diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..bc5f30d6632ac0efdc7be2e9095e9e9579af2e33 --- /dev/null +++ b/README.md @@ -0,0 +1,199 @@ +--- +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 diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..a223126f28e0b96e1dc939cc6369136a9bf31a33 --- /dev/null +++ b/config.json @@ -0,0 +1,34 @@ +{ + "_name_or_path": "/raid/pablo/molmo72B", + "architectures": [ + "MolmoForConditionalGeneration" + ], + "image_seq_length": 576, + "image_token_index": 152069, + "initializer_range": 0.02, + "model_type": "molmo", + "pooling_config": { + "model_type": "", + "text_hidden_size": 8192, + "text_intermediate_size": 59136 + }, + "text_config": { + "hidden_size": 8192, + "intermediate_size": 59136, + "layer_norm_eps": 1e-05, + "model_type": "molmo", + "num_attention_heads": 64, + "num_hidden_layers": 80, + "num_key_value_heads": 8 + }, + "torch_dtype": "float32", + "transformers_version": "4.47.0.dev0", + "vision_config": { + "model_type": "molmo_vision_model" + }, + "vision_feature_layers": [ + -2, + -9 + ], + "vision_feature_select_strategy": "default" +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..5578fb8ad934aa42c62d6af0fdd33ea4ce422be2 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,4 @@ +{ + "_from_model_config": true, + "transformers_version": "4.47.0.dev0" +} diff --git a/model-00001-of-00084.safetensors b/model-00001-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b673ff0009c6732ae00e015a20edc220614168c9 --- /dev/null +++ b/model-00001-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15d85a859cc8ec86d0cef81660b90f1e1f899d326c823e74b6cc2d58bdb78c19 +size 1163687168 diff --git a/model-00002-of-00084.safetensors b/model-00002-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a01439f7887a0bc7b945f5ad3f1e3fa8cb343807 --- /dev/null +++ b/model-00002-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8de538f89ef02f78c6287a5bc283b8f96476b53f7370e69f0ca5d71474ebfcb1 +size 4987027608 diff --git a/model-00003-of-00084.safetensors b/model-00003-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..53184f12af98363fa5c9326b9d58bd93d6559c18 --- /dev/null +++ b/model-00003-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a37a24efc1dccd4e32ff773a25ef8c43319383f291c2a0a5729fd1abcb12dd94 +size 4114762000 diff --git a/model-00004-of-00084.safetensors b/model-00004-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..309745de96fda3e1d5842e21a360d317ba685452 --- /dev/null +++ b/model-00004-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c20927ab5e7602ec59f2485840b26795f78fc63d13078efd73ef27b177bed6f +size 3510740368 diff --git a/model-00005-of-00084.safetensors b/model-00005-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..87bc1c2b09a0d7162f65a84be3165ae25291b01a --- /dev/null +++ b/model-00005-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd550801aaa46f726e9c826820868a0fd8b9cb3542eff87a9cf8c20a61349ddf +size 3510740368 diff --git a/model-00006-of-00084.safetensors b/model-00006-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8e8fb491a28acb643b686c69f53b83f2aeffd847 --- /dev/null +++ b/model-00006-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d95ffcafd2903e13d26c22d87053ce1300c82e1b41762810a422df6f446158e +size 3510740368 diff --git a/model-00007-of-00084.safetensors b/model-00007-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f58812d89f6a119cd54bc9093e92a2d4531000ae --- /dev/null +++ b/model-00007-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:941b417e55c2d4a9c96c9e2b73df17b6edd5333c5d12c1120213a89283362638 +size 3510740368 diff --git a/model-00008-of-00084.safetensors b/model-00008-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a7044cdee8a3318ed68949d5a7c43141c8ca888c --- /dev/null +++ b/model-00008-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f5b3e00a4c17a0f310a3adda0f7ecdd504ec9c47b4ee2f511144cae81387d3f +size 3510740368 diff --git a/model-00009-of-00084.safetensors b/model-00009-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fb2427b4b65dbf7aa97799da7d0ce1fbaa06e28f --- /dev/null +++ b/model-00009-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:899fe33ee9db14d822a84661e3c4e0391a53003d4ce46b7b9b967afe9daa5af6 +size 3510740368 diff --git a/model-00010-of-00084.safetensors b/model-00010-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..caadb450784b741e435940212e54e0d85356d945 --- /dev/null +++ b/model-00010-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d12ecb7c2d87d13d06eefa33ab6d89bd87ad6c59a6d77c8f86b406c83901bc3 +size 3510740368 diff --git a/model-00011-of-00084.safetensors b/model-00011-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5e8439cfaac8095d897488af6b6a69cddc0b46c6 --- /dev/null +++ b/model-00011-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe5efd25fc6a9394c2b2a47c8bc50cc6f95ab67809187d653fe28af3187a2fdc +size 3510740368 diff --git a/model-00012-of-00084.safetensors b/model-00012-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..68ea3776b793b741537f1e9d0ad6a6233884539d --- /dev/null +++ b/model-00012-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c43c6d9c80e9206efec0c4eaae7e0c368efb329d5818b1ceb92abd73889a46f +size 3510740360 diff --git a/model-00013-of-00084.safetensors b/model-00013-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..641c43502476acbbcf099c9d165ae0c6b948dcd1 --- /dev/null +++ b/model-00013-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55413326badb2b7c65e74532e91a4c189ba3d797cf0a961a7e1d2505b90c2cca +size 3510740384 diff --git a/model-00014-of-00084.safetensors b/model-00014-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1c4380f4cb6c8a0f827663b523d9c3ee4eba0e1d --- /dev/null +++ b/model-00014-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bbaef8574dfb1cc50e888b03e6a16152e69162683f120c0c01a566bba32c4f5 +size 3510740384 diff --git a/model-00015-of-00084.safetensors b/model-00015-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6d47d2269d434209a87ae038f5460a0a9f9344e8 --- /dev/null +++ b/model-00015-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41143c68347c74778afe129151a38e5492d2c5f3ed5bb315bebd6275c7f4addf +size 3510740384 diff --git a/model-00016-of-00084.safetensors b/model-00016-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7f033884d8501407d8c7be0c21658a829a2ff33c --- /dev/null +++ b/model-00016-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bb88880b7f84acd5b67f03d64a1da005fa1872e2d9a66f68c838ed825124ea4 +size 3510740384 diff --git a/model-00017-of-00084.safetensors b/model-00017-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7c784db962d6e8f2540d6cac11c5fb2cebabeea1 --- /dev/null +++ b/model-00017-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a38123eb3417ea3e57c0fc390e5214523c4b93c0333543dd8aff2ff97fa878a2 +size 3510740384 diff --git a/model-00018-of-00084.safetensors b/model-00018-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e399df132a271c179c8ad9dceb2ec4cc40b08f72 --- /dev/null +++ b/model-00018-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5728221d4d8e67161bfa9063079156d4c2b5e58096603f8d8de4028edce1057a +size 3510740384 diff --git a/model-00019-of-00084.safetensors b/model-00019-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3c22d660e7713aa2ea23f13b4f072c1c860be168 --- /dev/null +++ b/model-00019-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99771671a4bb66c8c6237588767af74cfc013e96cac12709d72e9735ecaa2182 +size 3510740384 diff --git a/model-00020-of-00084.safetensors b/model-00020-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..14495a2217a57059c42446174686cc4eda94e773 --- /dev/null +++ b/model-00020-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d86ec52c3f444d9d6b0d29f19ddb6aba7f7e6c0d818a86dc325ca6ea7a28f357 +size 3510740384 diff --git a/model-00021-of-00084.safetensors b/model-00021-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b0ba2dac4f30d73a5cf85459b9539d62c0ad159a --- /dev/null +++ b/model-00021-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7400968e98dcf66f21bc9287367fb3c9cc4c7922388c23cedca76bceefa9aff +size 3510740384 diff --git a/model-00022-of-00084.safetensors b/model-00022-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..84560a0e9e4dff4fa6283890eddccf7c081c90a3 --- /dev/null +++ b/model-00022-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee2a89cb3cc0523ed475fda1ac678fa69fd7a9505cf3d25f21c6ae625bf3d183 +size 3510740384 diff --git a/model-00023-of-00084.safetensors b/model-00023-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..68e114f79b2e78374cd5b86ed5f8680a5b205051 --- /dev/null +++ b/model-00023-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9db48c13f6241be1336b1bccfa4f4b1f4b6a5c7508de9a79fd7c1455a88efab +size 3510740384 diff --git a/model-00024-of-00084.safetensors b/model-00024-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..58fc9a21d4efe8a6020d30cdcae3eea4833d6357 --- /dev/null +++ b/model-00024-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e80ad1ecb4ad41aecaf95edc464f646946294da3c491b6db2c8a405111e7e172 +size 3510740384 diff --git a/model-00025-of-00084.safetensors b/model-00025-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..076c652720834aa1643bdf3d34bf4e650a7d54ca --- /dev/null +++ b/model-00025-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c68ae89d303bc5bbefd9bc1e598c0d374d65db3786e26b932f802a3a394c1b7a +size 3510740384 diff --git a/model-00026-of-00084.safetensors b/model-00026-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3f49f2a31af26cdc5e23488fd214e458ec7d5d68 --- /dev/null +++ b/model-00026-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:333de6b796a5c87e4fd69b8323f7c5be101dc5bb0e25d367ebf1f19ba1b82136 +size 3510740384 diff --git a/model-00027-of-00084.safetensors b/model-00027-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bcbc11255d827f3188040ee8d4ee1aa09fb0501e --- /dev/null +++ b/model-00027-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5adc57612d9cbfe839d0bdee28d62088025f8d8e0ee0d624e38a88af66056e91 +size 3510740384 diff --git a/model-00028-of-00084.safetensors b/model-00028-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8b02c368e25dd8b8f3bed143ff568e4ea5436e7e --- /dev/null +++ b/model-00028-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4e24145b843e912e5f65c2bab413c1ae205ad87d3626780e86ded6fa4650744 +size 3510740384 diff --git a/model-00029-of-00084.safetensors b/model-00029-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9c3a8e0d73a779e443322276ded593659c51af4c --- /dev/null +++ b/model-00029-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab0efc825c23a6e7c09c575e3957662f20e9e6f9dc6331d6fa77f0d0047bc07b +size 3510740384 diff --git a/model-00030-of-00084.safetensors b/model-00030-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cc0e5c63d194f8b67b96f7cd6745db5a33563efa --- /dev/null +++ b/model-00030-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cef64807a25b28793a22b4bdeb3661332ef3436be0a13f923bd1faa50757676 +size 3510740384 diff --git a/model-00031-of-00084.safetensors b/model-00031-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0523ba85560dec8404e70d1bde63ceb506fc17af --- /dev/null +++ b/model-00031-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e033bccc1eb7d129c0a66ab60b3cab6488db7ebbd4b27c6eb35689964db1e92c +size 3510740384 diff --git a/model-00032-of-00084.safetensors b/model-00032-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..24036ab8475628e0b42bde34c7c6e8e8f0ac60d3 --- /dev/null +++ b/model-00032-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b5f176fd91450b3b3d016d535b6127ad4ffce5e2dbd2fd70b257aac4d358b86 +size 3510740384 diff --git a/model-00033-of-00084.safetensors b/model-00033-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f01d7bd9590b3586411297d6ba724d864e50b275 --- /dev/null +++ b/model-00033-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a856a74817db4816dea61dcbd1671fb4466ae02cf4466e7571fabb745a6fa2ab +size 3510740384 diff --git a/model-00034-of-00084.safetensors b/model-00034-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b90437cc1105f424bd4fb7f7461af7b3ceb5f9d5 --- /dev/null +++ b/model-00034-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc6c462dc81ee1fb0b42f918f074a2cdaf39d8083dbc20420bc01ca740331e46 +size 3510740384 diff --git a/model-00035-of-00084.safetensors b/model-00035-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..314fda672b4701f69f876172c363338c9fa0d350 --- /dev/null +++ b/model-00035-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd64be96faa5002243af2098b076374b07808bb6e941771d2878b79d354df816 +size 3510740384 diff --git a/model-00036-of-00084.safetensors b/model-00036-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a258d61faba9429e0dbdea6b95a0dcbc4d1110d6 --- /dev/null +++ b/model-00036-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:771ac5da834965005394d00f6cf59e475c9530375c2ca675a51b1984be376427 +size 3510740384 diff --git a/model-00037-of-00084.safetensors b/model-00037-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cb533b8c5b570b48f898cd53fbb712c8e81b283f --- /dev/null +++ b/model-00037-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f80c1a2b9e0a7f4759758e7e5e6380dfe17b2321c053d5b9bc089bfd8122c1f0 +size 3510740384 diff --git a/model-00038-of-00084.safetensors b/model-00038-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..273b83d0b36114c86c01fb2064a9a00ccc626fbd --- /dev/null +++ b/model-00038-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03894dcfbd96d2e782455b0142203251b5ba9d03a5e885fd1a62aaa4da6b90af +size 3510740384 diff --git a/model-00039-of-00084.safetensors b/model-00039-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..35fcfa918cf13ea11237180e0eaa365972bb8c5a --- /dev/null +++ b/model-00039-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf381c60e903e4e972e64740e9f4a6906fb7146f71293e14f98bd3aa46ac79d2 +size 3510740384 diff --git a/model-00040-of-00084.safetensors b/model-00040-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6b8c732bde61ff128419edd0ba8cfbabaecf389b --- /dev/null +++ b/model-00040-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91530b0b32833591d9b9b687cd41e931d7e887e03eadd22c6fafb15a33a14a1d +size 3510740384 diff --git a/model-00041-of-00084.safetensors b/model-00041-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..46020bca784e3e6eb838e10df84eff191846c0ef --- /dev/null +++ b/model-00041-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88d615c4730f8d31620950bddcafeabb0ef727db73c6730b3b961f6728a8325d +size 3510740384 diff --git a/model-00042-of-00084.safetensors b/model-00042-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d1f71c728b1c2b8e10a1920fbb6fdee972eb98ac --- /dev/null +++ b/model-00042-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:671d28f3cd145014edd4ffe329798f72c1a63e06913eab98a5fed6d0eff4ed83 +size 3510740384 diff --git a/model-00043-of-00084.safetensors b/model-00043-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5d600d027ef7648df085da7f39f323d3221ec6f8 --- /dev/null +++ b/model-00043-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:491f092bc479c6af81cf25dcf37dbf19d7541319d326b952d393f88425d7f7e9 +size 3510740384 diff --git a/model-00044-of-00084.safetensors b/model-00044-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4a383cf22ac01b21644cbb15b2e9de99540d1388 --- /dev/null +++ b/model-00044-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:412f68581e9c060dd1f9de4b3203ac25c9d7430ad8f2f03dbd9a17b2aa1c70d1 +size 3510740384 diff --git a/model-00045-of-00084.safetensors b/model-00045-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5c89f3d33cc7d35968c01e0e12664bdd210522a0 --- /dev/null +++ b/model-00045-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e02531f7de3fbdce8929b45e37b3c83c0b436b3f7cec806b64138f7bbef1268 +size 3510740384 diff --git a/model-00046-of-00084.safetensors b/model-00046-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..08205053c419697e60c0d87044f47fa64f2bd153 --- /dev/null +++ b/model-00046-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d6396efbda13ae06f560569a3d58ae5dcc748fc4324667e91d3df9948b9b4ce +size 3510740384 diff --git a/model-00047-of-00084.safetensors b/model-00047-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8f7445c4ff8834b2f837344d11a213d672d0dafb --- /dev/null +++ b/model-00047-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:051a99f9ea80b29e85f0633b3482f2cd058abfeaea2b5c38f47515dd248082b0 +size 3510740384 diff --git a/model-00048-of-00084.safetensors b/model-00048-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9209914abbc39dd18e683f4abeca8e50c928f98a --- /dev/null +++ b/model-00048-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea745bd1cc2a9fd197c3d2af83505471bcf2a6088d764ab6fce40074050e6996 +size 3510740384 diff --git a/model-00049-of-00084.safetensors b/model-00049-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..203f07ed94eb36c69909c387506702059282c2e2 --- /dev/null +++ b/model-00049-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c88b84e41274d593a5201b381c3c7ba36baed956b2775f3408a31ecf6d6c7636 +size 3510740384 diff --git a/model-00050-of-00084.safetensors b/model-00050-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3a5aef49eedbd8c48bbf17edd822fc10ad938f2e --- /dev/null +++ b/model-00050-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:022fae0a1f14da6318d5f1fa43f09e309dd7ed705503fa75f7803f8f5823e801 +size 3510740384 diff --git a/model-00051-of-00084.safetensors b/model-00051-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..05541c1b0fd3368d0b495b77d7be3318dbf5ee8f --- /dev/null +++ b/model-00051-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fc413f6076d6554b343ac6c211f1140140a617c051018ab88b9bc7aa5c6fa92 +size 3510740384 diff --git a/model-00052-of-00084.safetensors b/model-00052-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3fd2e50b730316d4496a0a4a241b0f10b6c8f7b4 --- /dev/null +++ b/model-00052-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:580f9bc0b1bbf8e6158a10da1f92ccca2180a504c550abad6a5403a14e59cd01 +size 3510740384 diff --git a/model-00053-of-00084.safetensors b/model-00053-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e2004c2e3a4cbc19a8a86f19be3bd8345728422b --- /dev/null +++ b/model-00053-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbcb86da1401bab3683975f92a84010cb011818aba30c66af7f17ca66d23f196 +size 3510740384 diff --git a/model-00054-of-00084.safetensors b/model-00054-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..95f9753696247194481d72512f3da851e15690c2 --- /dev/null +++ b/model-00054-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7b4d89664275c5a1c0b0da136be756929043fb411d00ab3e6a18379bf5a785c +size 3510740384 diff --git a/model-00055-of-00084.safetensors b/model-00055-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d30b4ba022471100b6549f5d56e236649905a83e --- /dev/null +++ b/model-00055-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db1c98ab105aa893f815267832b440498db7dac3844b5e0a4decea0be8512246 +size 3510740384 diff --git a/model-00056-of-00084.safetensors b/model-00056-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b8041cbdd93e17754fb9ba3cecd6d2272a1179a5 --- /dev/null +++ b/model-00056-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95f5a7855ddaab005418bb501c1ef55247e9176e3fb3166e025638eb9b6f26da +size 3510740384 diff --git a/model-00057-of-00084.safetensors b/model-00057-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c84b91034b02c2070128c2b52cd1246e4964d15e --- /dev/null +++ b/model-00057-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6bcd7f9fcd3e8e6674dbc3a28307325411d1bd0cf015720a64232cb0d1d73af +size 3510740384 diff --git a/model-00058-of-00084.safetensors b/model-00058-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1e01a7e31fb25a8296b3f8c836560bf05f7a939f --- /dev/null +++ b/model-00058-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de4792010bcb9b8c5b353bb3032bb56c9089c6e7c160f9e3421a565020ad7efc +size 3510740384 diff --git a/model-00059-of-00084.safetensors b/model-00059-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..628a84bd5d44320a72b355c301ddbe535bf57b78 --- /dev/null +++ b/model-00059-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5989a5022981afadec9fa6fcdf685c052f7f0dd94e586d33096b26e85f30cd8e +size 3510740384 diff --git a/model-00060-of-00084.safetensors b/model-00060-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..76907906c1be3d5a2d62f990f6b0c643b763cdd0 --- /dev/null +++ b/model-00060-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:701d1ee789c270f6888266c26c24be62d6e0f27d1e5133158f3eff38f5ecea3c +size 3510740384 diff --git a/model-00061-of-00084.safetensors b/model-00061-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2e6204a9945f2ca2a782329de7215719ebdfb333 --- /dev/null +++ b/model-00061-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32d0bf18bbdc48bc8453fba7d1e8590e3016631b7c4f96e3e4e5d3a47a693502 +size 3510740384 diff --git a/model-00062-of-00084.safetensors b/model-00062-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3956f3eef4da600968f186173e50d27184e8bf84 --- /dev/null +++ b/model-00062-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f871460cebad2d89105d95efc906674ec55beadee8aa877bf24d8f87b0bb9ceb +size 3510740384 diff --git a/model-00063-of-00084.safetensors b/model-00063-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..99a1ed2edacbef373de189063d7696eaf30038a1 --- /dev/null +++ b/model-00063-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38c78b2fdd3317a1d5f3f5c2bc4387c1f0e6c89ece28be5a35114e3d06dafc4f +size 3510740384 diff --git a/model-00064-of-00084.safetensors b/model-00064-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8afa9a3c99a9d04eafff7670cda1610159fb2539 --- /dev/null +++ b/model-00064-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbac191d3bbc7c95a0b2958e55b88e95499af7a7b7854466cd33966b6ac1e86a +size 3510740384 diff --git a/model-00065-of-00084.safetensors b/model-00065-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6fbd4edeaca41e3b9e5b85633a92f9cc7d6455f0 --- /dev/null +++ b/model-00065-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5109d7aab97511711875143546c4c6024903ee4351bdef24f903dfbaefda6d3a +size 3510740384 diff --git a/model-00066-of-00084.safetensors b/model-00066-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3b27285416d9e98333cfa87be249db44fa17a29a --- /dev/null +++ b/model-00066-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad47351f964a6007f5deb01286e9432ab2b6116aa6fbef0638173c6c76d64a48 +size 3510740384 diff --git a/model-00067-of-00084.safetensors b/model-00067-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..994fd567deadb98d261ea6805c605e74fb2b599e --- /dev/null +++ b/model-00067-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2046750bebe0670882338a2cb7286a5ce2a29b30ae35e5ab59a3ede1130e504 +size 3510740384 diff --git a/model-00068-of-00084.safetensors b/model-00068-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b778da4ea2d762d50d9a003e0ec505c688de90f3 --- /dev/null +++ b/model-00068-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b16979394c19e272784adedede6ee661513414add6d12b402a23765c99b20d1c +size 3510740384 diff --git a/model-00069-of-00084.safetensors b/model-00069-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ab26cabcc57c2f62acfe940a70fd2ffeac37bc68 --- /dev/null +++ b/model-00069-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:572d599466a278e0eef90ac6394b3fd9923a295a1ccd6073e6f280ed11892c92 +size 3510740384 diff --git a/model-00070-of-00084.safetensors b/model-00070-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b288c23e2b0fe4b1f519ebc7d7def9bb0a36e7a7 --- /dev/null +++ b/model-00070-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ec51458d9560224c1ea68437eb084ed5213c408af41a22da51ef070294763ae +size 3510740384 diff --git a/model-00071-of-00084.safetensors b/model-00071-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..72ca962a7570ad4ff1714672ae076a0ed6c796b6 --- /dev/null +++ b/model-00071-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71d16da57b741a96a849a15aa4fcb9d0cd7c8b19e4351aade2ccbe5cea1cf437 +size 3510740384 diff --git a/model-00072-of-00084.safetensors b/model-00072-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e62461bdd2b0a1c48e7307d57828cc7c29ba3cd2 --- /dev/null +++ b/model-00072-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d104e556d76f24b545c35e42fd83d7f69514630d63cab853e21faa4d6053d154 +size 3510740384 diff --git a/model-00073-of-00084.safetensors b/model-00073-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ed22dbbf4de9ed87f426e9221e63fd4b18a9499e --- /dev/null +++ b/model-00073-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a31dacfe92c84caa1e8200bc8950dbf899e412958159f5a26b55b0ea5c9ef284 +size 3510740384 diff --git a/model-00074-of-00084.safetensors b/model-00074-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..425e1f6d40c56edc66efe2a3b7595ed6aab6960c --- /dev/null +++ b/model-00074-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ecb31a08cbf49e73606727488b3a0038c76377b7e1a9bea9ec5aed997caef04 +size 3510740384 diff --git a/model-00075-of-00084.safetensors b/model-00075-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..59022f8a76a47dec12df0ac7ae98a2d0a2fedd27 --- /dev/null +++ b/model-00075-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c480b6d3518f989753a6825780c11c7d4897247a4c83e6d836b3f49fbde79394 +size 3510740384 diff --git a/model-00076-of-00084.safetensors b/model-00076-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6cc0d64b4e3f3c95a301327bbb3dad9fe94fe981 --- /dev/null +++ b/model-00076-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90f12fa548a1b7172e1dd7cd57e73a909daaf196cd11886f27324d7785ad2931 +size 3510740384 diff --git a/model-00077-of-00084.safetensors b/model-00077-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c1855f69651334209495429e900cf6fa7a70973c --- /dev/null +++ b/model-00077-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a173403dd613c87b5b330149e8f351eaae86261a9ecba36970d2e048c4fb1461 +size 3510740384 diff --git a/model-00078-of-00084.safetensors b/model-00078-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1b9073430e46c538877b854869709dd6b9ecaa46 --- /dev/null +++ b/model-00078-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16c180910fa7bf5c6dc5b01cac7eb4da869806405e4b9535b0cac51d1b368f3f +size 3510740384 diff --git a/model-00079-of-00084.safetensors b/model-00079-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1b0d8a59fff5358c227b4cc5c7a99f8cf0899bbb --- /dev/null +++ b/model-00079-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a8169539199c2d4c1a0b1124027f7561b88c1bbf305fab5e30dc8cc96ac0a11 +size 3510740384 diff --git a/model-00080-of-00084.safetensors b/model-00080-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a7f18924a4844930fba91328f0beed412cd2c9ae --- /dev/null +++ b/model-00080-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8d683cbbae6d1e3e96cadd47cce07154d71b606ee5535149182a419a175def7 +size 3510740384 diff --git a/model-00081-of-00084.safetensors b/model-00081-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b0dbfd5b9ba159dad8751928a7e7a9109bf90e38 --- /dev/null +++ b/model-00081-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:297108c47e896497b8a9753bb4b756a1c7c8a749b6c966370cb069f4a66f5f36 +size 3510740384 diff --git a/model-00082-of-00084.safetensors b/model-00082-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..615d09f17ff8eeb5bfbba70af01324055ce2172b --- /dev/null +++ b/model-00082-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b6cffb955ca26210959a5df4bdac02ceb54cbdbe4870d2c456e793cf5f41f39 +size 2906751616 diff --git a/model-00083-of-00084.safetensors b/model-00083-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f6d634d4377a9fcb90a6800260612102fc95db8b --- /dev/null +++ b/model-00083-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c9662df48f221504c3d0a959f0c732ae0322838f8e1278133e0b03b2e425e99 +size 4995436984 diff --git a/model-00084-of-00084.safetensors b/model-00084-of-00084.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0cc038038e22d16f01cea01836ed3d411ac5e03f --- /dev/null +++ b/model-00084-of-00084.