diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..52373fe24473b1aa44333d318f578ae6bf04b49b 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,4 @@ 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 +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..8398d8c414bb1151c6dec8a4b01f6961685193b8 --- /dev/null +++ b/README.md @@ -0,0 +1,42 @@ +--- +base_model: [] +library_name: transformers +tags: +- mergekit +- merge + +--- +# prototype-0.4x273 + +This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). + +## Merge Details +### Merge Method + +This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using /workspace/cache/models--BruhzWater--Eden-L3.3-70b-0.3/snapshots/723770586b6603d44ac9bb1d4527e80e86d4dc8b as a base. + +### Models Merged + +The following models were included in the merge: +* /workspace/cache/models--BruhzWater--Liliths-Whisper-L3.3-70b-0.1/snapshots/2f5b9f0307fbb865a3f2e98eefaeb3c86955cb03 +* /workspace/cache/models--BruhzWater--Apocrypha-L3.3-70b-0.3/snapshots/3facb4c0a7b953ff34a5caa90976830bf82a84c2 +* /workspace/cache/models--BruhzWater--Serpents-Tongue-L3.3-70b-0.3/snapshots/d007a7bcc7047d712abb2dfb6ad940fe03cd2047 + +### Configuration + +The following YAML configuration was used to produce this model: + +```yaml +models: + - model: /workspace/cache/models--BruhzWater--Liliths-Whisper-L3.3-70b-0.1/snapshots/2f5b9f0307fbb865a3f2e98eefaeb3c86955cb03 + - model: /workspace/cache/models--BruhzWater--Serpents-Tongue-L3.3-70b-0.3/snapshots/d007a7bcc7047d712abb2dfb6ad940fe03cd2047 + - model: /workspace/cache/models--BruhzWater--Apocrypha-L3.3-70b-0.3/snapshots/3facb4c0a7b953ff34a5caa90976830bf82a84c2 +base_model: /workspace/cache/models--BruhzWater--Eden-L3.3-70b-0.3/snapshots/723770586b6603d44ac9bb1d4527e80e86d4dc8b +merge_method: model_stock +tokenizer: + source: base +chat_template: llama3 +int8_mask: true +pad_to_multiple_of: 8 +dtype: float32 +``` diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..0fcec78aaef89ed38b6a242c7405180036efc138 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,7 @@ +{% 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 %} diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..88b42c6eae4c498106131e13b89d0576e547bf83 --- /dev/null +++ b/config.json @@ -0,0 +1,39 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": [ + 128001, + 128008, + 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": "float32", + "transformers_version": "4.54.0", + "use_cache": true, + "vocab_size": 128256 +} diff --git a/mergekit_config.yml b/mergekit_config.yml new file mode 100644 index 0000000000000000000000000000000000000000..d0979dc4ba0ad903cdcd28e3a9a43ec3190d895b --- /dev/null +++ b/mergekit_config.yml @@ -0,0 +1,12 @@ +models: + - model: /workspace/cache/models--BruhzWater--Liliths-Whisper-L3.3-70b-0.1/snapshots/2f5b9f0307fbb865a3f2e98eefaeb3c86955cb03 + - model: /workspace/cache/models--BruhzWater--Serpents-Tongue-L3.3-70b-0.3/snapshots/d007a7bcc7047d712abb2dfb6ad940fe03cd2047 + - model: /workspace/cache/models--BruhzWater--Apocrypha-L3.3-70b-0.3/snapshots/3facb4c0a7b953ff34a5caa90976830bf82a84c2 +base_model: /workspace/cache/models--BruhzWater--Eden-L3.3-70b-0.3/snapshots/723770586b6603d44ac9bb1d4527e80e86d4dc8b +merge_method: model_stock +tokenizer: + source: base +chat_template: llama3 +int8_mask: true +pad_to_multiple_of: 8 +dtype: float32 \ No newline at end of file diff --git a/model-00001-of-00063.safetensors b/model-00001-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d3296b9502435241b92e9d899552f46f944f84a9 --- /dev/null +++ b/model-00001-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28df82549f8acb5ec8431f43f6fb691cb077a91e45475715ade2a261a409ebbf +size 4697753296 diff --git a/model-00002-of-00063.safetensors b/model-00002-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f34d9add7f6b8e27370c0c751a90aab3b6ca640e --- /dev/null +++ b/model-00002-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31555cfb05861c71ab6b58e7b8300a0d7b6352c38476dbc6d1984786621ba86d +size 4697687552 diff --git a/model-00003-of-00063.safetensors b/model-00003-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d55667f5d80375c1d7baf99bcd587440c4c304cc --- /dev/null +++ b/model-00003-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c8d13c6a6ae43940798a540e18293b8862a6453d7a912bccb179b9b68d62cf8 +size 4563502240 diff --git a/model-00004-of-00063.safetensors b/model-00004-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0c12afdd415a3b628ec517d4acf817fe578287dc --- /dev/null +++ b/model-00004-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04e1a4e71e6d7d3bbcf99d354fbde68ee1b0525d26e24bca1f0f7a924f898ffc +size 2415952488 diff --git a/model-00005-of-00063.safetensors b/model-00005-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f325898a29da4d7cfc4bdd6f1f62972b1e350eb5 --- /dev/null +++ b/model-00005-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc8ca7f82086e70d76371d2ec0a7c2351748cc25fb5123d0c15fe2c3e54bf1ed +size 4236247288 diff --git a/model-00006-of-00063.safetensors b/model-00006-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a6009a3be1fc4a7fa8c65b9c6d5b4e19ef5be932 --- /dev/null +++ b/model-00006-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92cf4f30b8170560c59428d8cbc363402e91d9934e2cdda5bf6acaa823f51845 +size 4160915056 diff --git a/model-00007-of-00063.safetensors b/model-00007-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f9ceb642b7c8f290a204b4be77b5490371196ec4 --- /dev/null +++ b/model-00007-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dcc4cc8b5b927e6b414b9ca02d5b8bc6daa0463daee02d746f61dc82250e52b +size 4362077112 diff --git a/model-00008-of-00063.safetensors b/model-00008-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cea5a0c675d1d0c57959099e257dad8572415b55 --- /dev/null +++ b/model-00008-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc5563d6349648785580eee63f71c87c8d6935183d306ccb81cecb8ff740c3e2 +size 4664133016 diff --git a/model-00009-of-00063.safetensors b/model-00009-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8bfce2c68ec4d2ab8004b9691549614ff1bfcc5a --- /dev/null +++ b/model-00009-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c2a826f4d446e6f4276b4ecdeedba05ec45ee33cbd60acb1779129a61a8eb31 +size 2415952472 diff --git a/model-00010-of-00063.safetensors b/model-00010-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0e29a029401d6861a9da5bc165e5022268c1bd6a --- /dev/null +++ b/model-00010-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f781782a932e3f34999f09165a644a6464d4e162a44dfaaf499503438a58723d +size 4202692744 diff --git a/model-00011-of-00063.safetensors b/model-00011-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f1e59c9895fb09b90553a38e69b61b2c2d319504 --- /dev/null +++ b/model-00011-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97c1fbee1c9b2de3ee8709a50b1958fa817ca79f50cb0624d9d0d38f3cb5fca5 +size 4764961040 diff --git a/model-00012-of-00063.safetensors b/model-00012-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4120eb8835fdadd0f5f883a9dd5449aa8b62fc0b --- /dev/null +++ b/model-00012-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e09e1cf8b2063041de219218589ab2b690e4539aea2de38dfa8eb78b4b52123 +size 4596991016 diff --git a/model-00013-of-00063.safetensors b/model-00013-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3e3d0a22dd2afd1b4d7c909dddca3359df02d812 --- /dev/null +++ b/model-00013-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4316883b0474b4dc9920456e694202f32a078282e81e3b92d3ea497db5a429cb +size 4596958144 diff --git a/model-00014-of-00063.safetensors b/model-00014-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9c48d90dd038dcda3439315f5d22919849239588 --- /dev/null +++ b/model-00014-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cd80f20a98befcf0bd5377e983268f4e6c7607bd3011d95ca30489f9a627df9 +size 4093740200 diff --git a/model-00015-of-00063.safetensors b/model-00015-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c60fbb76d282fcb8f1c061b221eb0e7fd5c6c549 --- /dev/null +++ b/model-00015-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bed1607ce06846ef29b412f3783fc1424dc39406cee963f4741980e5c3074c2 +size 4127360504 diff --git a/model-00016-of-00063.safetensors b/model-00016-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d9915372793f6605da69a939566ae83ac73ca46d --- /dev/null +++ b/model-00016-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0c4c0030a539b950d00e12e155c95c135b9bb433df9d6d45df81bb95194ea47 +size 4395697424 diff --git a/model-00017-of-00063.safetensors b/model-00017-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..86510ba03dea02d5edaf2f8c57d45a77e0abe113 --- /dev/null +++ b/model-00017-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e83947dd52fd237add07da4bb9e52125387e382628d16569385016c234f0995f +size 4898948256 diff --git a/model-00018-of-00063.safetensors b/model-00018-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f7517eef90868f935c03fb9fb266e854139d0f5c --- /dev/null +++ b/model-00018-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fda4558350940799c332b20662a2d7d9059878dfc900b50f5a3211151a52b059 +size 4966188888 diff --git a/model-00019-of-00063.safetensors