_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.76.self_attn.o_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.76.self_attn.q_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.76.self_attn.v_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.77.input_layernorm.weight": "model-00029-of-00030.safetensors", + "model.layers.77.mlp.down_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.77.mlp.gate_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.77.mlp.up_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.77.post_attention_layernorm.weight": "model-00029-of-00030.safetensors", + "model.layers.77.self_attn.k_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.77.self_attn.o_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.77.self_attn.q_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.77.self_attn.v_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.78.input_layernorm.weight": "model-00029-of-00030.safetensors", + "model.layers.78.mlp.down_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.78.mlp.gate_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.78.mlp.up_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.78.post_attention_layernorm.weight": "model-00029-of-00030.safetensors", + "model.layers.78.self_attn.k_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.78.self_attn.o_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.78.self_attn.q_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.78.self_attn.v_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.79.input_layernorm.weight": "model-00029-of-00030.safetensors", + "model.layers.79.mlp.down_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.79.mlp.gate_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.79.mlp.up_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.79.post_attention_layernorm.weight": "model-00029-of-00030.safetensors", + "model.layers.79.self_attn.k_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.79.self_attn.o_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.79.self_attn.q_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.79.self_attn.v_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.8.input_layernorm.weight": "model-00004-of-00030.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00004-of-00030.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00030.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00004-of-00030.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00030.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00030.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00030.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00030.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00030.safetensors", + "model.layers.9.input_layernorm.weight": "model-00004-of-00030.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00004-of-00030.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00030.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00004-of-00030.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00030.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00030.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00030.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00030.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00030.safetensors", + "model.norm.weight": "model-00029-of-00030.safetensors" + } +} diff --git a/checkpoint-36/rng_state_0.pth b/checkpoint-36/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..845b3d030ffaa64ffa22691fc49f246ebb3407e1 --- /dev/null +++ b/checkpoint-36/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5ed3e7dbdb967b68fdb8285c5a0a048dba7d4d232cee3a9ed4613fb8c6786f5 +size 15225 diff --git a/checkpoint-36/rng_state_1.pth b/checkpoint-36/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..2e7745a1d5960bacbc91b6fffaf386faba9e1894 --- /dev/null +++ b/checkpoint-36/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:248b8f01c99fe1ab31a8c68cb6bb99a25268a18f610cdde51234b58c12900da1 +size 15225 diff --git a/checkpoint-36/rng_state_10.pth b/checkpoint-36/rng_state_10.pth new file mode 100644 index 0000000000000000000000000000000000000000..e23cc357f1981b881570ef86fbbec74213fbc444 --- /dev/null +++ b/checkpoint-36/rng_state_10.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a31ed0773e2d676af0f73f00ac0b27e550d5ade3f76f2c94f952ff45ec72ea84 +size 15235 diff --git a/checkpoint-36/rng_state_11.pth b/checkpoint-36/rng_state_11.pth new file mode 100644 index 0000000000000000000000000000000000000000..7c8f0043c94042e22e55dd06589aaccb229d1a55 --- /dev/null +++ b/checkpoint-36/rng_state_11.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fa4115a9c6596e67e83e3a47763abe1026f01c8bcbb674cef98b4b3301d384d +size 15235 diff --git a/checkpoint-36/rng_state_12.pth b/checkpoint-36/rng_state_12.pth new file mode 100644 index 0000000000000000000000000000000000000000..41f37c5bf62899fd213f42865d207be71954ae5c --- /dev/null +++ b/checkpoint-36/rng_state_12.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:937b20e918053f5dca79ae2e954568b3f08a6185aa5df6e74ed58e641299da99 +size 15235 diff --git a/checkpoint-36/rng_state_13.pth b/checkpoint-36/rng_state_13.pth new file mode 100644 index 0000000000000000000000000000000000000000..6cb78ed9c37e118d479eb69fc32e7fce8888fce4 --- /dev/null +++ b/checkpoint-36/rng_state_13.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce893865e90139b191aeca366e9fdb2345af1479371ad9725aa29db4a3215714 +size 15235 diff --git a/checkpoint-36/rng_state_14.pth b/checkpoint-36/rng_state_14.pth new file mode 100644 index 0000000000000000000000000000000000000000..6beed520f9bd03cc0e59c58c4e734acdc3fb01bc --- /dev/null +++ b/checkpoint-36/rng_state_14.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ae074290f69414d50818e5020ff931f02bc391cbcdbfc992d819a7a83d3a27f +size 15235 diff --git a/checkpoint-36/rng_state_15.pth b/checkpoint-36/rng_state_15.pth new file mode 100644 index 0000000000000000000000000000000000000000..3880b8d71091cb181faa1604c5b16ff597cfcbe5 --- /dev/null +++ b/checkpoint-36/rng_state_15.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70b40a9d8b148d0cd4db89c829d064d058882d411c28f2e40e4514e5909d3e0c +size 15235 diff --git a/checkpoint-36/rng_state_16.pth b/checkpoint-36/rng_state_16.pth new file mode 100644 index 0000000000000000000000000000000000000000..52a853d02ec7405e0b91053d174600d70b1b2473 --- /dev/null +++ b/checkpoint-36/rng_state_16.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a7d340a63fd7280738a25a3f99f39d81fbae7dbf3b86561ebeeea8412e829b3 +size 15235 diff --git a/checkpoint-36/rng_state_17.pth b/checkpoint-36/rng_state_17.pth new file mode 100644 index 0000000000000000000000000000000000000000..68c13f1730ddd62c6a914474a56d5ca2df4cce9e --- /dev/null +++ b/checkpoint-36/rng_state_17.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a253ea19c96acc58f0f0ae096581549f4ff12f8f02053cf37c97d703029cef85 +size 15235 diff --git a/checkpoint-36/rng_state_18.pth b/checkpoint-36/rng_state_18.pth new file mode 100644 index 0000000000000000000000000000000000000000..da587415c41cfc137ea99cdbe53bac96bb721060 --- /dev/null +++ b/checkpoint-36/rng_state_18.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06cb849e1a6ded244763891d6f14418c505fb9db25c4667a13a2fa51a93e86d3 +size 15235 diff --git a/checkpoint-36/rng_state_19.pth b/checkpoint-36/rng_state_19.pth new file mode 100644 index 0000000000000000000000000000000000000000..f79b923f6091365b69a892811badc1f693ec07bc --- /dev/null +++ b/checkpoint-36/rng_state_19.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2beb90bfae67877f958d8b482f5c164066e0272304d74164771cd8bb3f55fd94 +size 15235 diff --git a/checkpoint-36/rng_state_2.pth b/checkpoint-36/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..a36215a73b69c975ed85ef08d043eeda69575433 --- /dev/null +++ b/checkpoint-36/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62074669aba81c1c8a2f41e03b0359b479719ffca186d2afeb3fdc3cb0fda5e8 +size 15225 diff --git a/checkpoint-36/rng_state_20.pth b/checkpoint-36/rng_state_20.pth new file mode 100644 index 0000000000000000000000000000000000000000..2117b75a7b8bcc488d5ed7e3c37feaf7e931727c --- /dev/null +++ b/checkpoint-36/rng_state_20.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d382b3bac48e07c8623f3850819e4baed1c45846cabceaa6c460ae03d7656293 +size 15235 diff --git a/checkpoint-36/rng_state_21.pth b/checkpoint-36/rng_state_21.pth new file mode 100644 index 0000000000000000000000000000000000000000..69352210f58cd442025a464ff4a6733c276cbb6e --- /dev/null +++ b/checkpoint-36/rng_state_21.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cee71db176692ac948292d0531c72dc7fa5673084f57929d70215adbc5d1789 +size 15235 diff --git a/checkpoint-36/rng_state_22.pth b/checkpoint-36/rng_state_22.pth new file mode 100644 index 0000000000000000000000000000000000000000..0d0d2e9d180e228bece29063d95626a4cf5c35b3 --- /dev/null +++ b/checkpoint-36/rng_state_22.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad497e9c2159308fe8b0bd0ba6209a518e3df99e8595e8063d8c23ffa82d664b +size 15235 diff --git a/checkpoint-36/rng_state_23.pth b/checkpoint-36/rng_state_23.pth new file mode 100644 index 0000000000000000000000000000000000000000..6dbbdb430110d6d39fc2466857641b896eaa55f8 --- /dev/null +++ b/checkpoint-36/rng_state_23.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c70e8f3f219bf3e0b8d6ecb9b629ec66dbf3bac1556d37a0eba77f5b2b92bd3c +size 15235 diff --git a/checkpoint-36/rng_state_24.pth b/checkpoint-36/rng_state_24.pth new file mode 100644 index 0000000000000000000000000000000000000000..ff09f150db04955169ee5dbe6cfe9a976d2b01b3 --- /dev/null +++ b/checkpoint-36/rng_state_24.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b0bac5424d44cd7418fe9e8c47d02022a26e5170f1e9f5daa9c25a4086384e9 +size 15235 diff --git a/checkpoint-36/rng_state_25.pth b/checkpoint-36/rng_state_25.pth new file mode 100644 index 0000000000000000000000000000000000000000..3bda1ea5dd0d93a44ac2fdc60be4b9013fc004f8 --- /dev/null +++ b/checkpoint-36/rng_state_25.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:983093281fbc1e999ae72d4cb10e6b5fb0d863b922308e047f13deede8305251 +size 15235 diff --git a/checkpoint-36/rng_state_26.pth b/checkpoint-36/rng_state_26.pth new file mode 100644 index 0000000000000000000000000000000000000000..e3d5058d17cbd131261b285e32b8e7afcd3ba619 --- /dev/null +++ b/checkpoint-36/rng_state_26.