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..96c6c494d7f2635a6ada34db5cc5955a4f222ad2 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: +- Sao10K/L3.1-70B-Euryale-v2.2 +- nvidia/Llama-3.1-Nemotron-70B-Instruct-HF +- NeverSleep/Lumimaid-v0.2-70B +library_name: transformers +tags: +- mergekit +- merge + +--- +# llama-3.1-70B-nemotron-lumiyale-120B + +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 [linear](https://arxiv.org/abs/2203.05482) merge method. + +### Models Merged + +The following models were included in the merge: +* [Sao10K/L3.1-70B-Euryale-v2.2](https://huggingface.co/Sao10K/L3.1-70B-Euryale-v2.2) +* [nvidia/Llama-3.1-Nemotron-70B-Instruct-HF](https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF) +* [NeverSleep/Lumimaid-v0.2-70B](https://huggingface.co/NeverSleep/Lumimaid-v0.2-70B) + +### Configuration + +The following YAML configuration was used to produce this model: + +```yaml +merge_method: linear +parameters: + weight: 1.0 +slices: +- sources: + - model: NeverSleep/Lumimaid-v0.2-70B + layer_range: [0, 16] +- sources: + - model: NeverSleep/Lumimaid-v0.2-70B + layer_range: [8, 24] +- sources: + - model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF + layer_range: [17, 32] +- sources: + - model: Sao10K/L3.1-70B-Euryale-v2.2 + layer_range: [25, 40] +- sources: + - model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF + layer_range: [33, 48] +- sources: + - model: Sao10K/L3.1-70B-Euryale-v2.2 + layer_range: [41, 56] +- sources: + - model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF + layer_range: [49, 64] +- sources: + - model: NeverSleep/Lumimaid-v0.2-70B + layer_range: [57, 72] +- sources: + - model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF + layer_range: [65, 80] +dtype: float16 +tokenizer_source: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF + +``` diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..64a7c89bfdee9eecefe2e3219753f0b76822c224 --- /dev/null +++ b/config.json @@ -0,0 +1,36 @@ +{ + "_name_or_path": "Sao10K/L3.1-70B-Euryale-v2.2", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128009, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 8192, + "initializer_range": 0.02, + "intermediate_size": 28672, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 64, + "num_hidden_layers": 137, + "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": "float16", + "transformers_version": "4.45.2", + "use_cache": false, + "vocab_size": 128256 +} diff --git a/mergekit_config.yml b/mergekit_config.yml new file mode 100644 index 0000000000000000000000000000000000000000..fae5cab11f1d77dd2784589b8f96fd20ad5d78fb --- /dev/null +++ b/mergekit_config.yml @@ -0,0 +1,33 @@ +merge_method: linear +parameters: + weight: 1.0 +slices: +- sources: + - model: NeverSleep/Lumimaid-v0.2-70B + layer_range: [0, 16] +- sources: + - model: NeverSleep/Lumimaid-v0.2-70B + layer_range: [8, 24] +- sources: + - model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF + layer_range: [17, 32] +- sources: + - model: Sao10K/L3.1-70B-Euryale-v2.2 + layer_range: [25, 40] +- sources: + - model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF + layer_range: [33, 48] +- sources: + - model: Sao10K/L3.1-70B-Euryale-v2.2 + layer_range: [41, 56] +- sources: + - model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF + layer_range: [49, 64] +- sources: + - model: NeverSleep/Lumimaid-v0.2-70B + layer_range: [57, 72] +- sources: + - model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF + layer_range: [65, 80] +dtype: float16 +tokenizer_source: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF diff --git a/model-00001-of-00050.safetensors b/model-00001-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..79e774678521231d06f220bc07ca895e1f210b7e --- /dev/null +++ b/model-00001-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b252dfdb70781c1e3df4956d4e0c11dfa01d5093509a2011ec9d269c24d2f4d4 +size 4672471496 diff --git a/model-00002-of-00050.safetensors b/model-00002-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d05f915d81f6ef8cb7562faf3cb0dabc33efd8a0 --- /dev/null +++ b/model-00002-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:738f6cfef7ac5443b14f5f086fd3536c1fe12d86a70f0266379e87395ca524e3 +size 4831922680 diff --git a/model-00003-of-00050.safetensors b/model-00003-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b2375428a1af77277927a7b48a692c4c652d0aeb --- /dev/null +++ b/model-00003-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2634345211d0f7d7e98ed199e642082fa445eaee082eb3af1e0f1b82bcd955a9 +size 4966190736 diff --git a/model-00004-of-00050.safetensors b/model-00004-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a695b3979420463fe30095adc115a122c8ccf82a --- /dev/null +++ b/model-00004-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a991b9c32edc3046464cdb0945e256f1c7945181d23ac680516dcdaa45dd89a +size 4831906200 diff --git a/model-00005-of-00050.safetensors b/model-00005-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..857562d50a7cdb8d83d18b890534a3de63277884 --- /dev/null +++ b/model-00005-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab0bd59824f55ccb19dff8165cc561f36feccb28ecdd447dc5e933bc474d4cc0 +size 4999711712 diff --git a/model-00006-of-00050.safetensors b/model-00006-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d31934b8f8ee4c85c670b9f44ac78bad52ce0863 --- /dev/null +++ b/model-00006-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c3ef73f326d75ca3a0493bfa5c24cd71b2d3afbc7ba6a6c1e02b474ec407d20 +size 4798368728 diff --git a/model-00007-of-00050.safetensors b/model-00007-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9df82eb3afe38bbb407e12767b206ecbaf7d3457 --- /dev/null +++ b/model-00007-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d5acbc047f9b21b559ebeed79eebf27b5964e10b3da8867bf79ba78777a99ca +size 4664183880 diff --git a/model-00008-of-00050.safetensors b/model-00008-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..27b60cd950330946608e6bc0580b8f75ed1cf751 --- /dev/null +++ b/model-00008-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81b28de3ad68e0943db485b122163de76aecd2636eb05ad708d2f4a145d85ff0 +size 4831906200 diff --git a/model-00009-of-00050.safetensors b/model-00009-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..807167b011abc54ef4d331f0496e67e583c1a9e8 --- /dev/null +++ b/model-00009-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de94ebd011aa48fef814b37c6dc40c64fdce805eb6d75b2ace3d16fa61119c45 +size 4664167376 diff --git a/model-00010-of-00050.safetensors b/model-00010-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2af0e767c32efa341d5b1c38c6ae7f6749dddcc4 --- /dev/null +++ b/model-00010-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30acfc0d347660bbc9391da5f890bf3814798198f836e839f16e9b1e70a1dea0 +size 4999711712 diff --git a/model-00011-of-00050.safetensors b/model-00011-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..74dad436ea66786a981f9804efc373c3d8084f28 --- /dev/null +++ b/model-00011-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca487eef7075adf005dade8c0656d139dd5688fa813b5256cce04612e023d61f +size 4798385224 diff --git a/model-00012-of-00050.safetensors b/model-00012-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ef8fb180b94d9038624fd37d90b88883a91a7bc1 --- /dev/null +++ b/model-00012-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3264e20d0e20cf135b26133cf53c014078f6ab4c7702467910f46777258ba60c +size 4664167392 diff --git a/model-00013-of-00050.safetensors b/model-00013-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0afe5c2aab505ca9bbd74c2a895e75bb63797798 --- /dev/null +++ b/model-00013-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40d78436fd890873451c432986b214cbcb6c07e23a97e5136ce5c9f1bb78cb44 +size 4831906200 diff --git a/model-00014-of-00050.safetensors b/model-00014-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d8444a7830276d96459e6c33768456156b2e78d6 --- /dev/null +++ b/model-00014-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:747ed6d00a0e4b28d8cd58e0868ac396b9a90eb1a283ed90051f5aa2b761f5a9 +size 4966190736 diff --git a/model-00015-of-00050.safetensors b/model-00015-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..53e9d5348cb86766094143e52b7577226f6b2799 --- /dev/null +++ b/model-00015-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e42c28947a1624f090bcd4f0086f264a54edaafabe1194df62a0fc2931903a6b +size 4831906200 diff --git a/model-00016-of-00050.safetensors b/model-00016-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..154ed90f4397dae18c96ab8d9494bd6dea86a46c --- /dev/null +++ b/model-00016-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71c476100eb86b0acdb30b0efcc20b6c757cdff48b32061331d75852ebbeb9d5 +size 4664167376 diff --git a/model-00017-of-00050.safetensors b/model-00017-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4261e9a93de95777099c90c93760de74007e83f8 --- /dev/null +++ b/model-00017-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d45c80b772950c45c7acf5ec04f74bdb0e7c9ad2ebbd1c7403995bcf191e5b77 +size 4831906200 diff --git a/model-00018-of-00050.safetensors b/model-00018-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9fef941a4d1453b63eb9fe515346a909b7f68444 --- /dev/null +++ b/model-00018-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfdf84d1b077f0360cd0aaf9f172dda57027279939c34ecd7c7c398805518b5d +size 4664167384 diff --git a/model-00019-of-00050.safetensors b/model-00019-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..173f88b9a2fbaf21d693c8cef8cfaf36db8418b3 --- /dev/null +++ b/model-00019-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4eac0f774e2520fc6bca46877ee5e5b1785c51e9eae7db71f03ec9f3ba28bcc4 +size 4966190736 diff --git a/model-00020-of-00050.safetensors b/model-00020-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c744ff3b70d6bd5c5791a44db03080f864c4353f --- /dev/null +++ b/model-00020-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b533aa59cd7b7e42fe2fae430e007557169f82d714b2cbddfa2e3181223dff6 +size 4831906200 diff --git a/model-00021-of-00050.safetensors b/model-00021-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..14d79961f877c3bd970c52327e0c998730df77ba --- /dev/null +++ b/model-00021-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efef74bf3782ecbe8763fc1d18f85953037c863d9b179c828ccba8977d5c1962 +size 4999711712 diff --git a/model-00022-of-00050.safetensors b/model-00022-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b28215121b7567cfafa4f1d16d15e1854f3dd4ea --- /dev/null +++ b/model-00022-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f94514ef037a25d78af7a0a67be8d3cc2763be05dca236d18ae7c2d5291f554 +size 4798385224 diff --git a/model-00023-of-00050.safetensors b/model-00023-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7631bf39be59e92d0b909e6be8d3068e67cbe67d --- /dev/null +++ b/model-00023-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51061f5e8f9701dca910be395a80e8ce466d8785058f865386b8ad902136074a +size 4664150880 diff --git a/model-00024-of-00050.safetensors b/model-00024-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8e0fe697aea1aa4b47ee7eff2887cfa886276525 --- /dev/null +++ b/model-00024-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83f55c49adf1371cb63453db4ea5d3e2a968c6bb6189229f7bd6f15c88e6c0f7 +size 4664183888 diff --git a/model-00025-of-00050.safetensors b/model-00025-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3d6238f075a606ee92d79d802f22d641ad5fa62a --- /dev/null +++ b/model-00025-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28c204c46c980e33fa6f81e46a5a0a3b1c03f4b40b9e3b50c428ebc35e57e66d +size 4831906200 diff --git a/model-00026-of-00050.safetensors b/model-00026-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fdbc70a19dc8a51c70c4459571833963009240e1 --- /dev/null +++ b/model-00026-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfa6a5f989b4d58d3e04f2de2cd856ce7712e9a92acc3395684e644046d0dff3 +size 4999711712 diff --git a/model-00027-of-00050.safetensors b/model-00027-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1f9404815f05f6f1ed4ad3e6937767334060629c --- /dev/null +++ b/model-00027-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a194e90122d86dfc36f7c624eff46c5a5c0899fabe2a8ed7eb68721ca88eab0 +size 4798385224 diff --git a/model-00028-of-00050.safetensors b/model-00028-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ade37b66bd78b620f58b90d04d4ca6180324219e --- /dev/null +++ b/model-00028-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:989b157e5ccd7ee97f60fac86bab736c642ebb5341baaccaddc5b4c1aefd1d57 +size 4831906200 diff --git a/model-00029-of-00050.safetensors b/model-00029-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..328092f424f42487c12d34d66c2ea487071ba2e5 --- /dev/null +++ b/model-00029-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61f78ccf758931224c2eacabcc7d6853b676368d79fbac3201971e72fccba4ab +size 4664167384 diff --git a/model-00030-of-00050.safetensors b/model-00030-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c348a9f998e427202c1170c6e7bedf42f8a392b3 --- /dev/null +++ b/model-00030-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5737b8d1f2382b79dfb493a5ec8ab0418d1025580d39ce04e8086eb28390f7e9 +size 4664167376 diff --git a/model-00031-of-00050.safetensors b/model-00031-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..29628d9bf488517fb9e132b178af24318aeff6ee --- /dev/null +++ b/model-00031-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d5c0e7d77bb34c48a555260a11a854386c45749dd4fb333f69e422d92e63148 +size 4999711712 