diff --git a/README.md b/README.md index 986b8a7acb2813b3ed1ae340e7e3adcc839f2910..7b95401dc46245ac339fc25059d4a56d90b4cde5 100644 --- a/README.md +++ b/README.md @@ -1,202 +1,3 @@ ---- -license: apache-2.0 ---- ---- -library_name: transformers -tags: [] ---- - -# Model Card for Model ID - - - - - -## Model Details - -### Model Description - - - -This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - -- **Developed by:** [More Information Needed] -- **Funded by [optional]:** [More Information Needed] -- **Shared by [optional]:** [More Information Needed] -- **Model type:** [More Information Needed] -- **Language(s) (NLP):** [More Information Needed] -- **License:** [More Information Needed] -- **Finetuned from model [optional]:** [More Information Needed] - -### Model Sources [optional] - - - -- **Repository:** [More Information Needed] -- **Paper [optional]:** [More Information Needed] -- **Demo [optional]:** [More Information Needed] - -## Uses - - - -### Direct Use - - - -[More Information Needed] - -### Downstream Use [optional] - - - -[More Information Needed] - -### Out-of-Scope Use - - - -[More Information Needed] - -## Bias, Risks, and Limitations - - - -[More Information Needed] - -### Recommendations - - - -Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. - -## How to Get Started with the Model - -Use the code below to get started with the model. - -[More Information Needed] - -## Training Details - -### Training Data - - - -[More Information Needed] - -### Training Procedure - - - -#### Preprocessing [optional] - -[More Information Needed] - - -#### Training Hyperparameters - -- **Training regime:** [More Information Needed] - -#### Speeds, Sizes, Times [optional] - - - -[More Information Needed] - -## Evaluation - - - -### Testing Data, Factors & Metrics - -#### Testing Data - - - -[More Information Needed] - -#### Factors - - - -[More Information Needed] - -#### Metrics - - - -[More Information Needed] - -### Results - -[More Information Needed] - -#### Summary - - - -## Model Examination [optional] - - - -[More Information Needed] - -## Environmental Impact - - - -Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - -- **Hardware Type:** [More Information Needed] -- **Hours used:** [More Information Needed] -- **Cloud Provider:** [More Information Needed] -- **Compute Region:** [More Information Needed] -- **Carbon Emitted:** [More Information Needed] - -## Technical Specifications [optional] - -### Model Architecture and Objective - -[More Information Needed] - -### Compute Infrastructure - -[More Information Needed] - -#### Hardware - -[More Information Needed] - -#### Software - -[More Information Needed] - -## Citation [optional] - - - -**BibTeX:** - -[More Information Needed] - -**APA:** - -[More Information Needed] - -## Glossary [optional] - - - -[More Information Needed] - -## More Information [optional] - -[More Information Needed] - -## Model Card Authors [optional] - -[More Information Needed] - -## Model Card Contact - -[More Information Needed] \ No newline at end of file +--- +license: apache-2.0 +--- diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..3a977cd172a732de23c6f2699dbb7bd22ab078f3 --- /dev/null +++ b/config.json @@ -0,0 +1,27 @@ +{ + "_name_or_path": "airev-ai/Jais-Inception-70b-V1.2.2", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 8192, + "initializer_range": 0.02, + "intermediate_size": 29568, + "max_position_embeddings": 131072, + "max_window_layers": 28, + "model_type": "qwen2", + "num_attention_heads": 64, + "num_hidden_layers": 80, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-05, + "rope_theta": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.43.3", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 152064 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..3ffdb66c1e17e6272ba24f39d0ee3474574c9d70 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": 151643, + "max_new_tokens": 2048, + "transformers_version": "4.43.3" +} diff --git a/model-00001-of-00082.safetensors b/model-00001-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..efb86dd80e25853745d341271cc1403d7dcab9ff --- /dev/null +++ b/model-00001-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0176936410ae77d886b3e1ec011b0d7de259fd6f78113232a18375958855a090 +size 2491416712 diff --git a/model-00002-of-00082.safetensors b/model-00002-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9dd9f073fceea8ca95589d07dba63233f79ffc3f --- /dev/null +++ b/model-00002-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef68ae215efd367fdcbdd4e615e178396137a2b493754e4419f6210d109365a1 +size 1923164168 diff --git a/model-00003-of-00082.safetensors b/model-00003-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2112577c258ca73db658a74672c26d7369e944da --- /dev/null +++ b/model-00003-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42f166fc48d020898a83c8b1ec88c884a6eafdf468818f9b1d71eec9a45a9f07 +size 1889588696 diff --git a/model-00004-of-00082.safetensors b/model-00004-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..be76f930da6838b7266d8de3865dc0c97b0b28ac --- /dev/null +++ b/model-00004-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22b009a58649fb847241fb2d9c94b246941cdf85db453494df3bdea04498bd38 +size 1755370856 diff --git a/model-00005-of-00082.safetensors b/model-00005-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..47d0694acf79028c6e1729d891af7f8eb9a8e391 --- /dev/null +++ b/model-00005-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d97a6664aa615bcfc93bc67efdcda9de434c1db7184df383a2a499e4ddc5d86 +size 1755370856 diff --git a/model-00006-of-00082.safetensors b/model-00006-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..def62414252de670b0ad4f437ff2ebfc828093b9 --- /dev/null +++ b/model-00006-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92f8d282df6925a1b2fc187369544afab9423c8a860fb766077376abe4961773 +size 1755370856 diff --git a/model-00007-of-00082.safetensors b/model-00007-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7172afeab10970d2b8f9271ded05d40affd2d1a9 --- /dev/null +++ b/model-00007-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:862ccc02a93239290781290633b0d5cc52eb199b5032bfc467e0bee711ae4cab +size 1755370856 diff --git a/model-00008-of-00082.safetensors b/model-00008-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dc30fbcd9c2971876f6d259518b7ded778b612a2 --- /dev/null +++ b/model-00008-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c59d9670d7b18374dfbf6735d0db1c461cd5a7d13cdbbf877f3c16830c1ac926 +size 1755370856 diff --git a/model-00009-of-00082.safetensors b/model-00009-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d520b3c87ebf22679d15c4be4fa3826b5411221b --- /dev/null +++ b/model-00009-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60c3ee634bb337c0491a0b55cb213fe1174175d8d4080b4f007e3834eae6d40d +size 1755370856 diff --git a/model-00010-of-00082.safetensors b/model-00010-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8f6324689e927589a06fdc344520a7bdd242b873 --- /dev/null +++ b/model-00010-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71b9b31c2ec6f20075c6a33ddbbc7ff4dcf02d07b1887b385025777927805fd2 +size 1755370856 diff --git a/model-00011-of-00082.safetensors b/model-00011-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..607c68f2ad222ca4c4fd44fe96d3a2fb9828bdac --- /dev/null +++ b/model-00011-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2b3514b4837a2320586f050b8a67ee8e37bbe4cf51f99ec7a27c828157b3c61 +size 1755370840 diff --git a/model-00012-of-00082.safetensors b/model-00012-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e2eb8cbce4e4da0ed462687025dce5a8df10b881 --- /dev/null +++ b/model-00012-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d42d107f06fcfcb69b90dd0ab736526afc83695292db92eab37822b56af44258 +size 1755370864 diff --git a/model-00013-of-00082.safetensors b/model-00013-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2a7791762e1b07baf5f9a4771ce3e3f094ae6fc8 --- /dev/null +++ b/model-00013-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea2ebd82520107c822ca1f7c31e2e57b60fbb9fc6f68b887704d8ea1a52e0133 +size 1755370864 diff --git a/model-00014-of-00082.safetensors b/model-00014-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9403302b7b08a69db18f272e21385a1aa16ad347 --- /dev/null +++ b/model-00014-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bc1ae53931f1995f88a32a099f14f49435c6f75167a3a6941a291e69202dac0 +size 1755370864 diff --git a/model-00015-of-00082.safetensors b/model-00015-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c512b4e2e9815a9b55ec3b31317f8241d4fed11c --- /dev/null +++ b/model-00015-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:794e2f93b5beca7328a72525a909adf7d4c45770f882bc6b0b01523b04b1460b +size 1755370864 diff --git a/model-00016-of-00082.safetensors b/model-00016-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d70e49f8c18fdd6620a1772894751dd07e9c2ec6 --- /dev/null +++ b/model-00016-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7b61af2cc03bbc7a1116c3a98610ec5f1edf6884fd097e280d7f6c874228e75 +size 1755370864 diff --git a/model-00017-of-00082.safetensors b/model-00017-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..70724fcf5b3ffaa7012fb488a87c0ed452a73ca8 --- /dev/null +++ b/model-00017-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72d809e6a7e672526239232a81e9ccf8c54e060bf72fea4ab25d894bd31245d5 +size 1755370864 diff --git a/model-00018-of-00082.safetensors b/model-00018-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..677320224f0e0b7e306cf6b254f3e02483e2ec7a --- /dev/null +++ b/model-00018-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26d5f8d7f50eed8b56329da693b019a0e1409480ab07c030769520370ade5bee +size 1755370864 diff --git a/model-00019-of-00082.safetensors b/model-00019-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b9ae7a58c21462b113bd6053a444ae6b1480bcd1 --- /dev/null +++ b/model-00019-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5e28d550ecb7042d26d662e577e79347b79a27c9fd87ae5e80d7752ef46853f +size 1755370864 diff --git a/model-00020-of-00082.safetensors b/model-00020-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..43000c8d07f90f1a18f1091b4796ba0f5c060626 --- /dev/null +++ b/model-00020-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3be50ee6dd5752cdb2242afaadfdd6553652b3366ebb24b5ed018f6dff023ad0 +size 1755370864 diff --git a/model-00021-of-00082.safetensors b/model-00021-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9e066b7c54fece57e0f47ce7e664502f9e9f97ad --- /dev/null +++ b/model-00021-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10f05e3901831ebed960521ceaa550fafad45b9e8477fbddd91bfc3867ec2115 +size 1755370864 diff --git a/model-00022-of-00082.safetensors b/model-00022-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..622fd11aaf326e981c48f98e077bf2a911f4300d --- /dev/null +++ b/model-00022-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4683ab50f63524aeee2fae0bf9c2cdec6776265dd8a7062defdc70cb9ed2f29 +size 1755370864 diff --git a/model-00023-of-00082.safetensors b/model-00023-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a177fcf9187581b64e50ec35d23fbada844f6e4e --- /dev/null +++ b/model-00023-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf1894109ba67c985ce47d0dc468d23b6cff9df1aabae3a7498138af29b4a081 +size 1755370864 diff --git a/model-00024-of-00082.safetensors b/model-00024-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..adca77d95f75e437a036a366de5eb5eeee102f69 --- /dev/null +++ b/model-00024-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:968d251442eb163a39998577738551c3dbb259886b7a7c5d0c8093a55d498fa8 +size 1755370864 diff --git a/model-00025-of-00082.safetensors b/model-00025-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..18499ba148b3f49817c57d48c8762e707fb04936 --- /dev/null +++ b/model-00025-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f72a43531a3737c99a76c806f0844fd6c231adce7d26de09d3febd01e31f7bfe +size 1755370864 diff --git a/model-00026-of-00082.safetensors b/model-00026-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0753c02a3e5c77a50e5b6831bfb7ddff4aa6c390 --- /dev/null +++ b/model-00026-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72d73dff5e7bdeb5481574635647e0ba252e74c719c8917dd37405c78dadcc64 +size 1755370864 diff --git a/model-00027-of-00082.safetensors b/model-00027-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e53a77a6bf54c41d184658dbaaef22e371c6ab9e --- /dev/null +++ b/model-00027-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd8e236a24c3b56fa2578687a628641f8ea6634eaab0e7b42f71b50044de125b +size 