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..8ca57fcc332e1e90cf9e37107266302efe4e01af --- /dev/null +++ b/README.md @@ -0,0 +1,47 @@ +--- +base_model: [] +library_name: transformers +tags: +- mergekit +- merge + +--- +# prototype-0.4x299 + +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 [SCE](https://arxiv.org/abs/2408.07990) merge method using /workspace/prototype-0.4x295 as a base. + +### Models Merged + +The following models were included in the merge: +* /workspace/cache/models--SicariusSicariiStuff--Negative_LLAMA_70B/snapshots/f84e61554251d9355146537e39ba081c7b5580eb +* /workspace/cache/models--Sao10K--L3.3-70B-Euryale-v2.3/snapshots/e5737724a37ae00926e95acf663ca73d430dc8ad +* /workspace/cache/models--TheDrummer--Fallen-Llama-3.3-70B-v1/snapshots/d46ef2629f1c3cd46789a55793c5ff0af60de3e8 +* /workspace/cache/models--ReadyArt--L3.3-The-Omega-Directive-70B-Unslop-v2.1/snapshots/61e03f3fe59b3b22b7e9e17e9bbe807f434da16d +* /workspace/cache/models--ArliAI--Llama-3.3-70B-ArliAI-RPMax-v2/snapshots/3a47eabeb5861db09dad26fcf0fb0d57114e40d3 + +### Configuration + +The following YAML configuration was used to produce this model: + +```yaml +models: + - model: /workspace/cache/models--SicariusSicariiStuff--Negative_LLAMA_70B/snapshots/f84e61554251d9355146537e39ba081c7b5580eb + - model: /workspace/cache/models--ArliAI--Llama-3.3-70B-ArliAI-RPMax-v2/snapshots/3a47eabeb5861db09dad26fcf0fb0d57114e40d3 + - model: /workspace/cache/models--Sao10K--L3.3-70B-Euryale-v2.3/snapshots/e5737724a37ae00926e95acf663ca73d430dc8ad + - model: /workspace/cache/models--ReadyArt--L3.3-The-Omega-Directive-70B-Unslop-v2.1/snapshots/61e03f3fe59b3b22b7e9e17e9bbe807f434da16d + - model: /workspace/cache/models--TheDrummer--Fallen-Llama-3.3-70B-v1/snapshots/d46ef2629f1c3cd46789a55793c5ff0af60de3e8 +base_model: /workspace/prototype-0.4x295 +select_topk: 0.24 +merge_method: sce +tokenizer: + source: base +chat_template: llama3 +pad_to_multiple_of: 8 +int8_mask: true +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..fb7e20717b2a6ac86d90bd43b28a9a0d64745b7e --- /dev/null +++ b/config.json @@ -0,0 +1,35 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128001, + "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": "4.55.0", + "use_cache": true, + "vocab_size": 128256 +} diff --git a/mergekit_config.yml b/mergekit_config.yml new file mode 100644 index 0000000000000000000000000000000000000000..78c7e59c9b7c56ea7d35b88b2ad4a39cf25e19a9 --- /dev/null +++ b/mergekit_config.yml @@ -0,0 +1,15 @@ +models: + - model: /workspace/cache/models--SicariusSicariiStuff--Negative_LLAMA_70B/snapshots/f84e61554251d9355146537e39ba081c7b5580eb + - model: /workspace/cache/models--ArliAI--Llama-3.3-70B-ArliAI-RPMax-v2/snapshots/3a47eabeb5861db09dad26fcf0fb0d57114e40d3 + - model: /workspace/cache/models--Sao10K--L3.3-70B-Euryale-v2.3/snapshots/e5737724a37ae00926e95acf663ca73d430dc8ad + - model: /workspace/cache/models--ReadyArt--L3.3-The-Omega-Directive-70B-Unslop-v2.1/snapshots/61e03f3fe59b3b22b7e9e17e9bbe807f434da16d + - model: /workspace/cache/models--TheDrummer--Fallen-Llama-3.3-70B-v1/snapshots/d46ef2629f1c3cd46789a55793c5ff0af60de3e8 +base_model: /workspace/prototype-0.4x295 +select_topk: 0.24 +merge_method: sce +tokenizer: + source: base +chat_template: llama3 +pad_to_multiple_of: 8 +int8_mask: true +dtype: float32 \ No newline at end of file diff --git a/model-00001-of-00064.safetensors b/model-00001-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8a8d4c2804fd0656cb6c1ed8371d97a910369c2e --- /dev/null +++ b/model-00001-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ce0e62e4b17e8bd56156522f8ff623502340126385c9076f6c4bbc348924fc2 +size 4093740184 diff --git a/model-00002-of-00064.safetensors b/model-00002-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7b8c97cbf225572f907b83b7e832ca4e07cbc582 --- /dev/null +++ b/model-00002-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af7964870aafa7651109e15c23baceebc55ebfddb2c7b1e4f9f81633ffcc8f58 +size 1241514360 diff --git a/model-00003-of-00064.safetensors b/model-00003-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6086fe3f93f53c888b50e9a39c0ac733fb2c23fe --- /dev/null +++ b/model-00003-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86558a3645f4269dbc24b4d5099f6f3ca1c7dad04feb4d93b69b83ded5070f0c +size 4202692736 diff --git a/model-00004-of-00064.safetensors b/model-00004-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cd5c780ab09a9b2d04eb8c9c4d59e6690bcaeac7 --- /dev/null +++ b/model-00004-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93aa46f0109f22e22dcd7d7fc79051aa397e795bbf109d95d03483ebfee5d365 +size 2214626008 diff --git a/model-00005-of-00064.safetensors b/model-00005-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f78d81d57fcc3222205198cb49a32af0f832e61e --- /dev/null +++ b/model-00005-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acf45ee2194f71adf8ee36354c82db93bbf972a62bc3f6de916af885bd994d41 +size 4202692744 diff --git a/model-00006-of-00064.safetensors b/model-00006-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e142dba66c66f4145e8916b3ad2b87eeb4cbcd70 --- /dev/null +++ b/model-00006-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53f9365a8507a6aa926ad3819f2af7f7adb7ce8b2b3a504cb2a954f46bb576f3 +size 4664165888 diff --git a/model-00007-of-00064.safetensors b/model-00007-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3fac2d058822f46a1ab629da300ce55fe4656c83 --- /dev/null +++ b/model-00007-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5441459c4419e0aa117845bc1a2398c806eeceb0edd60761762e3499830b7c14 +size 4664165880 diff --git a/model-00008-of-00064.safetensors b/model-00008-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..961502db8f458770cfdd37dd819fb2adc6793945 --- /dev/null +++ b/model-00008-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25a9ce0de1e70a92461b16e9f5b47bc53ebacd4b042177a22101dde6b504dc70 +size 4362142880 diff --git a/model-00009-of-00064.safetensors b/model-00009-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..db2a532e1d30351409af7e186af9e8b22cd59d7b --- /dev/null +++ b/model-00009-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4361674c6354a85bab87b8487e8995b18e5bb50482740abbe7f431cf28a88a42 +size 4664198776 diff --git a/model-00010-of-00064.safetensors b/model-00010-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ee8b1db6629313b49d7f781eb0d24b92fe5086d4 --- /dev/null +++ b/model-00010-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b944cd992eaccd7c17eabb61b9987f9327e4bf131090a4734ae0245f3a8c0963 +size 4362142880 diff --git a/model-00011-of-00064.safetensors b/model-00011-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..49a32447ee9cb3481e1d9bce17a2c43a5c7945dd --- /dev/null +++ b/model-00011-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1368e839c2d178b8307d20f196a164396bf7285213a78607241baf37f96cf10d +size 4932601456 diff --git a/model-00012-of-00064.safetensors b/model-00012-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9af3b03d55171ba663a9833db884c6f2feeea7ec --- /dev/null +++ b/model-00012-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f1cd35f7f3329ef80a5586d4f617f0d4f85e3872b26bc1fc9e8e975051899a6 +size 4362142888 diff --git a/model-00013-of-00064.safetensors b/model-00013-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b979b565a61ae48175d67f906afc6037846835d2 --- /dev/null +++ b/model-00013-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4c42b32fa56d8a47dbdd3c1021c0d13be99d05238f7bf0ec1a2d74ce1914b6f +size 4664165888 diff --git a/model-00014-of-00064.safetensors b/model-00014-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..584a0b62423870414a382138206465a0badb32c1 --- /dev/null +++ b/model-00014-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae84831bd7de9484def2239cff6e72eb0056236e75dd02af1c8632b9c9875f9c +size 4664165872 diff --git a/model-00015-of-00064.safetensors b/model-00015-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5fd8e5bc88395229dcf82fb218239c15c649a099 --- /dev/null +++ b/model-00015-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:986afed0d56ae2e31abe7f3606f936fd63ba2d0bec91090c52de889efbdd05ab +size 4362142880 diff --git a/model-00016-of-00064.safetensors b/model-00016-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b33ce299477e5edc99912f5109a4e0bf986c1217 --- /dev/null +++ b/model-00016-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50782c03aa4a9d028eddddf021273031720898fcc248d12c85c38ca75c7966c6 +size 4664198776 diff --git a/model-00017-of-00064.safetensors b/model-00017-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f3970a6fd2028b4a25cdc7cacb4ab423218952b3 --- /dev/null +++ b/model-00017-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2018e2c597235d631b86d85ed67b99b1eaac46df54f53a1b02de899fb22b7a61 +size 4362142880 diff --git a/model-00018-of-00064.safetensors b/model-00018-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7df2eaca089b4172c8fcf1b837cdbc594a7e0c43 --- /dev/null +++ b/model-00018-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33fb14d6529a49ca53bc6d43a4c3c84e228a7031b89dc5533f0dcdfd51c3ba3b +size 4932601456 diff --git a/model-00019-of-00064.safetensors