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37471e6522a08007e178d43ad08055269541ddc6fd19299e4ddfef7b2775abbb +size 15235 diff --git a/checkpoint-36/rng_state_27.pth b/checkpoint-36/rng_state_27.pth new file mode 100644 index 0000000000000000000000000000000000000000..189cc177982847fe3a944260bb9321af3b05f9f8 --- /dev/null +++ b/checkpoint-36/rng_state_27.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0672c669cc3d79b39da38d58e24ef7824a257dd4098142e5d12cd8191b139267 +size 15235 diff --git a/checkpoint-36/rng_state_28.pth b/checkpoint-36/rng_state_28.pth new file mode 100644 index 0000000000000000000000000000000000000000..1a3287eafbf56986a8f4fb9e4e2169d3e683bc8e --- /dev/null +++ b/checkpoint-36/rng_state_28.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c0e320e3849da3fce8d8971559a6623ca7fa04d5ee3d56e573aef8b91bac19b +size 15235 diff --git a/checkpoint-36/rng_state_29.pth b/checkpoint-36/rng_state_29.pth new file mode 100644 index 0000000000000000000000000000000000000000..eba4c5abb5b00a8d2261195c2b6d7ae2d2ca7f4c --- /dev/null +++ b/checkpoint-36/rng_state_29.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96787158a75b38b69da5de384a0c466572c171db1bfa2f5071153e6e96847812 +size 15235 diff --git a/checkpoint-36/rng_state_3.pth b/checkpoint-36/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..e83f4e9a9cc18eb150c78db70f8f9c7b9b161734 --- /dev/null +++ b/checkpoint-36/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3980d49b261752741ff62dbd41f222267d41a1adba69c51e66ab38155c44ac8b +size 15225 diff --git a/checkpoint-36/rng_state_30.pth b/checkpoint-36/rng_state_30.pth new file mode 100644 index 0000000000000000000000000000000000000000..58e18fec32c305efa408a3f63046b805f4cdd351 --- /dev/null +++ b/checkpoint-36/rng_state_30.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a06e221ee2d4a7aefa1d6d718833f9fdfaaf574be8663b9aad98e40d4027efe5 +size 15235 diff --git a/checkpoint-36/rng_state_31.pth b/checkpoint-36/rng_state_31.pth new file mode 100644 index 0000000000000000000000000000000000000000..af5333955a88d3287ecbcbf896b8a04b21b3671c --- /dev/null +++ b/checkpoint-36/rng_state_31.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89fb30a398e6065203a7d81716270f1c8667451c796b98a8b0eac439f65bf0b9 +size 15235 diff --git a/checkpoint-36/rng_state_4.pth b/checkpoint-36/rng_state_4.pth new file mode 100644 index 0000000000000000000000000000000000000000..19f5c4b6da29264dabf4acd1372136d3b659d195 --- /dev/null +++ b/checkpoint-36/rng_state_4.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d78d44315bb391ea0221f074566cd19b85a6700ba09dacc5ae343f4a97b19edf +size 15225 diff --git a/checkpoint-36/rng_state_5.pth b/checkpoint-36/rng_state_5.pth new file mode 100644 index 0000000000000000000000000000000000000000..2d14578a0cd04b46881f7b84d6ba61f395aab17c --- /dev/null +++ b/checkpoint-36/rng_state_5.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34085e17b1badb36490ecc5e40f9e8c68c1123a64b6a7f398c1b8dc83a85bb26 +size 15225 diff --git a/checkpoint-36/rng_state_6.pth b/checkpoint-36/rng_state_6.pth new file mode 100644 index 0000000000000000000000000000000000000000..534549c62365f585f2081cfebbbe82a64e171f03 --- /dev/null +++ b/checkpoint-36/rng_state_6.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9284c112cff88ca749b027a620721ed6dd34678c9a3aaa25e7367ddec9e7e9df +size 15225 diff --git a/checkpoint-36/rng_state_7.pth b/checkpoint-36/rng_state_7.pth new file mode 100644 index 0000000000000000000000000000000000000000..3fe6e65442f61ce0b963448c5aaa68c1b1d56e79 --- /dev/null +++ b/checkpoint-36/rng_state_7.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cdd3098269742b740e38c9415b24f6e65b60297d17fd3552ca40bc37a1cfcae +size 15225 diff --git a/checkpoint-36/rng_state_8.pth b/checkpoint-36/rng_state_8.pth new file mode 100644 index 0000000000000000000000000000000000000000..1cd98ea9efebe3e62ad6cdabe1af7e31cbbd1e81 --- /dev/null +++ b/checkpoint-36/rng_state_8.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:def9822579f0a2e9331d44796767e6393d1f86bada96b444306eca210dee6ec1 +size 15225 diff --git a/checkpoint-36/rng_state_9.pth b/checkpoint-36/rng_state_9.pth new file mode 100644 index 0000000000000000000000000000000000000000..26c726bae3401d53e74023483d8318c440665fb6 --- /dev/null +++ b/checkpoint-36/rng_state_9.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb6d237cb2133cc7b028031b21c66ab100f6337e0f627493827006a198997821 +size 15225 diff --git a/checkpoint-36/scheduler.pt b/checkpoint-36/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..2141f5fb3c557e77b3ad1f60aac811bb750bef31 --- /dev/null +++ b/checkpoint-36/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24561c546eb547ded000acf838359da5900ea244e83a180abae31aa89e88bb35 +size 1263 diff --git a/checkpoint-36/special_tokens_map.json b/checkpoint-36/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..278b7f0f84be865c4687700ee7b3c63d89a51e18 --- /dev/null +++ b/checkpoint-36/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-36/tokenizer.json b/checkpoint-36/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..af2d22fff23798bea98b1730ae7cdacaee0b087a --- /dev/null +++ b/checkpoint-36/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ade1dac458f86f9bea8bf35b713f14e1bbed24228429534038e9f7e54ea3e8b6 +size 17208712 diff --git a/checkpoint-36/tokenizer_config.json b/checkpoint-36/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..809816119c8164bd275957569b7c8c708c8d1092 --- /dev/null +++ b/checkpoint-36/tokenizer_config.json @@ -0,0 +1,2064 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "extra_special_tokens": {}, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|end_of_text|>", + "tokenizer_class": "PreTrainedTokenizer" +} diff --git a/checkpoint-36/trainer_state.json b/checkpoint-36/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..1538fb376bec2efb785623fbab6dd723ad20f6e3 --- /dev/null +++ b/checkpoint-36/trainer_state.json @@ -0,0 +1,286 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.0, + "eval_steps": 500, + "global_step": 36, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.027777777777777776, + "grad_norm": 33.53114241539531, + "learning_rate": 5e-06, + "loss": 19.062, + "step": 1 + }, + { + "epoch": 0.05555555555555555, + "grad_norm": 42.84474547203142, + "learning_rate": 4.9914380707064284e-06, + "loss": 18.2499, + "step": 2 + }, + { + "epoch": 0.08333333333333333, + "grad_norm": 62.29220504145651, + "learning_rate": 4.965817444277469e-06, + "loss": 15.809, + "step": 3 + }, + { + "epoch": 0.1111111111111111, + "grad_norm": 22.95196099229298, + "learning_rate": 4.923333109150404e-06, + "loss": 14.897, + "step": 4 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 165.7977927348648, + "learning_rate": 4.864308396768294e-06, + "loss": 14.9434, + "step": 5 + }, + { + "epoch": 0.16666666666666666, + "grad_norm": 45.03607660519894, + "learning_rate": 4.789192520832463e-06, + "loss": 13.6098, + "step": 6 + }, + { + "epoch": 0.19444444444444445, + "grad_norm": 20.126716948755167, + "learning_rate": 4.698557158514988e-06, + "loss": 12.9685, + "step": 7 + }, + { + "epoch": 0.2222222222222222, + "grad_norm": 20.06570448778295, + "learning_rate": 4.593092099650232e-06, + "loss": 12.4369, + "step": 8 + }, + { + "epoch": 0.25, + "grad_norm": 22.65063979014986, + "learning_rate": 4.473599997017701e-06, + "loss": 12.0047, + "step": 9 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 70.91542109599729, + "learning_rate": 4.340990257669732e-06, + "loss": 11.5876, + "step": 10 + }, + { + "epoch": 0.3055555555555556, + "grad_norm": 12.082557329221926, + "learning_rate": 4.196272121794714e-06, + "loss": 11.2749, + "step": 11 + }, + { + "epoch": 0.3333333333333333, + "grad_norm": 12.550168999423985, + "learning_rate": 4.040546981789854e-06, + "loss": 10.7477, + "step": 12 + }, + { + "epoch": 0.3611111111111111, + "grad_norm": 8.827348020968335, + "learning_rate": 3.875e-06, + "loss": 10.2632, + "step": 13 + }, + { + "epoch": 0.3888888888888889, + "grad_norm": 12.394367079322855, + "learning_rate": 3.700891088916574e-06, + "loss": 10.0137, + "step": 14 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 9.286757446404465, + "learning_rate": 3.5195453224827552e-06, + "loss": 9.7255, + "step": 15 + }, + { + "epoch": 0.4444444444444444, + "grad_norm": 10.15211072828483, + "learning_rate": 3.332342851480672e-06, + "loss": 9.2203, + "step": 16 + }, + { + "epoch": 0.4722222222222222, + "grad_norm": 10.426428146187629, + "learning_rate": 3.140708399750594e-06, + "loss": 8.8231, + "step": 17 + }, + { + "epoch": 0.5, + "grad_norm": 10.580506627149108, + "learning_rate": 2.9461004211822313e-06, + "loss": 8.5927, + "step": 18 + }, + { + "epoch": 0.5277777777777778, + "grad_norm": 9.614867948226818, + "learning_rate": 2.7500000000000004e-06, + "loss": 8.4726, + "step": 19 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 7.358015240330244, + "learning_rate": 2.553899578817769e-06, + "loss": 7.9606, + "step": 20 + }, + { + "epoch": 0.5833333333333334, + "grad_norm": 13.145060234596546, + "learning_rate": 2.359291600249407e-06, + "loss": 7.6972, + "step": 21 + }, + { + "epoch": 0.6111111111111112, + "grad_norm": 11.804666920273716, + "learning_rate": 2.167657148519328e-06, + "loss": 7.5072, + "step": 22 + }, + { + "epoch": 0.6388888888888888, + "grad_norm": 8.3548484530948, + "learning_rate": 1.9804546775172455e-06, + "loss": 7.3315, + "step": 23 + }, + { + "epoch": 0.6666666666666666, + "grad_norm": 9.105638737736317, + "learning_rate": 1.799108911083427e-06, + "loss": 7.3131, + "step": 24 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 6.945053218616064, + "learning_rate": 1.6250000000000007e-06, + "loss": 7.0754, + "step": 25 + }, + { + "epoch": 0.7222222222222222, + "grad_norm": 7.24944737566883, + "learning_rate": 1.4594530182101472e-06, + "loss": 6.9281, + "step": 26 + }, + { + "epoch": 0.75, + "grad_norm": 6.41161136997122, + "learning_rate": 1.3037278782052865e-06, + "loss": 6.6446, + "step": 27 + }, + { + "epoch": 0.7777777777777778, + "grad_norm": 5.712279511665765, + "learning_rate": 1.1590097423302683e-06, + "loss": 6.5429, + "step": 28 + }, + { + "epoch": 0.8055555555555556, + "grad_norm": 7.0400325928064085, + "learning_rate": 1.0264000029823e-06, + "loss": 6.4264, + "step": 29 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 5.489757665173993, + "learning_rate": 9.069079003497683e-07, + "loss": 6.3249, + "step": 30 + }, + { + "epoch": 0.8611111111111112, + "grad_norm": 5.7783196208782766, + "learning_rate": 8.01442841485013e-07, + "loss": 6.0586, + "step": 31 + }, + { + "epoch": 0.8888888888888888, + "grad_norm": 4.6024061019552915, + "learning_rate": 7.108074791675378e-07, + "loss": 6.2605, + "step": 32 + }, + { + "epoch": 0.9166666666666666, + "grad_norm": 5.5663806338408, + "learning_rate": 6.356916032317063e-07, + "loss": 6.0488, + "step": 33 + }, + { + "epoch": 0.9444444444444444, + "grad_norm": 4.246970082642438, + "learning_rate": 5.766668908495966e-07, + "loss": 6.1624, + "step": 34 + }, + { + "epoch": 0.9722222222222222, + "grad_norm": 5.215470422371497, + "learning_rate": 5.341825557225321e-07, + "loss": 5.9146, + "step": 35 + }, + { + "epoch": 1.0, + "grad_norm": 7.122849870050112, + "learning_rate": 5.085619292935726e-07, + "loss": 5.8958, + "step": 36 + } + ], + "logging_steps": 1, + "max_steps": 36, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 74680891342848.0, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-36/training_args.bin b/checkpoint-36/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..1285b0a62e3c1abbe7883517f10388cc0c705fda --- /dev/null +++ b/checkpoint-36/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94aa0eaccf48363aa0ce66e0d66748ccb8a33089eb92307bbe1842f7894e4f55 +size 9539 diff --git a/checkpoint-36/zero_to_fp32.py b/checkpoint-36/zero_to_fp32.py new file mode 100644 index 0000000000000000000000000000000000000000..24cc342e78d1a006c782b3a4cd68d9ce786d8fd8 --- /dev/null +++ b/checkpoint-36/zero_to_fp32.py @@ -0,0 +1,604 @@ +#!