diff --git a/model-00032-of-00050.safetensors b/model-00032-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6f958852f643ec064b09894b2eb9d1d37d23eeab --- /dev/null +++ b/model-00032-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cbfe6663cbdcaf5655dc43b361a15d22244dd4ed1f29e761bd75416b8d504bf +size 4798385224 diff --git a/model-00033-of-00050.safetensors b/model-00033-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..778228e897d403eaf3d6de8136c6623057ecc421 --- /dev/null +++ b/model-00033-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73af39b6d8f80e1e08d48fa8de8934a3b7855a96f7f7eb7507748a17212a2f5f +size 4831906200 diff --git a/model-00034-of-00050.safetensors b/model-00034-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..93597d8cda8ac4e29d4a0779ece3f6a0be70a2e2 --- /dev/null +++ b/model-00034-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fdb635574defe22da158ebeff880358978607748ddc31b03e5062f9e3075c16 +size 4966174240 diff --git a/model-00035-of-00050.safetensors b/model-00035-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9e6b1ccb3ac31b78e4e4dbaa253b20fd9cbb5c6f --- /dev/null +++ b/model-00035-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:349cc13f32bb6a5b50c0ca16135ee25fbecff1832c068c6c0ae8e3e730d2c789 +size 4664183896 diff --git a/model-00036-of-00050.safetensors b/model-00036-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d9c200337b599a8d76a4c935145bf9028fab4820 --- /dev/null +++ b/model-00036-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:821811f73e2b98db19fa86438ef8922af7310dce6a1a2e21481fadae586ab027 +size 4831906224 diff --git a/model-00037-of-00050.safetensors b/model-00037-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6eed7434e743bda2802e852982c62b7ef3f09650 --- /dev/null +++ b/model-00037-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ea0f1165d16ea4a5c95f2efa5d7cc82d9564025bb8dbea5586f2abaad3e0b5a +size 4664167400 diff --git a/model-00038-of-00050.safetensors b/model-00038-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8b6d1278ea3ef608eaab7d609777e4826d177c78 --- /dev/null +++ b/model-00038-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b104837cc64f8a3aee541e3be542683fa5c42a6024a7bfc613df5fa614ec33ba +size 4831906216 diff --git a/model-00039-of-00050.safetensors b/model-00039-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8f508885184ec4a99ddeed29b0b15c31b896e7a8 --- /dev/null +++ b/model-00039-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:091cafafb639b11e2102c2c5751c8ec132da358553165384e8b49350cf46ef6b +size 4966190768 diff --git a/model-00040-of-00050.safetensors b/model-00040-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1e2752db20889da0ee16878d97d18d9b9bc79385 --- /dev/null +++ b/model-00040-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e32fd1d83df2cd688089c828e02dc59eff56dc0024035fb1164b9a190052589 +size 4664167416 diff --git a/model-00041-of-00050.safetensors b/model-00041-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6fd083e10867c0e125c2f7b9ff54fc045ca4c805 --- /dev/null +++ b/model-00041-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08796b2b977b01e8a0e552998383ba874387ce34a4a7c48d8006bd7e243b6a6e +size 4831906224 diff --git a/model-00042-of-00050.safetensors b/model-00042-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..910b039cbbad473e89516db2516bc0c04caebe3d --- /dev/null +++ b/model-00042-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:027c21d0ed6b5cfc879ead7434486c5c648034bf2fc049b2477bfc3737657043 +size 4999711744 diff --git a/model-00043-of-00050.safetensors b/model-00043-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ab691ca48fe9a6c5cd78f4ade505c5b7c6da964f --- /dev/null +++ b/model-00043-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:203d9f6c8a85dfe1dc122be6844b839afd9dc468e38c95e65db2df98a5cdb2e9 +size 4798385256 diff --git a/model-00044-of-00050.safetensors b/model-00044-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..93a2069d1b1860f90a7810c884f092af9fe1c409 --- /dev/null +++ b/model-00044-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e98f80484ccc150b109c3fd4d6573fc85877f477a438aeded43fda67cdcbe7bf +size 4664167400 diff --git a/model-00045-of-00050.safetensors b/model-00045-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d3714d33f3fa7f0fd93ab571e0c6ffe1a7959086 --- /dev/null +++ b/model-00045-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a3c20bb4766862529e202a9f70a7f59ca0f865501f1bc3c9fe1d14d8af2950c +size 4831906224 diff --git a/model-00046-of-00050.safetensors b/model-00046-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bb933a81e213eaf577ed01e2f3cc21afaf8be8c3 --- /dev/null +++ b/model-00046-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3070361816605a22a9c793803d68c63f71407d05600dd253f98e86b3d1fb022 +size 4966174272 diff --git a/model-00047-of-00050.safetensors b/model-00047-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f43c6df3617962e5f4659423df43bcc829cc58b8 --- /dev/null +++ b/model-00047-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e77fade27a8996d247cfb0374d8f5aae37d92f06a4585825ce12286131796d3 +size 4982917904 diff --git a/model-00048-of-00050.safetensors b/model-00048-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..378c2c91eb313613660dba5124526293ebf77d6b --- /dev/null +++ b/model-00048-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff5753cac749f3bb5472ad4986876888b2f28607e864a6556c7a9a80b77c5cca +size 4999711736 diff --git a/model-00049-of-00050.safetensors b/model-00049-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..513a1546a8d0befbedbf1a148500eba1b77dc64f --- /dev/null +++ b/model-00049-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5f973430fbc4635722ad62ff5e87a5c91eb51e5523f5c3fbce9127924495423 +size 4647390040 diff --git a/model-00050-of-00050.safetensors b/model-00050-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..db1d5beab8de94dd27129e568729f332d3651a21 --- /dev/null +++ b/model-00050-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61468e15d686c7a507e83091da53f2597fded26756e7252db36fa00f078b36ba +size 2483078864 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..4968407c60137df443304400465c2ed69249d63e --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1 @@ +{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 238652014592}, "weight_map": {"lm_head.weight": "model-00001-of-00050.safetensors", "model.embed_tokens.weight": "model-00001-of-00050.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00050.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00050.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00050.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00050.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00050.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00050.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00050.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00050.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00050.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00050.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00050.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00050.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00050.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00050.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00050.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00050.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00050.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00050.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00050.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00050.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00050.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00050.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00050.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00050.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00050.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00050.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00050.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00050.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00050.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00050.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00050.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00050.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00050.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00050.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00050.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00050.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00050.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00050.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00050.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00050.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00050.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00050.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00050.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00050.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00050.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00050.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00050.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00050.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00050.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00050.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00050.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00050.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00050.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00050.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00050.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00050.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00050.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00050.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00050.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00050.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00050.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00050.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00050.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00050.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00050.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00050.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00050.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00050.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00050.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00050.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00050.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00050.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00050.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00050.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00050.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00050.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00050.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00050.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00005-of-00050.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00050.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00050.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00050.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00050.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00050.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00050.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00050.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00050.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00050.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00050.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00050.safetensors", "model.layers.22.input_layernorm.weight": "model-00005-of-00050.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00050.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00005-of-00050.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00005-of-00050.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00050.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00050.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00005-of-00050.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00005-of-00050.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00050.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00050.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00050.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00050.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00050.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00050.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00050.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00050.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00050.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00050.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00050.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00050.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00006-of-00050.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00006-of-00050.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00050.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00050.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00006-of-00050.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00006-of-00050.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00050.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00050.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00050.