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f10f818604873a9f8f7b48d006e38f43e903b99b1ed6ada827af87b21c3b1ab1 +size 1232090128 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..c6ea4c8fe49cb130a0c2210dfa23d40caa326f61 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,1275 @@ +{ + "metadata": { + "total_size": 293237338112 + }, + "weight_map": { + "adapter.image_pooling_2d.k_proj.bias": "model-00083-of-00084.safetensors", + "adapter.image_pooling_2d.k_proj.weight": "model-00083-of-00084.safetensors", + "adapter.image_pooling_2d.o_proj.bias": "model-00084-of-00084.safetensors", + "adapter.image_pooling_2d.o_proj.weight": "model-00084-of-00084.safetensors", + "adapter.image_pooling_2d.q_proj.bias": "model-00084-of-00084.safetensors", + "adapter.image_pooling_2d.q_proj.weight": "model-00084-of-00084.safetensors", + "adapter.image_pooling_2d.v_proj.bias": "model-00084-of-00084.safetensors", + "adapter.image_pooling_2d.v_proj.weight": "model-00084-of-00084.safetensors", + "adapter.multi_modal_projector.linear_1.weight": "model-00084-of-00084.safetensors", + "adapter.multi_modal_projector.linear_2.weight": "model-00084-of-00084.safetensors", + "adapter.multi_modal_projector.linear_3.weight": "model-00084-of-00084.safetensors", + "adapter.pad_embed": "model-00083-of-00084.safetensors", + "language_model.lm_head.weight": "model-00083-of-00084.safetensors", + "language_model.model.embed_tokens.weight": "model-00002-of-00084.safetensors", + "language_model.model.layers.0.input_layernorm.weight": "model-00003-of-00084.safetensors", + "language_model.model.layers.0.mlp.fc1.weight": "model-00003-of-00084.safetensors", + "language_model.model.layers.0.mlp.fc2.weight": "model-00003-of-00084.safetensors", + "language_model.model.layers.0.post_attention_layernorm.weight": "model-00003-of-00084.safetensors", + "language_model.model.layers.0.self_attn.k_proj.bias": "model-00003-of-00084.safetensors", + "language_model.model.layers.0.self_attn.k_proj.weight": "model-00003-of-00084.safetensors", + "language_model.model.layers.0.self_attn.o_proj.weight": "model-00003-of-00084.safetensors", + "language_model.model.layers.0.self_attn.q_proj.bias": "model-00003-of-00084.safetensors", + "language_model.model.layers.0.self_attn.q_proj.weight": "model-00003-of-00084.safetensors", + "language_model.model.layers.0.self_attn.v_proj.bias": "model-00003-of-00084.safetensors", + "language_model.model.layers.0.self_attn.v_proj.weight": "model-00003-of-00084.safetensors", + "language_model.model.layers.1.input_layernorm.weight": "model-00004-of-00084.safetensors", + "language_model.model.layers.1.mlp.fc1.weight": "model-00004-of-00084.safetensors", + "language_model.model.layers.1.mlp.fc2.weight": "model-00004-of-00084.safetensors", + "language_model.model.layers.1.post_attention_layernorm.weight": "model-00004-of-00084.safetensors", + "language_model.model.layers.1.self_attn.k_proj.bias": "model-00003-of-00084.safetensors", + "language_model.model.layers.1.self_attn.k_proj.weight": "model-00003-of-00084.safetensors", + "language_model.model.layers.1.self_attn.o_proj.weight": "model-00003-of-00084.safetensors", + "language_model.model.layers.1.self_attn.q_proj.bias": "model-00003-of-00084.safetensors", + "language_model.model.layers.1.self_attn.q_proj.weight": "model-00003-of-00084.safetensors", + "language_model.model.layers.1.self_attn.v_proj.bias": "model-00003-of-00084.safetensors", + "language_model.model.layers.1.self_attn.v_proj.weight": "model-00003-of-00084.safetensors", + "language_model.model.layers.10.input_layernorm.weight": "model-00013-of-00084.safetensors", + "language_model.model.layers.10.mlp.fc1.weight": "model-00013-of-00084.safetensors", + "language_model.model.layers.10.mlp.fc2.weight": "model-00013-of-00084.safetensors", + "language_model.model.layers.10.post_attention_layernorm.weight": "model-00013-of-00084.safetensors", + "language_model.model.layers.10.self_attn.k_proj.bias": "model-00012-of-00084.safetensors", + "language_model.model.layers.10.self_attn.k_proj.weight": "model-00012-of-00084.safetensors", + "language_model.model.layers.10.self_attn.o_proj.weight": "model-00012-of-00084.safetensors", + "language_model.model.layers.10.self_attn.q_proj.bias": "model-00012-of-00084.safetensors", + "language_model.model.layers.10.self_attn.q_proj.weight": "model-00012-of-00084.safetensors", + "language_model.model.layers.10.self_attn.v_proj.bias": "model-00012-of-00084.safetensors", + "language_model.model.layers.10.self_attn.v_proj.weight": "model-00012-of-00084.safetensors", + "language_model.model.layers.11.input_layernorm.weight": "model-00014-of-00084.safetensors", + "language_model.model.layers.11.mlp.fc1.weight": "model-00014-of-00084.safetensors", + "language_model.model.layers.11.mlp.fc2.weight": "model-00014-of-00084.safetensors", + "language_model.model.layers.11.post_attention_layernorm.weight": "model-00014-of-00084.safetensors", + "language_model.model.layers.11.self_attn.k_proj.bias": "model-00013-of-00084.safetensors", + "language_model.model.layers.11.self_attn.k_proj.weight": "model-00013-of-00084.safetensors", + "language_model.model.layers.11.self_attn.o_proj.weight": "model-00013-of-00084.safetensors", + "language_model.model.layers.11.self_attn.q_proj.bias": "model-00013-of-00084.safetensors", + "language_model.model.layers.11.self_attn.q_proj.weight": "model-00013-of-00084.safetensors", + "language_model.model.layers.11.self_attn.v_proj.bias": "model-00013-of-00084.safetensors", + "language_model.model.layers.11.self_attn.v_proj.weight": "model-00013-of-00084.safetensors", + "language_model.model.layers.12.input_layernorm.weight": "model-00015-of-00084.safetensors", + "language_model.model.layers.12.mlp.fc1.weight": "model-00015-of-00084.safetensors", + "language_model.model.layers.12.mlp.fc2.weight": "model-00015-of-00084.safetensors", + "language_model.model.layers.12.post_attention_layernorm.weight": "model-00015-of-00084.safetensors", + "language_model.model.layers.12.self_attn.k_proj.bias": "model-00014-of-00084.safetensors", + "language_model.model.layers.12.self_attn.k_proj.weight": "model-00014-of-00084.safetensors", + "language_model.model.layers.12.self_attn.o_proj.weight": "model-00014-of-00084.safetensors", + "language_model.model.layers.12.self_attn.q_proj.bias": "model-00014-of-00084.safetensors", + "language_model.model.layers.12.self_attn.q_proj.weight": "model-00014-of-00084.safetensors", + "language_model.model.layers.12.self_attn.v_proj.bias": "model-00014-of-00084.safetensors", + "language_model.model.layers.12.self_attn.v_proj.weight": "model-00014-of-00084.safetensors", + "language_model.model.layers.13.input_layernorm.weight": "model-00016-of-00084.safetensors", + "language_model.model.layers.13.mlp.fc1.weight": "model-00016-of-00084.safetensors", + "language_model.model.layers.13.mlp.fc2.weight": "model-00016-of-00084.safetensors", + "language_model.model.layers.13.post_attention_layernorm.weight": "model-00016-of-00084.safetensors", + "language_model.model.layers.13.self_attn.k_proj.bias": "model-00015-of-00084.safetensors", + "language_model.model.layers.13.self_attn.k_proj.weight": "model-00015-of-00084.safetensors", + "language_model.model.layers.13.self_attn.o_proj.weight": "model-00015-of-00084.safetensors", + "language_model.model.layers.13.self_attn.q_proj.bias": "model-00015-of-00084.safetensors", + "language_model.model.layers.13.self_attn.q_proj.weight": "model-00015-of-00084.safetensors", + "language_model.model.layers.13.self_attn.v_proj.bias": "model-00015-of-00084.safetensors", + "language_model.model.layers.13.self_attn.v_proj.weight": "model-00015-of-00084.safetensors", + "language_model.model.layers.14.input_layernorm.weight": "model-00017-of-00084.safetensors", + "language_model.model.layers.14.mlp.fc1.weight": "model-00017-of-00084.safetensors", + "language_model.model.layers.14.mlp.fc2.weight": "model-00017-of-00084.safetensors", + "language_model.model.layers.14.post_attention_layernorm.weight": "model-00017-of-00084.safetensors", + "language_model.model.layers.14.self_attn.k_proj.bias": "model-00016-of-00084.safetensors", + "language_model.model.layers.14.self_attn.k_proj.weight": "model-00016-of-00084.safetensors", + "language_model.model.layers.14.self_attn.o_proj.weight": "model-00016-of-00084.safetensors", + "language_model.model.layers.14.self_attn.q_proj.bias": "model-00016-of-00084.safetensors", + "language_model.model.layers.14.self_attn.q_proj.weight": "model-00016-of-00084.safetensors", + "language_model.model.layers.14.self_attn.v_proj.bias": "model-00016-of-00084.safetensors", + "language_model.model.layers.14.self_attn.v_proj.weight": "model-00016-of-00084.safetensors", + "language_model.model.layers.15.input_layernorm.weight": "model-00018-of-00084.safetensors", + "language_model.model.layers.15.mlp.fc1.weight": "model-00018-of-00084.safetensors", + "language_model.model.layers.15.mlp.fc2.weight": "model-00018-of-00084.safetensors", + "language_model.model.layers.15.post_attention_layernorm.weight": "model-00018-of-00084.safetensors", + "language_model.model.layers.15.self_attn.k_proj.bias": "model-00017-of-00084.safetensors", + "language_model.model.layers.15.self_attn.k_proj.weight": "model-00017-of-00084.safetensors", + "language_model.model.layers.15.self_attn.o_proj.weight": "model-00017-of-00084.safetensors", + "language_model.model.layers.15.self_attn.q_proj.bias": "model-00017-of-00084.safetensors", + "language_model.model.layers.15.self_attn.q_proj.weight": "model-00017-of-00084.safetensors", + "language_model.model.layers.15.self_attn.v_proj.bias": "model-00017-of-00084.safetensors", + "language_model.model.layers.15.self_attn.v_proj.weight": "model-00017-of-00084.safetensors", + "language_model.model.layers.16.input_layernorm.weight": "model-00019-of-00084.safetensors", + "language_model.model.layers.16.mlp.fc1.weight": "model-00019-of-00084.safetensors", + "language_model.model.layers.16.mlp.fc2.weight": "model-00019-of-00084.safetensors", + "language_model.model.layers.16.post_attention_layernorm.weight": "model-00019-of-00084.safetensors", + "language_model.model.layers.16.self_attn.k_proj.bias": "model-00018-of-00084.safetensors", + "language_model.model.layers.16.self_attn.k_proj.weight": "model-00018-of-00084.safetensors", + "language_model.model.layers.16.self_attn.o_proj.weight": "model-00018-of-00084.safetensors", + "language_model.model.layers.16.self_attn.q_proj.bias": "model-00018-of-00084.safetensors", + "language_model.model.layers.16.self_attn.q_proj.weight": "model-00018-of-00084.safetensors", + "language_model.model.layers.16.self_attn.v_proj.bias": "model-00018-of-00084.safetensors", + "language_model.model.layers.16.self_attn.v_proj.weight": "model-00018-of-00084.safetensors", + "language_model.model.layers.17.input_layernorm.weight": "model-00020-of-00084.safetensors", + "language_model.model.layers.17.mlp.fc1.weight": "model-00020-of-00084.safetensors", + "language_model.model.layers.17.mlp.fc2.weight": "model-00020-of-00084.safetensors", + "language_model.model.layers.17.post_attention_layernorm.weight": "model-00020-of-00084.safetensors", + "language_model.model.layers.17.self_attn.k_proj.bias": "model-00019-of-00084.safetensors", + "language_model.model.layers.17.self_attn.k_proj.weight": "model-00019-of-00084.safetensors", + "language_model.model.layers.17.self_attn.o_proj.weight": "model-00019-of-00084.safetensors", + "language_model.model.layers.17.self_attn.q_proj.bias": "model-00019-of-00084.safetensors", + "language_model.model.layers.17.self_attn.q_proj.weight": "model-00019-of-00084.safetensors", + "language_model.model.layers.17.self_attn.v_proj.bias": "model-00019-of-00084.safetensors", + "language_model.model.layers.17.self_attn.v_proj.weight": "model-00019-of-00084.safetensors", + "language_model.model.layers.18.input_layernorm.weight": "model-00021-of-00084.safetensors", + "language_model.model.layers.18.mlp.fc1.weight": "model-00021-of-00084.safetensors", + "language_model.model.layers.18.mlp.fc2.weight": "model-00021-of-00084.safetensors", + "language_model.model.layers.18.post_attention_layernorm.weight": "model-00021-of-00084.safetensors", + "language_model.model.layers.18.self_attn.k_proj.bias": "model-00020-of-00084.safetensors", + "language_model.model.layers.18.self_attn.k_proj.weight": "model-00020-of-00084.safetensors", + "language_model.model.layers.18.self_attn.o_proj.weight": "model-00020-of-00084.safetensors", + "language_model.model.layers.18.self_attn.q_proj.bias": "model-00020-of-00084.safetensors", + "language_model.model.layers.18.self_attn.q_proj.weight": "model-00020-of-00084.safetensors", + "language_model.model.layers.18.self_attn.v_proj.bias": "model-00020-of-00084.safetensors", + "language_model.model.layers.18.self_attn.v_proj.weight": "model-00020-of-00084.safetensors", + "language_model.model.layers.19.input_layernorm.weight": "model-00022-of-00084.safetensors", + "language_model.model.layers.19.mlp.fc1.weight": "model-00022-of-00084.safetensors", + "language_model.model.layers.19.mlp.fc2.weight": "model-00022-of-00084.safetensors", + "language_model.model.layers.19.post_attention_layernorm.weight": "model-00022-of-00084.safetensors", + "language_model.model.layers.19.self_attn.k_proj.bias": "model-00021-of-00084.safetensors", + "language_model.model.layers.19.self_attn.k_proj.weight": "model-00021-of-00084.safetensors", + "language_model.model.layers.19.self_attn.o_proj.weight": "model-00021-of-00084.safetensors", + "language_model.model.layers.19.self_attn.q_proj.bias": "model-00021-of-00084.safetensors", + "language_model.model.layers.19.self_attn.q_proj.weight": "model-00021-of-00084.safetensors", + "language_model.model.layers.19.self_attn.v_proj.bias": "model-00021-of-00084.safetensors", + "language_model.model.layers.19.self_attn.v_proj.weight": "model-00021-of-00084.safetensors", + "language_model.model.layers.2.input_layernorm.weight": "model-00005-of-00084.safetensors", + "language_model.model.layers.2.mlp.fc1.weight": "model-00005-of-00084.safetensors", + "language_model.model.layers.2.mlp.fc2.weight": "model-00005-of-00084.safetensors", + "language_model.model.layers.2.post_attention_layernorm.weight": "model-00005-of-00084.safetensors", + "language_model.model.layers.2.self_attn.k_proj.bias": "model-00004-of-00084.safetensors", + "language_model.model.layers.2.self_attn.k_proj.weight": "model-00004-of-00084.safetensors", + "language_model.model.layers.2.self_attn.o_proj.weight": "model-00004-of-00084.safetensors", + "language_model.model.layers.2.self_attn.q_proj.bias": "model-00004-of-00084.safetensors", + "language_model.model.layers.2.self_attn.q_proj.weight": "model-00004-of-00084.safetensors", + "language_model.model.layers.2.self_attn.v_proj.bias": "model-00004-of-00084.safetensors", + "language_model.model.layers.2.self_attn.v_proj.weight": "model-00004-of-00084.safetensors", + "language_model.model.layers.20.input_layernorm.weight": "model-00023-of-00084.safetensors", + "language_model.model.layers.20.mlp.fc1.weight": "model-00023-of-00084.safetensors", + "language_model.model.layers.20.mlp.fc2.weight": "model-00023-of-00084.safetensors", + "language_model.model.layers.20.post_attention_layernorm.weight": "model-00023-of-00084.safetensors", + "language_model.model.layers.20.self_attn.k_proj.bias": "model-00022-of-00084.safetensors", + "language_model.model.layers.20.self_attn.k_proj.weight": "model-00022-of-00084.safetensors", + "language_model.model.layers.20.self_attn.o_proj.weight": "model-00022-of-00084.safetensors", + "language_model.model.layers.20.self_attn.q_proj.bias": "model-00022-of-00084.safetensors", + "language_model.model.layers.20.self_attn.q_proj.weight": "model-00022-of-00084.safetensors", + "language_model.model.layers.20.self_attn.v_proj.bias": "model-00022-of-00084.safetensors", + "language_model.model.layers.20.self_attn.v_proj.weight": "model-00022-of-00084.safetensors", + "language_model.model.layers.21.input_layernorm.weight": "model-00024-of-00084.safetensors", + "language_model.model.layers.21.mlp.fc1.weight": "model-00024-of-00084.safetensors", + "language_model.model.layers.21.mlp.fc2.weight": "model-00024-of-00084.safetensors", + "language_model.model.layers.21.post_attention_layernorm.weight": "model-00024-of-00084.safetensors", + "language_model.model.layers.21.self_attn.k_proj.bias": "model-00023-of-00084.safetensors", + "language_model.model.layers.21.self_attn.k_proj.weight": "model-00023-of-00084.safetensors", + "language_model.model.layers.21.self_attn.o_proj.weight": "model-00023-of-00084.safetensors", + "language_model.model.layers.21.self_attn.q_proj.bias": "model-00023-of-00084.safetensors", + "language_model.model.layers.21.self_attn.q_proj.weight": "model-00023-of-00084.safetensors", + "language_model.model.layers.21.self_attn.v_proj.bias": "model-00023-of-00084.safetensors", + "language_model.model.layers.21.self_attn.v_proj.weight": "model-00023-of-00084.safetensors", + "language_model.model.layers.22.input_layernorm.weight": "model-00025-of-00084.safetensors", + "language_model.model.layers.22.mlp.fc1.weight": "model-00025-of-00084.safetensors", + "language_model.model.layers.22.mlp.fc2.weight": "model-00025-of-00084.safetensors", + "language_model.model.layers.22.post_attention_layernorm.weight": "model-00025-of-00084.safetensors", + "language_model.model.layers.22.self_attn.k_proj.bias": "model-00024-of-00084.safetensors", + "language_model.model.layers.22.self_attn.k_proj.weight": "model-00024-of-00084.safetensors", + "language_model.model.layers.22.self_attn.o_proj.weight": "model-00024-of-00084.safetensors", + "language_model.model.layers.22.self_attn.q_proj.bias": "model-00024-of-00084.safetensors", + "language_model.model.layers.22.self_attn.q_proj.weight": "model-00024-of-00084.safetensors", + "language_model.model.layers.22.self_attn.v_proj.bias": "model-00024-of-00084.safetensors", + "language_model.model.layers.22.self_attn.v_proj.weight": "model-00024-of-00084.safetensors", + "language_model.model.layers.23.input_layernorm.weight": "model-00026-of-00084.safetensors", + "language_model.model.layers.23.mlp.fc1.weight": "model-00026-of-00084.safetensors", + "language_model.model.layers.23.mlp.fc2.weight": "model-00026-of-00084.safetensors", + "language_model.model.layers.23.post_attention_layernorm.weight": "model-00026-of-00084.safetensors", + "language_model.model.layers.23.self_attn.k_proj.bias": "model-00025-of-00084.safetensors", + "language_model.model.layers.23.self_attn.k_proj.weight": "model-00025-of-00084.safetensors", + "language_model.model.layers.23.self_attn.o_proj.weight": "model-00025-of-00084.safetensors", + "language_model.model.layers.23.self_attn.q_proj.bias": "model-00025-of-00084.safetensors", + "language_model.model.layers.23.self_attn.q_proj.weight": "model-00025-of-00084.safetensors", + "language_model.model.layers.23.self_attn.v_proj.bias": "model-00025-of-00084.safetensors", + "language_model.model.layers.23.self_attn.v_proj.weight": "model-00025-of-00084.safetensors", + "language_model.model.layers.24.input_layernorm.weight": "model-00027-of-00084.safetensors", + "language_model.model.layers.24.mlp.fc1.weight": "model-00027-of-00084.safetensors", + "language_model.model.layers.24.mlp.fc2.weight": "model-00027-of-00084.safetensors", + "language_model.model.layers.24.post_attention_layernorm.weight": "model-00027-of-00084.safetensors", + "language_model.model.layers.24.self_attn.k_proj.bias": "model-00026-of-00084.safetensors", + "language_model.model.layers