1755370864 diff --git a/model-00028-of-00082.safetensors b/model-00028-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f965c10bb9d2e76575a713b0a2242b8b2e5e9677 --- /dev/null +++ b/model-00028-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ba64fa2a79e3e96caff19c833a7882ac7b6aa750134ef199492485473c8ac66 +size 1755370864 diff --git a/model-00029-of-00082.safetensors b/model-00029-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b8ebd2d943bbdee5f38e009809ba59097b3474ce --- /dev/null +++ b/model-00029-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c328066d391b853e32d97082ae8a6a58978fe64b9f83a62c6192e2d61a8a4a5e +size 1755370864 diff --git a/model-00030-of-00082.safetensors b/model-00030-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6d212164d4f4b8161f56a3657c3966dbe4b6a4ee --- /dev/null +++ b/model-00030-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba618e08409a7193761b1735c25db69578a05ef0d70f54f97995eb002dbe2e49 +size 1755370864 diff --git a/model-00031-of-00082.safetensors b/model-00031-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6ae5d7825036554677c8e52b68cad0d38703df09 --- /dev/null +++ b/model-00031-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53fa3171698027d2f77d4df8866c223a072e0aaf52d5031e4866508a3435c30d +size 1755370864 diff --git a/model-00032-of-00082.safetensors b/model-00032-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..80fc2acb5e4686bf9462f3af390a69c0c7484cc6 --- /dev/null +++ b/model-00032-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b99f0acd5bd08e144c3fa140de4211c413e7e39f575d48beedb225a22ddfd569 +size 1755370864 diff --git a/model-00033-of-00082.safetensors b/model-00033-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0cdac0f10da6ff28bf6202434d856dc6b52aec75 --- /dev/null +++ b/model-00033-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c88074b5b9c841228b6761cf9645d5d09c9042ac799071f931784567b3f41657 +size 1755370864 diff --git a/model-00034-of-00082.safetensors b/model-00034-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0acb8cac9d7380851e08f9e724ee693afbb4e124 --- /dev/null +++ b/model-00034-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:701e831956e52e12a3e543f66b0584af1ca3ca483fe2e4e733ea137fd73d5d19 +size 1755370864 diff --git a/model-00035-of-00082.safetensors b/model-00035-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..86d7bfc924782b595c36e704071076161230ef3e --- /dev/null +++ b/model-00035-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dabfae952dd2ad0932a7d0fd5f4b0c16f601af18e1fd8287f37b5daf47198d3 +size 1755370864 diff --git a/model-00036-of-00082.safetensors b/model-00036-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e98af6d793678e8f7761d39ca70def2ad42e5ffe --- /dev/null +++ b/model-00036-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7514691510a321aac87a8ac993015be8b307017f9cbd96caf7f02f463a68ff77 +size 1755370864 diff --git a/model-00037-of-00082.safetensors b/model-00037-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7751c07e7cc85a961aefc4d9105b6fcde13194bc --- /dev/null +++ b/model-00037-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b46514688f2011e9909614bd15f35664171d3a92b61c7595cd65c1708c57bbd1 +size 1755370864 diff --git a/model-00038-of-00082.safetensors b/model-00038-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4ec6d5ae4dda9edc6d773151d0678680de41942e --- /dev/null +++ b/model-00038-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2eb43ff02316e9dd277d2b2a006bdf8f08bbc8d8fa5fc6c0893dd5ca88a68316 +size 1755370864 diff --git a/model-00039-of-00082.safetensors b/model-00039-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2d8dce2aa318b97f484dd70af763453d2c6c7d17 --- /dev/null +++ b/model-00039-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a42c7053ff76adf5992dae67004d34963dcb8008d622b8c354f01f7052312955 +size 1755370864 diff --git a/model-00040-of-00082.safetensors b/model-00040-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..45f2b083e980f35a51f9ec584dfcdf8cecf49b3b --- /dev/null +++ b/model-00040-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b7970a2c8a32f146faeec7ca29273b6c073099fc19748ee5c8cfe6fe929ead5 +size 1755370864 diff --git a/model-00041-of-00082.safetensors b/model-00041-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7073af862dc57283ecaa7c43ebf1e828fc6db38e --- /dev/null +++ b/model-00041-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1e1ba0962929da32b5b912d8c4fb123514413ec0ba1a93ed557e3cdcb6d7bf4 +size 1755370864 diff --git a/model-00042-of-00082.safetensors b/model-00042-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7ed3ce59407aa9782e160428bb07283bd7b8d156 --- /dev/null +++ b/model-00042-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cb927692fb628d2ea6280a5c326ea942690918a61757bb905b7a99aac4d1650 +size 1755370864 diff --git a/model-00043-of-00082.safetensors b/model-00043-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..995970df156fe6b36b01025a7e89432d0d3fb828 --- /dev/null +++ b/model-00043-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:589d1e9426285ef945a3e47a28487a8a68c1c11b0e1dfbd20f3d19925b386512 +size 1755370864 diff --git a/model-00044-of-00082.safetensors b/model-00044-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ef56e6333fb085aa2e3ec69184f194c5d1c76ff8 --- /dev/null +++ b/model-00044-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b0b08d78db56afe939c86113a0a84b1c89483d1f4231754fa3cb1a106432b5f +size 1755370864 diff --git a/model-00045-of-00082.safetensors b/model-00045-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..eb526361f06b4253588843edb037c2808e10cceb --- /dev/null +++ b/model-00045-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb43494d51f5c8e0858d5685c87d5f5221acfafbd0a37ccce1502ecc1e4e7a14 +size 1755370864 diff --git a/model-00046-of-00082.safetensors b/model-00046-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..937fbf59a49aec282fb230947bf81f227e5c90e7 --- /dev/null +++ b/model-00046-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d74ebb61ee055d97b80101630374b16d131155084c1996415550978c782977a7 +size 1755370864 diff --git a/model-00047-of-00082.safetensors b/model-00047-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4be01e5e5030b2458064da7cac7f866fe6b61d91 --- /dev/null +++ b/model-00047-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4efbc0260b31e72794231efa4102d43d4b805648fbf15a1f824d0216b7d0f8f +size 1755370864 diff --git a/model-00048-of-00082.safetensors b/model-00048-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..96ffbbc8fbac988c21aee9557957fe41a72e5401 --- /dev/null +++ b/model-00048-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39259f8c4cecbf3db9bfb8ebbaa4f72848d69a647346dac8a845b3b1bff53e6e +size 1755370864 diff --git a/model-00049-of-00082.safetensors b/model-00049-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1c18b4c921d5d92532ff9586a03b092cb9f3625d --- /dev/null +++ b/model-00049-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:685b2ae4ee621f4f509feb9fd28796693d681c5623eb91da995255547c598e63 +size 1755370864 diff --git a/model-00050-of-00082.safetensors b/model-00050-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..13523748e11ad0b693cac32798d2f34ff69da423 --- /dev/null +++ b/model-00050-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55ed0ae662861915917e7f49164befd235eac940740be161875dcbbfc6071a3b +size 1755370864 diff --git a/model-00051-of-00082.safetensors b/model-00051-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..db7a4384eac12b4ecff11ce7dc52713b132436a5 --- /dev/null +++ b/model-00051-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfb56f1400e1c4d8c675ec3abe2cc198efb90962bd3b11a6902b9b7dc8f0b7b3 +size 1755370864 diff --git a/model-00052-of-00082.safetensors b/model-00052-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..02a4bf6733aeae6508b51f15293fb393273d580d --- /dev/null +++ b/model-00052-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc7ecad03e333053838f4f7391ba3ba6f55ef141e432577d7fe40a4b89d735b6 +size 1755370864 diff --git a/model-00053-of-00082.safetensors b/model-00053-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6c8ff33c1b8cc0caf0f8683d9b458843c4af2700 --- /dev/null +++ b/model-00053-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49d6500bd7161491310a0118e18c95f1ac3fd6e24a69aab8407e67cd301d5263 +size 1755370864 diff --git a/model-00054-of-00082.safetensors b/model-00054-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..87b3c7e45b36e45b118b52907e9d1440716075db --- /dev/null +++ b/model-00054-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df42105e208fdf313197b83818be4162e7c3fe060f28678439b097790c41c1d2 +size 1755370864 diff --git a/model-00055-of-00082.safetensors b/model-00055-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cba15e31d6b4a59a70d02f70c2b95e96910472a1 --- /dev/null +++ b/model-00055-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a72e3fc9cc217a905d5b535816ad4243c5c91086eb737a39a93cc4a644ebfa98 +size 1755370864 diff --git a/model-00056-of-00082.safetensors b/model-00056-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f948f7345e1c67e8f98b5820841310336f8853e7 --- /dev/null +++ b/model-00056-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d670faf48f5579a149deb05be8b2e51806bf684091db8db8171738d7160bd56 +size 1755370864 diff --git a/model-00057-of-00082.safetensors b/model-00057-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..503f8d07a5fa6c0ff0c9cfcf39f0ee3a2ce5621b --- /dev/null +++ b/model-00057-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:350fcb6e7ef92bc08236448c73ccf2ec2a3190a89ae5bbaa51e72a7da6036a65 +size 1755370864 diff --git a/model-00058-of-00082.safetensors b/model-00058-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bdda474e8c4ba9fe312889a866fb3025e143503a --- /dev/null +++ b/model-00058-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc63d817afe9cebf72ddafb877a2e7ec29fc7b5ca62ffc224172a359804a547c +size 1755370864 diff --git a/model-00059-of-00082.safetensors b/model-00059-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1907bf748e087bafbe52c2b0cb48a93b1c998384 --- /dev/null +++ b/model-00059-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:012fe71bae79da023ae24ce16feec877bcce5ef9ef7008f80f6714177489cef5 +size 1755370864 diff --git a/model-00060-of-00082.safetensors b/model-00060-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4bc896f6c1174d0b681636d2e270bad4b848e364 --- /dev/null +++ b/model-00060-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb94b164fa5bbe21dfb2355b0a4c9b69614ce0725158036a1418b6cacb1586c2 +size 1755370864 diff --git a/model-00061-of-00082.safetensors b/model-00061-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bba256931ade730dbf631d6b6d0bc89effec3077 --- /dev/null +++ b/model-00061-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fb5e69f55a1350c8f269896241852840ad6af01750e15462791a7da622deec1 +size 1755370864 diff --git a/model-00062-of-00082.safetensors b/model-00062-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..933ac8babaf042e600eab02c9e9793b78436f1e1 --- /dev/null +++ b/model-00062-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f62a4ff4e6858dd317c7fa3884dbc8cfd88797e976c88f90960a65ae549e4b8 +size 1755370864 diff --git a/model-00063-of-00082.safetensors b/model-00063-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6c5f10e4b906894670d980f3f12a66905fcdbd52 --- /dev/null +++ b/model-00063-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d9c4d4eb8f99282a1481c0d64f74c4f5fa228ef13602925adce1fd97fadcab5 +size 1755370864 diff --git a/model-00064-of-00082.safetensors b/model-00064-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d222768c0a8ae8260a1d7619c689df0ab28aff56 --- /dev/null +++ b/model-00064-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1469828fc807b4f029a2865a7ef42e6304027857a0034b0c3b63548f87fa7970 +size 1755370864 diff --git a/model-00065-of-00082.safetensors b/model-00065-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c22d88e3433e0126fd8dc6b68478425bc17d1453 --- /dev/null +++ b/model-00065-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:119c6edddfba335fa521a536733e5e56b8049453c2c70f4c94aaea22e658c877 +size 1755370864 diff --git a/model-00066-of-00082.safetensors b/model-00066-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2d0d53a5c369021696ee5cc14c684b9389958592 --- /dev/null +++ b/model-00066-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e7100e9ec4faf9f244d25676175baac9936e13c1a13a41e4ada6077848e6063 +size 1755370864 diff --git a/model-00067-of-00082.safetensors b/model-00067-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f49273da294b6fbcc0a986c6f13315a0b022b049 --- /dev/null +++ b/model-00067-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ce6376427b0fc28331d8b86607369d35e37a09b22f0149215115110b5034e85 +size 1755370864 diff --git a/model-00068-of-00082.safetensors b/model-00068-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..114d84237b490a16927211185918a9c40ce83528 --- /dev/null +++ b/model-00068-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:262e0e7f274e50593e8b544ccf052d05fa2aedea973d6c6641911796f3ee0908 +size 1755370864 diff --git a/model-00069-of-00082.safetensors b/model-00069-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f514c65823320b3da1958f7335e8ae0f10b87c81 --- /dev/null +++ b/model-00069-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f33eccacede16e880e93335bbc367a42726678bccd4cd7cd6a6325a1b4c6368 +size 1755370864 diff --git a/model-00070-of-00082.safetensors b/model-00070-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..76a72965eff19c06dbbfad7eb6f888145376abbd --- /dev/null +++ b/model-00070-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3696da8066d6b406e2d0a581b6068f53b5394318820dfc7dd66bfe977f0a477 +size 1755370864 diff --git a/model-00071-of-00082.safetensors b/model-00071-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..eae72c821f9c2e95db11f0024defc9a7c80c9f9a --- /dev/null +++ b/model-00071-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4505c9f932222a1f8255a1f967aa856d7120ea3ef31bf03774bca33ef1276211 +size 1755370864 diff --git a/model-00072-of-00082.safetensors b/model-00072-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7e3a140c6c61a5e508bd7c0883f6f00813858f23 --- /dev/null +++ b/model-00072-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b1d338f13a30940b9ceb136104585454ea4f886dd329c2a949af2fb475b5f8e +size 1755370864 diff --git a/model-00073-of-00082.safetensors b/model-00073-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c46b7bc46a642652d5255e895ee78b52f38cc78d --- /dev/null +++ b/model-00073-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:455247aa38c7ba29c9ac5bd081f6ec209af44a2f0c5e24696be99c972d9b185d +size 1755370864 diff --git a/model-00074-of-00082.safetensors b/model-00074-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2e44e552e5e580c6b5621f9e7a1aea75c63bc866 --- /dev/null +++ b/model-00074-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df662034bbd1ff29c0250ce231723423653db9a48048b2a440225f22ac1e0481 +size 1755370864 diff --git a/model-00075-of-00082.safetensors b/model-00075-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3226ff2b4c0da52a5dc49cacb0ed5f7678a22ee9 --- /dev/null +++ b/model-00075-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e82b2e6e1120e7f5f1e905e9a6f1c2c1f2b57edd8d53bc511bd55d2e72f461e +size 1755370864 diff --git a/model-00076-of-00082.safetensors b/model-00076-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f61aaf58e49056c7e48d4a667669110cee6d77cd --- /dev/null +++ b/model-00076-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:286715fc5f4629f4be4662d80171451af4c398204b62570f6140bec98204da6b +size 1755370864 diff --git a/model-00077-of-00082.safetensors b/model-00077-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e418c027f9ec612223e547ce2d793f7c74c9fb76 --- /dev/null +++ b/model-00077-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d252810b55a6a0cd6890b34abab0eab30481c0c43a580c06c5b1ef447cc93dd7 +size 1755370864 diff --git a/model-00078-of-00082.safetensors b/model-00078-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cdb3162ede46897ca3819fe481438be01257a926 --- /dev/null +++ b/model-00078-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:451d70143acba998e445b835bb63d4e8a4906dfd679f89548de1564fe9dd8941 +size 1755370864 diff --git a/model-00079-of-00082.safetensors b/model-00079-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d109a77499e9e2012060d9fc40fa442973c2e8a9 --- /dev/null +++ b/model-00079-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d0798e49af09ffefee315d1be9a22dc1faebfa7a83f251bb0c7477ec17fb6ce +size 1755370864 diff --git a/model-00080-of-00082.safetensors b/model-00080-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1ccb27f25e60b60dc6d5e4f53c41dd2e94689249 --- /dev/null +++ b/model-00080-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6112dfabe3a16aae234fde8a90b8e2d3774043c8a4e6dd979143f550bb80a6b6 +size 1755370864 diff --git a/model-00081-of-00082.safetensors b/model-00081-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e46d5eab863aa63c5397da210830611fca5de4b2 --- /dev/null +++ b/model-00081-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1a5741e940d8038c2ed5988b810e9e7e06328bd5fc88995d213e742c6430011 +size 2491416704 diff --git a/model-00082-of-00082.safetensors b/model-00082-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..62d973579cb2830ea9a3c8b441f77c7aec8329af --- /dev/null +++ b/model-00082-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:802745758f86d1c63cce14a479d00f1175f1030be26f01a0cf86f56d323575cf +size 1453376176 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..7586a1e894d26d2be9b5cf5a2e1201e6f61d2b7a --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,970 @@ +{ + "metadata": { + "total_size": 145412407296 + }, + "weight_map": { + "lm_head.weight": "model-00081-of-00082.safetensors", + "model.embed_tokens.weight": "model-00001-of-00082.safetensors", + "model.layers.0.input_layernorm.weight": "model-00002-of-00082.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00002-of-00082.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00082.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00002-of-00082.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00082.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00002-of-00082.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00082.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00082.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00002-of-00082.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00082.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00002-of-00082.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00082.safetensors", + "model.layers.1.input_layernorm.weight": "model-00003-of-00082.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00003-of-00082.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00082.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00003-of-00082.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00082.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00082.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00082.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00082.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00082.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00082.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00082.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00082.safetensors", + "model.layers.10.input_layernorm.weight": "model-00012-of-00082.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00012-of-00082.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00012-of-00082.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00012-of-00082.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00012-of-00082.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00011-of-00082.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00011-of-00082.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00011-of-00082.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00011-of-00082.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00011-of-00082.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00011-of-00082.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00011-of-00082.safetensors", + "model.layers.11.input_layernorm.weight": "model-00013-of-00082.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00013-of-00082.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00013-of-00082.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00013-of-00082.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00013-of-00082.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00012-of-00082.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00012-of-00082.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00012-of-00082.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00012-of-00082.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00012-of-00082.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00012-of-00082.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00012-of-00082.safetensors", + "model.layers.12.input_layernorm.weight": "model-00014-of-00082.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00014-of-00082.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00014-of-00082.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00014-of-00082.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00014-of-00082.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00013-of-00082.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00013-of-00082.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00013-of-00082.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00013-of-00082.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00013-of-00082.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00013-of-00082.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00013-of-00082.safetensors", + "model.layers.13.input_layernorm.weight": "model-00015-of-00082.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00015-of-00082.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00015-of-00082.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00015-of-00082.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00015-of-00082.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00014-of-00082.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00014-of-00082.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00014-of-00082.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00014-of-00082.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00014-of-00082.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00014-of-00082.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00014-of-00082.safetensors", + "model.layers.14.input_layernorm.weight": "model-00016-of-00082.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00016-of-00082.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00016-of-00082.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00016-of-00082.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00016-of-00082.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00015-of-00082.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00015-of-00082.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00015-of-00082.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00015-of-00082.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00015-of-00082.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00015-of-00082.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00015-of-00082.safetensors", + "model.layers.15.input_layernorm.weight": "model-00017-of-00082.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00017-of-00082.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00017-of-00082.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00017-of-00082.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00017-of-00082.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00016-of-00082.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00016-of-00082.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00016-of-00082.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00016-of-00082.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00016-of-00082.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00016-of-00082.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00016-of-00082.safetensors", + "model.layers.16.input_layernorm.weight": "model-00018-of-00082.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00018-of-00082.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00018-of-00082.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00018-of-00082.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00018-of-00082.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00017-of-00082.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00017-of-00082.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00017-of-00082.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00017-of-00082.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00017-of-00082.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00017-of-00082.