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00050.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00050.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00050.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00050.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00050.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00050.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00050.safetensors", "model.layers.24.input_layernorm.weight": "model-00006-of-00050.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00006-of-00050.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00050.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00007-of-00050.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00050.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00050.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00050.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00050.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00050.safetensors", "model.layers.32.input_layernorm.weight": "model-00007-of-00050.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00050.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00007-of-00050.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00007-of-00050.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00050.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00050.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00007-of-00050.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00007-of-00050.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00050.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00050.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00050.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00050.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00050.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00050.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00050.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00050.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00050.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00050.safetensors", "model.layers.33.input_layernorm.weight": "model-00007-of-00050.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00050.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00007-of-00050.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00008-of-00050.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00050.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00050.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00008-of-00050.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00008-of-00050.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00050.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00050.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00050.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00050.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00050.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00050.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00050.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00050.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00050.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00050.safetensors", "model.layers.34.input_layernorm.weight": "model-00008-of-00050.safetensors", "model.layers.27.input_layernorm.weight": "model-00008-of-00050.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00008-of-00050.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00008-of-00050.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00050.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00050.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00009-of-00050.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00009-of-00050.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00009-of-00050.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00050.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00050.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00050.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00050.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00050.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00050.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00050.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00050.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00050.safetensors", "model.layers.2.input_layernorm.weight": "model-00009-of-00050.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00009-of-00050.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00009-of-00050.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00009-of-00050.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00009-of-00050.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00009-of-00050.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00009-of-00050.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00009-of-00050.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00009-of-00050.safetensors", "model.layers.35.input_layernorm.weight": "model-00009-of-00050.safetensors", "model.layers.28.input_layernorm.weight": "model-00009-of-00050.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00009-of-00050.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00009-of-00050.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00050.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00010-of-00050.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00010-of-00050.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00010-of-00050.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00010-of-00050.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00010-of-00050.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00010-of-00050.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00010-of-00050.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00010-of-00050.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00010-of-00050.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00010-of-00050.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00010-of-00050.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00010-of-00050.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00010-of-00050.safetensors", "model.layers.36.input_layernorm.weight": "model-00010-of-00050.safetensors", "model.layers.29.input_layernorm.weight": "model-00010-of-00050.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00010-of-00050.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00010-of-00050.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00010-of-00050.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00010-of-00050.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00010-of-00050.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00010-of-00050.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00010-of-00050.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00050.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00010-of-00050.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00050.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00010-of-00050.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00050.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00011-of-00050.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00050.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00011-of-00050.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00050.safetensors", "model.layers.37.input_layernorm.weight": "model-00011-of-00050.safetensors", "model.layers.30.input_layernorm.weight": "model-00011-of-00050.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00011-of-00050.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00011-of-00050.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00011-of-00050.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00011-of-00050.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00011-of-00050.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00011-of-00050.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00011-of-00050.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00011-of-00050.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00011-of-00050.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00011-of-00050.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00011-of-00050.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00050.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00011-of-00050.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00050.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00011-of-00050.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00050.safetensors", "model.layers.38.input_layernorm.weight": "model-00011-of-00050.safetensors", "model.layers.31.input_layernorm.weight": "model-00011-of-00050.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00011-of-00050.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00011-of-00050.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00012-of-00050.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00050.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00012-of-00050.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00012-of-00050.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00012-of-00050.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00050.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00012-of-00050.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00050.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00012-of-00050.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00050.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00012-of-00050.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00050.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00012-of-00050.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00050.safetensors", "model.layers.39.input_layernorm.weight": "model-00012-of-00050.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00012-of-00050.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00012-of-00050.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00012-of-00050.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00012-of-00050.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00012-of-00050.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00012-of-00050.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00012-of-00050.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00012-of-00050.safetensors", "model.layers.47.input_layernorm.weight": "model-00012-of-00050.safetensors", "model.layers.40.input_layernorm.weight": "model-00012-of-00050.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00012-of-00050.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00013-of-00050.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00013-of-00050.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00013-of-00050.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00013-of-00050.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00013-of-00050.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00013-of-00050.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00013-of-00050.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00013-of-00050.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00013-of-00050.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00013-of-00050.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00013-of-00050.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00013-of-00050.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00013-of-00050.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00013-of-00050.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00013-of-00050.safetensors", "model.layers.48.input_layernorm.weight": "model-00013-of-00050.safetensors", "model.layers.41.input_layernorm.weight": "model-00013-of-00050.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00013-of-00050.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00013-of-00050.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00013-of-00050.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00013-of-00050.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00014-of-00050.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00014-of-00050.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00014-of-00050.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00014-of-00050.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00014-of-00050.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00014-of-00050.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00014-of-00050.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00014-of-00050.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00014-of-00050.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00014-of-00050.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00014-of-00050.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00014-of-00050.safetensors", "model.layers.49.input_layernorm.weight": "model-00014-of-00050.safetensors", "model.layers.42.input_layernorm.weight": "model-00014-of-00050.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00014-of-00050.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00014-of-00050.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00014-of-00050.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00014-of-00050.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00014-of-00050.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00014-of-00050.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00014-of-00050.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00014-of-00050.