/usr/bin/env python + +# Copyright (c) Microsoft Corporation. +# SPDX-License-Identifier: Apache-2.0 + +# DeepSpeed Team + +# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets +# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in +# the future. Once extracted, the weights don't require DeepSpeed and can be used in any +# application. +# +# example: python zero_to_fp32.py . pytorch_model.bin + +import argparse +import torch +import glob +import math +import os +import re +from collections import OrderedDict +from dataclasses import dataclass + +# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with +# DeepSpeed data structures it has to be available in the current python environment. +from deepspeed.utils import logger +from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS, + FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES, + FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS) + + +@dataclass +class zero_model_state: + buffers: dict() + param_shapes: dict() + shared_params: list + ds_version: int + frozen_param_shapes: dict() + frozen_param_fragments: dict() + + +debug = 0 + +# load to cpu +device = torch.device('cpu') + + +def atoi(text): + return int(text) if text.isdigit() else text + + +def natural_keys(text): + ''' + alist.sort(key=natural_keys) sorts in human order + http://nedbatchelder.com/blog/200712/human_sorting.html + (See Toothy's implementation in the comments) + ''' + return [atoi(c) for c in re.split(r'(\d+)', text)] + + +def get_model_state_file(checkpoint_dir, zero_stage): + if not os.path.isdir(checkpoint_dir): + raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist") + + # there should be only one file + if zero_stage <= 2: + file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt") + elif zero_stage == 3: + file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt") + + if not os.path.exists(file): + raise FileNotFoundError(f"can't find model states file at '{file}'") + + return file + + +def get_checkpoint_files(checkpoint_dir, glob_pattern): + # XXX: need to test that this simple glob rule works for multi-node setup too + ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys) + + if len(ckpt_files) == 0: + raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'") + + return ckpt_files + + +def get_optim_files(checkpoint_dir): + return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt") + + +def get_model_state_files(checkpoint_dir): + return get_checkpoint_files(checkpoint_dir, "*_model_states.pt") + + +def parse_model_states(files): + zero_model_states = [] + for file in files: + state_dict = torch.load(file, map_location=device) + + if BUFFER_NAMES not in state_dict: + raise ValueError(f"{file} is not a model state checkpoint") + buffer_names = state_dict[BUFFER_NAMES] + if debug: + print("Found buffers:", buffer_names) + + # recover just the buffers while restoring them to fp32 if they were saved in fp16 + buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names} + param_shapes = state_dict[PARAM_SHAPES] + + # collect parameters that are included in param_shapes + param_names = [] + for s in param_shapes: + for name in s.keys(): + param_names.append(name) + + # update with frozen parameters + frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None) + if frozen_param_shapes is not None: + if debug: + print(f"Found frozen_param_shapes: {frozen_param_shapes}") + param_names += list(frozen_param_shapes.keys()) + + # handle shared params + shared_params = [[k, v] for k, v in state_dict["shared_params"].items()] + + ds_version = state_dict.get(DS_VERSION, None) + + frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None) + + z_model_state = zero_model_state(buffers=buffers, + param_shapes=param_shapes, + shared_params=shared_params, + ds_version=ds_version, + frozen_param_shapes=frozen_param_shapes, + frozen_param_fragments=frozen_param_fragments) + zero_model_states.append(z_model_state) + + return zero_model_states + + +def parse_optim_states(files, ds_checkpoint_dir): + + total_files = len(files) + state_dicts = [] + for f in files: + state_dict = torch.load(f, map_location=device) + # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights + # and also handle the case where it was already removed by another helper script + state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None) + state_dicts.append(state_dict) + + if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]: + raise ValueError(f"{files[0]} is not a zero checkpoint") + zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE] + world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT] + + # For ZeRO-2 each param group can have different partition_count as data parallelism for expert + # parameters can be different from data parallelism for non-expert parameters. So we can just + # use the max of the partition_count to get the dp world_size. + + if type(world_size) is list: + world_size = max(world_size) + + if world_size != total_files: + raise ValueError( + f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. " + "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes." + ) + + # the groups are named differently in each stage + if zero_stage <= 2: + fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS + elif zero_stage == 3: + fp32_groups_key = FP32_FLAT_GROUPS + else: + raise ValueError(f"unknown zero stage {zero_stage}") + + if zero_stage <= 2: + fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))] + elif zero_stage == 3: + # if there is more than one param group, there will be multiple flattened tensors - one + # flattened tensor per group - for simplicity merge them into a single tensor + # + # XXX: could make the script more memory efficient for when there are multiple groups - it + # will require matching the sub-lists of param_shapes for each param group flattened tensor + + fp32_flat_groups = [ + torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts)) + ] + + return zero_stage, world_size, fp32_flat_groups + + +def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters): + """ + Returns fp32 state_dict reconstructed from ds checkpoint + + Args: + - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are) + + """ + print(f"Processing zero checkpoint '{ds_checkpoint_dir}'") + + optim_files = get_optim_files(ds_checkpoint_dir) + zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir) + print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}") + + model_files = get_model_state_files(ds_checkpoint_dir) + + zero_model_states = parse_model_states(model_files) + print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}') + + if zero_stage <= 2: + return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states, + exclude_frozen_parameters) + elif zero_stage == 3: + return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states, + exclude_frozen_parameters) + + +def _zero2_merge_frozen_params(state_dict, zero_model_states): + if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0: + return + + frozen_param_shapes = zero_model_states[0].frozen_param_shapes + frozen_param_fragments = zero_model_states[0].frozen_param_fragments + + if debug: + num_elem = sum(s.numel() for s in frozen_param_shapes.values()) + print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}') + + wanted_params = len(frozen_param_shapes) + wanted_numel = sum(s.numel() for s in frozen_param_shapes.values()) + avail_numel = sum([p.numel() for p in frozen_param_fragments.values()]) + print(f'Frozen params: Have {avail_numel} numels to process.') + print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params') + + total_params = 0 + total_numel = 0 + for name, shape in frozen_param_shapes.items(): + total_params += 1 + unpartitioned_numel = shape.numel() + total_numel += unpartitioned_numel + + state_dict[name] = frozen_param_fragments[name] + + if debug: + print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ") + + print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements") + + +def _has_callable(obj, fn): + attr = getattr(obj, fn, None) + return callable(attr) + + +def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states): + param_shapes = zero_model_states[0].param_shapes + + # Reconstruction protocol: + # + # XXX: document this + + if debug: + for i in range(world_size): + for j in range(len(fp32_flat_groups[0])): + print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}") + + # XXX: memory usage doubles here (zero2) + num_param_groups = len(fp32_flat_groups[0]) + merged_single_partition_of_fp32_groups = [] + for i in range(num_param_groups): + merged_partitions = [sd[i] for sd in fp32_flat_groups] + full_single_fp32_vector = torch.cat(merged_partitions, 0) + merged_single_partition_of_fp32_groups.append(full_single_fp32_vector) + avail_numel = sum( + [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups]) + + if debug: + wanted_params = sum([len(shapes) for shapes in param_shapes]) + wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes]) + # not asserting if there is a mismatch due to possible padding + print(f"Have {avail_numel} numels to process.") + print(f"Need {wanted_numel} numels in {wanted_params} params.") + + # params + # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support + # out-of-core computing solution + total_numel = 0 + total_params = 0 + for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups): + offset = 0 + avail_numel = full_single_fp32_vector.numel() + for name, shape in shapes.items(): + + unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape) + total_numel += unpartitioned_numel + total_params += 1 + + if debug: + print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ") + state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape) + offset += unpartitioned_numel + + # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and + # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex + # paddings performed in the code it's almost impossible to predict the exact numbers w/o the + # live optimizer object, so we are checking that the numbers are within the right range + align_to = 2 * world_size + + def zero2_align(x): + return align_to * math.ceil(x / align_to) + + if debug: + print(f"original offset={offset}, avail_numel={avail_numel}") + + offset = zero2_align(offset) + avail_numel = zero2_align(avail_numel) + + if debug: + print(f"aligned offset={offset}, avail_numel={avail_numel}") + + # Sanity check + if offset != avail_numel: + raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong") + + print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements") + + +def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states, + exclude_frozen_parameters): + state_dict = OrderedDict() + + # buffers + buffers = zero_model_states[0].buffers + state_dict.update(buffers) + if debug: + print(f"added {len(buffers)} buffers") + + if not exclude_frozen_parameters: + _zero2_merge_frozen_params(state_dict, zero_model_states) + + _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states) + + # recover shared parameters + for pair in zero_model_states[0].shared_params: + if pair[1] in state_dict: + state_dict[pair[0]] = state_dict[pair[1]] + + return state_dict + + +def zero3_partitioned_param_info(unpartitioned_numel, world_size): + remainder = unpartitioned_numel % world_size + padding_numel = (world_size - remainder) if remainder else 0 + partitioned_numel = math.ceil(unpartitioned_numel / world_size) + return partitioned_numel, padding_numel + + +def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states): + if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0: + return + + if debug: + for i in range(world_size): + num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values()) + print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}') + + frozen_param_shapes = zero_model_states[0].frozen_param_shapes + wanted_params = len(frozen_param_shapes) + wanted_numel = sum(s.numel() for s in frozen_param_shapes.values()) + avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size + print(f'Frozen params: Have {avail_numel} numels to process.') + print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params') + + total_params = 0 + total_numel = 0 + for name, shape in zero_model_states[0].frozen_param_shapes.items(): + total_params += 1 + unpartitioned_numel = shape.numel() + total_numel += unpartitioned_numel + + param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states) + state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape) + + partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size) + + if debug: + print( + f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}" + ) + + print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements") + + +def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states): + param_shapes = zero_model_states[0].param_shapes + avail_numel = fp32_flat_groups[0].numel() * world_size + # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each + # param, re-consolidating each param, while dealing with padding if any + + # merge list of dicts, preserving order + param_shapes = {k: v for d in param_shapes for k, v in d.items()} + + if debug: + for i in range(world_size): + print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}") + + wanted_params = len(param_shapes) + wanted_numel = sum(shape.numel() for shape in param_shapes.values()) + # not asserting if there is a mismatch due to possible padding + avail_numel = fp32_flat_groups[0].numel() * world_size + print(f"Trainable params: Have {avail_numel} numels to process.") + print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.") + + # params + # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support + # out-of-core computing solution + offset = 0 + total_numel = 0 + total_params = 0 + for name, shape in param_shapes.items(): + + unpartitioned_numel = shape.numel() + total_numel += unpartitioned_numel + total_params += 1 + + partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size) + + if debug: + print( + f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}" + ) + + # XXX: memory usage doubles here + state_dict[name] = torch.cat( + tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)), + 0).narrow(0, 0, unpartitioned_numel).view(shape) + offset += partitioned_numel + + offset *= world_size + + # Sanity check + if offset != avail_numel: + raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong") + + print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements") + + +def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states, + exclude_frozen_parameters): + state_dict = OrderedDict() + + # buffers + buffers = zero_model_states[0].buffers + state_dict.update(buffers) + if debug: + print(f"added {len(buffers)} buffers") + + if not exclude_frozen_parameters: + _zero3_merge_frozen_params(state_dict, world_size, zero_model_states) + + _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states) + + # recover shared parameters + for pair in zero_model_states[0].shared_params: + if pair[1] in state_dict: + state_dict[pair[0]] = state_dict[pair[1]] + + return state_dict + + +def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False): + """ + Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with + ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example + via a model hub. + + Args: + - ``checkpoint_dir``: path to the desired checkpoint folder + - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14`` + - ``exclude_frozen_parameters``: exclude frozen parameters + + Returns: + - pytorch ``state_dict`` + + Note: this approach may not work if your application doesn't have sufficient free CPU memory and + you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with + the checkpoint. + + A typical usage might be :: + + from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint + # do the training and checkpoint saving + state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu + model = model.cpu() # move to cpu + model.load_state_dict(state_dict) + # submit to model hub or save the model to share with others + + In this example the ``model`` will no longer be usable in the deepspeed context of the same + application. i.e. you will need to re-initialize the deepspeed engine, since + ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it. + + If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead. + + """ + if tag is None: + latest_path = os.path.join(checkpoint_dir, 'latest') + if os.path.isfile(latest_path): + with open(latest_path, 'r') as fd: + tag = fd.read().strip() + else: + raise ValueError(f"Unable to find 'latest' file at {latest_path}") + + ds_checkpoint_dir = os.path.join(checkpoint_dir, tag) + + if not os.path.isdir(ds_checkpoint_dir): + raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist") + + return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters) + + +def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False): + """ + Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be + loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed. + + Args: + - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``) + - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin) + - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14`` + - ``exclude_frozen_parameters``: exclude frozen parameters + """ + + state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters) + print(f"Saving fp32 state dict to {output_file}") + torch.save(state_dict, output_file) + + +def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None): + """ + 1. Put the provided model to cpu + 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` + 3. Load it into the provided model + + Args: + - ``model``: the model object to update + - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``) + - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14`` + + Returns: + - ``model`: modified model + + Make sure you have plenty of CPU memory available before you call this function. If you don't + have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it + conveniently placed for you in the checkpoint folder. + + A typical usage might be :: + + from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint + model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir) + # submit to model hub or save the model to share with others + + Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context + of the same application. i.e. you will need to re-initialize the deepspeed engine, since + ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it. + + """ + logger.info(f"Extracting fp32 weights") + state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag) + + logger.info(f"Overwriting model with fp32 weights") + model = model.cpu() + model.load_state_dict(state_dict, strict=False) + + return model + + +if __name__ == "__main__": + + parser = argparse.ArgumentParser() + parser.add_argument("checkpoint_dir", + type=str, + help="path to the desired checkpoint folder, e.g., path/checkpoint-12") + parser.add_argument( + "output_file", + type=str, + help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)") + parser.add_argument("-t", + "--tag", + type=str, + default=None, + help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1") + parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters") + parser.add_argument("-d", "--debug", action='store_true', help="enable debug") + args = parser.parse_args() + + debug = args.debug + + convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, + args.output_file, + tag=args.tag, + exclude_frozen_parameters=args.exclude_frozen_parameters) diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..4946add7353eabbc5791c753f11b44b5be1f89b9 --- /dev/null +++ b/config.json @@ -0,0 +1,35 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128009, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 8192, + "initializer_range": 0.02, + "intermediate_size": 28672, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 64, + "num_hidden_layers": 80, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.51.3", + "use_cache": false, + "vocab_size": 128256 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..cd28e19ed02358fd2089710dcd138907439c525b --- /dev/null +++ b/generation_config.json @@ -0,0 +1,8 @@ +{ + "_from_model_config": true, + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": 128009, + "transformers_version": "4.51.3", + "use_cache": false +} diff --git a/model-00001-of-00030.safetensors b/model-00001-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..033593d292ed2fcef62eb2e37f36218b92eac53d --- /dev/null +++ b/model-00001-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4cabb5d59084cfa0516e1ee9733929ab22844b6f28be8133e20a098dd1d40e1 +size 4584408808 diff --git a/model-00002-of-00030.safetensors b/model-00002-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..446e42a65a5f73bc5529b2a8c690902e576df3a0 --- /dev/null +++ b/model-00002-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ddc59c1cc80f904fc1987d24f0c421df9eefaf8074e787b0ee14b67b90a4f8b +size 4664167376 diff --git a/model-00003-of-00030.safetensors b/model-00003-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..71559b7831aad3c8b70f8c0824c5814a3d841844 --- /dev/null +++ b/model-00003-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22513694fe0f63a9a036561351b57c0cfae48fc00cf36c12b662649ce8cb078e +size 4999711704 diff --git a/model-00004-of-00030.safetensors b/model-00004-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bb62ce95c63f77b715a9ff87eef0e9dfc1ceee43 --- /dev/null +++ b/model-00004-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:691e9246e1d9092c75352c97f0eccb8dd02639553042f0f5a51db2531b6c74f3 +size 4966157032 diff --git a/model-00005-of-00030.safetensors b/model-00005-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9f842617523301d625fcc209775b9dc4ad793dc4 --- /dev/null +++ b/model-00005-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1e5a69ab2e16687429773b4b3f681852518869dbbcec8e61caa012064cf0f0a +size 4664134408 diff --git a/model-00006-of-00030.safetensors b/model-00006-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8984b19cd0deb7d687ca52345399b891a8fa8cea --- /dev/null +++ b/model-00006-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e3a1b59792281c7d8ae475ce26bf81cf057c68b243cb62946c97a07dc4594ee +size 4664167408 diff --git a/model-00007-of-00030.safetensors b/model-00007-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..147a1fb80453297df1f994aee9e7697b2980bec3 --- /dev/null +++ b/model-00007-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d748bcea229e07f1eb39f922e2722b88f64ed8b1c927d8468a5a7255722cc1f +size 4664167408 diff --git a/model-00008-of-00030.safetensors b/model-00008-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4d1ef19cb75adaabb878baa1eec5ab10d13cb697 --- /dev/null +++ b/model-00008-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e19bfcd9e549ef045b6f6c65da24295bc1d616fef032cfa3ed3d9d070c2e079 +size 4999711728 diff --git a/model-00009-of-00030.safetensors b/model-00009-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e9f0f96a980427add67024e806820e7b69527fc9 --- /dev/null +++ b/model-00009-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb099d9ff85178472649e0ff678c2c773ce39107fddb3eafaed71031499a2e9b +size 4966157056 diff --git a/model-00010-of-00030.safetensors b/model-00010-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8a43714c237c6900642f8480591d112ecd9b2a7e --- /dev/null +++ b/model-00010-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afbf674bac3fabfce368a362c07ce6657d0cba056611928f06589c35cce5f747 +size 4664134408 diff --git a/model-00011-of-00030.safetensors b/model-00011-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1f85a9ef08e7a95f94f930b46eaa0476b9e3cf92 --- /dev/null +++ b/model-00011-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e42f2db2ecfc3ee540cb85949151df7dbc675ca10fe9bd70937ad3ab97d7fd52 +size 4664167408 diff --git a/model-00012-of-00030.safetensors b/model-00012-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6f196eae0cd1c6e943bc388a4cb803eee86c1949 --- /dev/null +++ b/model-00012-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:677690d7c7590a54095252fe70aa438cbc8e237cf6af60da9069f733bf4ff4ce +size 4664167408 diff --git a/model-00013-of-00030.safetensors b/model-00013-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e7c9ffc9f09d43ca8ccd6a839008b246d96bf38d --- /dev/null +++ b/model-00013-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d703720cd04e2b35c0528029a2ece4a6d621ab43b075d39d929df54202a267ee +size 4999711728 diff --git a/model-00014-of-00030.safetensors b/model-00014-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7ab6485f7a376a23b8d9eaf1398946eb5e1b202a --- /dev/null +++ b/model-00014-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c63ae134dbaa344665789b8b0ef2697a4984bf2a4060b7e9b4d7d2202b5e4ade +size 4966157056 diff --git a/model-00015-of-00030.safetensors b/model-00015-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3a0af656a33007be9948cfd8d6e8b08520736eaa --- /dev/null +++ b/model-00015-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:960ae0a271bb777784dc8cdeb96bb88451e6d6620c1400073fe8d37552c74173 +size 4664134408 diff --git a/model-00016-of-00030.safetensors b/model-00016-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cad213e04f1b91bdd12b51e9917e5f43ac12aba8 --- /dev/null +++ b/model-00016-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44abb02c211d7aded70a0f23c996afdb4505a287155e5b344cb7b2a43ec8640b +size 4664167408 diff --git a/model-00017-of-00030.safetensors b/model-00017-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..42f81fcd692c27a534244a4e7b9d9915008c8685 --- /dev/null +++ b/model-00017-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22aeaf179ffde50a10aecbda803a140446fc76b609e42c05aae821a527dbca75 +size 4664167408 diff --git a/model-00018-of-00030.safetensors b/model-00018-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b9ceb087fa0864768d72f549d3e8967e6d2966ae --- /dev/null +++ b/model-00018-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2798d3191824f504e59750f67a75e4f620956610e79eb5451d32ea4addf2c7f3 +size 4999711728 diff --git a/model-00019-of-00030.safetensors b/model-00019-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..11f761a31b38f451644b476ed434c05b2b0d8a57 --- /dev/null +++ b/model-00019-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd045f6262276c5c417d6d381ea88c24ab7b506398d1172c8a06612eccc55640 +size 4966157056 diff --git a/model-00020-of-00030.safetensors b/model-00020-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4785512474540a8b10253806117ea6e210106d9b --- /dev/null +++ b/model-00020-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0048cf26d97567fac9f8c491373844b43fda8da0293f6eeccf4fb63e44bfea1 +size 4664134408 diff --git a/model-00021-of-00030.safetensors b/model-00021-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bc037f2544096a32cb33c50be7afb12bf071462a --- /dev/null +++ b/model-00021-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07330fd90ed976fb41f9ca657a413ed2d3444b8ed8a7fdca64838706e9834bad +size 4664167408 diff --git a/model-00022-of-00030.safetensors b/model-00022-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..90b9c987a0f69f89fefa37e4fa22cb55087cdac2 --- /dev/null +++ b/model-00022-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d3e63e361e2f21b9a8dc8a7c27a63384371427803ef8a96a6ea7d7c9fdf25bd +size 4664167408 diff --git a/model-00023-of-00030.safetensors b/model-00023-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..17c60a61d31b33f6907d523024ced7b5ecfd3d74 --- /dev/null +++ b/model-00023-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cdbb795719a187775a5edb2431d214e38882a8954d994d3d6fc921f817d2636 +size 4999711728 diff --git a/model-00024-of-00030.safetensors b/model-00024-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2bc3c5d0068473ef5aaaa61e30836eb91af7f059 --- /dev/null +++ b/model-00024-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:756d4e1a1fc22a9d38285c03568635c2a3440455047aa515d7653221f1fa0e18 +size 4966157056 diff --git a/model-00025-of-00030.safetensors b/model-00025-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5d1fb58abd6dc7b4c539f9cdf9c975cd6b0472b8 --- /dev/null +++ b/model-00025-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4b93c281b20705b010ed1af2fb461fae6317c6f3034fad649fde5fed3ac9e80 +size 4664134408 diff --git a/model-00026-of-00030.safetensors b/model-00026-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6d429b5614d0bea063a8a8679e104d9841cba596 --- /dev/null +++ b/model-00026-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cb003d2d89c383dcde824c418a1a832ff908f8ee2b98e8d27cbb3707e363cda +size 4664167408 diff --git a/model-00027-of-00030.safetensors b/model-00027-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5471659e734724652b85d5f8b4c2e932c466b3e9 --- /dev/null +++ b/model-00027-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:043f5027e70ee23b4d65d56106055018ab5746fdfbf856a4a5ca963bede6679b +size 4664167408 diff --git a/model-00028-of-00030.safetensors b/model-00028-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6e3b477a84e9e876cf7add95c8d6fb517b5cd89f --- /dev/null +++ b/model-00028-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08b1d835c29f3f1ed6fb37c22dd449cb0eb587373866a2009959c22d852f1824 +size 4999711728 diff --git a/model-00029-of-00030.safetensors b/model-00029-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..40657cd94cd7484bfe53de232c0b37f31c900862 --- /dev/null +++ b/model-00029-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b02c8b1e7875bd4be22db0d438e28a4ed47c4279914b5cf02200c5bdeccdb0c6 +size 4966173536 diff --git a/model-00030-of-00030.safetensors b/model-00030-of-00030.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a92bae86487bffc2c07e97dd23d54198d8efe174 --- /dev/null +++ b/model-00030-of-00030.