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00017-of-00082.safetensors", + "model.layers.17.input_layernorm.weight": "model-00019-of-00082.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00019-of-00082.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00019-of-00082.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00019-of-00082.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00019-of-00082.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00018-of-00082.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00018-of-00082.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00018-of-00082.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00018-of-00082.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00018-of-00082.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00018-of-00082.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00018-of-00082.safetensors", + "model.layers.18.input_layernorm.weight": "model-00020-of-00082.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00020-of-00082.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00020-of-00082.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00020-of-00082.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00020-of-00082.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00019-of-00082.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00019-of-00082.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00019-of-00082.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00019-of-00082.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00019-of-00082.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00019-of-00082.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00019-of-00082.safetensors", + "model.layers.19.input_layernorm.weight": "model-00021-of-00082.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00021-of-00082.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00021-of-00082.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00021-of-00082.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00021-of-00082.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00020-of-00082.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00020-of-00082.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00020-of-00082.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00020-of-00082.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00020-of-00082.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00020-of-00082.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00020-of-00082.safetensors", + "model.layers.2.input_layernorm.weight": "model-00004-of-00082.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00004-of-00082.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00082.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00004-of-00082.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00082.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00003-of-00082.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00082.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00082.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00003-of-00082.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00082.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00003-of-00082.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00082.safetensors", + "model.layers.20.input_layernorm.weight": "model-00022-of-00082.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00022-of-00082.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00022-of-00082.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00022-of-00082.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00022-of-00082.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00021-of-00082.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00021-of-00082.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00021-of-00082.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00021-of-00082.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00021-of-00082.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00021-of-00082.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00021-of-00082.safetensors", + "model.layers.21.input_layernorm.weight": "model-00023-of-00082.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00023-of-00082.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00023-of-00082.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00023-of-00082.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00023-of-00082.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00022-of-00082.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00022-of-00082.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00022-of-00082.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00022-of-00082.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00022-of-00082.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00022-of-00082.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00022-of-00082.safetensors", + "model.layers.22.input_layernorm.weight": "model-00024-of-00082.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00024-of-00082.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00024-of-00082.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00024-of-00082.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00024-of-00082.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00023-of-00082.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00023-of-00082.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00023-of-00082.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00023-of-00082.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00023-of-00082.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00023-of-00082.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00023-of-00082.safetensors", + "model.layers.23.input_layernorm.weight": "model-00025-of-00082.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00025-of-00082.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00025-of-00082.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00025-of-00082.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00025-of-00082.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00024-of-00082.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00024-of-00082.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00024-of-00082.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00024-of-00082.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00024-of-00082.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00024-of-00082.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00024-of-00082.safetensors", + "model.layers.24.input_layernorm.weight": "model-00026-of-00082.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00026-of-00082.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00026-of-00082.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00026-of-00082.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00026-of-00082.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00025-of-00082.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00025-of-00082.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00025-of-00082.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00025-of-00082.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00025-of-00082.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00025-of-00082.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00025-of-00082.safetensors", + "model.layers.25.input_layernorm.weight": "model-00027-of-00082.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00027-of-00082.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00027-of-00082.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00027-of-00082.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00027-of-00082.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00026-of-00082.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00026-of-00082.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00026-of-00082.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00026-of-00082.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00026-of-00082.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00026-of-00082.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00026-of-00082.safetensors", + "model.layers.26.input_layernorm.weight": "model-00028-of-00082.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00028-of-00082.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00028-of-00082.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00028-of-00082.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00028-of-00082.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00027-of-00082.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00027-of-00082.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00027-of-00082.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00027-of-00082.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00027-of-00082.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00027-of-00082.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00027-of-00082.safetensors", + "model.layers.27.input_layernorm.weight": "model-00029-of-00082.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00029-of-00082.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00029-of-00082.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00029-of-00082.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00029-of-00082.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00028-of-00082.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00028-of-00082.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00028-of-00082.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00028-of-00082.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00028-of-00082.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00028-of-00082.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00028-of-00082.safetensors", + "model.layers.28.input_layernorm.weight": "model-00030-of-00082.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00030-of-00082.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00030-of-00082.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00030-of-00082.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00030-of-00082.safetensors", + "model.layers.28.self_attn.k_proj.bias": "model-00029-of-00082.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00029-of-00082.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00029-of-00082.safetensors", + "model.layers.28.self_attn.q_proj.bias": "model-00029-of-00082.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00029-of-00082.safetensors", + "model.layers.28.self_attn.v_proj.bias": "model-00029-of-00082.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00029-of-00082.safetensors", + "model.layers.29.input_layernorm.weight": "model-00031-of-00082.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00031-of-00082.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00031-of-00082.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00031-of-00082.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00031-of-00082.safetensors", + "model.layers.29.self_attn.k_proj.bias": "model-00030-of-00082.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00030-of-00082.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00030-of-00082.safetensors", + "model.layers.29.self_attn.q_proj.bias": "model-00030-of-00082.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00030-of-00082.safetensors", + "model.layers.29.self_attn.v_proj.bias": "model-00030-of-00082.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00030-of-00082.safetensors", + "model.layers.3.input_layernorm.weight": "model-00005-of-00082.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00005-of-00082.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00005-of-00082.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00005-of-00082.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00082.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00004-of-00082.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00082.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00082.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00004-of-00082.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00082.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00004-of-00082.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00082.safetensors", + "model.layers.30.input_layernorm.weight": "model-00032-of-00082.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00032-of-00082.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00032-of-00082.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00032-of-00082.