.24.self_attn.k_proj.weight": "model-00026-of-00084.safetensors", + "language_model.model.layers.24.self_attn.o_proj.weight": "model-00026-of-00084.safetensors", + "language_model.model.layers.24.self_attn.q_proj.bias": "model-00026-of-00084.safetensors", + "language_model.model.layers.24.self_attn.q_proj.weight": "model-00026-of-00084.safetensors", + "language_model.model.layers.24.self_attn.v_proj.bias": "model-00026-of-00084.safetensors", + "language_model.model.layers.24.self_attn.v_proj.weight": "model-00026-of-00084.safetensors", + "language_model.model.layers.25.input_layernorm.weight": "model-00028-of-00084.safetensors", + "language_model.model.layers.25.mlp.fc1.weight": "model-00028-of-00084.safetensors", + "language_model.model.layers.25.mlp.fc2.weight": "model-00028-of-00084.safetensors", + "language_model.model.layers.25.post_attention_layernorm.weight": "model-00028-of-00084.safetensors", + "language_model.model.layers.25.self_attn.k_proj.bias": "model-00027-of-00084.safetensors", + "language_model.model.layers.25.self_attn.k_proj.weight": "model-00027-of-00084.safetensors", + "language_model.model.layers.25.self_attn.o_proj.weight": "model-00027-of-00084.safetensors", + "language_model.model.layers.25.self_attn.q_proj.bias": "model-00027-of-00084.safetensors", + "language_model.model.layers.25.self_attn.q_proj.weight": "model-00027-of-00084.safetensors", + "language_model.model.layers.25.self_attn.v_proj.bias": "model-00027-of-00084.safetensors", + "language_model.model.layers.25.self_attn.v_proj.weight": "model-00027-of-00084.safetensors", + "language_model.model.layers.26.input_layernorm.weight": "model-00029-of-00084.safetensors", + "language_model.model.layers.26.mlp.fc1.weight": "model-00029-of-00084.safetensors", + "language_model.model.layers.26.mlp.fc2.weight": "model-00029-of-00084.safetensors", + "language_model.model.layers.26.post_attention_layernorm.weight": "model-00029-of-00084.safetensors", + "language_model.model.layers.26.self_attn.k_proj.bias": "model-00028-of-00084.safetensors", + "language_model.model.layers.26.self_attn.k_proj.weight": "model-00028-of-00084.safetensors", + "language_model.model.layers.26.self_attn.o_proj.weight": "model-00028-of-00084.safetensors", + "language_model.model.layers.26.self_attn.q_proj.bias": "model-00028-of-00084.safetensors", + "language_model.model.layers.26.self_attn.q_proj.weight": "model-00028-of-00084.safetensors", + "language_model.model.layers.26.self_attn.v_proj.bias": "model-00028-of-00084.safetensors", + "language_model.model.layers.26.self_attn.v_proj.weight": "model-00028-of-00084.safetensors", + "language_model.model.layers.27.input_layernorm.weight": "model-00030-of-00084.safetensors", + "language_model.model.layers.27.mlp.fc1.weight": "model-00030-of-00084.safetensors", + "language_model.model.layers.27.mlp.fc2.weight": "model-00030-of-00084.safetensors", + "language_model.model.layers.27.post_attention_layernorm.weight": "model-00030-of-00084.safetensors", + "language_model.model.layers.27.self_attn.k_proj.bias": "model-00029-of-00084.safetensors", + "language_model.model.layers.27.self_attn.k_proj.weight": "model-00029-of-00084.safetensors", + "language_model.model.layers.27.self_attn.o_proj.weight": "model-00029-of-00084.safetensors", + "language_model.model.layers.27.self_attn.q_proj.bias": "model-00029-of-00084.safetensors", + "language_model.model.layers.27.self_attn.q_proj.weight": "model-00029-of-00084.safetensors", + "language_model.model.layers.27.self_attn.v_proj.bias": "model-00029-of-00084.safetensors", + "language_model.model.layers.27.self_attn.v_proj.weight": "model-00029-of-00084.safetensors", + "language_model.model.layers.28.input_layernorm.weight": "model-00031-of-00084.safetensors", + "language_model.model.layers.28.mlp.fc1.weight": "model-00031-of-00084.safetensors", + "language_model.model.layers.28.mlp.fc2.weight": "model-00031-of-00084.safetensors", + "language_model.model.layers.28.post_attention_layernorm.weight": "model-00031-of-00084.safetensors", + "language_model.model.layers.28.self_attn.k_proj.bias": "model-00030-of-00084.safetensors", + "language_model.model.layers.28.self_attn.k_proj.weight": "model-00030-of-00084.safetensors", + "language_model.model.layers.28.self_attn.o_proj.weight": "model-00030-of-00084.safetensors", + "language_model.model.layers.28.self_attn.q_proj.bias": "model-00030-of-00084.safetensors", + "language_model.model.layers.28.self_attn.q_proj.weight": "model-00030-of-00084.safetensors", + "language_model.model.layers.28.self_attn.v_proj.bias": "model-00030-of-00084.safetensors", + "language_model.model.layers.28.self_attn.v_proj.weight": "model-00030-of-00084.safetensors", + "language_model.model.layers.29.input_layernorm.weight": "model-00032-of-00084.safetensors", + "language_model.model.layers.29.mlp.fc1.weight": "model-00032-of-00084.safetensors", + "language_model.model.layers.29.mlp.fc2.weight": "model-00032-of-00084.safetensors", + "language_model.model.layers.29.post_attention_layernorm.weight": "model-00032-of-00084.safetensors", + "language_model.model.layers.29.self_attn.k_proj.bias": "model-00031-of-00084.safetensors", + "language_model.model.layers.29.self_attn.k_proj.weight": "model-00031-of-00084.safetensors", + "language_model.model.layers.29.self_attn.o_proj.weight": "model-00031-of-00084.safetensors", + "language_model.model.layers.29.self_attn.q_proj.bias": "model-00031-of-00084.safetensors", + "language_model.model.layers.29.self_attn.q_proj.weight": "model-00031-of-00084.safetensors", + "language_model.model.layers.29.self_attn.v_proj.bias": "model-00031-of-00084.safetensors", + "language_model.model.layers.29.self_attn.v_proj.weight": "model-00031-of-00084.safetensors", + "language_model.model.layers.3.input_layernorm.weight": "model-00006-of-00084.safetensors", + "language_model.model.layers.3.mlp.fc1.weight": "model-00006-of-00084.safetensors", + "language_model.model.layers.3.mlp.fc2.weight": "model-00006-of-00084.safetensors", + "language_model.model.layers.3.post_attention_layernorm.weight": "model-00006-of-00084.safetensors", + "language_model.model.layers.3.self_attn.k_proj.bias": "model-00005-of-00084.safetensors", + "language_model.model.layers.3.self_attn.k_proj.weight": "model-00005-of-00084.safetensors", + "language_model.model.layers.3.self_attn.o_proj.weight": "model-00005-of-00084.safetensors", + "language_model.model.layers.3.self_attn.q_proj.bias": "model-00005-of-00084.safetensors", + "language_model.model.layers.3.self_attn.q_proj.weight": "model-00005-of-00084.safetensors", + "language_model.model.layers.3.self_attn.v_proj.bias": "model-00005-of-00084.safetensors", + "language_model.model.layers.3.self_attn.v_proj.weight": "model-00005-of-00084.safetensors", + "language_model.model.layers.30.input_layernorm.weight": "model-00033-of-00084.safetensors", + "language_model.model.layers.30.mlp.fc1.weight": "model-00033-of-00084.safetensors", + "language_model.model.layers.30.mlp.fc2.weight": "model-00033-of-00084.safetensors", + "language_model.model.layers.30.post_attention_layernorm.weight": "model-00033-of-00084.safetensors", + "language_model.model.layers.30.self_attn.k_proj.bias": "model-00032-of-00084.safetensors", + "language_model.model.layers.30.self_attn.k_proj.weight": "model-00032-of-00084.safetensors", + "language_model.model.layers.30.self_attn.o_proj.weight": "model-00032-of-00084.safetensors", + "language_model.model.layers.30.self_attn.q_proj.bias": "model-00032-of-00084.safetensors", + "language_model.model.layers.30.self_attn.q_proj.weight": "model-00032-of-00084.safetensors", + "language_model.model.layers.30.self_attn.v_proj.bias": "model-00032-of-00084.safetensors", + "language_model.model.layers.30.self_attn.v_proj.weight": "model-00032-of-00084.safetensors", + "language_model.model.layers.31.input_layernorm.weight": "model-00034-of-00084.safetensors", + "language_model.model.layers.31.mlp.fc1.weight": "model-00034-of-00084.safetensors", + "language_model.model.layers.31.mlp.fc2.weight": "model-00034-of-00084.safetensors", + "language_model.model.layers.31.post_attention_layernorm.weight": "model-00034-of-00084.safetensors", + "language_model.model.layers.31.self_attn.k_proj.bias": "model-00033-of-00084.safetensors", + "language_model.model.layers.31.self_attn.k_proj.weight": "model-00033-of-00084.safetensors", + "language_model.model.layers.31.self_attn.o_proj.weight": "model-00033-of-00084.safetensors", + "language_model.model.layers.31.self_attn.q_proj.bias": "model-00033-of-00084.safetensors", + "language_model.model.layers.31.self_attn.q_proj.weight": "model-00033-of-00084.safetensors", + "language_model.model.layers.31.self_attn.v_proj.bias": "model-00033-of-00084.safetensors", + "language_model.model.layers.31.self_attn.v_proj.weight": "model-00033-of-00084.safetensors", + "language_model.model.layers.32.input_layernorm.weight": "model-00035-of-00084.safetensors", + "language_model.model.layers.32.mlp.fc1.weight": "model-00035-of-00084.safetensors", + "language_model.model.layers.32.mlp.fc2.weight": "model-00035-of-00084.safetensors", + "language_model.model.layers.32.post_attention_layernorm.weight": "model-00035-of-00084.safetensors", + "language_model.model.layers.32.self_attn.k_proj.bias": "model-00034-of-00084.safetensors", + "language_model.model.layers.32.self_attn.k_proj.weight": "model-00034-of-00084.safetensors", + "language_model.model.layers.32.self_attn.o_proj.weight": "model-00034-of-00084.safetensors", + "language_model.model.layers.32.self_attn.q_proj.bias": "model