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a200ab4a9f6e3c246058e2742fc5a09a7586ac85a2c7215aa5c42bb051df0b5 +size 2101346432 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..37b1afe63cadc4ddce30aaff1b149c2f3083650c --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,730 @@ +{ + "metadata": { + "total_size": 141107412992 + }, + "weight_map": { + "lm_head.weight": "model-00030-of-00030.safetensors", + "model.embed_tokens.weight": "model-00001-of-00030.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00030.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00030.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00030.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00030.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00030.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00030.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00030.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00030.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00030.safetensors", + "model.layers.1.input_layernorm.weight": "model-00002-of-00030.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00030.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00030.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00030.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00030.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00030.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00030.safetensors", + "model.layers.10.input_layernorm.weight": "model-00005-of-00030.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00030.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.11.input_layernorm.weight": "model-00005-of-00030.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00030.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.12.input_layernorm.weight": "model-00006-of-00030.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00030.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00030.safetensors", + "model.layers.13.input_layernorm.weight": "model-00006-of-00030.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00030.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.14.input_layernorm.weight": "model-00006-of-00030.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00030.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.15.input_layernorm.weight": "model-00007-of-00030.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00030.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00030.safetensors", + "model.layers.16.input_layernorm.weight": "model-00007-of-00030.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00030.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.17.input_layernorm.weight": "model-00007-of-00030.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00030.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.18.input_layernorm.weight": "model-00008-of-00030.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00030.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00030.safetensors", + "model.layers.19.input_layernorm.weight": "model-00008-of-00030.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00030.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.2.input_layernorm.weight": "model-00002-of-00030.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00030.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.20.input_layernorm.weight": "model-00008-of-00030.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00030.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.21.input_layernorm.weight": "model-00009-of-00030.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00030.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00030.safetensors", + "model.layers.22.input_layernorm.weight": "model-00009-of-00030.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00030.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.23.input_layernorm.weight": "model-00009-of-00030.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00030.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00030.safetensors", + "model.layers.24.input_layernorm.weight": "model-00010-of-00030.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00030.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.25.input_layernorm.weight": "model-00010-of-00030.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00030.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.26.input_layernorm.weight": "model-00011-of-00030.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00030.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00030.safetensors", + "model.layers.27.input_layernorm.weight": "model-00011-of-00030.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00030.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.28.input_layernorm.weight": "model-00011-of-00030.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00030.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.29.input_layernorm.weight": "model-00012-of-00030.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00012-of-00030.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00030.safetensors", + "model.layers.3.input_layernorm.weight": "model-00002-of-00030.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00030.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.30.input_layernorm.weight": "model-00012-of-00030.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00030.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.31.input_layernorm.weight": "model-00012-of-00030.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00030.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.32.input_layernorm.weight": "model-00013-of-00030.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00013-of-00030.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00012-of-00030.safetensors", + "model.layers.33.input_layernorm.weight": "model-00013-of-00030.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00013-of-00030.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.34.input_layernorm.weight": "model-00013-of-00030.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00013-of-00030.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.35.input_layernorm.weight": "model-00014-of-00030.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00014-of-00030.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00013-of-00030.safetensors", + "model.layers.36.input_layernorm.weight": "model-00014-of-00030.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00014-of-00030.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.37.input_layernorm.weight": "model-00014-of-00030.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00014-of-00030.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00014-of-00030.safetensors", + "model.layers.38.input_layernorm.weight": "model-00015-of-00030.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00015-of-00030.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.39.input_layernorm.weight": "model-00015-of-00030.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00015-of-00030.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.4.input_layernorm.weight": "model-00003-of-00030.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00030.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00030.safetensors", + "model.layers.40.input_layernorm.weight": "model-00016-of-00030.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00016-of-00030.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00015-of-00030.safetensors", + "model.layers.41.input_layernorm.weight": "model-00016-of-00030.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00016-of-00030.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.42.input_layernorm.weight": "model-00016-of-00030.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00016-of-00030.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.43.input_layernorm.weight": "model-00017-of-00030.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00017-of-00030.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00016-of-00030.safetensors", + "model.layers.44.input_layernorm.weight": "model-00017-of-00030.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00017-of-00030.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.45.input_layernorm.weight": "model-00017-of-00030.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00017-of-00030.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.46.input_layernorm.weight": "model-00018-of-00030.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00018-of-00030.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00017-of-00030.safetensors", + "model.layers.47.input_layernorm.weight": "model-00018-of-00030.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00018-of-00030.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.48.input_layernorm.weight": "model-00018-of-00030.safetensors", + "model.layers.48.mlp.down_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.48.mlp.gate_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.48.mlp.up_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00018-of-00030.safetensors", + "model.layers.48.self_attn.k_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.48.self_attn.q_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.48.self_attn.v_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.49.input_layernorm.weight": "model-00019-of-00030.safetensors", + "model.layers.49.mlp.down_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.49.mlp.gate_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.49.mlp.up_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00019-of-00030.safetensors", + "model.layers.49.self_attn.k_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.49.self_attn.o_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.49.self_attn.q_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.49.self_attn.v_proj.weight": "model-00018-of-00030.safetensors", + "model.layers.5.input_layernorm.weight": "model-00003-of-00030.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00030.