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00014-of-00050.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00014-of-00050.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00014-of-00050.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00014-of-00050.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00014-of-00050.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00014-of-00050.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00014-of-00050.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00014-of-00050.safetensors", "model.layers.50.input_layernorm.weight": "model-00014-of-00050.safetensors", "model.layers.43.input_layernorm.weight": "model-00014-of-00050.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00015-of-00050.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00015-of-00050.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00015-of-00050.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00015-of-00050.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00015-of-00050.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00015-of-00050.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00015-of-00050.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00015-of-00050.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00015-of-00050.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00015-of-00050.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00015-of-00050.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00015-of-00050.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00015-of-00050.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00015-of-00050.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00015-of-00050.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00015-of-00050.safetensors", "model.layers.51.input_layernorm.weight": "model-00015-of-00050.safetensors", "model.layers.44.input_layernorm.weight": "model-00015-of-00050.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00015-of-00050.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00015-of-00050.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00015-of-00050.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00016-of-00050.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00016-of-00050.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00016-of-00050.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00016-of-00050.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00016-of-00050.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00016-of-00050.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00016-of-00050.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00016-of-00050.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00016-of-00050.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00016-of-00050.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00016-of-00050.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00016-of-00050.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00016-of-00050.safetensors", "model.layers.3.input_layernorm.weight": "model-00016-of-00050.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00016-of-00050.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00016-of-00050.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00016-of-00050.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00016-of-00050.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00016-of-00050.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00016-of-00050.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00016-of-00050.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00016-of-00050.safetensors", "model.layers.52.input_layernorm.weight": "model-00016-of-00050.safetensors", "model.layers.45.input_layernorm.weight": "model-00016-of-00050.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00016-of-00050.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00016-of-00050.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00017-of-00050.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00017-of-00050.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00017-of-00050.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00017-of-00050.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00017-of-00050.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00017-of-00050.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00017-of-00050.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00017-of-00050.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00017-of-00050.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00017-of-00050.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00017-of-00050.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00017-of-00050.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00017-of-00050.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00017-of-00050.safetensors", "model.layers.53.input_layernorm.weight": "model-00017-of-00050.safetensors", "model.layers.46.input_layernorm.weight": "model-00017-of-00050.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00017-of-00050.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00017-of-00050.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00017-of-00050.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00017-of-00050.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00017-of-00050.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00018-of-00050.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00018-of-00050.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00018-of-00050.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00018-of-00050.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00018-of-00050.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00018-of-00050.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00018-of-00050.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00018-of-00050.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00018-of-00050.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00018-of-00050.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00018-of-00050.safetensors", "model.layers.54.input_layernorm.weight": "model-00018-of-00050.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00018-of-00050.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00018-of-00050.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00018-of-00050.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00018-of-00050.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00018-of-00050.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00018-of-00050.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00018-of-00050.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00018-of-00050.safetensors", "model.layers.62.input_layernorm.weight": "model-00018-of-00050.safetensors", "model.layers.55.input_layernorm.weight": "model-00018-of-00050.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00018-of-00050.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00018-of-00050.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00018-of-00050.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00018-of-00050.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00019-of-00050.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00019-of-00050.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00019-of-00050.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00019-of-00050.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00019-of-00050.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00019-of-00050.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00019-of-00050.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00019-of-00050.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00019-of-00050.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00019-of-00050.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00019-of-00050.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00019-of-00050.safetensors", "model.layers.63.input_layernorm.weight": "model-00019-of-00050.safetensors", "model.layers.56.input_layernorm.weight": "model-00019-of-00050.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00019-of-00050.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00019-of-00050.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00019-of-00050.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00019-of-00050.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00019-of-00050.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00019-of-00050.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00019-of-00050.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00019-of-00050.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00019-of-00050.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00019-of-00050.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00019-of-00050.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00019-of-00050.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00019-of-00050.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00019-of-00050.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00019-of-00050.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00019-of-00050.safetensors", "model.layers.64.input_layernorm.weight": "model-00019-of-00050.safetensors", "model.layers.57.input_layernorm.weight": "model-00019-of-00050.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00020-of-00050.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00020-of-00050.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00020-of-00050.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00020-of-00050.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00020-of-00050.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00020-of-00050.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00020-of-00050.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00020-of-00050.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00020-of-00050.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00020-of-00050.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00020-of-00050.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00020-of-00050.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00020-of-00050.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00020-of-00050.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00020-of-00050.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00020-of-00050.safetensors", "model.layers.65.input_layernorm.weight": "model-00020-of-00050.safetensors", "model.layers.58.input_layernorm.weight": "model-00020-of-00050.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00020-of-00050.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00020-of-00050.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00020-of-00050.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00021-of-00050.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00021-of-00050.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00021-of-00050.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00021-of-00050.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00021-of-00050.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00021-of-00050.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00021-of-00050.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00021-of-00050.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00021-of-00050.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00021-of-00050.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00021-of-00050.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00021-of-00050.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00021-of-00050.safetensors", "model.layers.66.input_layernorm.weight": "model-00021-of-00050.safetensors", "model.layers.59.input_layernorm.weight": "model-00021-of-00050.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00021-of-00050.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00021-of-00050.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00021-of-00050.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00021-of-00050.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00021-of-00050.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00021-of-00050.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00021-of-00050.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00021-of-00050.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00021-of-00050.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00021-of-00050.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00021-of-00050.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00022-of-00050.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00022-of-00050.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00022-of-00050.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00022-of-00050.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00022-of-00050.safetensors", "model.layers.67.input_layernorm.weight": "model-00022-of-00050.safetensors", "model.layers.60.input_layernorm.weight": "model-00022-of-00050.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00022-of-00050.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00022-of-00050.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00022-of-00050.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00022-of-00050.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00022-of-00050.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00022-of-00050.