b/model-00019-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..50d3780152e0995631a8ce1ea4d8689cc984dd11 --- /dev/null +++ b/model-00019-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb1b4df9f5852a27a41bf526f698ccf2921d2a5abbad451190fcc6089cddc828 +size 4731340744 diff --git a/model-00020-of-00063.safetensors b/model-00020-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1f71ee4632a9aeb1fc138e638fbef3801588d06f --- /dev/null +++ b/model-00020-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa128ba82492f2b840c907ef43e3d73d5302fffae9abe1b6642f41a0fdd5d166 +size 4295000896 diff --git a/model-00021-of-00063.safetensors b/model-00021-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8038247c2c0979f53ac4b02902e7db7a271183bf --- /dev/null +++ b/model-00021-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cc5151c3a6736b5e6c9d82244c901444ecc36c72b38353b77bb0651bb24ca55 +size 4295000912 diff --git a/model-00022-of-00063.safetensors b/model-00022-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7f7d80a17dfc2b6fe10824854c56a766fd2891e2 --- /dev/null +++ b/model-00022-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ceaa7d8d6435f1fe166f6d104867e8b4616f78abf3394797c500b59b6c605382 +size 4462905176 diff --git a/model-00023-of-00063.safetensors b/model-00023-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7168bd3a2c3d82b5c5185c01abcbcd260c6675c0 --- /dev/null +++ b/model-00023-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c85d5a4ff83fe3377d6d26973bf640c7fee06bb77b6bfd8734e8a09df74faa87 +size 4664198768 diff --git a/model-00024-of-00063.safetensors b/model-00024-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b5d3f9dbd6b9b5d44234d12fd15943776cba998d --- /dev/null +++ b/model-00024-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b064e2ca56e70fa4b5338845a82733c3f9eb8e28c5a56eca30a6fe257e31d367 +size 4664067240 diff --git a/model-00025-of-00063.safetensors b/model-00025-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2f12389b9f3e8f6c77acda88ec560597f1c2c3fc --- /dev/null +++ b/model-00025-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe626bf6f0e1053abd813cd74a10edc5bb4e547fa604bba45be6fa0ab694e9c9 +size 4899014024 diff --git a/model-00026-of-00063.safetensors b/model-00026-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6ef6068c932608381fc66acf5315f10345a33e30 --- /dev/null +++ b/model-00026-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd8af77841b97ac92f10fe2263d3a260e252aa39d8cce1ae5ebdcf6be6088912 +size 4462938048 diff --git a/model-00027-of-00063.safetensors b/model-00027-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..94754046f3635c44ab83262708374664e65f0ad8 --- /dev/null +++ b/model-00027-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9f6c3eb7fb239e040908998781574746bc508af0c0d6e0f956196e3ea3f999b +size 4898981144 diff --git a/model-00028-of-00063.safetensors b/model-00028-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9ea9a1f7fb5a15b6ba867ade73e4ee9a3b8fd2a5 --- /dev/null +++ b/model-00028-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09d6eda99ce7399c437113a6c041ea2a9d476a7982414821601e79f2c1cd30c3 +size 4328555448 diff --git a/model-00029-of-00063.safetensors b/model-00029-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6bceaef768bda5dffd9dc6f1a54c171979d521b6 --- /dev/null +++ b/model-00029-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c88a2b1434e52d94b4780cba4c9cd6c3cde79962720b57890667b1a403611439 +size 4362208656 diff --git a/model-00030-of-00063.safetensors b/model-00030-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8f2dfca2775176bf9f294be27695387c8152a362 --- /dev/null +++ b/model-00030-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c87f98306b525999925165a246e66e792e7d81659807dff7afbcaedd15e063ad +size 4832003688 diff --git a/model-00031-of-00063.safetensors b/model-00031-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..427c366660e315c46e7d89d067244fd1745468d8 --- /dev/null +++ b/model-00031-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9c235d62ce61ca7804a13894eee98b7d8aaa40ec56246fbf7cb70dc173ff166 +size 4898981152 diff --git a/model-00032-of-00063.safetensors b/model-00032-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..477b7297e1866f3c4d800c44dd41b383e227a3aa --- /dev/null +++ b/model-00032-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3ae11765b804bec43e21c8c724596835a51635fbff1e6630ecff7c18b9bbc73 +size 4227859632 diff --git a/model-00033-of-00063.safetensors b/model-00033-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..21961d975abf5bc73fa7ed218a413177b8b06d5c --- /dev/null +++ b/model-00033-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e8e201fd4b9e104622ecdb815f0c23cef0a6977bdc3519387cdcb06a3650e9f +size 4697819080 diff --git a/model-00034-of-00063.safetensors b/model-00034-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4d921016c39ce7e7e61f121af0ca01d163b319eb --- /dev/null +++ b/model-00034-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ad8429cbcbec747055321dbd519aa5b1a1345f6e84df49458c4e69df36a77e8 +size 4160849288 diff --git a/model-00035-of-00063.safetensors b/model-00035-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1cc2afeb9853bca0b00343a3055e97d66b176d5f --- /dev/null +++ b/model-00035-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d4b0ac0a620530a8c23fc29446c871aa160cb0b5cd14ca804874c1072fdc2b2 +size 4328555448 diff --git a/model-00036-of-00063.safetensors b/model-00036-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a72900e3edf36f7c6945c8791d6d83fc373c4017 --- /dev/null +++ b/model-00036-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1882323501f4816b59dde0f156c688336a075ff1a34f47a8930470d94f791de +size 4831839160 diff --git a/model-00037-of-00063.safetensors b/model-00037-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1bcd874806a26776c1e41e3e333d985da1ecd7dc --- /dev/null +++ b/model-00037-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:822afa97f66a97001037c169da64e465ef6e8b37be6dedc82f60c7881f2e29ab +size 4228089920 diff --git a/model-00038-of-00063.safetensors b/model-00038-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1081f2d653c1f02d0ee0c7c5ed6ed0d1a5f5b789 --- /dev/null +++ b/model-00038-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40ea7f3f8ce9a8ea1c96c7eb4723fce677d5fbed82a2ae93b9e697385b4dbf0c +size 4630611336 diff --git a/model-00039-of-00063.safetensors b/model-00039-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..14383b8804b0029e8309c4a3bc3eef6aa33bb99b --- /dev/null +++ b/model-00039-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acc1c2e9031dc9c50d65629363d4fdadfd0b1fe9552f6d9eb6c78f6ff0eac736 +size 4898948264 diff --git a/model-00040-of-00063.safetensors b/model-00040-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8f78c10c7bb0311d555d880e8c438c099e31040a --- /dev/null +++ b/model-00040-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f6b413c71258c44c7179b7d6d993e8340306e991091c6f7889dcd63ccd6324b +size 4966188872 diff --git a/model-00041-of-00063.safetensors b/model-00041-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1eda9fc5593d7091ff14fcb284d6b0cc3d932cc9 --- /dev/null +++ b/model-00041-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:316024bf4c1a06cd3b9e8c1a6ff0d42615080bbb04ce1576f4073ba404924201 +size 4160882184 diff --git a/model-00042-of-00063.safetensors b/model-00042-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a003203e1204006586216516c8fdd2d3fdfdaa0d --- /dev/null +++ b/model-00042-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:055918a7a0ebc5063ac24f205805a3618df766404d96b52c612980ca63bdcfc7 +size 4362142880 diff --git a/model-00043-of-00063.safetensors b/model-00043-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..625034e5dae4b0e1d212b20294cb1db5c8850339 --- /dev/null +++ b/model-00043-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f518cf3219e78132735ea25b6545fc75dc718378dd25dc54d7e7c70429eb024e +size 4563403592 diff --git a/model-00044-of-00063.safetensors b/model-00044-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b47945f0127c5be6440ce7cb0591c473cd233b15 --- /dev/null +++ b/model-00044-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e9f83946c8e094fbc7f436f11b3af6ccc7dd6edbb1fb35f94fa0679d74eb130 +size 4596991024 diff --git a/model-00045-of-00063.safetensors b/model-00045-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..34ca92a4ad075496595c4617a318c17cd4b97e32 --- /dev/null +++ b/model-00045-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d19bab4996e40c76eb31291f1dc4ccdefa252ecdc33ac2016be0ee283989c0ed +size 4261644448 diff --git a/model-00046-of-00063.safetensors b/model-00046-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f85187a96dc83162767f57b405fd2d42959c6886 --- /dev/null +++ b/model-00046-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e143f7b070a79898dfec2843bb941b3c38205bd4e5e550ab4b84fc846788eed4 +size 4597023912 diff --git a/model-00047-of-00063.safetensors b/model-00047-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2d0671bb4acc98ad2cd7a77a3e81c6759f83d0a9 --- /dev/null +++ b/model-00047-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60813b3fb02905e378254fc610752700c5f2a7adcbeb2c8ee922d703f0bb9511 +size 4194305080 diff --git a/model-00048-of-00063.safetensors b/model-00048-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9988f867045da71d3a525e8a86551ca2d646a545 --- /dev/null +++ b/model-00048-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e44f359b459d8361cefe2504306df17e6c63dc64181b05ac995584dc2dc50b15 +size 4462970928 diff --git a/model-00049-of-00063.safetensors b/model-00049-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..601974c598879b3da27a56c90e1d57f55f315ddc --- /dev/null +++ b/model-00049-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f551331bccad86887323b118055ee13c58107f9243509f3bfae5bb049858e47e +size 4160816408 diff --git a/model-00050-of-00063.safetensors b/model-00050-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..17431039afa829839ac98c79cd370df475791747 --- /dev/null +++ b/model-00050-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:632208099891235e2c06c6ab5b86d481ce4d39a42c1ae723b71562f7580d8a6c +size 4328555448 diff --git a/model-00051-of-00063.safetensors b/model-00051-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6180cde5649765458994a0ed1fbd10257b5124a3 --- /dev/null +++ b/model-00051-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b48269b1f24ca8e2a24bc2387ef6502bcf4af0b0f249bf54cf9648937c982e2 +size 4831839168 diff --git a/model-00052-of-00063.safetensors b/model-00052-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3ac6cbc83a7b9795ebc5d0072e1782855f01828e --- /dev/null +++ b/model-00052-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed2e832962ddbcd7d7bc65de2e61b1608c830f8a2e211d991715706e4e29856a +size 4362175776 diff --git a/model-00053-of-00063.safetensors b/model-00053-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ceec7269cf7a075c037ce09b6ec9e630f0e58f4a --- /dev/null +++ b/model-00053-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c014e00e6d7a768228776d53d564cc6ab5a4eb2d88d9ffc098c1caf8ab6a0603 +size 4865525336 diff --git a/model-00054-of-00063.safetensors b/model-00054-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e86a3b1a245a674ada81335ab6d83a18012e012e --- /dev/null +++ b/model-00054-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64e8356f794e28e906a04a453527efbe065b3d1b090db1c667d05f6b38210c88 +size 4496393840 diff --git a/model-00055-of-00063.safetensors b/model-00055-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ef184bcadeca79368b6002193f03eb057c8e32a1 --- /dev/null +++ b/model-00055-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64c3e849a235790486daa8cb4184484ed1d80134a12165774fb48178e6f8478a +size 4966057360 diff --git a/model-00056-of-00063.safetensors b/model-00056-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..99441139bf61b1875e05ca19214f411bfa022536 --- /dev/null +++ b/model-00056-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb491218f15ee220dece1b462a3d057b63b3b98e1dbee1c536f16d04df8ed02f +size 4395796064 diff --git a/model-00057-of-00063.safetensors b/model-00057-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2a0e520fd67033697e780994e2adba4268623c3a --- /dev/null +++ b/model-00057-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c4d808c8601da334d1d2aa9cf48843ce774343f390a6cc3480da55a1e7bc43e +size 4429350616 diff --git a/model-00058-of-00063.safetensors b/model-00058-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..876844e9294ce68a47491f270d2246836e0afaba --- /dev/null +++ b/model-00058-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8fb49a49c2ab234bc6ffc3ddc488b1acb0d6c5ee6015f9e4fbf25265bb0b0aa +size 4563403592 diff --git a/model-00059-of-00063.safetensors b/model-00059-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..be1ef6b231f0827de7ae0078c5361feb9477b96c --- /dev/null +++ b/model-00059-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:741969a4bcc6551cfb94d60ffc0ff131c308254eede2d9f90b9f1c54b42e1532 +size 4630578464 diff --git a/model-00060-of-00063.safetensors b/model-00060-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0de63e75a1ef481486659cadcaf205cc63d92c19 --- /dev/null +++ b/model-00060-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8e7d8dfc2b4d32663bab4b0c95b3892769f46c9a330d6cb2175882bb2cd8bb8 +size 4831937920 diff --git a/model-00061-of-00063.safetensors b/model-00061-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7ef24dfd66b3a64deae8fd4f6b2d0c8c62fbbd2e --- /dev/null +++ b/model-00061-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f32328b39f924f52201b59e5fa484517fdf6c57289a041db9562323ac5b2bd37 +size 4865558128 diff --git a/model-00062-of-00063.safetensors b/model-00062-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..aaa7a10e067f0f014b042c2ffa24ed92a983b72b --- /dev/null +++ b/model-00062-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:461e12bf0752ff8f4ded45af1c52376f4aa97c263ecf86a9bfc60edfb313ab7c +size 4731176320 diff --git a/model-00063-of-00063.safetensors b/model-00063-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9b474d46e2ed57d648e68b033ef5e4d82037a2c8 --- /dev/null +++ b/model-00063-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02199e7d1ee7133e1a551727ce77b2b8c7576f0d0e9ab98a13e9e6fdc79e3483 +size 4932667192 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..350bc5b7cf47747c1331cdf64ac76978814b7854 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1 @@ +{"metadata": {"mergekit_version": "0.1.3"}, "weight_map": {"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00063.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00063.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00063.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00063.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00063.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00063.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00063.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00063.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00063.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00063.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00063.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00063.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00063.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00063.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00063.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00063.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00063.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00063.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00063.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00063.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00063.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00063.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00063.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00063.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00063.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00063.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00063.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00063.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00063.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00063.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00063.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00063.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00063.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00063.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00063.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00063.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00063.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00063.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00063.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00063.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00063.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00063.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00063.safetensors", "lm_head.weight": "model-00005-of-00063.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00063.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00006-of-00063.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00063.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00006-of-00063.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00063.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00063.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00006-of-00063.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00063.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00063.safetensors", "model.layers.14.input_layernorm.weight": "model-00006-of-00063.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00063.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00063.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00063.safetensors", "model.layers.16.input_layernorm.weight": "model-00006-of-00063.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00063.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00063.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00063.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00007-of-00063.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00063.