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.50.input_layernorm.weight": "model-00019-of-00030.safetensors", + "model.layers.50.mlp.down_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.50.mlp.gate_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.50.mlp.up_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00019-of-00030.safetensors", + "model.layers.50.self_attn.k_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.50.self_attn.o_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.50.self_attn.q_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.50.self_attn.v_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.51.input_layernorm.weight": "model-00019-of-00030.safetensors", + "model.layers.51.mlp.down_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.51.mlp.gate_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.51.mlp.up_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00019-of-00030.safetensors", + "model.layers.51.self_attn.k_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.51.self_attn.o_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.51.self_attn.q_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.51.self_attn.v_proj.weight": "model-00019-of-00030.safetensors", + "model.layers.52.input_layernorm.weight": "model-00020-of-00030.safetensors", + "model.layers.52.mlp.down_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.52.mlp.gate_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.52.mlp.up_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00020-of-00030.safetensors", + "model.layers.52.self_attn.k_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.52.self_attn.o_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.52.self_attn.q_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.52.self_attn.v_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.53.input_layernorm.weight": "model-00020-of-00030.safetensors", + "model.layers.53.mlp.down_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.53.mlp.gate_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.53.mlp.up_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00020-of-00030.safetensors", + "model.layers.53.self_attn.k_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.53.self_attn.o_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.53.self_attn.q_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.53.self_attn.v_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.54.input_layernorm.weight": "model-00021-of-00030.safetensors", + "model.layers.54.mlp.down_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.54.mlp.gate_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.54.mlp.up_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00021-of-00030.safetensors", + "model.layers.54.self_attn.k_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.54.self_attn.o_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.54.self_attn.q_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.54.self_attn.v_proj.weight": "model-00020-of-00030.safetensors", + "model.layers.55.input_layernorm.weight": "model-00021-of-00030.safetensors", + "model.layers.55.mlp.down_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.55.mlp.gate_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.55.mlp.up_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00021-of-00030.safetensors", + "model.layers.55.self_attn.k_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.55.self_attn.o_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.55.self_attn.q_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.55.self_attn.v_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.56.input_layernorm.weight": "model-00021-of-00030.safetensors", + "model.layers.56.mlp.down_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.56.mlp.gate_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.56.mlp.up_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00021-of-00030.safetensors", + "model.layers.56.self_attn.k_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.56.self_attn.o_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.56.self_attn.q_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.56.self_attn.v_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.57.input_layernorm.weight": "model-00022-of-00030.safetensors", + "model.layers.57.mlp.down_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.57.mlp.gate_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.57.mlp.up_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00022-of-00030.safetensors", + "model.layers.57.self_attn.k_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.57.self_attn.o_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.57.self_attn.q_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.57.self_attn.v_proj.weight": "model-00021-of-00030.safetensors", + "model.layers.58.input_layernorm.weight": "model-00022-of-00030.safetensors", + "model.layers.58.mlp.down_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.58.mlp.gate_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.58.mlp.up_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00022-of-00030.safetensors", + "model.layers.58.self_attn.k_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.58.self_attn.o_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.58.self_attn.q_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.58.self_attn.v_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.59.input_layernorm.weight": "model-00022-of-00030.safetensors", + "model.layers.59.mlp.down_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.59.mlp.gate_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.59.mlp.up_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00022-of-00030.safetensors", + "model.layers.59.self_attn.k_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.59.self_attn.o_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.59.self_attn.q_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.59.self_attn.v_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.6.input_layernorm.weight": "model-00003-of-00030.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00030.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.60.input_layernorm.weight": "model-00023-of-00030.safetensors", + "model.layers.60.mlp.down_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.60.mlp.gate_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.60.mlp.up_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.60.post_attention_layernorm.weight": "model-00023-of-00030.safetensors", + "model.layers.60.self_attn.k_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.60.self_attn.o_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.60.self_attn.q_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.60.self_attn.v_proj.weight": "model-00022-of-00030.safetensors", + "model.layers.61.input_layernorm.weight": "model-00023-of-00030.safetensors", + "model.layers.61.mlp.down_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.61.mlp.gate_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.61.mlp.up_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.61.post_attention_layernorm.weight": "model-00023-of-00030.safetensors", + "model.layers.61.self_attn.k_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.61.self_attn.o_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.61.self_attn.q_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.61.self_attn.v_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.62.input_layernorm.weight": "model-00023-of-00030.safetensors", + "model.layers.62.mlp.down_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.62.mlp.gate_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.62.mlp.up_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.62.post_attention_layernorm.weight": "model-00023-of-00030.safetensors", + "model.layers.62.self_attn.k_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.62.self_attn.o_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.62.self_attn.q_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.62.self_attn.v_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.63.input_layernorm.weight": "model-00024-of-00030.safetensors", + "model.layers.63.mlp.down_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.63.mlp.gate_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.63.mlp.up_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.63.post_attention_layernorm.weight": "model-00024-of-00030.safetensors", + "model.layers.63.self_attn.k_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.63.self_attn.o_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.63.self_attn.q_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.63.self_attn.v_proj.weight": "model-00023-of-00030.safetensors", + "model.layers.64.input_layernorm.weight": "model-00024-of-00030.safetensors", + "model.layers.64.mlp.down_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.64.mlp.gate_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.64.mlp.up_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.64.post_attention_layernorm.weight": "model-00024-of-00030.safetensors", + "model.layers.64.self_attn.k_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.64.self_attn.o_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.64.self_attn.q_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.64.self_attn.v_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.65.input_layernorm.weight": "model-00024-of-00030.safetensors", + "model.layers.65.mlp.down_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.65.mlp.gate_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.65.mlp.up_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.65.post_attention_layernorm.weight": "model-00024-of-00030.safetensors", + "model.layers.65.self_attn.k_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.65.self_attn.o_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.65.self_attn.q_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.65.self_attn.v_proj.weight": "model-00024-of-00030.safetensors", + "model.layers.66.input_layernorm.weight": "model-00025-of-00030.safetensors", + "model.layers.66.mlp.down_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.66.mlp.gate_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.66.mlp.up_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.66.post_attention_layernorm.weight": "model-00025-of-00030.safetensors", + "model.layers.66.self_attn.k_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.66.self_attn.o_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.66.self_attn.q_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.66.self_attn.v_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.67.input_layernorm.weight": "model-00025-of-00030.safetensors", + "model.layers.67.mlp.down_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.67.mlp.gate_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.67.mlp.up_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.67.post_attention_layernorm.weight": "model-00025-of-00030.safetensors", + "model.layers.67.self_attn.k_