b/model-00019-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..454b358e75e4b1cd735cf26ec2f4b3857b6f365d --- /dev/null +++ b/model-00019-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64253a85a35fe46f85dcf1da32a20c32e68d3ff046456aa44e88a2acb3c80063 +size 4395730320 diff --git a/model-00020-of-00064.safetensors b/model-00020-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9154a0361637a53e30d84e3e877b8763aaa57e5d --- /dev/null +++ b/model-00020-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7362fa2635af071703a342751864c3ad53a2b916e75ad53b4b8089de4dd69cb +size 4362142880 diff --git a/model-00021-of-00064.safetensors b/model-00021-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..57d0aaf05741f0cbb080bc6fdfe9f1f21d2f7c26 --- /dev/null +++ b/model-00021-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bb260b151a94715493d156b7c822f5ff3dfbfd33f831957a08b0fd728964e40 +size 4932601448 diff --git a/model-00022-of-00064.safetensors b/model-00022-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ff78a7f88ffa78d1e440d467aee8754b0369dc19 --- /dev/null +++ b/model-00022-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e4ad261ba71f7d9bdb1666b46e2ec6602a06019434e42abfa7834fcdc24de70 +size 4362142880 diff --git a/model-00023-of-00064.safetensors b/model-00023-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1033d198bb1925285dc0cac3f9bf4cec7394a52a --- /dev/null +++ b/model-00023-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1cb5db1119e317f8f9f3f4aac8314d88c129bb85626b638a56fc3fb667e2018 +size 4664165896 diff --git a/model-00024-of-00064.safetensors b/model-00024-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ca9a846e61479b4b6e39945ac6ea1adfb47fa8a7 --- /dev/null +++ b/model-00024-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce2edb9d25f4fca616acc3e2e5cf0b6cdf08d1f1000292da074a4e364afbef56 +size 4664165880 diff --git a/model-00025-of-00064.safetensors b/model-00025-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f35211c34b93461094c351514ee270f13c1d5e20 --- /dev/null +++ b/model-00025-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca1ead1a7bf445895b85570754079f49074b7429f1ac339c27a1dc68a6c7bb63 +size 4362142880 diff --git a/model-00026-of-00064.safetensors b/model-00026-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..35c1006c0b0dc1c74b24c9983338aefc041d8be1 --- /dev/null +++ b/model-00026-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a03862395a269004521385972a2e43a43c27f8dea482716bbc6f8cbd46772409 +size 4664198768 diff --git a/model-00027-of-00064.safetensors b/model-00027-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f827c07512c64fb2a38a52bd29d681cea55ba4ee --- /dev/null +++ b/model-00027-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a3a3e91bee78142a6296a99b9c14588a6158704e4743150079361081e9d2425 +size 4362142880 diff --git a/model-00028-of-00064.safetensors b/model-00028-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d0e9d9a3ada1d22cb70e1ccb57637ec93544d4f9 --- /dev/null +++ b/model-00028-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4b1e33c292cd395e82640015abf46efa4512a26c9a067871f671ae4d51e78f0 +size 4932601456 diff --git a/model-00029-of-00064.safetensors b/model-00029-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0b918371429b4aee78bfbdcdabc792b48330f582 --- /dev/null +++ b/model-00029-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3370af3c6895a4e417d967ec2657567404c3e945df9e2383b67ba2f787005478 +size 4362142880 diff --git a/model-00030-of-00064.safetensors b/model-00030-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..009738111b7e392178cf14fe691a36c569262fdc --- /dev/null +++ b/model-00030-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:272980f4b8956526d1e4781b6fcb4bb83d49faf6acc5c8b022d866e4f6e3dff2 +size 4664165880 diff --git a/model-00031-of-00064.safetensors b/model-00031-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dc9dc2adc95a8ff1427dc645666029e6ba4d791a --- /dev/null +++ b/model-00031-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a10dcc26961bf066c8cbf583c1636e13a6e8205593062e0790c435f98577fb9 +size 4664165888 diff --git a/model-00032-of-00064.safetensors b/model-00032-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d2303ac5a0683a8dd7ef98042ead386f50d74c23 --- /dev/null +++ b/model-00032-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13284da402c610b8f89eccb0e9ccbd9daa98aa6fc7dd4b423f11019be9e1faff +size 4362142880 diff --git a/model-00033-of-00064.safetensors b/model-00033-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d5587e62ad7c56fa34e936006dd0961da56e44a8 --- /dev/null +++ b/model-00033-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63c1bfab99f69f0042a072a02a901424a5ee5be69a02fba23fcc2770c424c553 +size 4664198768 diff --git a/model-00034-of-00064.safetensors b/model-00034-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..397469d83cd23f41bb162da00aec56a01005ed55 --- /dev/null +++ b/model-00034-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bccbf9ee52b2adfba2904bd9b0c0678df92a660eb42ed1ae5752c65bdf0e2f6b +size 4362142880 diff --git a/model-00035-of-00064.safetensors b/model-00035-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cc13397a4d9c8c3918b66e6cc2cfe75087e76934 --- /dev/null +++ b/model-00035-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:616dbfc85ad4899f935026b058306bbfea654de8336907693acb3546fb89778b +size 4932601456 diff --git a/model-00036-of-00064.safetensors b/model-00036-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a2c16eff8b5203e0e1a8315ed7e66c347e9c0840 --- /dev/null +++ b/model-00036-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4776b208f406a91e57b8310ecd51ecb048fc4ae25ada30b97e57f82f867c320c +size 4362142880 diff --git a/model-00037-of-00064.safetensors b/model-00037-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..55c548e3aede4c3d63c82b1644dbc94b1943544c --- /dev/null +++ b/model-00037-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96dd450af9d9cae73fa017f6f0ec058653676111b6618de91ce46aeed929b22f +size 4664165888 diff --git a/model-00038-of-00064.safetensors b/model-00038-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1b525e19ac5566d143d7c1f8c60a70254c233b65 --- /dev/null +++ b/model-00038-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c00b4e2929e3a7dbfb77b386695b023649a0cf2d3f13795272426f7e366380f9 +size 4664165880 diff --git a/model-00039-of-00064.safetensors b/model-00039-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5870681cd54c60b38b72ee5a3ef077b80820281d --- /dev/null +++ b/model-00039-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca1328b1df61f90a11be7b686e0394cf06a187b817070fbb3f0297b3a2d679f5 +size 4362142880 diff --git a/model-00040-of-00064.safetensors b/model-00040-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..99489543e5735996ad8bad245fc2d0a6ada75807 --- /dev/null +++ b/model-00040-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:affeb8ed15ef99312dd7e80c84674839357bf46b3a90e99289ed2db56529c5a2 +size 4932634344 diff --git a/model-00041-of-00064.safetensors b/model-00041-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..58a708db9e831888fa5b0ebbf7f08eb540f34d2b --- /dev/null +++ b/model-00041-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dad5be7d82eae437ad239807f372d94cdc397d8da6c136107141026da2e046bf +size 4362142880 diff --git a/model-00042-of-00064.safetensors b/model-00042-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ae1b458fd9ec79aa5a49ee92cd227dc0163ff0e3 --- /dev/null +++ b/model-00042-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d57f3232b3b023cab9ef468b3a29aead61f189ea7f47ce9a6cd7174dffa0a226 +size 4630611344 diff --git a/model-00043-of-00064.safetensors b/model-00043-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..aa9e00e13db67295a1b9cedbef3613683bfcadee --- /dev/null +++ b/model-00043-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e109dd857c1ed3e01fb5148e1ababf3f0360059acd15265fa25df4d3d7d966b +size 4664165888 diff --git a/model-00044-of-00064.safetensors b/model-00044-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..10fdcae4cdc90853f3a0221a72888c7e89615e07 --- /dev/null +++ b/model-00044-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bca6e4d39ec70780028637322b16d70757d9d4ac1d0d01b5a105cb2dc124a38 +size 4362142880 diff --git a/model-00045-of-00064.safetensors b/model-00045-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c25e02ae817071e012fb5b3faa1742976bee9709 --- /dev/null +++ b/model-00045-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cdc2f8ddf33c2935777c8663b2cc112660834fee1c43b7c4a98a4fff6356925 +size 4932634344 diff --git a/model-00046-of-00064.safetensors b/model-00046-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..def61b39c993f9bd4ca92353a9ac204125898c49 --- /dev/null +++ b/model-00046-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a045634f5856ec1edb43ce0be8f2e98df69d479a867583a2d30f561ef7f9181 +size 4630578448 diff --git a/model-00047-of-00064.safetensors b/model-00047-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4b781e43b0ea0317550d4c772249cdc3187065b6 --- /dev/null +++ b/model-00047-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa83fc19ecebfa85ebc5bb1c943404d672a4a6a6a894e5be1e298c008fe6b5bb +size 