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00007-of-00063.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00007-of-00063.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00063.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00063.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00008-of-00063.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00063.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00063.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00008-of-00063.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00063.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00063.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00063.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00063.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00063.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00063.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00063.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00063.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00009-of-00063.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00063.safetensors", "model.layers.17.input_layernorm.weight": "model-00009-of-00063.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00063.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00009-of-00063.safetensors", "model.embed_tokens.weight": "model-00010-of-00063.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00011-of-00063.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00011-of-00063.safetensors", "model.layers.18.input_layernorm.weight": "model-00011-of-00063.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00011-of-00063.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00011-of-00063.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00011-of-00063.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00011-of-00063.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00063.safetensors", "model.layers.11.input_layernorm.weight": "model-00011-of-00063.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00011-of-00063.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00011-of-00063.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00011-of-00063.safetensors", "model.layers.19.input_layernorm.weight": "model-00011-of-00063.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00011-of-00063.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00011-of-00063.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00011-of-00063.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00011-of-00063.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00011-of-00063.safetensors", "model.layers.2.input_layernorm.weight": "model-00011-of-00063.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00011-of-00063.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00012-of-00063.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00012-of-00063.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00012-of-00063.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00012-of-00063.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00012-of-00063.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00012-of-00063.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00012-of-00063.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00012-of-00063.safetensors", "model.layers.21.input_layernorm.weight": "model-00012-of-00063.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00013-of-00063.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00013-of-00063.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00013-of-00063.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00063.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00013-of-00063.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00013-of-00063.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00013-of-00063.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00013-of-00063.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00014-of-00063.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00014-of-00063.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00014-of-00063.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00014-of-00063.safetensors", "model.layers.22.input_layernorm.weight": "model-00014-of-00063.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00014-of-00063.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00014-of-00063.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00014-of-00063.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00014-of-00063.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00014-of-00063.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00015-of-00063.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00015-of-00063.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00015-of-00063.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00015-of-00063.safetensors", "model.layers.23.input_layernorm.weight": "model-00015-of-00063.safetensors", "model.layers.24.input_layernorm.weight": "model-00015-of-00063.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00015-of-00063.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00015-of-00063.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00015-of-00063.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00015-of-00063.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00015-of-00063.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00015-of-00063.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00015-of-00063.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00016-of-00063.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00016-of-00063.safetensors", "model.layers.25.input_layernorm.weight": "model-00016-of-00063.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00016-of-00063.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00016-of-00063.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00016-of-00063.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00016-of-00063.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00016-of-00063.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00016-of-00063.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00016-of-00063.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00016-of-00063.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00017-of-00063.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00017-of-00063.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00017-of-00063.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00017-of-00063.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00017-of-00063.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00017-of-00063.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00017-of-00063.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00017-of-00063.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00017-of-00063.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00017-of-00063.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00018-of-00063.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00018-of-00063.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00018-of-00063.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00018-of-00063.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00018-of-00063.safetensors", "model.layers.26.input_layernorm.weight": "model-00018-of-00063.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00018-of-00063.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00018-of-00063.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00018-of-00063.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00018-of-00063.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00018-of-00063.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00018-of-00063.safetensors", "model.layers.27.input_layernorm.weight": "model-00018-of-00063.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00018-of-00063.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00018-of-00063.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00018-of-00063.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00019-of-00063.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00019-of-00063.safetensors", "model.layers.20.input_layernorm.weight": "model-00019-of-00063.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00019-of-00063.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00019-of-00063.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00019-of-00063.safetensors", "model.layers.28.input_layernorm.weight": "model-00019-of-00063.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00019-of-00063.safetensors", "model.layers.29.input_layernorm.weight": "model-00019-of-00063.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00019-of-00063.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00019-of-00063.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00019-of-00063.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00019-of-00063.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00019-of-00063.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00019-of-00063.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00019-of-00063.