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00032-of-00082.safetensors", + "model.layers.30.self_attn.k_proj.bias": "model-00031-of-00082.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00031-of-00082.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00031-of-00082.safetensors", + "model.layers.30.self_attn.q_proj.bias": "model-00031-of-00082.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00031-of-00082.safetensors", + "model.layers.30.self_attn.v_proj.bias": "model-00031-of-00082.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00031-of-00082.safetensors", + "model.layers.31.input_layernorm.weight": "model-00033-of-00082.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00033-of-00082.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00033-of-00082.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00033-of-00082.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00033-of-00082.safetensors", + "model.layers.31.self_attn.k_proj.bias": "model-00032-of-00082.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00032-of-00082.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00032-of-00082.safetensors", + "model.layers.31.self_attn.q_proj.bias": "model-00032-of-00082.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00032-of-00082.safetensors", + "model.layers.31.self_attn.v_proj.bias": "model-00032-of-00082.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00032-of-00082.safetensors", + "model.layers.32.input_layernorm.weight": "model-00034-of-00082.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00034-of-00082.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00034-of-00082.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00034-of-00082.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00034-of-00082.safetensors", + "model.layers.32.self_attn.k_proj.bias": "model-00033-of-00082.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00033-of-00082.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00033-of-00082.safetensors", + "model.layers.32.self_attn.q_proj.bias": "model-00033-of-00082.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00033-of-00082.safetensors", + "model.layers.32.self_attn.v_proj.bias": "model-00033-of-00082.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00033-of-00082.safetensors", + "model.layers.33.input_layernorm.weight": "model-00035-of-00082.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00035-of-00082.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00035-of-00082.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00035-of-00082.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00035-of-00082.safetensors", + "model.layers.33.self_attn.k_proj.bias": "model-00034-of-00082.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00034-of-00082.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00034-of-00082.safetensors", + "model.layers.33.self_attn.q_proj.bias": "model-00034-of-00082.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00034-of-00082.safetensors", + "model.layers.33.self_attn.v_proj.bias": "model-00034-of-00082.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00034-of-00082.safetensors", + "model.layers.34.input_layernorm.weight": "model-00036-of-00082.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00036-of-00082.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00036-of-00082.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00036-of-00082.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00036-of-00082.safetensors", + "model.layers.34.self_attn.k_proj.bias": "model-00035-of-00082.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00035-of-00082.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00035-of-00082.safetensors", + "model.layers.34.self_attn.q_proj.bias": "model-00035-of-00082.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00035-of-00082.safetensors", + "model.layers.34.self_attn.v_proj.bias": "model-00035-of-00082.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00035-of-00082.safetensors", + "model.layers.35.input_layernorm.weight": "model-00037-of-00082.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00037-of-00082.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00037-of-00082.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00037-of-00082.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00037-of-00082.safetensors", + "model.layers.35.self_attn.k_proj.bias": "model-00036-of-00082.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00036-of-00082.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00036-of-00082.safetensors", + "model.layers.35.self_attn.q_proj.bias": "model-00036-of-00082.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00036-of-00082.safetensors", + "model.layers.35.self_attn.v_proj.bias": "model-00036-of-00082.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00036-of-00082.safetensors", + "model.layers.36.input_layernorm.weight": "model-00038-of-00082.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00038-of-00082.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00038-of-00082.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00038-of-00082.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00038-of-00082.safetensors", + "model.layers.36.self_attn.k_proj.bias": "model-00037-of-00082.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00037-of-00082.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00037-of-00082.safetensors", + "model.layers.36.self_attn.q_proj.bias": "model-00037-of-00082.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00037-of-00082.safetensors", + "model.layers.36.self_attn.v_proj.bias": "model-00037-of-00082.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00037-of-00082.safetensors", + "model.layers.37.input_layernorm.weight": "model-00039-of-00082.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00039-of-00082.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00039-of-00082.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00039-of-00082.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00039-of-00082.safetensors", + "model.layers.37.self_attn.k_proj.bias": "model-00038-of-00082.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00038-of-00082.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00038-of-00082.safetensors", + "model.layers.37.self_attn.q_proj.bias": "model-00038-of-00082.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00038-of-00082.safetensors", + "model.layers.37.self_attn.v_proj.bias": "model-00038-of-00082.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00038-of-00082.safetensors", + "model.layers.38.input_layernorm.weight": "model-00040-of-00082.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00040-of-00082.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00040-of-00082.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00040-of-00082.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00040-of-00082.safetensors", + "model.layers.38.self_attn.k_proj.bias": "model-00039-of-00082.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00039-of-00082.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00039-of-00082.safetensors", + "model.layers.38.self_attn.q_proj.bias": "model-00039-of-00082.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00039-of-00082.safetensors", + "model.layers.38.self_attn.v_proj.bias": "model-00039-of-00082.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00039-of-00082.safetensors", + "model.layers.39.input_layernorm.weight": "model-00041-of-00082.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00041-of-00082.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00041-of-00082.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00041-of-00082.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00041-of-00082.safetensors", + "model.layers.39.self_attn.k_proj.bias": "model-00040-of-00082.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00040-of-00082.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00040-of-00082.safetensors", + "model.layers.39.self_attn.q_proj.bias": "model-00040-of-00082.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00040-of-00082.safetensors", + "model.layers.39.self_attn.v_proj.bias": "model-00040-of-00082.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00040-of-00082.safetensors", + "model.layers.4.input_layernorm.weight": "model-00006-of-00082.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00006-of-00082.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00006-of-00082.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00006-of-00082.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00006-of-00082.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00005-of-00082.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00082.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00082.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00005-of-00082.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00082.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00005-of-00082.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00082.safetensors", + "model.layers.40.input_layernorm.weight": "model-00042-of-00082.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00042-of-00082.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00042-of-00082.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00042-of-00082.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00042-of-00082.safetensors", + "model.layers.40.self_attn.k_proj.bias": "model-00041-of-00082.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00041-of-00082.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00041-of-00082.safetensors", + "model.layers.40.self_attn.q_proj.bias": "model-00041-of-00082.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00041-of-00082.safetensors", + "model.layers.40.self_attn.v_proj.bias": "model-00041-of-00082.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00041-of-00082.safetensors", + "model.layers.41.input_layernorm.weight": "model-00043-of-00082.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00043-of-00082.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00043-of-00082.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00043-of-00082.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00043-of-00082.safetensors", + "model.layers.41.self_attn.k_proj.bias": "model-00042-of-00082.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00042-of-00082.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00042-of-00082.safetensors", + "model.layers.41.self_attn.q_proj.bias": "model-00042-of-00082.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00042-of-00082.safetensors", + "model.layers.41.self_attn.v_proj.bias": "model-00042-of-00082.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00042-of-00082.safetensors", + "model.layers.42.input_layernorm.weight": "model-00044-of-00082.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00044-of-00082.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00044-of-00082.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00044-of-00082.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00044-of-00082.safetensors", + "model.layers.42.self_attn.k_proj.bias": "model-00043-of-00082.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00043-of-00082.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00043-of-00082.safetensors", + "model.layers.42.self_attn.q_proj.bias": "model-00043-of-00082.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00043-of-00082.safetensors", + "model.layers.42.self_attn.v_proj.bias": "model-00043-of-00082.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00043-of-00082.safetensors", + "model.layers.43.input_layernorm.weight": "model-00045-of-00082.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00045-of-00082.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00045-of-00082.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00045-of-00082.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00045-of-00082.safetensors", + "model.layers.43.self_attn.k_proj.bias": "model-00044-of-00082.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00044-of-00082.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00044-of-00082.safetensors", + "model.layers.43.self_attn.q_proj.bias": "model-00044-of-00082.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00044-of-00082.safetensors", + "model.layers.43.self_attn.v_proj.bias": "model-00044-of-00082.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00044-of-00082.safetensors", + "model.layers.44.input_layernorm.weight": "model-00046-of-00082.