4362175760 diff --git a/model-00048-of-00064.safetensors b/model-00048-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7ae1b79af586628bd59a3927e5292cf7f12e96ba --- /dev/null +++ b/model-00048-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b6b2c304b28f4a9f1453ee273a668357c90b5dab7e8983d8e1d32e9470fddc0 +size 4362175768 diff --git a/model-00049-of-00064.safetensors b/model-00049-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5923d87fb2cedeeec18dd5a72f38d076aa0cb6cb --- /dev/null +++ b/model-00049-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4068cd778ce8c463c425e1f29f033e54d600403e1fbcaf3af7093c5b379264e6 +size 4966156000 diff --git a/model-00050-of-00064.safetensors b/model-00050-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2d3fb49162c011bdb072894dd6159b51f87b3d3a --- /dev/null +++ b/model-00050-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e73fead578656a333275b2e0fcc41469a469ad9e3aa62cd1b58fea98585a0003 +size 4362142880 diff --git a/model-00051-of-00064.safetensors b/model-00051-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..97b38ea9e2b1d5edd8066508773befc0bb31f0b5 --- /dev/null +++ b/model-00051-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce8d6566bd912866369828d2bf903ddcf7821bea033fdef4ce9c88d2696f2523 +size 4362142880 diff --git a/model-00052-of-00064.safetensors b/model-00052-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0c99d115264112b240524782af40f96529381de7 --- /dev/null +++ b/model-00052-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b3cbdb0b2496f3c5c94df95a434c4d7f355af619dc52e89f9e57f68fdf835c2 +size 4966188896 diff --git a/model-00053-of-00064.safetensors b/model-00053-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..77a70017337ee9c6915241bf811d2df8c720e29d --- /dev/null +++ b/model-00053-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e32f93777a5c1c2a5733c57a072415ed7909ea79d2009b115a7a17ef6789ed82 +size 4362142880 diff --git a/model-00054-of-00064.safetensors b/model-00054-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5b84841c8c57443b3358f8e3284ea33318fea366 --- /dev/null +++ b/model-00054-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cc7c9f0a1283ea5ed0e1f6f251f97b22c391792c82fc8e5c66ffb532668c90b +size 4630611336 diff --git a/model-00055-of-00064.safetensors b/model-00055-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6fe4017b78e12252ea317a099113316c7f685469 --- /dev/null +++ b/model-00055-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c04011c17b27c402877fbca276103352a810b1431e3a3c6298cb7542a278eb24 +size 4362175768 diff --git a/model-00056-of-00064.safetensors b/model-00056-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bf37ddd3983cccdbb7fa6c04c045c0cd539be9e3 --- /dev/null +++ b/model-00056-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77f32a0f9b3a4bf22bf2c38f13c1e36ea49497aa6f47f7b50a1d53ede394484d +size 4966156000 diff --git a/model-00057-of-00064.safetensors b/model-00057-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..69244072a5e19741a907c13acb32a8399768ba3c --- /dev/null +++ b/model-00057-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e631bd4b8e82f6b0b5f316b0671add195ba99e76bb7a3548a3d2fba7f6c208f +size 4362142880 diff --git a/model-00058-of-00064.safetensors b/model-00058-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bb87dfdcf50d387ebdf17a9e5599ef03ae8b36fc --- /dev/null +++ b/model-00058-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee8cffd58e08fb8b9393669f42643203d0e4dad75b700b24bc81dc5424951839 +size 4630611344 diff --git a/model-00059-of-00064.safetensors b/model-00059-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fca4b332bb8413b99ae6abe4cab3bbd53c0c2995 --- /dev/null +++ b/model-00059-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75239214073a8663a8a5dc25365a3c6838502350ad049e615b491a6bb71d6c44 +size 4664165888 diff --git a/model-00060-of-00064.safetensors b/model-00060-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6441c71c4b189558c3c3215e737c862153bbab2f --- /dev/null +++ b/model-00060-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:199dbe9398c555c9965fec93ead6f7343d188dabe71f7b9fb39a56bc95b83543 +size 4362142880 diff --git a/model-00061-of-00064.safetensors b/model-00061-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e563f61a50c85263fc35f82188ac8f7c1235d135 --- /dev/null +++ b/model-00061-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d2dad376f81ff80655fb1920ba6dc6c7323013df1074bae920cac603c4e65d9 +size 4664198744 diff --git a/model-00062-of-00064.safetensors b/model-00062-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4acfe25bdad8f16c3fd0432c4b67200ee2c58e3 --- /dev/null +++ b/model-00062-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cb293ee3cae4e6b0cd96e7d6cd63cb746012c617f7335cc017cdb798d6075da +size 4697687560 diff --git a/model-00063-of-00064.safetensors b/model-00063-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7f4ffa26aec350593e22f6f98fa085614cc8f5c8 --- /dev/null +++ b/model-00063-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:582095853eaca734e5ccd67b4486f3f05f4f81a4f050f7355209b75f18b132b9 +size 4227892624 diff --git a/model-00064-of-00064.safetensors b/model-00064-of-00064.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7c979177d7ef16fedad57ba1e1e4af514828187b --- /dev/null +++ b/model-00064-of-00064.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61b8604ed43ffe8f8ec88921b76c589920b17c91a6a74b514e83ba131e27a9e8 +size 1006633336 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..51f68323003bc115fef406c7adca56a559576812 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1 @@ +{"metadata": {"mergekit_version": "0.1.3"}, "weight_map": {"model.layers.0.input_layernorm.weight": "model-00001-of-00064.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00064.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00064.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00064.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00064.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00064.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00064.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00064.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00064.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00064.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00064.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00064.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00064.safetensors", "lm_head.weight": "model-00003-of-00064.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00004-of-00064.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00064.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00064.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00064.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00064.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00064.safetensors", "model.embed_tokens.weight": "model-00005-of-00064.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00006-of-00064.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00064.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00064.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00006-of-00064.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00064.safetensors", "model.layers.1.input_layernorm.weight": "model-00006-of-00064.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00064.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00064.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00006-of-00064.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00006-of-00064.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00064.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00064.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00006-of-00064.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00007-of-00064.safetensors", "model.layers.10.input_layernorm.weight": "model-00007-of-00064.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00007-of-00064.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00007-of-00064.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00007-of-00064.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00007-of-00064.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00007-of-00064.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00064.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00007-of-00064.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00064.safetensors", "model.layers.11.input_layernorm.weight": "model-00007-of-00064.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00064.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00064.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00008-of-00064.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00008-of-00064.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00008-of-00064.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00008-of-00064.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00008-of-00064.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00008-of-00064.safetensors", "model.layers.12.input_layernorm.weight": "model-00008-of-00064.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00008-of-00064.