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00019-of-00063.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00020-of-00063.safetensors", "model.layers.30.input_layernorm.weight": "model-00020-of-00063.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00020-of-00063.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00020-of-00063.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00020-of-00063.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00020-of-00063.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00020-of-00063.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00021-of-00063.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00021-of-00063.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00021-of-00063.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00021-of-00063.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00021-of-00063.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00021-of-00063.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00021-of-00063.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00022-of-00063.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00022-of-00063.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00022-of-00063.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00022-of-00063.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00022-of-00063.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00022-of-00063.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00022-of-00063.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00022-of-00063.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00022-of-00063.safetensors", "model.layers.32.input_layernorm.weight": "model-00022-of-00063.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00022-of-00063.safetensors", "model.layers.31.input_layernorm.weight": "model-00022-of-00063.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00022-of-00063.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00022-of-00063.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00022-of-00063.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00022-of-00063.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00023-of-00063.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00023-of-00063.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00023-of-00063.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00023-of-00063.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00023-of-00063.safetensors", "model.layers.33.input_layernorm.weight": "model-00023-of-00063.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00023-of-00063.safetensors", "model.layers.34.input_layernorm.weight": "model-00023-of-00063.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00023-of-00063.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00023-of-00063.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00023-of-00063.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00023-of-00063.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00023-of-00063.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00023-of-00063.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00024-of-00063.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00024-of-00063.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00024-of-00063.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00024-of-00063.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00024-of-00063.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00024-of-00063.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00024-of-00063.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00024-of-00063.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00024-of-00063.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00024-of-00063.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00025-of-00063.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00025-of-00063.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00025-of-00063.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00025-of-00063.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00025-of-00063.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00025-of-00063.safetensors", "model.layers.35.input_layernorm.weight": "model-00025-of-00063.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00025-of-00063.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00025-of-00063.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00025-of-00063.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00025-of-00063.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00025-of-00063.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00026-of-00063.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00026-of-00063.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00026-of-00063.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00026-of-00063.safetensors", "model.layers.3.input_layernorm.weight": "model-00026-of-00063.safetensors", "model.layers.36.input_layernorm.weight": "model-00026-of-00063.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00026-of-00063.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00026-of-00063.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00026-of-00063.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00026-of-00063.safetensors", "model.layers.37.input_layernorm.weight": "model-00026-of-00063.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00026-of-00063.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00026-of-00063.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00026-of-00063.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00026-of-00063.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00026-of-00063.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00026-of-00063.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00027-of-00063.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00027-of-00063.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00027-of-00063.safetensors", "model.layers.38.input_layernorm.weight": "model-00027-of-00063.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00027-of-00063.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00027-of-00063.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00027-of-00063.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00027-of-00063.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00027-of-00063.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00027-of-00063.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00027-of-00063.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00028-of-00063.safetensors", "model.layers.4.input_layernorm.weight": "model-00028-of-00063.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00028-of-00063.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00028-of-00063.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00028-of-00063.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00028-of-00063.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00028-of-00063.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00028-of-00063.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00029-of-00063.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00029-of-00063.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00029-of-00063.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00029-of-00063.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00029-of-00063.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00029-of-00063.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00029-of-00063.safetensors", "model.layers.41.input_layernorm.weight": "model-00029-of-00063.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00029-of-00063.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00029-of-00063.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00029-of-00063.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00029-of-00063.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00030-of-00063.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00030-of-00063.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00030-of-00063.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00030-of-00063.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00030-of-00063.safetensors", "model.layers.40.input_layernorm.weight": "model-00030-of-00063.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00030-of-00063.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00030-of-00063.safetensors", "model.layers.42.input_layernorm.weight": "model-00030-of-00063.safetensors", "model.layers.43.input_layernorm.weight": "model-00030-of-00063.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00030-of-00063.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00030-of-00063.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00030-of-00063.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00030-of-00063.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00031-of-00063.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00031-of-00063.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00031-of-00063.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00031-of-00063.