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.67.self_attn.o_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.67.self_attn.q_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.67.self_attn.v_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.68.input_layernorm.weight": "model-00026-of-00030.safetensors", + "model.layers.68.mlp.down_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.68.mlp.gate_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.68.mlp.up_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.68.post_attention_layernorm.weight": "model-00026-of-00030.safetensors", + "model.layers.68.self_attn.k_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.68.self_attn.o_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.68.self_attn.q_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.68.self_attn.v_proj.weight": "model-00025-of-00030.safetensors", + "model.layers.69.input_layernorm.weight": "model-00026-of-00030.safetensors", + "model.layers.69.mlp.down_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.69.mlp.gate_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.69.mlp.up_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.69.post_attention_layernorm.weight": "model-00026-of-00030.safetensors", + "model.layers.69.self_attn.k_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.69.self_attn.o_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.69.self_attn.q_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.69.self_attn.v_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.7.input_layernorm.weight": "model-00004-of-00030.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00004-of-00030.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00030.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00004-of-00030.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00030.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00030.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00030.safetensors", + "model.layers.70.input_layernorm.weight": "model-00026-of-00030.safetensors", + "model.layers.70.mlp.down_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.70.mlp.gate_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.70.mlp.up_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.70.post_attention_layernorm.weight": "model-00026-of-00030.safetensors", + "model.layers.70.self_attn.k_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.70.self_attn.o_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.70.self_attn.q_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.70.self_attn.v_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.71.input_layernorm.weight": "model-00027-of-00030.safetensors", + "model.layers.71.mlp.down_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.71.mlp.gate_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.71.mlp.up_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.71.post_attention_layernorm.weight": "model-00027-of-00030.safetensors", + "model.layers.71.self_attn.k_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.71.self_attn.o_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.71.self_attn.q_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.71.self_attn.v_proj.weight": "model-00026-of-00030.safetensors", + "model.layers.72.input_layernorm.weight": "model-00027-of-00030.safetensors", + "model.layers.72.mlp.down_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.72.mlp.gate_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.72.mlp.up_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.72.post_attention_layernorm.weight": "model-00027-of-00030.safetensors", + "model.layers.72.self_attn.k_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.72.self_attn.o_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.72.self_attn.q_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.72.self_attn.v_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.73.input_layernorm.weight": "model-00027-of-00030.safetensors", + "model.layers.73.mlp.down_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.73.mlp.gate_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.73.mlp.up_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.73.post_attention_layernorm.weight": "model-00027-of-00030.safetensors", + "model.layers.73.self_attn.k_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.73.self_attn.o_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.73.self_attn.q_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.73.self_attn.v_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.74.input_layernorm.weight": "model-00028-of-00030.safetensors", + "model.layers.74.mlp.down_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.74.mlp.gate_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.74.mlp.up_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.74.post_attention_layernorm.weight": "model-00028-of-00030.safetensors", + "model.layers.74.self_attn.k_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.74.self_attn.o_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.74.self_attn.q_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.74.self_attn.v_proj.weight": "model-00027-of-00030.safetensors", + "model.layers.75.input_layernorm.weight": "model-00028-of-00030.safetensors", + "model.layers.75.mlp.down_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.75.mlp.gate_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.75.mlp.up_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.75.post_attention_layernorm.weight": "model-00028-of-00030.safetensors", + "model.layers.75.self_attn.k_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.75.self_attn.o_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.75.self_attn.q_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.75.self_attn.v_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.76.input_layernorm.weight": "model-00028-of-00030.safetensors", + "model.layers.76.mlp.down_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.76.mlp.gate_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.76.mlp.up_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.76.post_attention_layernorm.weight": "model-00028-of-00030.safetensors", + "model.layers.76.self_attn.k_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.76.self_attn.o_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.76.self_attn.q_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.76.self_attn.v_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.77.input_layernorm.weight": "model-00029-of-00030.safetensors", + "model.layers.77.mlp.down_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.77.mlp.gate_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.77.mlp.up_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.77.post_attention_layernorm.weight": "model-00029-of-00030.safetensors", + "model.layers.77.self_attn.k_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.77.self_attn.o_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.77.self_attn.q_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.77.self_attn.v_proj.weight": "model-00028-of-00030.safetensors", + "model.layers.78.input_layernorm.weight": "model-00029-of-00030.safetensors", + "model.layers.78.mlp.down_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.78.mlp.gate_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.78.mlp.up_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.78.post_attention_layernorm.weight": "model-00029-of-00030.safetensors", + "model.layers.78.self_attn.k_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.78.self_attn.o_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.78.self_attn.q_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.78.self_attn.v_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.79.input_layernorm.weight": "model-00029-of-00030.safetensors", + "model.layers.79.mlp.down_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.79.mlp.gate_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.79.mlp.up_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.79.post_attention_layernorm.weight": "model-00029-of-00030.safetensors", + "model.layers.79.self_attn.k_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.79.self_attn.o_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.79.self_attn.q_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.79.self_attn.v_proj.weight": "model-00029-of-00030.safetensors", + "model.layers.8.input_layernorm.weight": "model-00004-of-00030.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00004-of-00030.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00030.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00004-of-00030.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00030.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00030.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00030.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00030.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00030.safetensors", + "model.layers.9.input_layernorm.weight": "model-00004-of-00030.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00004-of-00030.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00030.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00004-of-00030.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00030.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00030.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00030.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00030.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00030.safetensors", + "model.norm.weight": "model-00029-of-00030.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..278b7f0f84be865c4687700ee7b3c63d89a51e18 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..af2d22fff23798bea98b1730ae7cdacaee0b087a --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ade1dac458f86f9bea8bf35b713f14e1bbed24228429534038e9f7e54ea3e8b6 +size 17208712 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..809816119c8164bd275957569b7c8c708c8d1092 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2064 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "extra_special_tokens": {}, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|end_of_text|>", + "tokenizer_class": "PreTrainedTokenizer" +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..1285b0a62e3c1abbe7883517f10388cc0c705fda --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94aa0eaccf48363aa0ce66e0d66748ccb8a33089eb92307bbe1842f7894e4f55 +size 9539