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00008-of-00064.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00008-of-00064.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00009-of-00064.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00009-of-00064.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00009-of-00064.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00009-of-00064.safetensors", "model.layers.13.input_layernorm.weight": "model-00009-of-00064.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00009-of-00064.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00009-of-00064.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00009-of-00064.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00009-of-00064.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00009-of-00064.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00009-of-00064.safetensors", "model.layers.14.input_layernorm.weight": "model-00009-of-00064.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00009-of-00064.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00064.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00010-of-00064.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00010-of-00064.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00010-of-00064.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00010-of-00064.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00010-of-00064.safetensors", "model.layers.15.input_layernorm.weight": "model-00010-of-00064.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00010-of-00064.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00010-of-00064.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00010-of-00064.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00010-of-00064.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00011-of-00064.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00011-of-00064.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00011-of-00064.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00011-of-00064.safetensors", "model.layers.16.input_layernorm.weight": "model-00011-of-00064.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00011-of-00064.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00011-of-00064.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00011-of-00064.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00011-of-00064.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00011-of-00064.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00011-of-00064.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00011-of-00064.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00011-of-00064.safetensors", "model.layers.17.input_layernorm.weight": "model-00011-of-00064.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00012-of-00064.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00012-of-00064.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00012-of-00064.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00012-of-00064.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00012-of-00064.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00012-of-00064.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00012-of-00064.safetensors", "model.layers.18.input_layernorm.weight": "model-00012-of-00064.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00012-of-00064.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00012-of-00064.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00013-of-00064.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00013-of-00064.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00013-of-00064.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00013-of-00064.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00013-of-00064.safetensors", "model.layers.19.input_layernorm.weight": "model-00013-of-00064.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00013-of-00064.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00013-of-00064.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00013-of-00064.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00013-of-00064.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00013-of-00064.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00013-of-00064.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00013-of-00064.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00014-of-00064.safetensors", "model.layers.2.input_layernorm.weight": "model-00014-of-00064.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00014-of-00064.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00014-of-00064.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00014-of-00064.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00014-of-00064.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00014-of-00064.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00014-of-00064.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00014-of-00064.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00014-of-00064.safetensors", "model.layers.20.input_layernorm.weight": "model-00014-of-00064.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00014-of-00064.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00014-of-00064.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00015-of-00064.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00015-of-00064.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00015-of-00064.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00015-of-00064.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00015-of-00064.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00015-of-00064.safetensors", "model.layers.21.input_layernorm.weight": "model-00015-of-00064.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00015-of-00064.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00015-of-00064.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00015-of-00064.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00016-of-00064.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00016-of-00064.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00016-of-00064.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00016-of-00064.safetensors", "model.layers.22.input_layernorm.weight": "model-00016-of-00064.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00016-of-00064.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00016-of-00064.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00016-of-00064.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00016-of-00064.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00016-of-00064.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00016-of-00064.safetensors", "model.layers.23.input_layernorm.weight": "model-00016-of-00064.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00016-of-00064.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00016-of-00064.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00017-of-00064.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00017-of-00064.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00017-of-00064.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00017-of-00064.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00017-of-00064.safetensors", "model.layers.24.input_layernorm.weight": "model-00017-of-00064.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00017-of-00064.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00017-of-00064.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00017-of-00064.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00017-of-00064.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00018-of-00064.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00018-of-00064.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00018-of-00064.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00018-of-00064.safetensors", "model.layers.25.input_layernorm.weight": "model-00018-of-00064.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00018-of-00064.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00018-of-00064.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00018-of-00064.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00018-of-00064.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00018-of-00064.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00018-of-00064.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00018-of-00064.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00018-of-00064.safetensors", "model.layers.26.input_layernorm.weight": "model-00018-of-00064.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00019-of-00064.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00019-of-00064.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00019-of-00064.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00019-of-00064.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00019-of-00064.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00019-of-00064.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00019-of-00064.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00019-of-00064.safetensors", "model.layers.27.input_layernorm.weight": "model-00019-of-00064.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00019-of-00064.