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00046-of-00082.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00046-of-00082.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00046-of-00082.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00046-of-00082.safetensors", + "model.layers.44.self_attn.k_proj.bias": "model-00045-of-00082.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00045-of-00082.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00045-of-00082.safetensors", + "model.layers.44.self_attn.q_proj.bias": "model-00045-of-00082.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00045-of-00082.safetensors", + "model.layers.44.self_attn.v_proj.bias": "model-00045-of-00082.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00045-of-00082.safetensors", + "model.layers.45.input_layernorm.weight": "model-00047-of-00082.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00047-of-00082.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00047-of-00082.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00047-of-00082.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00047-of-00082.safetensors", + "model.layers.45.self_attn.k_proj.bias": "model-00046-of-00082.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00046-of-00082.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00046-of-00082.safetensors", + "model.layers.45.self_attn.q_proj.bias": "model-00046-of-00082.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00046-of-00082.safetensors", + "model.layers.45.self_attn.v_proj.bias": "model-00046-of-00082.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00046-of-00082.safetensors", + "model.layers.46.input_layernorm.weight": "model-00048-of-00082.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00048-of-00082.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00048-of-00082.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00048-of-00082.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00048-of-00082.safetensors", + "model.layers.46.self_attn.k_proj.bias": "model-00047-of-00082.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00047-of-00082.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00047-of-00082.safetensors", + "model.layers.46.self_attn.q_proj.bias": "model-00047-of-00082.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00047-of-00082.safetensors", + "model.layers.46.self_attn.v_proj.bias": "model-00047-of-00082.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00047-of-00082.safetensors", + "model.layers.47.input_layernorm.weight": "model-00049-of-00082.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00049-of-00082.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00049-of-00082.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00049-of-00082.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00049-of-00082.safetensors", + "model.layers.47.self_attn.k_proj.bias": "model-00048-of-00082.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00048-of-00082.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00048-of-00082.safetensors", + "model.layers.47.self_attn.q_proj.bias": "model-00048-of-00082.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00048-of-00082.safetensors", + "model.layers.47.self_attn.v_proj.bias": "model-00048-of-00082.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00048-of-00082.safetensors", + "model.layers.48.input_layernorm.weight": "model-00050-of-00082.safetensors", + "model.layers.48.mlp.down_proj.weight": "model-00050-of-00082.safetensors", + "model.layers.48.mlp.gate_proj.weight": "model-00050-of-00082.safetensors", + "model.layers.48.mlp.up_proj.weight": "model-00050-of-00082.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00050-of-00082.safetensors", + "model.layers.48.self_attn.k_proj.bias": "model-00049-of-00082.safetensors", + "model.layers.48.self_attn.k_proj.weight": "model-00049-of-00082.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00049-of-00082.safetensors", + "model.layers.48.self_attn.q_proj.bias": "model-00049-of-00082.safetensors", + "model.layers.48.self_attn.q_proj.weight": "model-00049-of-00082.safetensors", + "model.layers.48.self_attn.v_proj.bias": "model-00049-of-00082.safetensors", + "model.layers.48.self_attn.v_proj.weight": "model-00049-of-00082.safetensors", + "model.layers.49.input_layernorm.weight": "model-00051-of-00082.safetensors", + "model.layers.49.mlp.down_proj.weight": "model-00051-of-00082.safetensors", + "model.layers.49.mlp.gate_proj.weight": "model-00051-of-00082.safetensors", + "model.layers.49.mlp.up_proj.weight": "model-00051-of-00082.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00051-of-00082.safetensors", + "model.layers.49.self_attn.k_proj.bias": "model-00050-of-00082.safetensors", + "model.layers.49.self_attn.k_proj.weight": "model-00050-of-00082.safetensors", + "model.layers.49.self_attn.o_proj.weight": "model-00050-of-00082.safetensors", + "model.layers.49.self_attn.q_proj.bias": "model-00050-of-00082.safetensors", + "model.layers.49.self_attn.q_proj.weight": "model-00050-of-00082.safetensors", + "model.layers.49.self_attn.v_proj.bias": "model-00050-of-00082.safetensors", + "model.layers.49.self_attn.v_proj.weight": "model-00050-of-00082.safetensors", + "model.layers.5.input_layernorm.weight": "model-00007-of-00082.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00007-of-00082.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00007-of-00082.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00007-of-00082.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00007-of-00082.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00006-of-00082.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00082.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00082.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00006-of-00082.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00082.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00006-of-00082.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00082.safetensors", + "model.layers.50.input_layernorm.weight": "model-00052-of-00082.safetensors", + "model.layers.50.mlp.down_proj.weight": "model-00052-of-00082.safetensors", + "model.layers.50.mlp.gate_proj.weight": "model-00052-of-00082.safetensors", + "model.layers.50.mlp.up_proj.weight": "model-00052-of-00082.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00052-of-00082.safetensors", + "model.layers.50.self_attn.k_proj.bias": "model-00051-of-00082.safetensors", + "model.layers.50.self_attn.k_proj.weight": "model-00051-of-00082.safetensors", + "model.layers.50.self_attn.o_proj.weight": "model-00051-of-00082.safetensors", + "model.layers.50.self_attn.q_proj.bias": "model-00051-of-00082.safetensors", + "model.layers.50.self_attn.q_proj.weight": "model-00051-of-00082.safetensors", + "model.layers.50.self_attn.v_proj.bias": "model-00051-of-00082.safetensors", + "model.layers.50.self_attn.v_proj.weight": "model-00051-of-00082.safetensors", + "model.layers.51.input_layernorm.weight": "model-00053-of-00082.safetensors", + "model.layers.51.mlp.down_proj.weight": "model-00053-of-00082.safetensors", + "model.layers.51.mlp.gate_proj.weight": "model-00053-of-00082.safetensors", + "model.layers.51.mlp.up_proj.weight": "model-00053-of-00082.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00053-of-00082.safetensors", + "model.layers.51.self_attn.k_proj.bias": "model-00052-of-00082.safetensors", + "model.layers.51.self_attn.k_proj.weight": "model-00052-of-00082.safetensors", + "model.layers.51.self_attn.o_proj.weight": "model-00052-of-00082.safetensors", + "model.layers.51.self_attn.q_proj.bias": "model-00052-of-00082.safetensors", + "model.layers.51.self_attn.q_proj.weight": "model-00052-of-00082.safetensors", + "model.layers.51.self_attn.v_proj.bias": "model-00052-of-00082.safetensors", + "model.layers.51.self_attn.v_proj.weight": "model-00052-of-00082.safetensors", + "model.layers.52.input_layernorm.weight": "model-00054-of-00082.safetensors", + "model.layers.52.mlp.down_proj.weight": "model-00054-of-00082.safetensors", + "model.layers.52.mlp.gate_proj.weight": "model-00054-of-00082.safetensors", + "model.layers.52.mlp.up_proj.weight": "model-00054-of-00082.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00054-of-00082.safetensors", + "model.layers.52.self_attn.k_proj.bias": "model-00053-of-00082.safetensors", + "model.layers.52.self_attn.k_proj.weight": "model-00053-of-00082.safetensors", + "model.layers.52.self_attn.o_proj.weight": "model-00053-of-00082.safetensors", + "model.layers.52.self_attn.q_proj.bias": "model-00053-of-00082.safetensors", + "model.layers.52.self_attn.q_proj.weight": "model-00053-of-00082.safetensors", + "model.layers.52.self_attn.v_proj.bias": "model-00053-of-00082.safetensors", + "model.layers.52.self_attn.v_proj.weight": "model-00053-of-00082.safetensors", + "model.layers.53.input_layernorm.weight": "model-00055-of-00082.safetensors", + "model.layers.53.mlp.down_proj.weight": "model-00055-of-00082.safetensors", + "model.layers.53.mlp.gate_proj.weight": "model-00055-of-00082.safetensors", + "model.layers.53.mlp.up_proj.weight": "model-00055-of-00082.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00055-of-00082.safetensors", + "model.layers.53.self_attn.k_proj.bias": "model-00054-of-00082.safetensors", + "model.layers.53.self_attn.k_proj.weight": "model-00054-of-00082.safetensors", + "model.layers.53.self_attn.o_proj.weight": "model-00054-of-00082.safetensors", + "model.layers.53.self_attn.q_proj.bias": "model-00054-of-00082.safetensors", + "model.layers.53.self_attn.q_proj.weight": "model-00054-of-00082.safetensors", + "model.layers.53.self_attn.v_proj.bias": "model-00054-of-00082.safetensors", + "model.layers.53.self_attn.v_proj.weight": "model-00054-of-00082.safetensors", + "model.layers.54.input_layernorm.weight": "model-00056-of-00082.safetensors", + "model.layers.54.mlp.down_proj.weight": "model-00056-of-00082.safetensors", + "model.layers.54.mlp.gate_proj.weight": "model-00056-of-00082.safetensors", + "model.layers.54.mlp.up_proj.weight": "model-00056-of-00082.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00056-of-00082.safetensors", + "model.layers.54.self_attn.k_proj.bias": "model-00055-of-00082.safetensors", + "model.layers.54.self_attn.k_proj.weight": "model-00055-of-00082.safetensors", + "model.layers.54.self_attn.o_proj.weight": "model-00055-of-00082.safetensors", + "model.layers.54.self_attn.q_proj.bias": "model-00055-of-00082.safetensors", + "model.layers.54.self_attn.q_proj.weight": "model-00055-of-00082.safetensors", + "model.layers.54.self_attn.v_proj.bias": "model-00055-of-00082.safetensors", + "model.layers.54.self_attn.v_proj.weight": "model-00055-of-00082.safetensors", + "model.layers.55.input_layernorm.weight": "model-00057-of-00082.safetensors", + "model.layers.55.mlp.down_proj.weight": "model-00057-of-00082.safetensors", + "model.layers.55.mlp.gate_proj.weight": "model-00057-of-00082.safetensors", + "model.layers.55.mlp.up_proj.weight": "model-00057-of-00082.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00057-of-00082.safetensors", + "model.layers.55.self_attn.k_proj.bias": "model-00056-of-00082.safetensors", + "model.layers.55.self_attn.k_proj.weight": "model-00056-of-00082.safetensors", + "model.layers.55.self_attn.o_proj.weight": "model-00056-of-00082.safetensors", + "model.layers.55.self_attn.q_proj.bias": "model-00056-of-00082.safetensors", + "model.layers.55.self_attn.q_proj.weight": "model-00056-of-00082.safetensors", + "model.layers.55.self_attn.v_proj.bias": "model-00056-of-00082.safetensors", + "model.layers.55.self_attn.v_proj.weight": "model-00056-of-00082.safetensors", + "model.layers.56.input_layernorm.weight": "model-00058-of-00082.safetensors", + "model.layers.56.mlp.down_proj.weight": "model-00058-of-00082.safetensors", + "model.layers.56.mlp.gate_proj.weight": "model-00058-of-00082.safetensors", + "model.layers.56.mlp.up_proj.weight": "model-00058-of-00082.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00058-of-00082.safetensors", + "model.layers.56.self_attn.k_proj.bias": "model-00057-of-00082.safetensors", + "model.layers.56.self_attn.k_proj.weight": "model-00057-of-00082.safetensors", + "model.layers.56.self_attn.o_proj.weight": "model-00057-of-00082.safetensors", + "model.layers.56.self_attn.q_proj.bias": "model-00057-of-00082.safetensors", + "model.layers.56.self_attn.q_proj.weight": "model-00057-of-00082.safetensors", + "model.layers.56.self_attn.v_proj.bias": "model-00057-of-00082.safetensors", + "model.layers.56.self_attn.v_proj.weight": "model-00057-of-00082.safetensors", + "model.layers.57.input_layernorm.weight": "model-00059-of-00082.safetensors", + "model.layers.57.mlp.down_proj.weight": "model-00059-of-00082.safetensors", + "model.layers.57.mlp.gate_proj.weight": "model-00059-of-00082.safetensors", + "model.layers.57.mlp.up_proj.weight": "model-00059-of-00082.