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00031-of-00063.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00031-of-00063.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00031-of-00063.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00031-of-00063.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00031-of-00063.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00031-of-00063.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00031-of-00063.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00032-of-00063.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00032-of-00063.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00032-of-00063.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00032-of-00063.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00032-of-00063.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00032-of-00063.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00032-of-00063.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00032-of-00063.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00032-of-00063.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00032-of-00063.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00033-of-00063.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00033-of-00063.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00033-of-00063.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00033-of-00063.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00033-of-00063.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00033-of-00063.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00033-of-00063.safetensors", "model.layers.44.input_layernorm.weight": "model-00033-of-00063.safetensors", "model.layers.45.input_layernorm.weight": "model-00033-of-00063.safetensors", "model.layers.39.input_layernorm.weight": "model-00033-of-00063.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00033-of-00063.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00033-of-00063.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00033-of-00063.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00033-of-00063.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00033-of-00063.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00033-of-00063.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00033-of-00063.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00034-of-00063.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00034-of-00063.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00034-of-00063.safetensors", "model.layers.46.input_layernorm.weight": "model-00034-of-00063.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00034-of-00063.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00034-of-00063.safetensors", "model.layers.47.input_layernorm.weight": "model-00034-of-00063.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00034-of-00063.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00034-of-00063.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00034-of-00063.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00034-of-00063.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00034-of-00063.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00035-of-00063.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00035-of-00063.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00035-of-00063.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00035-of-00063.safetensors", "model.layers.49.input_layernorm.weight": "model-00035-of-00063.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00035-of-00063.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00035-of-00063.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00035-of-00063.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00036-of-00063.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00036-of-00063.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00036-of-00063.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00036-of-00063.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00036-of-00063.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00036-of-00063.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00036-of-00063.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00036-of-00063.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00037-of-00063.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00037-of-00063.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00037-of-00063.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00037-of-00063.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00037-of-00063.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00037-of-00063.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00037-of-00063.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00037-of-00063.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00037-of-00063.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00037-of-00063.safetensors", "model.layers.5.input_layernorm.weight": "model-00037-of-00063.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00037-of-00063.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00037-of-00063.safetensors", "model.layers.50.input_layernorm.weight": "model-00037-of-00063.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00037-of-00063.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00037-of-00063.safetensors", "model.layers.51.input_layernorm.weight": "model-00037-of-00063.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00037-of-00063.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00038-of-00063.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00038-of-00063.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00038-of-00063.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00038-of-00063.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00038-of-00063.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00038-of-00063.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00038-of-00063.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00038-of-00063.safetensors", "model.layers.52.input_layernorm.weight": "model-00038-of-00063.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00038-of-00063.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00038-of-00063.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00038-of-00063.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00039-of-00063.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00039-of-00063.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00039-of-00063.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00039-of-00063.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00039-of-00063.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00039-of-00063.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00039-of-00063.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00039-of-00063.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00039-of-00063.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00039-of-00063.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00040-of-00063.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00040-of-00063.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00040-of-00063.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00040-of-00063.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00040-of-00063.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00040-of-00063.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00040-of-00063.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00040-of-00063.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00040-of-00063.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00040-of-00063.safetensors", "model.layers.53.input_layernorm.weight": "model-00040-of-00063.safetensors", "model.layers.54.input_layernorm.weight": "model-00040-of-00063.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00040-of-00063.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00040-of-00063.safetensors", "model.layers.48.input_layernorm.weight": "model-00040-of-00063.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00040-of-00063.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00041-of-00063.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00041-of-00063.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00041-of-00063.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00041-of-00063.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00041-of-00063.safetensors", "model.layers.55.input_layernorm.weight": "model-00041-of-00063.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00041-of-00063.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00041-of-00063.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00041-of-00063.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00041-of-00063.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00041-of-00063.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00041-of-00063.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00041-of-00063.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00042-of-00063.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00042-of-00063.