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00019-of-00064.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00019-of-00064.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00020-of-00064.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00020-of-00064.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00020-of-00064.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00020-of-00064.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00020-of-00064.safetensors", "model.layers.28.input_layernorm.weight": "model-00020-of-00064.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00020-of-00064.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00020-of-00064.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00020-of-00064.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00020-of-00064.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00021-of-00064.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00021-of-00064.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00021-of-00064.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00021-of-00064.safetensors", "model.layers.29.input_layernorm.weight": "model-00021-of-00064.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00021-of-00064.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00021-of-00064.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00021-of-00064.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00021-of-00064.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00021-of-00064.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00021-of-00064.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00021-of-00064.safetensors", "model.layers.3.input_layernorm.weight": "model-00021-of-00064.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00021-of-00064.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00022-of-00064.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00022-of-00064.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00022-of-00064.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00022-of-00064.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00022-of-00064.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00022-of-00064.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00022-of-00064.safetensors", "model.layers.30.input_layernorm.weight": "model-00022-of-00064.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00022-of-00064.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00022-of-00064.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00023-of-00064.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00023-of-00064.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00023-of-00064.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00023-of-00064.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00023-of-00064.safetensors", "model.layers.31.input_layernorm.weight": "model-00023-of-00064.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00023-of-00064.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00023-of-00064.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00023-of-00064.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00023-of-00064.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00023-of-00064.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00023-of-00064.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00023-of-00064.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00024-of-00064.safetensors", "model.layers.32.input_layernorm.weight": "model-00024-of-00064.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00024-of-00064.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00024-of-00064.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00024-of-00064.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00024-of-00064.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00024-of-00064.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00024-of-00064.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00024-of-00064.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00024-of-00064.safetensors", "model.layers.33.input_layernorm.weight": "model-00024-of-00064.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00024-of-00064.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00024-of-00064.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00025-of-00064.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00025-of-00064.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00025-of-00064.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00025-of-00064.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00025-of-00064.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00025-of-00064.safetensors", "model.layers.34.input_layernorm.weight": "model-00025-of-00064.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00025-of-00064.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00025-of-00064.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00025-of-00064.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00026-of-00064.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00026-of-00064.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00026-of-00064.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00026-of-00064.safetensors", "model.layers.35.input_layernorm.weight": "model-00026-of-00064.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00026-of-00064.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00026-of-00064.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00026-of-00064.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00026-of-00064.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00026-of-00064.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00026-of-00064.safetensors", "model.layers.36.input_layernorm.weight": "model-00026-of-00064.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00026-of-00064.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00026-of-00064.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00027-of-00064.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00027-of-00064.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00027-of-00064.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00027-of-00064.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00027-of-00064.safetensors", "model.layers.37.input_layernorm.weight": "model-00027-of-00064.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00027-of-00064.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00027-of-00064.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00027-of-00064.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00027-of-00064.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00028-of-00064.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00028-of-00064.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00028-of-00064.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00028-of-00064.safetensors", "model.layers.38.input_layernorm.weight": "model-00028-of-00064.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00028-of-00064.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00028-of-00064.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00028-of-00064.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00028-of-00064.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00028-of-00064.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00028-of-00064.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00028-of-00064.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00028-of-00064.safetensors", "model.layers.39.input_layernorm.weight": "model-00028-of-00064.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00029-of-00064.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00029-of-00064.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00029-of-00064.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00029-of-00064.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00029-of-00064.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00029-of-00064.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00029-of-00064.safetensors", "model.layers.4.input_layernorm.weight": "model-00029-of-00064.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00029-of-00064.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00029-of-00064.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00030-of-00064.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00030-of-00064.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00030-of-00064.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00030-of-00064.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00030-of-00064.safetensors", "model.layers.40.input_layernorm.weight": "model-00030-of-00064.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00030-of-00064.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00030-of-00064.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00030-of-00064.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00030-of-00064.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00030-of-00064.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00030-of-00064.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00030-of-00064.