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00022-of-00050.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00022-of-00050.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00022-of-00050.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00022-of-00050.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00022-of-00050.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00022-of-00050.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00022-of-00050.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00022-of-00050.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00022-of-00050.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00022-of-00050.safetensors", "model.layers.68.input_layernorm.weight": "model-00022-of-00050.safetensors", "model.layers.61.input_layernorm.weight": "model-00022-of-00050.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00022-of-00050.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00022-of-00050.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00023-of-00050.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00023-of-00050.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00023-of-00050.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00023-of-00050.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00023-of-00050.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00023-of-00050.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00023-of-00050.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00023-of-00050.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00023-of-00050.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00023-of-00050.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00023-of-00050.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00023-of-00050.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00023-of-00050.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00023-of-00050.safetensors", "model.layers.4.input_layernorm.weight": "model-00023-of-00050.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00023-of-00050.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00023-of-00050.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00023-of-00050.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00023-of-00050.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00023-of-00050.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00023-of-00050.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00023-of-00050.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00023-of-00050.safetensors", "model.layers.69.input_layernorm.weight": "model-00023-of-00050.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00023-of-00050.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00024-of-00050.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00024-of-00050.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00024-of-00050.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00024-of-00050.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00024-of-00050.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00024-of-00050.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00024-of-00050.safetensors", "model.layers.77.input_layernorm.weight": "model-00024-of-00050.safetensors", "model.layers.70.input_layernorm.weight": "model-00024-of-00050.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00024-of-00050.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00024-of-00050.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00024-of-00050.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00024-of-00050.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00024-of-00050.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00024-of-00050.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00024-of-00050.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00024-of-00050.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00024-of-00050.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00024-of-00050.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00024-of-00050.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00024-of-00050.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00024-of-00050.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00024-of-00050.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00024-of-00050.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00024-of-00050.safetensors", "model.layers.78.input_layernorm.weight": "model-00024-of-00050.safetensors", "model.layers.71.input_layernorm.weight": "model-00024-of-00050.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00025-of-00050.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00025-of-00050.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00025-of-00050.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00025-of-00050.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00025-of-00050.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00025-of-00050.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00025-of-00050.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00025-of-00050.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00025-of-00050.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00025-of-00050.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00025-of-00050.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00025-of-00050.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00025-of-00050.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00025-of-00050.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00025-of-00050.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00025-of-00050.safetensors", "model.layers.79.input_layernorm.weight": "model-00025-of-00050.safetensors", "model.layers.72.input_layernorm.weight": "model-00025-of-00050.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00025-of-00050.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00025-of-00050.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00025-of-00050.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00026-of-00050.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00026-of-00050.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00026-of-00050.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00026-of-00050.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00026-of-00050.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00026-of-00050.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00026-of-00050.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00026-of-00050.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00026-of-00050.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00026-of-00050.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00026-of-00050.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00026-of-00050.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00026-of-00050.safetensors", "model.layers.80.input_layernorm.weight": "model-00026-of-00050.safetensors", "model.layers.73.input_layernorm.weight": "model-00026-of-00050.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00026-of-00050.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00026-of-00050.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00026-of-00050.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00026-of-00050.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00026-of-00050.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00026-of-00050.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00026-of-00050.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00026-of-00050.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00026-of-00050.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00026-of-00050.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00026-of-00050.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00027-of-00050.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00027-of-00050.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00027-of-00050.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00027-of-00050.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00027-of-00050.safetensors", "model.layers.81.input_layernorm.weight": "model-00027-of-00050.safetensors", "model.layers.74.input_layernorm.weight": "model-00027-of-00050.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00027-of-00050.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00027-of-00050.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00027-of-00050.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00027-of-00050.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00027-of-00050.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00027-of-00050.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00027-of-00050.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00027-of-00050.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00027-of-00050.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00027-of-00050.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00027-of-00050.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00027-of-00050.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00027-of-00050.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00027-of-00050.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00027-of-00050.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00027-of-00050.safetensors", "model.layers.82.input_layernorm.weight": "model-00027-of-00050.safetensors", "model.layers.75.input_layernorm.weight": "model-00027-of-00050.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00027-of-00050.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00027-of-00050.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00028-of-00050.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00028-of-00050.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00028-of-00050.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00028-of-00050.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00028-of-00050.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00028-of-00050.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00028-of-00050.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00028-of-00050.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00028-of-00050.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00028-of-00050.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00028-of-00050.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00028-of-00050.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00028-of-00050.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00028-of-00050.safetensors", "model.layers.83.input_layernorm.weight": "model-00028-of-00050.safetensors", "model.layers.76.input_layernorm.weight": "model-00028-of-00050.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00028-of-00050.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00028-of-00050.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00028-of-00050.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00028-of-00050.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00028-of-00050.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00029-of-00050.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00029-of-00050.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00029-of-00050.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00029-of-00050.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00029-of-00050.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00029-of-00050.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00029-of-00050.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00029-of-00050.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00029-of-00050.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00029-of-00050.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00029-of-00050.safetensors", "model.layers.84.input_layernorm.weight": "model-00029-of-00050.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00029-of-00050.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00029-of-00050.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00029-of-00050.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00029-of-00050.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00029-of-00050.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00029-of-00050.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00029-of-00050.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00029-of-00050.safetensors", "model.layers.92.input_layernorm.weight": "model-00029-of-00050.safetensors", "model.layers.85.input_layernorm.weight": "model-00029-of-00050.safetensors", "model.layers.92.mlp.down_proj.weight": "model-00029-of-00050.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00029-of-00050.safetensors", "model.layers.92.mlp.gate_proj.weight": "model-00029-of-00050.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00029-of-00050.safetensors", "model.layers.92.mlp.up_proj.weight": "model-00030-of-00050.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00030-of-00050.safetensors", "model.layers.92.post_attention_layernorm.weight": "model-00030-of-00050.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00030-of-00050.safetensors", "model.layers.92.self_attn.k_proj.weight": "model-00030-of-00050.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00030-of-00050.safetensors", "model.layers.92.self_attn.o_proj.weight": "model-00030-of-00050.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00030-of-00050.safetensors", "model.layers.92.self_attn.q_proj.weight": "model-00030-of-00050.