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00042-of-00063.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00042-of-00063.safetensors", "model.layers.56.input_layernorm.weight": "model-00042-of-00063.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00042-of-00063.safetensors", "model.layers.58.input_layernorm.weight": "model-00042-of-00063.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00042-of-00063.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00042-of-00063.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00042-of-00063.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00043-of-00063.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00043-of-00063.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00043-of-00063.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00043-of-00063.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00043-of-00063.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00043-of-00063.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00043-of-00063.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00044-of-00063.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00044-of-00063.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00044-of-00063.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00044-of-00063.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00044-of-00063.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00044-of-00063.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00044-of-00063.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00044-of-00063.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00044-of-00063.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00045-of-00063.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00045-of-00063.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00045-of-00063.safetensors", "model.layers.59.input_layernorm.weight": "model-00045-of-00063.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00045-of-00063.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00045-of-00063.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00045-of-00063.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00045-of-00063.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00045-of-00063.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00045-of-00063.safetensors", "model.layers.6.input_layernorm.weight": "model-00045-of-00063.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00045-of-00063.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00045-of-00063.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00045-of-00063.safetensors", "model.layers.60.input_layernorm.weight": "model-00045-of-00063.safetensors", "model.layers.61.input_layernorm.weight": "model-00045-of-00063.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00045-of-00063.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00045-of-00063.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00045-of-00063.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00046-of-00063.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00046-of-00063.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00046-of-00063.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00046-of-00063.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00046-of-00063.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00046-of-00063.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00046-of-00063.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00046-of-00063.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00046-of-00063.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00046-of-00063.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00047-of-00063.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00047-of-00063.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00047-of-00063.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00047-of-00063.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00047-of-00063.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00047-of-00063.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00047-of-00063.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00047-of-00063.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00047-of-00063.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00048-of-00063.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00048-of-00063.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00048-of-00063.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00048-of-00063.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00048-of-00063.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00048-of-00063.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00048-of-00063.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00048-of-00063.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00048-of-00063.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00048-of-00063.safetensors", "model.layers.62.input_layernorm.weight": "model-00048-of-00063.safetensors", "model.layers.63.input_layernorm.weight": "model-00048-of-00063.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00048-of-00063.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00048-of-00063.safetensors", "model.layers.64.input_layernorm.weight": "model-00048-of-00063.safetensors", "model.layers.57.input_layernorm.weight": "model-00048-of-00063.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00048-of-00063.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00048-of-00063.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00049-of-00063.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00049-of-00063.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00049-of-00063.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00049-of-00063.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00049-of-00063.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00049-of-00063.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00049-of-00063.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00049-of-00063.safetensors", "model.layers.65.input_layernorm.weight": "model-00049-of-00063.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00049-of-00063.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00049-of-00063.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00050-of-00063.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00050-of-00063.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00050-of-00063.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00050-of-00063.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00050-of-00063.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00050-of-00063.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00050-of-00063.safetensors", "model.layers.67.input_layernorm.weight": "model-00050-of-00063.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00051-of-00063.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00051-of-00063.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00051-of-00063.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00051-of-00063.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00051-of-00063.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00051-of-00063.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00051-of-00063.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00051-of-00063.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00052-of-00063.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00052-of-00063.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00052-of-00063.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00052-of-00063.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00052-of-00063.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00052-of-00063.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00052-of-00063.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00052-of-00063.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00052-of-00063.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00052-of-00063.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00052-of-00063.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00053-of-00063.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00053-of-00063.safetensors", "model.layers.68.input_layernorm.weight": "model-00053-of-00063.safetensors", "model.layers.69.input_layernorm.weight": "model-00053-of-00063.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00053-of-00063.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00053-of-00063.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00053-of-00063.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00053-of-00063.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00053-of-00063.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00053-of-00063.safetensors", "model.layers.7.input_layernorm.weight": "model-00053-of-00063.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00053-of-00063.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00053-of-00063.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00053-of-00063.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00054-of-00063.