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00031-of-00064.safetensors", "model.layers.41.input_layernorm.weight": "model-00031-of-00064.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00031-of-00064.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00031-of-00064.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00031-of-00064.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00031-of-00064.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00031-of-00064.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00031-of-00064.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00031-of-00064.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00031-of-00064.safetensors", "model.layers.42.input_layernorm.weight": "model-00031-of-00064.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00031-of-00064.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00031-of-00064.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00032-of-00064.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00032-of-00064.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00032-of-00064.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00032-of-00064.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00032-of-00064.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00032-of-00064.safetensors", "model.layers.43.input_layernorm.weight": "model-00032-of-00064.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00032-of-00064.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00032-of-00064.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00032-of-00064.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00033-of-00064.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00033-of-00064.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00033-of-00064.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00033-of-00064.safetensors", "model.layers.44.input_layernorm.weight": "model-00033-of-00064.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00033-of-00064.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00033-of-00064.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00033-of-00064.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00033-of-00064.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00033-of-00064.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00033-of-00064.safetensors", "model.layers.45.input_layernorm.weight": "model-00033-of-00064.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00033-of-00064.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00033-of-00064.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00034-of-00064.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00034-of-00064.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00034-of-00064.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00034-of-00064.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00034-of-00064.safetensors", "model.layers.46.input_layernorm.weight": "model-00034-of-00064.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00034-of-00064.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00034-of-00064.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00034-of-00064.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00034-of-00064.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00035-of-00064.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00035-of-00064.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00035-of-00064.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00035-of-00064.safetensors", "model.layers.47.input_layernorm.weight": "model-00035-of-00064.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00035-of-00064.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00035-of-00064.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00035-of-00064.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00035-of-00064.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00035-of-00064.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00035-of-00064.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00035-of-00064.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00035-of-00064.safetensors", "model.layers.48.input_layernorm.weight": "model-00035-of-00064.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00036-of-00064.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00036-of-00064.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00036-of-00064.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00036-of-00064.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00036-of-00064.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00036-of-00064.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00036-of-00064.safetensors", "model.layers.49.input_layernorm.weight": "model-00036-of-00064.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00036-of-00064.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00036-of-00064.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00037-of-00064.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00037-of-00064.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00037-of-00064.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00037-of-00064.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00037-of-00064.safetensors", "model.layers.5.input_layernorm.weight": "model-00037-of-00064.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00037-of-00064.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00037-of-00064.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00037-of-00064.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00037-of-00064.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00037-of-00064.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00037-of-00064.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00037-of-00064.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00038-of-00064.safetensors", "model.layers.50.input_layernorm.weight": "model-00038-of-00064.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00038-of-00064.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00038-of-00064.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00038-of-00064.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00038-of-00064.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00038-of-00064.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00038-of-00064.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00038-of-00064.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00038-of-00064.safetensors", "model.layers.51.input_layernorm.weight": "model-00038-of-00064.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00038-of-00064.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00038-of-00064.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00039-of-00064.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00039-of-00064.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00039-of-00064.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00039-of-00064.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00039-of-00064.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00039-of-00064.safetensors", "model.layers.52.input_layernorm.weight": "model-00039-of-00064.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00039-of-00064.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00039-of-00064.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00039-of-00064.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00040-of-00064.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00040-of-00064.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00040-of-00064.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00040-of-00064.safetensors", "model.layers.53.input_layernorm.weight": "model-00040-of-00064.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00040-of-00064.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00040-of-00064.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00040-of-00064.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00040-of-00064.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00040-of-00064.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00040-of-00064.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00040-of-00064.safetensors", "model.layers.54.input_layernorm.weight": "model-00040-of-00064.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00040-of-00064.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00040-of-00064.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00041-of-00064.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00041-of-00064.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00041-of-00064.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00041-of-00064.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00041-of-00064.safetensors", "model.layers.55.input_layernorm.weight": "model-00041-of-00064.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00041-of-00064.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00041-of-00064.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00041-of-00064.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00041-of-00064.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00042-of-00064.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00042-of-00064.