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00030-of-00050.safetensors", "model.layers.92.self_attn.v_proj.weight": "model-00030-of-00050.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00030-of-00050.safetensors", "model.layers.5.input_layernorm.weight": "model-00030-of-00050.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00030-of-00050.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00030-of-00050.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00030-of-00050.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00030-of-00050.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00030-of-00050.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00030-of-00050.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00030-of-00050.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00030-of-00050.safetensors", "model.layers.93.input_layernorm.weight": "model-00030-of-00050.safetensors", "model.layers.86.input_layernorm.weight": "model-00030-of-00050.safetensors", "model.layers.93.mlp.down_proj.weight": "model-00030-of-00050.safetensors", "model.layers.86.mlp.down_proj.weight": "model-00030-of-00050.safetensors", "model.layers.93.mlp.gate_proj.weight": "model-00030-of-00050.safetensors", "model.layers.86.mlp.gate_proj.weight": "model-00031-of-00050.safetensors", "model.layers.93.mlp.up_proj.weight": "model-00031-of-00050.safetensors", "model.layers.86.mlp.up_proj.weight": "model-00031-of-00050.safetensors", "model.layers.93.post_attention_layernorm.weight": "model-00031-of-00050.safetensors", "model.layers.86.post_attention_layernorm.weight": "model-00031-of-00050.safetensors", "model.layers.93.self_attn.k_proj.weight": "model-00031-of-00050.safetensors", "model.layers.86.self_attn.k_proj.weight": "model-00031-of-00050.safetensors", "model.layers.93.self_attn.o_proj.weight": "model-00031-of-00050.safetensors", "model.layers.86.self_attn.o_proj.weight": "model-00031-of-00050.safetensors", "model.layers.93.self_attn.q_proj.weight": "model-00031-of-00050.safetensors", "model.layers.86.self_attn.q_proj.weight": "model-00031-of-00050.safetensors", "model.layers.93.self_attn.v_proj.weight": "model-00031-of-00050.safetensors", "model.layers.86.self_attn.v_proj.weight": "model-00031-of-00050.safetensors", "model.layers.94.input_layernorm.weight": "model-00031-of-00050.safetensors", "model.layers.87.input_layernorm.weight": "model-00031-of-00050.safetensors", "model.layers.94.mlp.down_proj.weight": "model-00031-of-00050.safetensors", "model.layers.87.mlp.down_proj.weight": "model-00031-of-00050.safetensors", "model.layers.94.mlp.gate_proj.weight": "model-00031-of-00050.safetensors", "model.layers.87.mlp.gate_proj.weight": "model-00031-of-00050.safetensors", "model.layers.94.mlp.up_proj.weight": "model-00031-of-00050.safetensors", "model.layers.87.mlp.up_proj.weight": "model-00031-of-00050.safetensors", "model.layers.94.post_attention_layernorm.weight": "model-00031-of-00050.safetensors", "model.layers.87.post_attention_layernorm.weight": "model-00031-of-00050.safetensors", "model.layers.94.self_attn.k_proj.weight": "model-00031-of-00050.safetensors", "model.layers.87.self_attn.k_proj.weight": "model-00031-of-00050.safetensors", "model.layers.94.self_attn.o_proj.weight": "model-00031-of-00050.safetensors", "model.layers.87.self_attn.o_proj.weight": "model-00032-of-00050.safetensors", "model.layers.94.self_attn.q_proj.weight": "model-00032-of-00050.safetensors", "model.layers.87.self_attn.q_proj.weight": "model-00032-of-00050.safetensors", "model.layers.94.self_attn.v_proj.weight": "model-00032-of-00050.safetensors", "model.layers.87.self_attn.v_proj.weight": "model-00032-of-00050.safetensors", "model.layers.95.input_layernorm.weight": "model-00032-of-00050.safetensors", "model.layers.88.input_layernorm.weight": "model-00032-of-00050.safetensors", "model.layers.95.mlp.down_proj.weight": "model-00032-of-00050.safetensors", "model.layers.88.mlp.down_proj.weight": "model-00032-of-00050.safetensors", "model.layers.95.mlp.gate_proj.weight": "model-00032-of-00050.safetensors", "model.layers.88.mlp.gate_proj.weight": "model-00032-of-00050.safetensors", "model.layers.95.mlp.up_proj.weight": "model-00032-of-00050.safetensors", "model.layers.88.mlp.up_proj.weight": "model-00032-of-00050.safetensors", "model.layers.95.post_attention_layernorm.weight": "model-00032-of-00050.safetensors", "model.layers.88.post_attention_layernorm.weight": "model-00032-of-00050.safetensors", "model.layers.95.self_attn.k_proj.weight": "model-00032-of-00050.safetensors", "model.layers.88.self_attn.k_proj.weight": "model-00032-of-00050.safetensors", "model.layers.95.self_attn.o_proj.weight": "model-00032-of-00050.safetensors", "model.layers.88.self_attn.o_proj.weight": "model-00032-of-00050.safetensors", "model.layers.95.self_attn.q_proj.weight": "model-00032-of-00050.safetensors", "model.layers.88.self_attn.q_proj.weight": "model-00032-of-00050.safetensors", "model.layers.95.self_attn.v_proj.weight": "model-00032-of-00050.safetensors", "model.layers.88.self_attn.v_proj.weight": "model-00032-of-00050.safetensors", "model.layers.96.input_layernorm.weight": "model-00032-of-00050.safetensors", "model.layers.89.input_layernorm.weight": "model-00032-of-00050.safetensors", "model.layers.96.mlp.down_proj.weight": "model-00032-of-00050.safetensors", "model.layers.89.mlp.down_proj.weight": "model-00032-of-00050.safetensors", "model.layers.96.mlp.gate_proj.weight": "model-00033-of-00050.safetensors", "model.layers.89.mlp.gate_proj.weight": "model-00033-of-00050.safetensors", "model.layers.96.mlp.up_proj.weight": "model-00033-of-00050.safetensors", "model.layers.89.mlp.up_proj.weight": "model-00033-of-00050.safetensors", "model.layers.96.post_attention_layernorm.weight": "model-00033-of-00050.safetensors", "model.layers.89.post_attention_layernorm.weight": "model-00033-of-00050.safetensors", "model.layers.96.self_attn.k_proj.weight": "model-00033-of-00050.safetensors", "model.layers.89.self_attn.k_proj.weight": "model-00033-of-00050.safetensors", "model.layers.96.self_attn.o_proj.weight": "model-00033-of-00050.safetensors", "model.layers.89.self_attn.o_proj.weight": "model-00033-of-00050.safetensors", "model.layers.96.self_attn.q_proj.weight": "model-00033-of-00050.safetensors", "model.layers.89.self_attn.q_proj.weight": "model-00033-of-00050.safetensors", "model.layers.96.self_attn.v_proj.weight": "model-00033-of-00050.safetensors", "model.layers.89.self_attn.v_proj.weight": "model-00033-of-00050.safetensors", "model.layers.97.input_layernorm.weight": "model-00033-of-00050.safetensors", "model.layers.90.input_layernorm.weight": "model-00033-of-00050.safetensors", "model.layers.97.mlp.down_proj.weight": "model-00033-of-00050.safetensors", "model.layers.90.mlp.down_proj.weight": "model-00033-of-00050.safetensors", "model.layers.97.mlp.gate_proj.weight": "model-00033-of-00050.safetensors", "model.layers.90.mlp.gate_proj.weight": "model-00033-of-00050.safetensors", "model.layers.97.mlp.up_proj.weight": "model-00033-of-00050.safetensors", "model.layers.90.mlp.up_proj.weight": "model-00034-of-00050.safetensors", "model.layers.97.post_attention_layernorm.weight": "model-00034-of-00050.safetensors", "model.layers.90.post_attention_layernorm.weight": "model-00034-of-00050.safetensors", "model.layers.97.self_attn.k_proj.weight": "model-00034-of-00050.safetensors", "model.layers.90.self_attn.k_proj.weight": "model-00034-of-00050.safetensors", "model.layers.97.self_attn.o_proj.weight": "model-00034-of-00050.safetensors", "model.layers.90.self_attn.o_proj.weight": "model-00034-of-00050.safetensors", "model.layers.97.self_attn.q_proj.weight": "model-00034-of-00050.safetensors", "model.layers.90.self_attn.q_proj.weight": "model-00034-of-00050.safetensors", "model.layers.97.self_attn.v_proj.weight": "model-00034-of-00050.safetensors", "model.layers.90.self_attn.v_proj.weight": "model-00034-of-00050.safetensors", "model.layers.98.input_layernorm.weight": "model-00034-of-00050.safetensors", "model.layers.91.input_layernorm.weight": "model-00034-of-00050.safetensors", "model.layers.98.mlp.down_proj.weight": "model-00034-of-00050.safetensors", "model.layers.91.mlp.down_proj.weight": "model-00034-of-00050.safetensors", "model.layers.98.mlp.gate_proj.weight": "model-00034-of-00050.safetensors", "model.layers.91.mlp.gate_proj.weight": "model-00034-of-00050.safetensors", "model.layers.98.mlp.up_proj.weight": "model-00034-of-00050.safetensors", "model.layers.91.mlp.up_proj.weight": "model-00034-of-00050.safetensors", "model.layers.98.post_attention_layernorm.weight": "model-00034-of-00050.safetensors", "model.layers.91.post_attention_layernorm.weight": "model-00034-of-00050.safetensors", "model.layers.98.self_attn.k_proj.weight": "model-00034-of-00050.safetensors", "model.layers.91.self_attn.k_proj.weight": "model-00034-of-00050.safetensors", "model.layers.98.self_attn.o_proj.weight": "model-00034-of-00050.safetensors", "model.layers.91.self_attn.o_proj.weight": "model-00034-of-00050.safetensors", "model.layers.98.self_attn.q_proj.weight": "model-00034-of-00050.safetensors", "model.layers.91.self_attn.q_proj.weight": "model-00034-of-00050.safetensors", "model.layers.98.self_attn.v_proj.weight": "model-00034-of-00050.safetensors", "model.layers.91.self_attn.v_proj.weight": "model-00034-of-00050.safetensors", "model.layers.99.input_layernorm.weight": "model-00034-of-00050.safetensors", "model.layers.99.mlp.down_proj.weight": "model-00034-of-00050.safetensors", "model.layers.99.mlp.gate_proj.weight": "model-00035-of-00050.safetensors", "model.layers.99.mlp.up_proj.weight": "model-00035-of-00050.safetensors", "model.layers.99.post_attention_layernorm.weight": "model-00035-of-00050.safetensors", "model.layers.99.self_attn.k_proj.weight": "model-00035-of-00050.safetensors", "model.layers.99.self_attn.o_proj.weight": "model-00035-of-00050.safetensors", "model.layers.99.self_attn.q_proj.weight": "model-00035-of-00050.safetensors", "model.layers.99.self_attn.v_proj.weight": "model-00035-of-00050.safetensors", "model.layers.107.input_layernorm.weight": "model-00035-of-00050.safetensors", "model.layers.100.input_layernorm.weight": "model-00035-of-00050.safetensors", "model.layers.107.mlp.down_proj.weight": "model-00035-of-00050.safetensors", "model.layers.100.mlp.down_proj.weight": "model-00035-of-00050.safetensors", "model.layers.107.mlp.gate_proj.weight": "model-00035-of-00050.safetensors", "model.layers.100.mlp.gate_proj.weight": "model-00035-of-00050.safetensors", "model.layers.107.mlp.up_proj.weight": "model-00035-of-00050.safetensors", "model.layers.100.mlp.up_proj.weight": "model-00035-of-00050.safetensors", "model.layers.107.post_attention_layernorm.weight": "model-00035-of-00050.safetensors", "model.layers.100.post_attention_layernorm.weight": "model-00035-of-00050.safetensors", "model.layers.107.self_attn.k_proj.weight": "model-00035-of-00050.safetensors", "model.layers.100.self_attn.k_proj.weight": "model-00035-of-00050.safetensors", "model.layers.107.self_attn.o_proj.weight": "model-00035-of-00050.safetensors", "model.layers.100.self_attn.o_proj.weight": "model-00035-of-00050.safetensors", "model.layers.107.self_attn.q_proj.weight": "model-00035-of-00050.safetensors", "model.layers.100.self_attn.q_proj.weight": "model-00035-of-00050.safetensors", "model.layers.107.self_attn.v_proj.weight": "model-00035-of-00050.safetensors", "model.layers.100.self_attn.v_proj.weight": "model-00035-of-00050.safetensors", "model.layers.108.input_layernorm.weight": "model-00035-of-00050.safetensors", "model.layers.101.input_layernorm.weight": "model-00035-of-00050.safetensors", "model.layers.108.mlp.down_proj.weight": "model-00036-of-00050.safetensors", "model.layers.101.mlp.down_proj.weight": "model-00036-of-00050.safetensors", "model.layers.108.mlp.gate_proj.weight": "model-00036-of-00050.safetensors", "model.layers.101.mlp.gate_proj.weight": "model-00036-of-00050.safetensors", "model.layers.108.mlp.up_proj.weight": "model-00036-of-00050.safetensors", "model.layers.101.mlp.up_proj.weight": "model-00036-of-00050.safetensors", "model.layers.108.post_attention_layernorm.weight": "model-00036-of-00050.safetensors", "model.layers.101.post_attention_layernorm.weight": "model-00036-of-00050.safetensors", "model.layers.108.self_attn.k_proj.weight": "model-00036-of-00050.safetensors", "model.layers.101.self_attn.k_proj.weight": "model-00036-of-00050.safetensors", "model.layers.108.self_attn.o_proj.weight": "model-00036-of-00050.safetensors", "model.layers.101.self_attn.o_proj.weight": "model-00036-of-00050.safetensors", "model.layers.108.self_attn.q_proj.weight": "model-00036-of-00050.safetensors", "model.layers.101.self_attn.q_proj.weight": "model-00036-of-00050.safetensors", "model.layers.108.self_attn.v_proj.weight": "model-00036-of-00050.safetensors", "model.layers.101.self_attn.v_proj.weight": "model-00036-of-00050.safetensors", "model.layers.109.input_layernorm.weight": "model-00036-of-00050.safetensors", "model.layers.102.input_layernorm.weight": "model-00036-of-00050.safetensors", "model.layers.109.mlp.down_proj.weight": "model-00036-of-00050.safetensors", "model.layers.102.mlp.down_proj.weight": "model-00036-of-00050.safetensors", "model.layers.109.mlp.gate_proj.weight": "model-00036-of-00050.safetensors", "model.layers.102.mlp.gate_proj.weight": "model-00037-of-00050.safetensors", "model.layers.109.mlp.up_proj.weight": "model-00037-of-00050.safetensors", "model.layers.102.mlp.up_proj.weight": "model-00037-of-00050.safetensors", "model.layers.109.post_attention_layernorm.weight": "model-00037-of-00050.safetensors", "model.layers.102.post_attention_layernorm.weight": "model-00037-of-00050.safetensors", "model.layers.109.self_attn.k_proj.weight": "model-00037-of-00050.safetensors", "model.layers.102.self_attn.k_proj.weight": "model-00037-of-00050.safetensors", "model.layers.109.self_attn.o_proj.weight": "model-00037-of-00050.safetensors", "model.layers.102.self_attn.o_proj.weight": "model-00037-of-00050.safetensors", "model.layers.109.self_attn.q_proj.weight": "model-00037-of-00050.safetensors", "model.layers.102.self_attn.q_proj.weight": "model-00037-of-00050.safetensors", "model.layers.109.self_attn.v_proj.weight": "model-00037-of-00050.safetensors", "model.layers.102.self_attn.v_proj.weight": "model-00037-of-00050.safetensors", "model.layers.6.input_layernorm.weight": "model-00037-of-00050.