-00034-of-00084.safetensors", + "language_model.model.layers.32.self_attn.q_proj.weight": "model-00034-of-00084.safetensors", + "language_model.model.layers.32.self_attn.v_proj.bias": "model-00034-of-00084.safetensors", + "language_model.model.layers.32.self_attn.v_proj.weight": "model-00034-of-00084.safetensors", + "language_model.model.layers.33.input_layernorm.weight": "model-00036-of-00084.safetensors", + "language_model.model.layers.33.mlp.fc1.weight": "model-00036-of-00084.safetensors", + "language_model.model.layers.33.mlp.fc2.weight": "model-00036-of-00084.safetensors", + "language_model.model.layers.33.post_attention_layernorm.weight": "model-00036-of-00084.safetensors", + "language_model.model.layers.33.self_attn.k_proj.bias": "model-00035-of-00084.safetensors", + "language_model.model.layers.33.self_attn.k_proj.weight": "model-00035-of-00084.safetensors", + "language_model.model.layers.33.self_attn.o_proj.weight": "model-00035-of-00084.safetensors", + "language_model.model.layers.33.self_attn.q_proj.bias": "model-00035-of-00084.safetensors", + "language_model.model.layers.33.self_attn.q_proj.weight": "model-00035-of-00084.safetensors", + "language_model.model.layers.33.self_attn.v_proj.bias": "model-00035-of-00084.safetensors", + "language_model.model.layers.33.self_attn.v_proj.weight": "model-00035-of-00084.safetensors", + "language_model.model.layers.34.input_layernorm.weight": "model-00037-of-00084.safetensors", + "language_model.model.layers.34.mlp.fc1.weight": "model-00037-of-00084.safetensors", + "language_model.model.layers.34.mlp.fc2.weight": "model-00037-of-00084.safetensors", + "language_model.model.layers.34.post_attention_layernorm.weight": "model-00037-of-00084.safetensors", + "language_model.model.layers.34.self_attn.k_proj.bias": "model-00036-of-00084.safetensors", + "language_model.model.layers.34.self_attn.k_proj.weight": "model-00036-of-00084.safetensors", + "language_model.model.layers.34.self_attn.o_proj.weight": "model-00036-of-00084.safetensors", + "language_model.model.layers.34.self_attn.q_proj.bias": "model-00036-of-00084.safetensors", + "language_model.model.layers.34.self_attn.q_proj.weight": "model-00036-of-00084.safetensors", + "language_model.model.layers.34.self_attn.v_proj.bias": "model-00036-of-00084.safetensors", + "language_model.model.layers.34.self_attn.v_proj.weight": "model-00036-of-00084.safetensors", + "language_model.model.layers.35.input_layernorm.weight": "model-00038-of-00084.safetensors", + "language_model.model.layers.35.mlp.fc1.weight": "model-00038-of-00084.safetensors", + "language_model.model.layers.35.mlp.fc2.weight": "model-00038-of-00084.safetensors", + "language_model.model.layers.35.post_attention_layernorm.weight": "model-00038-of-00084.safetensors", + "language_model.model.layers.35.self_attn.k_proj.bias": "model-00037-of-00084.safetensors", + "language_model.model.layers.35.self_attn.k_proj.weight": "model-00037-of-00084.safetensors", + "language_model.model.layers.35.self_attn.o_proj.weight": "model-00037-of-00084.safetensors", + "language_model.model.layers.35.self_attn.q_proj.bias": "model-00037-of-00084.safetensors", + "language_model.model.layers.35.self_attn.q_proj.weight": "model-00037-of-00084.safetensors", + "language_model.model.layers.35.self_attn.v_proj.bias": "model-00037-of-00084.safetensors", + "language_model.model.layers.35.self_attn.v_proj.weight": "model-00037-of-00084.safetensors", + "language_model.model.layers.36.input_layernorm.weight": "model-00039-of-00084.safetensors", + "language_model.model.layers.36.mlp.fc1.weight": "model-00039-of-00084.safetensors", + "language_model.model.layers.36.mlp.fc2.weight": "model-00039-of-00084.safetensors", + "language_model.model.layers.36.post_attention_layernorm.weight": "model-00039-of-00084.safetensors", + "language_model.model.layers.36.self_attn.k_proj.bias": "model-00038-of-00084.safetensors", + "language_model.model.layers.36.self_attn.k_proj.weight": "model-00038-of-00084.safetensors", + "language_model.model.layers.36.self_attn.o_proj.weight": "model-00038-of-00084.safetensors", + "language_model.model.layers.36.self_attn.q_proj.bias": "model-00038-of-00084.safetensors", + "language_model.model.layers.36.self_attn.q_proj.weight": "model-00038-of-00084.safetensors", + "language_model.model.layers.36.self_attn.v_proj.bias": "model-00038-of-00084.safetensors", + "language_model.model.layers.36.self_attn.v_proj.weight": "model-00038-of-00084.safetensors", + "language_model.model.layers.37.input_layernorm.weight": "model-00040-of-00084.safetensors", + "language_model.model.layers.37.mlp.fc1.weight": "model-00040-of-00084.safetensors", + "language_model.model.layers.37.mlp.fc2.weight": "model-00040-of-00084.safetensors", + "language_model.model.layers.37.post_attention_layernorm.weight": "model-00040-of-00084.safetensors", + "language_model.model.layers.37.self_attn.k_proj.bias": "model-00039-of-00084.safetensors", + "language_model.model.layers.37.self_attn.k_proj.weight": "model-00039-of-00084.safetensors", + "language_model.model.layers.37.self_attn.o_proj.weight": "model-00039-of-00084.safetensors", + "language_model.model.layers.37.self_attn.q_proj.bias": "model-00039-of-00084.safetensors", + "language_model.model.layers.37.self_attn.q_proj.weight": "model-00039-of-00084.safetensors", + "language_model.model.layers.37.self_attn.v_proj.bias": "model-00039-of-00084.safetensors", + "language_model.model.layers.37.self_attn.v_proj.weight": "model-00039-of-00084.safetensors", + "language_model.model.layers.38.input_layernorm.weight": "model-00041-of-00084.safetensors", + "language_model.model.layers.38.mlp.fc1.weight": "model-00041-of-00084.safetensors", + "language_model.model.layers.38.mlp.fc2.weight": "model-00041-of-00084.safetensors", + "language_model.model.layers.38.post_attention_layernorm.weight": "model-00041-of-00084.safetensors", + "language_model.model.layers.38.self_attn.k_proj.bias": "model-00040-of-00084.safetensors", + "language_model.model.layers.38.self_attn.k_proj.weight": "model-00040-of-00084.safetensors", + "language_model.model.layers.38.self_attn.o_proj.weight": "model-00040-of-00084.safetensors", + "language_model.model.layers.38.self_attn.q_proj.bias": "model-00040-of-00084.safetensors", + "language_model.model.layers.38.self_attn.q_proj.weight": "model-00040-of-00084.safetensors", + "language_model.model.layers.38.self_attn.v_proj.bias": "model-00040-of-00084.safetensors", + "language_model.model.layers.38.self_attn.v_proj.weight": "model-00040-of-00084.safetensors", + "language_model.model.layers.39.input_layernorm.weight": "model-00042-of-00084.safetensors", + "language_model.model.layers.39.mlp.fc1.weight": "model-00042-of-00084.safetensors", + "language_model.model.layers.39.mlp.fc2.weight": "model-00042-of-00084.safetensors", + "language_model.model.layers.39.post_attention_layernorm.weight": "model-00042-of-00084.safetensors", + "language_model.model.layers.39.self_attn.k_proj.bias": "model-00041-of-00084.safetensors", + "language_model.model.layers.39.self_attn.k_proj.weight": "model-00041-of-00084.safetensors", + "language_model.model.layers.39.self_attn.o_proj.weight": "model-00041-of-00084.safetensors", + "language_model.model.layers.39.self_attn.q_proj.bias": "model-00041-of-00084.safetensors", + "language_model.model.layers.39.self_attn.q_proj.weight": "model-00041-of-00084.safetensors", + "language_model.model.layers.39.self_attn.v_proj.bias": "model-00041-of-00084.safetensors", + "language_model.model.layers.39.self_attn.v_proj.weight": "model-00041-of-00084.safetensors", + "language_model.model.layers.4.input_layernorm.weight": "model-00007-of-00084.safetensors", + "language_model.model.layers.4.mlp.fc1.weight": "model-00007-of-00084.safetensors", + "language_model.model.layers.4.mlp.fc2.weight": "model-00007-of-00084.safetensors", + "language_model.model.layers.4.post_attention_layernorm.weight": "model-00007-of-00084.safetensors", + "language_model.model.layers.4.self_attn.k_proj.bias": "model-00006-of-00084.safetensors", + "language_model.model.layers.4.self_attn.k_proj.weight": "model-00006-of-00084.safetensors", + "language_model.model.layers.4.self_attn.o_proj.weight": "model-00006-of-00084.safetensors", + "language_model.model.layers.4.self_attn.q_proj.bias": "model-00006-of-00084.safetensors", + "language_model.model.layers.4.self_attn.q_proj.weight": "model-00006-of-00084.safetensors", + "language_model.model.layers.4.self_attn.v_proj.bias": "model-00006-of-00084.safetensors", + "language_model.model.layers.4.self_attn.v_proj.weight": "model-00006-of-00084.safetensors", + "language_model.model.layers.40.input_layernorm.weight": "model-00043-of-00084.safetensors", + "language_model.model.layers.40.mlp.fc1.weight": "model-00043-of-00084.safetensors", + "language_model.model.layers.40.mlp.fc2.weight": "model-00043-of-00084.safetensors", + "language_model.model.layers.40.post_attention_layernorm.weight": "model-00043-of-00084.safetensors", + "language_model.model.layers.40.self_attn.k_proj.bias": "model-00042-of-00084.safetensors", + "language_model.model.layers.40.self_attn.k_proj.weight": "model-00042-of-00084.safetensors", + "language_model.model.layers.40.self_attn.o_proj.weight": "model-00042-of-00084.safetensors", + "language_model.model.layers.40.self_attn.q_proj.bias": "model-00042-of-00084.safetensors", + "language_model.model.layers.40.self_attn.q_proj.weight": "model-00042-of-00084.safetensors", + "language_model.model.layers.40.self_attn.v_proj.bias": "model-00042-of-00084.safetensors", + "language