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00042-of-00064.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00042-of-00064.safetensors", "model.layers.56.input_layernorm.weight": "model-00042-of-00064.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00042-of-00064.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00042-of-00064.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00042-of-00064.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00042-of-00064.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00042-of-00064.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00042-of-00064.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00042-of-00064.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00043-of-00064.safetensors", "model.layers.57.input_layernorm.weight": "model-00043-of-00064.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00043-of-00064.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00043-of-00064.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00043-of-00064.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00043-of-00064.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00043-of-00064.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00043-of-00064.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00043-of-00064.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00043-of-00064.safetensors", "model.layers.58.input_layernorm.weight": "model-00043-of-00064.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00043-of-00064.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00043-of-00064.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00044-of-00064.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00044-of-00064.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00044-of-00064.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00044-of-00064.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00044-of-00064.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00044-of-00064.safetensors", "model.layers.59.input_layernorm.weight": "model-00044-of-00064.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00044-of-00064.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00044-of-00064.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00044-of-00064.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00045-of-00064.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00045-of-00064.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00045-of-00064.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00045-of-00064.safetensors", "model.layers.6.input_layernorm.weight": "model-00045-of-00064.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00045-of-00064.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00045-of-00064.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00045-of-00064.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00045-of-00064.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00045-of-00064.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00045-of-00064.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00045-of-00064.safetensors", "model.layers.60.input_layernorm.weight": "model-00045-of-00064.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00045-of-00064.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00045-of-00064.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00046-of-00064.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00046-of-00064.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00046-of-00064.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00046-of-00064.safetensors", "model.layers.61.input_layernorm.weight": "model-00046-of-00064.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00046-of-00064.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00046-of-00064.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00046-of-00064.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00046-of-00064.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00046-of-00064.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00046-of-00064.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00047-of-00064.safetensors", "model.layers.62.input_layernorm.weight": "model-00047-of-00064.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00047-of-00064.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00047-of-00064.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00047-of-00064.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00047-of-00064.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00047-of-00064.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00047-of-00064.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00047-of-00064.safetensors", "model.layers.63.input_layernorm.weight": "model-00047-of-00064.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00047-of-00064.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00048-of-00064.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00048-of-00064.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00048-of-00064.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00048-of-00064.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00048-of-00064.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00048-of-00064.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00048-of-00064.safetensors", "model.layers.64.input_layernorm.weight": "model-00048-of-00064.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00048-of-00064.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00048-of-00064.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00048-of-00064.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00049-of-00064.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00049-of-00064.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00049-of-00064.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00049-of-00064.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00049-of-00064.safetensors", "model.layers.65.input_layernorm.weight": "model-00049-of-00064.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00049-of-00064.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00049-of-00064.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00049-of-00064.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00049-of-00064.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00049-of-00064.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00049-of-00064.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00049-of-00064.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00049-of-00064.safetensors", "model.layers.66.input_layernorm.weight": "model-00049-of-00064.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00050-of-00064.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00050-of-00064.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00050-of-00064.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00050-of-00064.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00050-of-00064.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00050-of-00064.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00050-of-00064.safetensors", "model.layers.67.input_layernorm.weight": "model-00050-of-00064.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00050-of-00064.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00050-of-00064.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00051-of-00064.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00051-of-00064.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00051-of-00064.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00051-of-00064.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00051-of-00064.safetensors", "model.layers.68.input_layernorm.weight": "model-00051-of-00064.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00051-of-00064.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00051-of-00064.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00051-of-00064.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00051-of-00064.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00052-of-00064.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00052-of-00064.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00052-of-00064.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00052-of-00064.safetensors", "model.layers.69.input_layernorm.weight": "model-00052-of-00064.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00052-of-00064.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00052-of-00064.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00052-of-00064.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00052-of-00064.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00052-of-00064.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00052-of-00064.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00052-of-00064.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00052-of-00064.safetensors", "model.layers.7.input_layernorm.weight": "model-00052-of-00064.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00052-of-00064.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00052-of-00064.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00053-of-00064.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00053-of-00064.