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00037-of-00050.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00037-of-00050.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00037-of-00050.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00037-of-00050.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00037-of-00050.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00037-of-00050.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00037-of-00050.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00037-of-00050.safetensors", "model.layers.110.input_layernorm.weight": "model-00037-of-00050.safetensors", "model.layers.103.input_layernorm.weight": "model-00037-of-00050.safetensors", "model.layers.110.mlp.down_proj.weight": "model-00037-of-00050.safetensors", "model.layers.103.mlp.down_proj.weight": "model-00037-of-00050.safetensors", "model.layers.110.mlp.gate_proj.weight": "model-00038-of-00050.safetensors", "model.layers.103.mlp.gate_proj.weight": "model-00038-of-00050.safetensors", "model.layers.110.mlp.up_proj.weight": "model-00038-of-00050.safetensors", "model.layers.103.mlp.up_proj.weight": "model-00038-of-00050.safetensors", "model.layers.110.post_attention_layernorm.weight": "model-00038-of-00050.safetensors", "model.layers.103.post_attention_layernorm.weight": "model-00038-of-00050.safetensors", "model.layers.110.self_attn.k_proj.weight": "model-00038-of-00050.safetensors", "model.layers.103.self_attn.k_proj.weight": "model-00038-of-00050.safetensors", "model.layers.110.self_attn.o_proj.weight": "model-00038-of-00050.safetensors", "model.layers.103.self_attn.o_proj.weight": "model-00038-of-00050.safetensors", "model.layers.110.self_attn.q_proj.weight": "model-00038-of-00050.safetensors", "model.layers.103.self_attn.q_proj.weight": "model-00038-of-00050.safetensors", "model.layers.110.self_attn.v_proj.weight": "model-00038-of-00050.safetensors", "model.layers.103.self_attn.v_proj.weight": "model-00038-of-00050.safetensors", "model.layers.111.input_layernorm.weight": "model-00038-of-00050.safetensors", "model.layers.104.input_layernorm.weight": "model-00038-of-00050.safetensors", "model.layers.111.mlp.down_proj.weight": "model-00038-of-00050.safetensors", "model.layers.104.mlp.down_proj.weight": "model-00038-of-00050.safetensors", "model.layers.111.mlp.gate_proj.weight": "model-00038-of-00050.safetensors", "model.layers.104.mlp.gate_proj.weight": "model-00038-of-00050.safetensors", "model.layers.111.mlp.up_proj.weight": "model-00038-of-00050.safetensors", "model.layers.104.mlp.up_proj.weight": "model-00039-of-00050.safetensors", "model.layers.111.post_attention_layernorm.weight": "model-00039-of-00050.safetensors", "model.layers.104.post_attention_layernorm.weight": "model-00039-of-00050.safetensors", "model.layers.111.self_attn.k_proj.weight": "model-00039-of-00050.safetensors", "model.layers.104.self_attn.k_proj.weight": "model-00039-of-00050.safetensors", "model.layers.111.self_attn.o_proj.weight": "model-00039-of-00050.safetensors", "model.layers.104.self_attn.o_proj.weight": "model-00039-of-00050.safetensors", "model.layers.111.self_attn.q_proj.weight": "model-00039-of-00050.safetensors", "model.layers.104.self_attn.q_proj.weight": "model-00039-of-00050.safetensors", "model.layers.111.self_attn.v_proj.weight": "model-00039-of-00050.safetensors", "model.layers.104.self_attn.v_proj.weight": "model-00039-of-00050.safetensors", "model.layers.112.input_layernorm.weight": "model-00039-of-00050.safetensors", "model.layers.105.input_layernorm.weight": "model-00039-of-00050.safetensors", "model.layers.112.mlp.down_proj.weight": "model-00039-of-00050.safetensors", "model.layers.105.mlp.down_proj.weight": "model-00039-of-00050.safetensors", "model.layers.112.mlp.gate_proj.weight": "model-00039-of-00050.safetensors", "model.layers.105.mlp.gate_proj.weight": "model-00039-of-00050.safetensors", "model.layers.112.mlp.up_proj.weight": "model-00039-of-00050.safetensors", "model.layers.105.mlp.up_proj.weight": "model-00039-of-00050.safetensors", "model.layers.112.post_attention_layernorm.weight": "model-00039-of-00050.safetensors", "model.layers.105.post_attention_layernorm.weight": "model-00039-of-00050.safetensors", "model.layers.112.self_attn.k_proj.weight": "model-00039-of-00050.safetensors", "model.layers.105.self_attn.k_proj.weight": "model-00039-of-00050.safetensors", "model.layers.112.self_attn.o_proj.weight": "model-00039-of-00050.safetensors", "model.layers.105.self_attn.o_proj.weight": "model-00039-of-00050.safetensors", "model.layers.112.self_attn.q_proj.weight": "model-00039-of-00050.safetensors", "model.layers.105.self_attn.q_proj.weight": "model-00039-of-00050.safetensors", "model.layers.112.self_attn.v_proj.weight": "model-00039-of-00050.safetensors", "model.layers.105.self_attn.v_proj.weight": "model-00039-of-00050.safetensors", "model.layers.113.input_layernorm.weight": "model-00039-of-00050.safetensors", "model.layers.106.input_layernorm.weight": "model-00039-of-00050.safetensors", "model.layers.113.mlp.down_proj.weight": "model-00039-of-00050.safetensors", "model.layers.106.mlp.down_proj.weight": "model-00040-of-00050.safetensors", "model.layers.113.mlp.gate_proj.weight": "model-00040-of-00050.safetensors", "model.layers.106.mlp.gate_proj.weight": "model-00040-of-00050.safetensors", "model.layers.113.mlp.up_proj.weight": "model-00040-of-00050.safetensors", "model.layers.106.mlp.up_proj.weight": "model-00040-of-00050.safetensors", "model.layers.113.post_attention_layernorm.weight": "model-00040-of-00050.safetensors", "model.layers.106.post_attention_layernorm.weight": "model-00040-of-00050.safetensors", "model.layers.113.self_attn.k_proj.weight": "model-00040-of-00050.safetensors", "model.layers.106.self_attn.k_proj.weight": "model-00040-of-00050.safetensors", "model.layers.113.self_attn.o_proj.weight": "model-00040-of-00050.safetensors", "model.layers.106.self_attn.o_proj.weight": "model-00040-of-00050.safetensors", "model.layers.113.self_attn.q_proj.weight": "model-00040-of-00050.safetensors", "model.layers.106.self_attn.q_proj.weight": "model-00040-of-00050.safetensors", "model.layers.113.self_attn.v_proj.weight": "model-00040-of-00050.safetensors", "model.layers.106.self_attn.v_proj.weight": "model-00040-of-00050.safetensors", "model.layers.114.input_layernorm.weight": "model-00040-of-00050.safetensors", "model.layers.114.mlp.down_proj.weight": "model-00040-of-00050.safetensors", "model.layers.114.mlp.gate_proj.weight": "model-00040-of-00050.safetensors", "model.layers.114.mlp.up_proj.weight": "model-00040-of-00050.safetensors", "model.layers.114.post_attention_layernorm.weight": "model-00040-of-00050.safetensors", "model.layers.114.self_attn.k_proj.weight": "model-00040-of-00050.safetensors", "model.layers.114.self_attn.o_proj.weight": "model-00040-of-00050.safetensors", "model.layers.114.self_attn.q_proj.weight": "model-00040-of-00050.safetensors", "model.layers.114.self_attn.v_proj.weight": "model-00040-of-00050.safetensors", "model.layers.122.input_layernorm.weight": "model-00040-of-00050.safetensors", "model.layers.115.input_layernorm.weight": "model-00040-of-00050.safetensors", "model.layers.122.mlp.down_proj.weight": "model-00041-of-00050.safetensors", "model.layers.115.mlp.down_proj.weight": "model-00041-of-00050.safetensors", "model.layers.122.mlp.gate_proj.weight": "model-00041-of-00050.safetensors", "model.layers.115.mlp.gate_proj.weight": "model-00041-of-00050.safetensors", "model.layers.122.mlp.up_proj.weight": "model-00041-of-00050.safetensors", "model.layers.115.mlp.up_proj.weight": "model-00041-of-00050.safetensors", "model.layers.122.post_attention_layernorm.weight": "model-00041-of-00050.safetensors", "model.layers.115.post_attention_layernorm.weight": "model-00041-of-00050.safetensors", "model.layers.122.self_attn.k_proj.weight": "model-00041-of-00050.safetensors", "model.layers.115.self_attn.k_proj.weight": "model-00041-of-00050.safetensors", "model.layers.122.self_attn.o_proj.weight": "model-00041-of-00050.safetensors", "model.layers.115.self_attn.o_proj.weight": "model-00041-of-00050.safetensors", "model.layers.122.self_attn.q_proj.weight": "model-00041-of-00050.safetensors", "model.layers.115.self_attn.q_proj.weight": "model-00041-of-00050.safetensors", "model.layers.122.self_attn.v_proj.weight": "model-00041-of-00050.safetensors", "model.layers.115.self_attn.v_proj.weight": "model-00041-of-00050.safetensors", "model.layers.123.input_layernorm.weight": "model-00041-of-00050.safetensors", "model.layers.116.input_layernorm.weight": "model-00041-of-00050.safetensors", "model.layers.123.mlp.down_proj.weight": "model-00041-of-00050.safetensors", "model.layers.116.mlp.down_proj.weight": "model-00041-of-00050.safetensors", "model.layers.123.mlp.gate_proj.weight": "model-00041-of-00050.safetensors", "model.layers.116.mlp.gate_proj.weight": "model-00042-of-00050.safetensors", "model.layers.123.mlp.up_proj.weight": "model-00042-of-00050.safetensors", "model.layers.116.mlp.up_proj.weight": "model-00042-of-00050.safetensors", "model.layers.123.post_attention_layernorm.weight": "model-00042-of-00050.safetensors", "model.layers.116.post_attention_layernorm.weight": "model-00042-of-00050.safetensors", "model.layers.123.self_attn.k_proj.weight": "model-00042-of-00050.safetensors", "model.layers.116.self_attn.k_proj.weight": "model-00042-of-00050.safetensors", "model.layers.123.self_attn.o_proj.weight": "model-00042-of-00050.safetensors", "model.layers.116.self_attn.o_proj.weight": "model-00042-of-00050.safetensors", "model.layers.123.self_attn.q_proj.weight": "model-00042-of-00050.safetensors", "model.layers.116.self_attn.q_proj.weight": "model-00042-of-00050.safetensors", "model.layers.123.self_attn.v_proj.weight": "model-00042-of-00050.safetensors", "model.layers.116.self_attn.v_proj.weight": "model-00042-of-00050.safetensors", "model.layers.124.input_layernorm.weight": "model-00042-of-00050.safetensors", "model.layers.117.input_layernorm.weight": "model-00042-of-00050.safetensors", "model.layers.124.mlp.down_proj.weight": "model-00042-of-00050.safetensors", "model.layers.117.mlp.down_proj.weight": "model-00042-of-00050.safetensors", "model.layers.124.mlp.gate_proj.weight": "model-00042-of-00050.safetensors", "model.layers.117.mlp.gate_proj.weight": "model-00042-of-00050.safetensors", "model.layers.124.mlp.up_proj.weight": "model-00042-of-00050.safetensors", "model.layers.117.mlp.up_proj.weight": "model-00042-of-00050.safetensors", "model.layers.124.post_attention_layernorm.weight": "model-00042-of-00050.safetensors", "model.layers.117.post_attention_layernorm.weight": "model-00042-of-00050.safetensors", "model.layers.124.self_attn.k_proj.weight": "model-00042-of-00050.safetensors", "model.layers.117.self_attn.k_proj.weight": "model-00042-of-00050.safetensors", "model.layers.124.self_attn.o_proj.weight": "model-00042-of-00050.safetensors", "model.layers.117.self_attn.o_proj.weight": "model-00043-of-00050.safetensors", "model.layers.124.self_attn.q_proj.weight": "model-00043-of-00050.safetensors", "model.layers.117.self_attn.q_proj.weight": "model-00043-of-00050.safetensors", "model.layers.124.self_attn.v_proj.weight": "model-00043-of-00050.safetensors", "model.layers.117.self_attn.v_proj.weight": "model-00043-of-00050.safetensors", "model.layers.125.input_layernorm.weight": "model-00043-of-00050.safetensors", "model.layers.118.input_layernorm.weight": "model-00043-of-00050.safetensors", "model.layers.125.mlp.down_proj.weight": "model-00043-of-00050.safetensors", "model.layers.118.mlp.down_proj.weight": "model-00043-of-00050.safetensors", "model.layers.125.mlp.gate_proj.weight": "model-00043-of-00050.safetensors", "model.layers.118.mlp.gate_proj.weight": "model-00043-of-00050.safetensors", "model.layers.125.mlp.up_proj.weight": "model-00043-of-00050.safetensors", "model.layers.118.mlp.up_proj.weight": "model-00043-of-00050.safetensors", "model.layers.125.post_attention_layernorm.weight": "model-00043-of-00050.safetensors", "model.layers.118.post_attention_layernorm.weight": "model-00043-of-00050.safetensors", "model.layers.125.self_attn.k_proj.weight": "model-00043-of-00050.safetensors", "model.layers.118.self_attn.k_proj.weight": "model-00043-of-00050.safetensors", "model.layers.125.self_attn.o_proj.weight": "model-00043-of-00050.safetensors", "model.layers.118.self_attn.o_proj.weight": "model-00043-of-00050.safetensors", "model.layers.125.self_attn.q_proj.weight": "model-00043-of-00050.safetensors", "model.layers.118.self_attn.q_proj.weight": "model-00043-of-00050.safetensors", "model.layers.125.self_attn.v_proj.weight": "model-00043-of-00050.safetensors", "model.layers.118.self_attn.v_proj.weight": "model-00043-of-00050.safetensors", "model.layers.126.input_layernorm.weight": "model-00043-of-00050.safetensors", "model.layers.119.input_layernorm.weight": "model-00043-of-00050.safetensors", "model.layers.126.mlp.down_proj.weight": "model-00043-of-00050.safetensors", "model.layers.119.mlp.down_proj.weight": "model-00043-of-00050.safetensors", "model.layers.126.mlp.gate_proj.weight": "model-00044-of-00050.safetensors", "model.layers.119.mlp.gate_proj.weight": "model-00044-of-00050.safetensors", "model.layers.126.mlp.up_proj.weight": "model-00044-of-00050.safetensors", "model.layers.119.mlp.up_proj.weight": "model-00044-of-00050.safetensors", "model.layers.126.post_attention_layernorm.weight": "model-00044-of-00050.safetensors", "model.layers.119.post_attention_layernorm.weight": "model-00044-of-00050.safetensors", "model.layers.126.self_attn.k_proj.weight": "model-00044-of-00050.safetensors", "model.layers.119.self_attn.k_proj.weight": "model-00044-of-00050.safetensors", "model.layers.126.self_attn.o_proj.weight": "model-00044-of-00050.safetensors", "model.layers.119.self_attn.o_proj.weight": "model-00044-of-00050.safetensors", "model.layers.126.self_attn.q_proj.weight": "model-00044-of-00050.safetensors", "model.layers.119.self_attn.q_proj.weight": "model-00044-of-00050.safetensors", "model.layers.126.self_attn.v_proj.weight": "model-00044-of-00050.safetensors", "model.layers.119.self_attn.v_proj.weight": "model-00044-of-00050.safetensors", "model.layers.7.input_layernorm.weight": "model-00044-of-00050.