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00054-of-00063.safetensors", "model.layers.70.input_layernorm.weight": "model-00054-of-00063.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00054-of-00063.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00054-of-00063.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00054-of-00063.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00054-of-00063.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00054-of-00063.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00054-of-00063.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00054-of-00063.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00054-of-00063.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00054-of-00063.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00054-of-00063.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00054-of-00063.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00055-of-00063.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00055-of-00063.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00055-of-00063.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00055-of-00063.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00055-of-00063.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00055-of-00063.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00055-of-00063.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00055-of-00063.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00055-of-00063.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00055-of-00063.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00055-of-00063.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00055-of-00063.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00056-of-00063.safetensors", "model.layers.71.input_layernorm.weight": "model-00056-of-00063.safetensors", "model.layers.72.input_layernorm.weight": "model-00056-of-00063.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00056-of-00063.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00056-of-00063.safetensors", "model.layers.73.input_layernorm.weight": "model-00056-of-00063.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00056-of-00063.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00056-of-00063.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00056-of-00063.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00056-of-00063.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00056-of-00063.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00056-of-00063.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00056-of-00063.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00056-of-00063.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00057-of-00063.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00057-of-00063.safetensors", "model.layers.66.input_layernorm.weight": "model-00057-of-00063.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00057-of-00063.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00057-of-00063.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00057-of-00063.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00057-of-00063.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00057-of-00063.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00057-of-00063.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00057-of-00063.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00057-of-00063.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00057-of-00063.safetensors", "model.layers.74.input_layernorm.weight": "model-00057-of-00063.safetensors", "model.layers.76.input_layernorm.weight": "model-00057-of-00063.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00057-of-00063.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00058-of-00063.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00058-of-00063.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00058-of-00063.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00058-of-00063.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00058-of-00063.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00058-of-00063.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00058-of-00063.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00059-of-00063.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00059-of-00063.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00059-of-00063.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00059-of-00063.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00059-of-00063.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00059-of-00063.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00059-of-00063.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00059-of-00063.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00059-of-00063.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00059-of-00063.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00059-of-00063.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00060-of-00063.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00060-of-00063.safetensors", "model.layers.78.input_layernorm.weight": "model-00060-of-00063.safetensors", "model.layers.77.input_layernorm.weight": "model-00060-of-00063.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00060-of-00063.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00060-of-00063.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00060-of-00063.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00060-of-00063.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00060-of-00063.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00060-of-00063.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00060-of-00063.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00060-of-00063.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00061-of-00063.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00061-of-00063.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00061-of-00063.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00061-of-00063.safetensors", "model.layers.79.input_layernorm.weight": "model-00061-of-00063.safetensors", "model.layers.8.input_layernorm.weight": "model-00061-of-00063.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00061-of-00063.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00061-of-00063.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00061-of-00063.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00061-of-00063.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00061-of-00063.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00061-of-00063.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00061-of-00063.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00061-of-00063.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00062-of-00063.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00062-of-00063.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00062-of-00063.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00062-of-00063.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00062-of-00063.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00062-of-00063.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00062-of-00063.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00062-of-00063.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00062-of-00063.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00062-of-00063.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00062-of-00063.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00062-of-00063.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00063-of-00063.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00063-of-00063.safetensors", "model.layers.9.input_layernorm.weight": "model-00063-of-00063.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00063-of-00063.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00063-of-00063.safetensors", "model.norm.weight": "model-00063-of-00063.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00063-of-00063.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00063-of-00063.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00063-of-00063.safetensors", "model.layers.75.input_layernorm.weight": "model-00063-of-00063.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00063-of-00063.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00063-of-00063.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00063-of-00063.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00063-of-00063.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00063-of-00063.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00063-of-00063.safetensors"}} \ No newline at end of file diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..3c1d04911c269b925af977a3151c9704e990e4d0 --- /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": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..c68051fe3c4d23234a59316bc52d21f6e3a4182c --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2063 @@ +{ + "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|>", + "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": "<|finetune_right_pad_id|>", + "tokenizer_class": "PreTrainedTokenizerFast" +}