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00053-of-00064.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00053-of-00064.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00053-of-00064.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00053-of-00064.safetensors", "model.layers.70.input_layernorm.weight": "model-00053-of-00064.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00053-of-00064.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00053-of-00064.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00053-of-00064.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00054-of-00064.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00054-of-00064.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00054-of-00064.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00054-of-00064.safetensors", "model.layers.71.input_layernorm.weight": "model-00054-of-00064.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00054-of-00064.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00054-of-00064.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00054-of-00064.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00054-of-00064.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00054-of-00064.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00054-of-00064.safetensors", "model.layers.72.input_layernorm.weight": "model-00054-of-00064.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00055-of-00064.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00055-of-00064.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00055-of-00064.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00055-of-00064.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00055-of-00064.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00055-of-00064.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00055-of-00064.safetensors", "model.layers.73.input_layernorm.weight": "model-00055-of-00064.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00055-of-00064.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00055-of-00064.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00055-of-00064.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00056-of-00064.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00056-of-00064.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00056-of-00064.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00056-of-00064.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00056-of-00064.safetensors", "model.layers.74.input_layernorm.weight": "model-00056-of-00064.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00056-of-00064.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00056-of-00064.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00056-of-00064.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00056-of-00064.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00056-of-00064.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00056-of-00064.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00056-of-00064.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00056-of-00064.safetensors", "model.layers.75.input_layernorm.weight": "model-00056-of-00064.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00057-of-00064.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00057-of-00064.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00057-of-00064.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00057-of-00064.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00057-of-00064.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00057-of-00064.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00057-of-00064.safetensors", "model.layers.76.input_layernorm.weight": "model-00057-of-00064.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00057-of-00064.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00057-of-00064.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00058-of-00064.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00058-of-00064.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00058-of-00064.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00058-of-00064.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00058-of-00064.safetensors", "model.layers.77.input_layernorm.weight": "model-00058-of-00064.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00058-of-00064.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00058-of-00064.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00058-of-00064.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00058-of-00064.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00058-of-00064.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00058-of-00064.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00059-of-00064.safetensors", "model.layers.78.input_layernorm.weight": "model-00059-of-00064.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00059-of-00064.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00059-of-00064.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00059-of-00064.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00059-of-00064.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00059-of-00064.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00059-of-00064.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00059-of-00064.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00059-of-00064.safetensors", "model.layers.79.input_layernorm.weight": "model-00059-of-00064.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00059-of-00064.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00059-of-00064.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00060-of-00064.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00060-of-00064.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00060-of-00064.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00060-of-00064.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00060-of-00064.safetensors", "model.layers.8.input_layernorm.weight": "model-00060-of-00064.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00060-of-00064.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00060-of-00064.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00060-of-00064.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00060-of-00064.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00061-of-00064.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00061-of-00064.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00061-of-00064.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00061-of-00064.safetensors", "model.layers.9.input_layernorm.weight": "model-00061-of-00064.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00061-of-00064.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00061-of-00064.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00061-of-00064.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00061-of-00064.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00061-of-00064.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00061-of-00064.safetensors", "model.norm.weight": "model-00061-of-00064.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00061-of-00064.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00061-of-00064.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00062-of-00064.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00062-of-00064.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00062-of-00064.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00062-of-00064.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00062-of-00064.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00062-of-00064.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00062-of-00064.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00062-of-00064.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00062-of-00064.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00062-of-00064.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00062-of-00064.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00062-of-00064.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00062-of-00064.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00063-of-00064.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00063-of-00064.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00063-of-00064.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00063-of-00064.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00063-of-00064.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00063-of-00064.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00063-of-00064.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00063-of-00064.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00063-of-00064.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00063-of-00064.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00063-of-00064.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00063-of-00064.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00064-of-00064.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00064-of-00064.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00064-of-00064.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" +}