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00044-of-00050.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00044-of-00050.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00044-of-00050.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00044-of-00050.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00044-of-00050.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00044-of-00050.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00044-of-00050.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00044-of-00050.safetensors", "model.layers.127.input_layernorm.weight": "model-00044-of-00050.safetensors", "model.layers.120.input_layernorm.weight": "model-00044-of-00050.safetensors", "model.layers.127.mlp.down_proj.weight": "model-00044-of-00050.safetensors", "model.layers.120.mlp.down_proj.weight": "model-00045-of-00050.safetensors", "model.layers.127.mlp.gate_proj.weight": "model-00045-of-00050.safetensors", "model.layers.120.mlp.gate_proj.weight": "model-00045-of-00050.safetensors", "model.layers.127.mlp.up_proj.weight": "model-00045-of-00050.safetensors", "model.layers.120.mlp.up_proj.weight": "model-00045-of-00050.safetensors", "model.layers.127.post_attention_layernorm.weight": "model-00045-of-00050.safetensors", "model.layers.120.post_attention_layernorm.weight": "model-00045-of-00050.safetensors", "model.layers.127.self_attn.k_proj.weight": "model-00045-of-00050.safetensors", "model.layers.120.self_attn.k_proj.weight": "model-00045-of-00050.safetensors", "model.layers.127.self_attn.o_proj.weight": "model-00045-of-00050.safetensors", "model.layers.120.self_attn.o_proj.weight": "model-00045-of-00050.safetensors", "model.layers.127.self_attn.q_proj.weight": "model-00045-of-00050.safetensors", "model.layers.120.self_attn.q_proj.weight": "model-00045-of-00050.safetensors", "model.layers.127.self_attn.v_proj.weight": "model-00045-of-00050.safetensors", "model.layers.120.self_attn.v_proj.weight": "model-00045-of-00050.safetensors", "model.layers.128.input_layernorm.weight": "model-00045-of-00050.safetensors", "model.layers.121.input_layernorm.weight": "model-00045-of-00050.safetensors", "model.layers.128.mlp.down_proj.weight": "model-00045-of-00050.safetensors", "model.layers.121.mlp.down_proj.weight": "model-00045-of-00050.safetensors", "model.layers.128.mlp.gate_proj.weight": "model-00045-of-00050.safetensors", "model.layers.121.mlp.gate_proj.weight": "model-00045-of-00050.safetensors", "model.layers.128.mlp.up_proj.weight": "model-00046-of-00050.safetensors", "model.layers.121.mlp.up_proj.weight": "model-00046-of-00050.safetensors", "model.layers.128.post_attention_layernorm.weight": "model-00046-of-00050.safetensors", "model.layers.121.post_attention_layernorm.weight": "model-00046-of-00050.safetensors", "model.layers.128.self_attn.k_proj.weight": "model-00046-of-00050.safetensors", "model.layers.121.self_attn.k_proj.weight": "model-00046-of-00050.safetensors", "model.layers.128.self_attn.o_proj.weight": "model-00046-of-00050.safetensors", "model.layers.121.self_attn.o_proj.weight": "model-00046-of-00050.safetensors", "model.layers.128.self_attn.q_proj.weight": "model-00046-of-00050.safetensors", "model.layers.121.self_attn.q_proj.weight": "model-00046-of-00050.safetensors", "model.layers.128.self_attn.v_proj.weight": "model-00046-of-00050.safetensors", "model.layers.121.self_attn.v_proj.weight": "model-00046-of-00050.safetensors", "model.layers.129.input_layernorm.weight": "model-00046-of-00050.safetensors", "model.layers.129.mlp.down_proj.weight": "model-00046-of-00050.safetensors", "model.layers.129.mlp.gate_proj.weight": "model-00046-of-00050.safetensors", "model.layers.129.mlp.up_proj.weight": "model-00046-of-00050.safetensors", "model.layers.129.post_attention_layernorm.weight": "model-00046-of-00050.safetensors", "model.layers.129.self_attn.k_proj.weight": "model-00046-of-00050.safetensors", "model.layers.129.self_attn.o_proj.weight": "model-00046-of-00050.safetensors", "model.layers.129.self_attn.q_proj.weight": "model-00046-of-00050.safetensors", "model.layers.129.self_attn.v_proj.weight": "model-00046-of-00050.safetensors", "model.layers.130.input_layernorm.weight": "model-00046-of-00050.safetensors", "model.layers.130.mlp.down_proj.weight": "model-00046-of-00050.safetensors", "model.layers.130.mlp.gate_proj.weight": "model-00046-of-00050.safetensors", "model.layers.130.mlp.up_proj.weight": "model-00046-of-00050.safetensors", "model.layers.130.post_attention_layernorm.weight": "model-00046-of-00050.safetensors", "model.layers.130.self_attn.k_proj.weight": "model-00046-of-00050.safetensors", "model.layers.130.self_attn.o_proj.weight": "model-00046-of-00050.safetensors", "model.layers.130.self_attn.q_proj.weight": "model-00046-of-00050.safetensors", "model.layers.130.self_attn.v_proj.weight": "model-00046-of-00050.safetensors", "model.layers.131.input_layernorm.weight": "model-00046-of-00050.safetensors", "model.layers.131.mlp.down_proj.weight": "model-00047-of-00050.safetensors", "model.layers.131.mlp.gate_proj.weight": "model-00047-of-00050.safetensors", "model.layers.131.mlp.up_proj.weight": "model-00047-of-00050.safetensors", "model.layers.131.post_attention_layernorm.weight": "model-00047-of-00050.safetensors", "model.layers.131.self_attn.k_proj.weight": "model-00047-of-00050.safetensors", "model.layers.131.self_attn.o_proj.weight": "model-00047-of-00050.safetensors", "model.layers.131.self_attn.q_proj.weight": "model-00047-of-00050.safetensors", "model.layers.131.self_attn.v_proj.weight": "model-00047-of-00050.safetensors", "model.layers.132.input_layernorm.weight": "model-00047-of-00050.safetensors", "model.layers.132.mlp.down_proj.weight": "model-00047-of-00050.safetensors", "model.layers.132.mlp.gate_proj.weight": "model-00047-of-00050.safetensors", "model.layers.132.mlp.up_proj.weight": "model-00047-of-00050.safetensors", "model.layers.132.post_attention_layernorm.weight": "model-00047-of-00050.safetensors", "model.layers.132.self_attn.k_proj.weight": "model-00047-of-00050.safetensors", "model.layers.132.self_attn.o_proj.weight": "model-00047-of-00050.safetensors", "model.layers.132.self_attn.q_proj.weight": "model-00047-of-00050.safetensors", "model.layers.132.self_attn.v_proj.weight": "model-00047-of-00050.safetensors", "model.layers.133.input_layernorm.weight": "model-00047-of-00050.safetensors", "model.layers.133.mlp.down_proj.weight": "model-00047-of-00050.safetensors", "model.layers.133.mlp.gate_proj.weight": "model-00047-of-00050.safetensors", "model.layers.133.mlp.up_proj.weight": "model-00047-of-00050.safetensors", "model.layers.133.post_attention_layernorm.weight": "model-00047-of-00050.safetensors", "model.layers.133.self_attn.k_proj.weight": "model-00047-of-00050.safetensors", "model.layers.133.self_attn.o_proj.weight": "model-00047-of-00050.safetensors", "model.layers.133.self_attn.q_proj.weight": "model-00048-of-00050.safetensors", "model.layers.133.self_attn.v_proj.weight": "model-00048-of-00050.safetensors", "model.layers.134.input_layernorm.weight": "model-00048-of-00050.safetensors", "model.layers.134.mlp.down_proj.weight": "model-00048-of-00050.safetensors", "model.layers.134.mlp.gate_proj.weight": "model-00048-of-00050.safetensors", "model.layers.134.mlp.up_proj.weight": "model-00048-of-00050.safetensors", "model.layers.134.post_attention_layernorm.weight": "model-00048-of-00050.safetensors", "model.layers.134.self_attn.k_proj.weight": "model-00048-of-00050.safetensors", "model.layers.134.self_attn.o_proj.weight": "model-00048-of-00050.safetensors", "model.layers.134.self_attn.q_proj.weight": "model-00048-of-00050.safetensors", "model.layers.134.self_attn.v_proj.weight": "model-00048-of-00050.safetensors", "model.layers.135.input_layernorm.weight": "model-00048-of-00050.safetensors", "model.layers.135.mlp.down_proj.weight": "model-00048-of-00050.safetensors", "model.layers.135.mlp.gate_proj.weight": "model-00048-of-00050.safetensors", "model.layers.135.mlp.up_proj.weight": "model-00048-of-00050.safetensors", "model.layers.135.post_attention_layernorm.weight": "model-00048-of-00050.safetensors", "model.layers.135.self_attn.k_proj.weight": "model-00048-of-00050.safetensors", "model.layers.135.self_attn.o_proj.weight": "model-00048-of-00050.safetensors", "model.layers.135.self_attn.q_proj.weight": "model-00048-of-00050.safetensors", "model.layers.135.self_attn.v_proj.weight": "model-00048-of-00050.safetensors", "model.layers.136.input_layernorm.weight": "model-00048-of-00050.safetensors", "model.layers.136.mlp.down_proj.weight": "model-00048-of-00050.safetensors", "model.layers.136.mlp.gate_proj.weight": "model-00048-of-00050.safetensors", "model.layers.136.mlp.up_proj.weight": "model-00048-of-00050.safetensors", "model.layers.136.post_attention_layernorm.weight": "model-00048-of-00050.safetensors", "model.layers.136.self_attn.k_proj.weight": "model-00048-of-00050.safetensors", "model.layers.136.self_attn.o_proj.weight": "model-00049-of-00050.safetensors", "model.layers.136.self_attn.q_proj.weight": "model-00049-of-00050.safetensors", "model.layers.136.self_attn.v_proj.weight": "model-00049-of-00050.safetensors", "model.layers.16.input_layernorm.weight": "model-00049-of-00050.safetensors", "model.layers.8.input_layernorm.weight": "model-00049-of-00050.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00049-of-00050.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00049-of-00050.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00049-of-00050.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00049-of-00050.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00049-of-00050.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00049-of-00050.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00049-of-00050.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00049-of-00050.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00049-of-00050.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00049-of-00050.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00049-of-00050.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00049-of-00050.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00049-of-00050.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00049-of-00050.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00049-of-00050.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00049-of-00050.safetensors", "model.layers.17.input_layernorm.weight": "model-00049-of-00050.safetensors", "model.layers.9.input_layernorm.weight": "model-00049-of-00050.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00049-of-00050.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00049-of-00050.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00050-of-00050.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00050-of-00050.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00050-of-00050.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00050-of-00050.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00050-of-00050.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00050-of-00050.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00050-of-00050.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00050-of-00050.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00050-of-00050.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00050-of-00050.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00050-of-00050.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00050-of-00050.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00050-of-00050.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00050-of-00050.safetensors", "model.norm.weight": "model-00050-of-00050.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..02ee80b6196926a5ad790a004d9efd6ab1ba6542 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,16 @@ +{ + "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 + } +} 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..d6d6a8f24ffa7c60f7c95e06ec782b46adbe28e4 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2062 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "tokenizer_class": "PreTrainedTokenizerFast" +}