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00059-of-00082.safetensors", + "model.layers.57.self_attn.k_proj.bias": "model-00058-of-00082.safetensors", + "model.layers.57.self_attn.k_proj.weight": "model-00058-of-00082.safetensors", + "model.layers.57.self_attn.o_proj.weight": "model-00058-of-00082.safetensors", + "model.layers.57.self_attn.q_proj.bias": "model-00058-of-00082.safetensors", + "model.layers.57.self_attn.q_proj.weight": "model-00058-of-00082.safetensors", + "model.layers.57.self_attn.v_proj.bias": "model-00058-of-00082.safetensors", + "model.layers.57.self_attn.v_proj.weight": "model-00058-of-00082.safetensors", + "model.layers.58.input_layernorm.weight": "model-00060-of-00082.safetensors", + "model.layers.58.mlp.down_proj.weight": "model-00060-of-00082.safetensors", + "model.layers.58.mlp.gate_proj.weight": "model-00060-of-00082.safetensors", + "model.layers.58.mlp.up_proj.weight": "model-00060-of-00082.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00060-of-00082.safetensors", + "model.layers.58.self_attn.k_proj.bias": "model-00059-of-00082.safetensors", + "model.layers.58.self_attn.k_proj.weight": "model-00059-of-00082.safetensors", + "model.layers.58.self_attn.o_proj.weight": "model-00059-of-00082.safetensors", + "model.layers.58.self_attn.q_proj.bias": "model-00059-of-00082.safetensors", + "model.layers.58.self_attn.q_proj.weight": "model-00059-of-00082.safetensors", + "model.layers.58.self_attn.v_proj.bias": "model-00059-of-00082.safetensors", + "model.layers.58.self_attn.v_proj.weight": "model-00059-of-00082.safetensors", + "model.layers.59.input_layernorm.weight": "model-00061-of-00082.safetensors", + "model.layers.59.mlp.down_proj.weight": "model-00061-of-00082.safetensors", + "model.layers.59.mlp.gate_proj.weight": "model-00061-of-00082.safetensors", + "model.layers.59.mlp.up_proj.weight": "model-00061-of-00082.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00061-of-00082.safetensors", + "model.layers.59.self_attn.k_proj.bias": "model-00060-of-00082.safetensors", + "model.layers.59.self_attn.k_proj.weight": "model-00060-of-00082.safetensors", + "model.layers.59.self_attn.o_proj.weight": "model-00060-of-00082.safetensors", + "model.layers.59.self_attn.q_proj.bias": "model-00060-of-00082.safetensors", + "model.layers.59.self_attn.q_proj.weight": "model-00060-of-00082.safetensors", + "model.layers.59.self_attn.v_proj.bias": "model-00060-of-00082.safetensors", + "model.layers.59.self_attn.v_proj.weight": "model-00060-of-00082.safetensors", + "model.layers.6.input_layernorm.weight": "model-00008-of-00082.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00008-of-00082.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00008-of-00082.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00008-of-00082.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00008-of-00082.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00007-of-00082.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00007-of-00082.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00082.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00007-of-00082.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00082.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00007-of-00082.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00007-of-00082.safetensors", + "model.layers.60.input_layernorm.weight": "model-00062-of-00082.safetensors", + "model.layers.60.mlp.down_proj.weight": "model-00062-of-00082.safetensors", + "model.layers.60.mlp.gate_proj.weight": "model-00062-of-00082.safetensors", + "model.layers.60.mlp.up_proj.weight": "model-00062-of-00082.safetensors", + "model.layers.60.post_attention_layernorm.weight": "model-00062-of-00082.safetensors", + "model.layers.60.self_attn.k_proj.bias": "model-00061-of-00082.safetensors", + "model.layers.60.self_attn.k_proj.weight": "model-00061-of-00082.safetensors", + "model.layers.60.self_attn.o_proj.weight": "model-00061-of-00082.safetensors", + "model.layers.60.self_attn.q_proj.bias": "model-00061-of-00082.safetensors", + "model.layers.60.self_attn.q_proj.weight": "model-00061-of-00082.safetensors", + "model.layers.60.self_attn.v_proj.bias": "model-00061-of-00082.safetensors", + "model.layers.60.self_attn.v_proj.weight": "model-00061-of-00082.safetensors", + "model.layers.61.input_layernorm.weight": "model-00063-of-00082.safetensors", + "model.layers.61.mlp.down_proj.weight": "model-00063-of-00082.safetensors", + "model.layers.61.mlp.gate_proj.weight": "model-00063-of-00082.safetensors", + "model.layers.61.mlp.up_proj.weight": "model-00063-of-00082.safetensors", + "model.layers.61.post_attention_layernorm.weight": "model-00063-of-00082.safetensors", + "model.layers.61.self_attn.k_proj.bias": "model-00062-of-00082.safetensors", + "model.layers.61.self_attn.k_proj.weight": "model-00062-of-00082.safetensors", + "model.layers.61.self_attn.o_proj.weight": "model-00062-of-00082.safetensors", + "model.layers.61.self_attn.q_proj.bias": "model-00062-of-00082.safetensors", + "model.layers.61.self_attn.q_proj.weight": "model-00062-of-00082.safetensors", + "model.layers.61.self_attn.v_proj.bias": "model-00062-of-00082.safetensors", + "model.layers.61.self_attn.v_proj.weight": "model-00062-of-00082.safetensors", + "model.layers.62.input_layernorm.weight": "model-00064-of-00082.safetensors", + "model.layers.62.mlp.down_proj.weight": "model-00064-of-00082.safetensors", + "model.layers.62.mlp.gate_proj.weight": "model-00064-of-00082.safetensors", + "model.layers.62.mlp.up_proj.weight": "model-00064-of-00082.safetensors", + "model.layers.62.post_attention_layernorm.weight": "model-00064-of-00082.safetensors", + "model.layers.62.self_attn.k_proj.bias": "model-00063-of-00082.safetensors", + "model.layers.62.self_attn.k_proj.weight": "model-00063-of-00082.safetensors", + "model.layers.62.self_attn.o_proj.weight": "model-00063-of-00082.safetensors", + "model.layers.62.self_attn.q_proj.bias": "model-00063-of-00082.safetensors", + "model.layers.62.self_attn.q_proj.weight": "model-00063-of-00082.safetensors", + "model.layers.62.self_attn.v_proj.bias": "model-00063-of-00082.safetensors", + "model.layers.62.self_attn.v_proj.weight": "model-00063-of-00082.safetensors", + "model.layers.63.input_layernorm.weight": "model-00065-of-00082.safetensors", + "model.layers.63.mlp.down_proj.weight": "model-00065-of-00082.safetensors", + "model.layers.63.mlp.gate_proj.weight": "model-00065-of-00082.safetensors", + "model.layers.63.mlp.up_proj.weight": "model-00065-of-00082.safetensors", + "model.layers.63.post_attention_layernorm.weight": "model-00065-of-00082.safetensors", + "model.layers.63.self_attn.k_proj.bias": "model-00064-of-00082.safetensors", + "model.layers.63.self_attn.k_proj.weight": "model-00064-of-00082.safetensors", + "model.layers.63.self_attn.o_proj.weight": "model-00064-of-00082.safetensors", + "model.layers.63.self_attn.q_proj.bias": "model-00064-of-00082.safetensors", + "model.layers.63.self_attn.q_proj.weight": "model-00064-of-00082.safetensors", + "model.layers.63.self_attn.v_proj.bias": "model-00064-of-00082.safetensors", + "model.layers.63.self_attn.v_proj.weight": "model-00064-of-00082.safetensors", + "model.layers.64.input_layernorm.weight": "model-00066-of-00082.safetensors", + "model.layers.64.mlp.down_proj.weight": "model-00066-of-00082.safetensors", + "model.layers.64.mlp.gate_proj.weight": "model-00066-of-00082.safetensors", + "model.layers.64.mlp.up_proj.weight": "model-00066-of-00082.safetensors", + "model.layers.64.post_attention_layernorm.weight": "model-00066-of-00082.safetensors", + "model.layers.64.self_attn.k_proj.bias": "model-00065-of-00082.safetensors", + "model.layers.64.self_attn.k_proj.weight": "model-00065-of-00082.safetensors", + "model.layers.64.self_attn.o_proj.weight": "model-00065-of-00082.safetensors", + "model.layers.64.self_attn.q_proj.bias": "model-00065-of-00082.safetensors", + "model.layers.64.self_attn.q_proj.weight": "model-00065-of-00082.safetensors", + "model.layers.64.self_attn.v_proj.bias": "model-00065-of-00082.safetensors", + "model.layers.64.self_attn.v_proj.weight": "model-00065-of-00082.safetensors", + "model.layers.65.input_layernorm.weight": "model-00067-of-00082.safetensors", + "model.layers.65.mlp.down_proj.weight": "model-00067-of-00082.safetensors", + "model.layers.65.mlp.gate_proj.weight": "model-00067-of-00082.safetensors", + "model.layers.65.mlp.up_proj.weight": "model-00067-of-00082.safetensors", + "model.layers.65.post_attention_layernorm.weight": "model-00067-of-00082.safetensors", + "model.layers.65.self_attn.k_proj.bias": "model-00066-of-00082.safetensors", + "model.layers.65.self_attn.k_proj.weight": "model-00066-of-00082.safetensors", + "model.layers.65.self_attn.o_proj.weight": "model-00066-of-00082.safetensors", + "model.layers.65.self_attn.q_proj.bias": "model-00066-of-00082.safetensors", + "model.layers.65.self_attn.q_proj.weight": "model-00066-of-00082.safetensors", + "model.layers.65.self_attn.v_proj.bias": "model-00066-of-00082.safetensors", + "model.layers.65.self_attn.v_proj.weight": "model-00066-of-00082.safetensors", + "model.layers.66.input_layernorm.weight": "model-00068-of-00082.safetensors", + "model.layers.66.mlp.down_proj.weight": "model-00068-of-00082.safetensors", + "model.layers.66.mlp.gate_proj.weight": "model-00068-of-00082.safetensors", + "model.layers.66.mlp.up_proj.weight": "model-00068-of-00082.safetensors", + "model.layers.66.post_attention_layernorm.weight": "model-00068-of-00082.safetensors", + "model.layers.66.self_attn.k_proj.bias": "model-00067-of-00082.safetensors", + "model.layers.66.self_attn.k_proj.weight": "model-00067-of-00082.safetensors", + "model.layers.66.self_attn.o_proj.weight": "model-00067-of-00082.safetensors", + "model.layers.66.self_attn.q_proj.bias": "model-00067-of-00082.safetensors", + "model.layers.66.self_attn.q_proj.weight": "model-00067-of-00082.safetensors", + "model.layers.66.self_attn.v_proj.bias": "model-00067-of-00082.safetensors", + "model.layers.66.self_attn.v_proj.weight": "model-00067-of-00082.safetensors", + "model.layers.67.input_layernorm.weight": "model-00069-of-00082.safetensors", + "model.layers.67.mlp.down_proj.weight": "model-00069-of-00082.safetensors", + "model.layers.67.mlp.gate_proj.weight": "model-00069-of-00082.safetensors", + "model.layers.67.mlp.up_proj.weight": "model-00069-of-00082.safetensors", + "model.layers.67.post_attention_layernorm.weight": "model-00069-of-00082.safetensors", + "model.layers.67.self_attn.k_proj.bias": "model-00068-of-00082.safetensors", + "model.layers.67.self_attn.k_proj.weight": "model-00068-of-00082.safetensors", + "model.layers.67.self_attn.o_proj.weight": "model-00068-of-00082.safetensors", + "model.layers.67.self_attn.q_proj.bias": "model-00068-of-00082.safetensors", + "model.layers.67.self_attn.q_proj.weight": "model-00068-of-00082.safetensors", + "model.layers.67.self_attn.v_proj.bias": "model-00068-of-00082.safetensors", + "model.layers.67.self_attn.v_proj.weight": "model-00068-of-00082.safetensors", + "model.layers.68.input_layernorm.weight": "model-00070-of-00082.safetensors", + "model.layers.68.mlp.down_proj.weight": "model-00070-of-00082.safetensors", + "model.layers.68.mlp.gate_proj.weight": "model-00070-of-00082.safetensors", + "model.layers.68.mlp.up_proj.weight": "model-00070-of-00082.safetensors", + "model.layers.68.post_attention_layernorm.weight": "model-00070-of-00082.safetensors", + "model.layers.68.self_attn.k_proj.bias": "model-00069-of-00082.safetensors", + "model.layers.68.self_attn.k_proj.weight": "model-00069-of-00082.safetensors", + "model.layers.68.self_attn.o_proj.weight": "model-00069-of-00082.safetensors", + "model.layers.68.self_attn.q_proj.bias": "model-00069-of-00082.safetensors", + "model.layers.68.self_attn.q_proj.weight": "model-00069-of-00082.safetensors", + "model.layers.68.self_attn.v_proj.bias": "model-00069-of-00082.safetensors", + "model.layers.68.self_attn.v_proj.weight": "model-00069-of-00082.safetensors", + "model.layers.69.input_layernorm.weight": "model-00071-of-00082.safetensors", + "model.layers.69.mlp.down_proj.weight": "model-00071-of-00082.safetensors", + "model.layers.69.mlp.gate_proj.weight": "model-00071-of-00082.safetensors", + "model.layers.69.mlp.up_proj.weight": "model-00071-of-00082.safetensors", + "model.layers.69.post_attention_layernorm.weight": "model-00071-of-00082.safetensors", + "model.layers.69.self_attn.k_proj.bias": "model-00070-of-00082.safetensors", + "model.layers.69.self_attn.k_proj.weight": "model-00070-of-00082.safetensors", + "model.layers.69.self_attn.o_proj.weight": "model-00070-of-00082.safetensors", + "model.layers.69.self_attn.q_proj.bias": "model-00070-of-00082.safetensors", + "model.layers.69.self_attn.q_proj.weight": "model-00070-of-00082.safetensors", + "model.layers.69.self_attn.v_proj.bias": "model-00070-of-00082.safetensors", + "model.layers.69.self_attn.v_proj.weight": "model-00070-of-00082.safetensors", + "model.layers.7.input_layernorm.weight": "model-00009-of-00082.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00009-of-00082.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00009-of-00082.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00009-of-00082.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00009-of-00082.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00008-of-00082.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00008-of-00082.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00082.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00008-of-00082.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00008-of-00082.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00008-of-00082.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00008-of-00082.safetensors", + "model.layers.70.input_layernorm.weight": "model-00072-of-00082.safetensors", + "model.layers.70.mlp.down_proj.weight": "model-00072-of-00082.safetensors", + "model.layers.70.mlp.gate_proj.weight": "model-00072-of-00082.safetensors", + "model.layers.70.mlp.up_proj.weight": "model-00072-of-00082.safetensors", + "model.layers.70.post_attention_layernorm.weight": "model-00072-of-00082.safetensors", + "model.layers.70.self_attn.k_proj.bias": "model-00071-of-00082.safetensors", + "model.layers.70.self_attn.k_proj.weight": "model-00071-of-00082.safetensors", + "model.layers.70.self_attn.o_proj.weight": "model-00071-of-00082.safetensors", + "model.layers.70.self_attn.q_proj.bias": "model-00071-of-00082.safetensors", + "model.layers.70.self_attn.q_proj.weight": "model-00071-of-00082.safetensors", + "model.layers.70.self_attn.v_proj.bias": "model-00071-of-00082.safetensors", + "model.layers.70.self_attn.v_proj.weight": "model-00071-of-00082.safetensors", + "model.layers.71.input_layernorm.weight": "model-00073-of-00082.safetensors", + "model.layers.71.mlp.down_proj.weight": "model-00073-of-00082.safetensors", + "model.layers.71.mlp.gate_proj.weight": "model-00073-of-00082.safetensors", + "model.layers.71.mlp.up_proj.weight": "model-00073-of-00082.safetensors", + "model.layers.71.post_attention_layernorm.weight": "model-00073-of-00082.safetensors", + "model.layers.71.self_attn.k_proj.bias": "model-00072-of-00082.safetensors", + "model.layers.71.self_attn.k_proj.weight": "model-00072-of-00082.safetensors", + "model.layers.71.self_attn.o_proj.weight": "model-00072-of-00082.safetensors", + "model.layers.71.self_attn.q_proj.bias": "model-00072-of-00082.safetensors", + "model.layers.71.self_attn.q_proj.weight": "model-00072-of-00082.safetensors", + "model.layers.71.self_attn.v_proj.bias": "model-00072-of-00082.safetensors", + "model.layers.71.self_attn.v_proj.weight": "model-00072-of-00082.safetensors", + "model.layers.72.input_layernorm.weight": "model-00074-of-00082.safetensors", + "model.layers.72.mlp.down_proj.weight": "model-00074-of-00082.safetensors", + "model.layers.72.mlp.gate_proj.weight": "model-00074-of-00082.safetensors", + "model.layers.72.mlp.up_proj.weight": "model-00074-of-00082.safetensors", + "model.layers.72.post_attention_layernorm.weight": "model-00074-of-00082.safetensors", + "model.layers.72.self_attn.k_proj.bias": "model-00073-of-00082.safetensors", + "model.layers.72.self_attn.k_proj.weight": "model-00073-of-00082.safetensors", + "model.layers.72.self_attn.o_proj.weight": "model-00073-of-00082.safetensors", + "model.layers.72.self_attn.q_proj.bias": "model-00073-of-00082.safetensors", + "model.layers.72.self_attn.q_proj.weight": "model-00073-of-00082.safetensors", + "model.layers.72.self_attn.v_proj.bias": "model-00073-of-00082.safetensors", + "model.layers.72.self_attn.v_proj.weight": "model-00073-of-00082.safetensors", + "model.layers.73.input_layernorm.weight": "model-00075-of-00082.safetensors", + "model.layers.73.mlp.down_proj.weight": "model-00075-of-00082.safetensors", + "model.layers.73.mlp.gate_proj.weight": "model-00075-of-00082.safetensors", + "model.layers.73.mlp.up_proj.weight": "model-00075-of-00082.safetensors", + "model.layers.73.post_attention_layernorm.weight": "model-00075-of-00082.safetensors", + "model.layers.73.self_attn.k_proj.bias": "model-00074-of-00082.safetensors", + "model.layers.73.self_attn.k_proj.weight": "model-00074-of-00082.safetensors", + "model.layers.73.self_attn.o_proj.weight": "model-00074-of-00082.safetensors", + "model.layers.73.self_attn.q_proj.bias": "model-00074-of-00082.safetensors", + "model.layers.73.self_attn.q_proj.weight": "model-00074-of-00082.safetensors", + "model.layers.73.self_attn.v_proj.bias": "model-00074-of-00082.safetensors", + "model.layers.73.self_attn.v_proj.weight": "model-00074-of-00082.safetensors", + "model.layers.74.input_layernorm.weight": "model-00076-of-00082.safetensors", + "model.layers.74.mlp.down_proj.weight": "model-00076-of-00082.safetensors", + "model.layers.74.mlp.gate_proj.weight": "model-00076-of-00082.safetensors", + "model.layers.74.mlp.up_proj.weight": "model-00076-of-00082.safetensors", + "model.layers.74.post_attention_layernorm.weight": "model-00076-of-00082.safetensors", + "model.layers.74.self_attn.k_proj.bias": "model-00075-of-00082.safetensors", + "model.layers.74.self_attn.k_proj.weight": "model-00075-of-00082.safetensors", + "model.layers.74.self_attn.o_proj.weight": "model-00075-of-00082.safetensors", + "model.layers.74.self_attn.q_proj.bias": "model-00075-of-00082.safetensors", + "model.layers.74.self_attn.q_proj.weight": "model-00075-of-00082.safetensors", + "model.layers.74.self_attn.v_proj.bias": "model-00075-of-00082.safetensors", + "model.layers.74.self_attn.v_proj.weight": "model-00075-of-00082.safetensors", + "model.layers.75.input_layernorm.weight": "model-00077-of-00082.safetensors", + "model.layers.75.mlp.down_proj.weight": "model-00077-of-00082.safetensors", + "model.layers.75.mlp.gate_proj.weight": "model-00077-of-00082.safetensors", + "model.layers.75.mlp.up_proj.weight": "model-00077-of-00082.safetensors", + "model.layers.75.post_attention_layernorm.weight": "model-00077-of-00082.safetensors", + "model.layers.75.self_attn.k_proj.bias": "model-00076-of-00082.safetensors", + "model.layers.75.self_attn.k_proj.weight": "model-00076-of-00082.safetensors", + "model.layers.75.self_attn.o_proj.weight": "model-00076-of-00082.safetensors", + "model.layers.75.self_attn.q_proj.bias": "model-00076-of-00082.safetensors", + "model.layers.75.self_attn.q_proj.weight": "model-00076-of-00082.safetensors", + "model.layers.75.self_attn.v_proj.bias": "model-00076-of-00082.safetensors", + "model.layers.75.self_attn.v_proj.weight": "model-00076-of-00082.safetensors", + "model.layers.76.input_layernorm.weight": "model-00078-of-00082.safetensors", + "model.layers.76.mlp.down_proj.weight": "model-00078-of-00082.safetensors", + "model.layers.76.mlp.gate_proj.weight": "model-00078-of-00082.safetensors", + "model.layers.76.mlp.up_proj.weight": "model-00078-of-00082.safetensors", + "model.layers.76.post_attention_layernorm.weight": "model-00078-of-00082.safetensors", + "model.layers.76.self_attn.k_proj.bias": "model-00077-of-00082.safetensors", + "model.layers.76.self_attn.k_proj.weight": "model-00077-of-00082.safetensors", + "model.layers.76.self_attn.o_proj.weight": "model-00077-of-00082.safetensors", + "model.layers.76.self_attn.q_proj.bias": "model-00077-of-00082.safetensors", + "model.layers.76.self_attn.q_proj.weight": "model-00077-of-00082.safetensors", + "model.layers.76.self_attn.v_proj.bias": "model-00077-of-00082.safetensors", + "model.layers.76.self_attn.v_proj.weight": "model-00077-of-00082.safetensors", + "model.layers.77.input_layernorm.weight": "model-00079-of-00082.safetensors", + "model.layers.77.mlp.down_proj.weight": "model-00079-of-00082.safetensors", + "model.layers.77.mlp.gate_proj.weight": "model-00079-of-00082.safetensors", + "model.layers.77.mlp.up_proj.weight": "model-00079-of-00082.safetensors", + "model.layers.77.post_attention_layernorm.weight": "model-00079-of-00082.safetensors", + "model.layers.77.self_attn.k_proj.bias": "model-00078-of-00082.safetensors", + "model.layers.77.self_attn.k_proj.weight": "model-00078-of-00082.safetensors", + "model.layers.77.self_attn.o_proj.weight": "model-00078-of-00082.safetensors", + "model.layers.77.self_attn.q_proj.bias": "model-00078-of-00082.safetensors", + "model.layers.77.self_attn.q_proj.weight": "model-00078-of-00082.safetensors", + "model.layers.77.self_attn.v_proj.bias": "model-00078-of-00082.safetensors", + "model.layers.77.self_attn.v_proj.weight": "model-00078-of-00082.safetensors", + "model.layers.78.input_layernorm.weight": "model-00080-of-00082.safetensors", + "model.layers.78.mlp.down_proj.weight": "model-00080-of-00082.safetensors", + "model.layers.78.mlp.gate_proj.weight": "model-00080-of-00082.safetensors", + "model.layers.78.mlp.up_proj.weight": "model-00080-of-00082.safetensors", + "model.layers.78.post_attention_layernorm.weight": "model-00080-of-00082.safetensors", + "model.layers.78.self_attn.k_proj.bias": "model-00079-of-00082.safetensors", + "model.layers.78.self_attn.k_proj.weight": "model-00079-of-00082.safetensors", + "model.layers.78.self_attn.o_proj.weight": "model-00079-of-00082.safetensors", + "model.layers.78.self_attn.q_proj.bias": "model-00079-of-00082.safetensors", + "model.layers.78.self_attn.q_proj.weight": "model-00079-of-00082.safetensors", + "model.layers.78.self_attn.v_proj.bias": "model-00079-of-00082.safetensors", + "model.layers.78.self_attn.v_proj.weight": "model-00079-of-00082.safetensors", + "model.layers.79.input_layernorm.weight": "model-00082-of-00082.safetensors", + "model.layers.79.mlp.down_proj.weight": "model-00082-of-00082.safetensors", + "model.layers.79.mlp.gate_proj.weight": "model-00082-of-00082.safetensors", + "model.layers.79.mlp.up_proj.weight": "model-00082-of-00082.safetensors", + "model.layers.79.post_attention_layernorm.weight": "model-00082-of-00082.safetensors", + "model.layers.79.self_attn.k_proj.bias": "model-00080-of-00082.safetensors", + "model.layers.79.self_attn.k_proj.weight": "model-00080-of-00082.safetensors", + "model.layers.79.self_attn.o_proj.weight": "model-00080-of-00082.safetensors", + "model.layers.79.self_attn.q_proj.bias": "model-00080-of-00082.safetensors", + "model.layers.79.self_attn.q_proj.weight": "model-00080-of-00082.safetensors", + "model.layers.79.self_attn.v_proj.bias": "model-00080-of-00082.safetensors", + "model.layers.79.self_attn.v_proj.weight": "model-00080-of-00082.safetensors", + "model.layers.8.input_layernorm.weight": "model-00010-of-00082.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00010-of-00082.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00010-of-00082.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00010-of-00082.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00010-of-00082.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00009-of-00082.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00009-of-00082.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00082.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00009-of-00082.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00082.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00009-of-00082.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00082.safetensors", + "model.layers.9.input_layernorm.weight": "model-00011-of-00082.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00011-of-00082.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00011-of-00082.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00011-of-00082.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00011-of-00082.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00010-of-00082.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00010-of-00082.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00082.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00010-of-00082.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00082.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00010-of-00082.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00082.safetensors", + "model.norm.weight": "model-00082-of-00082.safetensors" + } +}