_model.model.layers.40.self_attn.v_proj.weight": "model-00042-of-00084.safetensors", + "language_model.model.layers.41.input_layernorm.weight": "model-00044-of-00084.safetensors", + "language_model.model.layers.41.mlp.fc1.weight": "model-00044-of-00084.safetensors", + "language_model.model.layers.41.mlp.fc2.weight": "model-00044-of-00084.safetensors", + "language_model.model.layers.41.post_attention_layernorm.weight": "model-00044-of-00084.safetensors", + "language_model.model.layers.41.self_attn.k_proj.bias": "model-00043-of-00084.safetensors", + "language_model.model.layers.41.self_attn.k_proj.weight": "model-00043-of-00084.safetensors", + "language_model.model.layers.41.self_attn.o_proj.weight": "model-00043-of-00084.safetensors", + "language_model.model.layers.41.self_attn.q_proj.bias": "model-00043-of-00084.safetensors", + "language_model.model.layers.41.self_attn.q_proj.weight": "model-00043-of-00084.safetensors", + "language_model.model.layers.41.self_attn.v_proj.bias": "model-00043-of-00084.safetensors", + "language_model.model.layers.41.self_attn.v_proj.weight": "model-00043-of-00084.safetensors", + "language_model.model.layers.42.input_layernorm.weight": "model-00045-of-00084.safetensors", + "language_model.model.layers.42.mlp.fc1.weight": "model-00045-of-00084.safetensors", + "language_model.model.layers.42.mlp.fc2.weight": "model-00045-of-00084.safetensors", + "language_model.model.layers.42.post_attention_layernorm.weight": "model-00045-of-00084.safetensors", + "language_model.model.layers.42.self_attn.k_proj.bias": "model-00044-of-00084.safetensors", + "language_model.model.layers.42.self_attn.k_proj.weight": "model-00044-of-00084.safetensors", + "language_model.model.layers.42.self_attn.o_proj.weight": "model-00044-of-00084.safetensors", + "language_model.model.layers.42.self_attn.q_proj.bias": "model-00044-of-00084.safetensors", + "language_model.model.layers.42.self_attn.q_proj.weight": "model-00044-of-00084.safetensors", + "language_model.model.layers.42.self_attn.v_proj.bias": "model-00044-of-00084.safetensors", + "language_model.model.layers.42.self_attn.v_proj.weight": "model-00044-of-00084.safetensors", + "language_model.model.layers.43.input_layernorm.weight": "model-00046-of-00084.safetensors", + "language_model.model.layers.43.mlp.fc1.weight": "model-00046-of-00084.safetensors", + "language_model.model.layers.43.mlp.fc2.weight": "model-00046-of-00084.safetensors", + "language_model.model.layers.43.post_attention_layernorm.weight": "model-00046-of-00084.safetensors", + "language_model.model.layers.43.self_attn.k_proj.bias": "model-00045-of-00084.safetensors", + "language_model.model.layers.43.self_attn.k_proj.weight": "model-00045-of-00084.safetensors", + "language_model.model.layers.43.self_attn.o_proj.weight": "model-00045-of-00084.safetensors", + "language_model.model.layers.43.self_attn.q_proj.bias": "model-00045-of-00084.safetensors", + "language_model.model.layers.43.self_attn.q_proj.weight": "model-00045-of-00084.safetensors", + "language_model.model.layers.43.self_attn.v_proj.bias": "model-00045-of-00084.safetensors", + "language_model.model.layers.43.self_attn.v_proj.weight": "model-00045-of-00084.safetensors", + "language_model.model.layers.44.input_layernorm.weight": "model-00047-of-00084.safetensors", + "language_model.model.layers.44.mlp.fc1.weight": "model-00047-of-00084.safetensors", + "language_model.model.layers.44.mlp.fc2.weight": "model-00047-of-00084.safetensors", + "language_model.model.layers.44.post_attention_layernorm.weight": "model-00047-of-00084.safetensors", + "language_model.model.layers.44.self_attn.k_proj.bias": "model-00046-of-00084.safetensors", + "language_model.model.layers.44.self_attn.k_proj.weight": "model-00046-of-00084.safetensors", + "language_model.model.layers.44.self_attn.o_proj.weight": "model-00046-of-00084.safetensors", + "language_model.model.layers.44.self_attn.q_proj.bias": "model-00046-of-00084.safetensors", + "language_model.model.layers.44.self_attn.q_proj.weight": "model-00046-of-00084.safetensors", + "language_model.model.layers.44.self_attn.v_proj.bias": "model-00046-of-00084.safetensors", + "language_model.model.layers.44.self_attn.v_proj.weight": "model-00046-of-00084.safetensors", + "language_model.model.layers.45.input_layernorm.weight": "model-00048-of-00084.safetensors", + "language_model.model.layers.45.mlp.fc1.weight": "model-00048-of-00084.safetensors", + "language_model.model.layers.45.mlp.fc2.weight": "model-00048-of-00084.safetensors", + "language_model.model.layers.45.post_attention_layernorm.weight": "model-00048-of-00084.safetensors", + "language_model.model.layers.45.self_attn.k_proj.bias": "model-00047-of-00084.safetensors", + "language_model.model.layers.45.self_attn.k_proj.weight": "model-00047-of-00084.safetensors", + "language_model.model.layers.45.self_attn.o_proj.weight": "model-00047-of-00084.safetensors", + "language_model.model.layers.45.self_attn.q_proj.bias": "model-00047-of-00084.safetensors", + "language_model.model.layers.45.self_attn.q_proj.weight": "model-00047-of-00084.safetensors", + "language_model.model.layers.45.self_attn.v_proj.bias": "model-00047-of-00084.safetensors", + "language_model.model.layers.45.self_attn.v_proj.weight": "model-00047-of-00084.safetensors", + "language_model.model.layers.46.input_layernorm.weight": "model-00049-of-00084.safetensors", + "language_model.model.layers.46.mlp.fc1.weight": "model-00049-of-00084.safetensors", + "language_model.model.layers.46.mlp.fc2.weight": "model-00049-of-00084.safetensors", + "language_model.model.layers.46.post_attention_layernorm.weight": "model-00049-of-00084.safetensors", + "language_model.model.layers.46.self_attn.k_proj.bias": "model-00048-of-00084.safetensors", + "language_model.model.layers.46.self_attn.k_proj.weight": "model-00048-of-00084.safetensors", + "language_model.model.layers.46.self_attn.o_proj.weight": "model-00048-of-00084.safetensors", + "language_model.model.layers.46.self_attn.q_proj.bias": "model-00048-of-00084.safetensors", + "language_model.model.layers.46.self_attn.q_proj.weight": "model-00048-of-00084.safetensors", + "language_model.model.layers.46.self_attn.v_proj.bias": "model-00048-of-00084.safetensors", + "language_model.model.layers.46.self_attn.v_proj.weight": "model-00048-of-00084.safetensors", + "language_model.model.layers.47.input_layernorm.weight": "model-00050-of-00084.safetensors", + "language_model.model.layers.47.mlp.fc1.weight": "model-00050-of-00084.safetensors", + "language_model.model.layers.47.mlp.fc2.weight": "model-00050-of-00084.safetensors", + "language_model.model.layers.47.post_attention_layernorm.weight": "model-00050-of-00084.safetensors", + "language_model.model.layers.47.self_attn.k_proj.bias": "model-00049-of-00084.safetensors", + "language_model.model.layers.47.self_attn.k_proj.weight": "model-00049-of-00084.safetensors", + "language_model.model.layers.47.self_attn.o_proj.weight": "model-00049-of-00084.safetensors", + "language_model.model.layers.47.self_attn.q_proj.bias": "model-00049-of-00084.safetensors", + "language_model.model.layers.47.self_attn.q_proj.weight": "model-00049-of-00084.safetensors", + "language_model.model.layers.47.self_attn.v_proj.bias": "model-00049-of-00084.safetensors", + "language_model.model.layers.47.self_attn.v_proj.weight": "model-00049-of-00084.safetensors", + "language_model.model.layers.48.input_layernorm.weight": "model-00051-of-00084.safetensors", + "language_model.model.layers.48.mlp.fc1.weight": "model-00051-of-00084.safetensors", + "language_model.model.layers.48.mlp.fc2.weight": "model-00051-of-00084.safetensors", + "language_model.model.layers.48.post_attention_layernorm.weight": "model-00051-of-00084.safetensors", + "language_model.model.layers.48.self_attn.k_proj.bias": "model-00050-of-00084.safetensors", + "language_model.model.layers.48.self_attn.k_proj.weight": "model-00050-of-00084.safetensors", + "language_model.model.layers.48.self_attn.o_proj.weight": "model-00050-of-00084.safetensors", + "language_model.model.layers.48.self_attn.q_proj.bias": "model-00050-of-00084.safetensors", + "language_model.model.layers.48.self_attn.q_proj.weight": "model-00050-of-00084.safetensors", + "language_model.model.layers.48.self_attn.v_proj.bias": "model-00050-of-00084.safetensors", + "language_model.model.layers.48.self_attn.v_proj.weight": "model-00050-of-00084.safetensors", + "language_model.model.layers.49.input_layernorm.weight": "model-00052-of-00084.safetensors", + "language_model.model.layers.49.mlp.fc1.weight": "model-00052-of-00084.safetensors", + "language_model.model.layers.49.mlp.fc2.weight": "model-00052-of-00084.safetensors", + "language_model.model.layers.49.post_attention_layernorm.weight": "model-00052-of-00084.safetensors", + "language_model.model.layers.49.self_attn.k_proj.bias": "model-00051-of-00084.safetensors", + "language_model.model.layers.49.self_attn.k_proj.weight": "model-00051-of-00084.safetensors", + "language_model.model.layers.49.self_attn.o_proj.weight": "model-00051-of-00084.safetensors", + "language_model.model.layers.49.self_attn.q_proj.bias": "model-00051-of-00084.safetensors", + "language_model.model.layers.49.self_attn.q_proj.weight": "model-00051-of-00084.safetensors", + "language_model.model.layers.49.self_attn.v_proj.bias": "model-00051-of-00084.safetensors", + "language_model.model.layers.49.self_attn.v_proj.weight": "model-00051-of-00084.safetensors", + "language_model.model.layers.5.input_layernorm.weight": "model-00008-of-00084.safetensors", + "language_model.model.layers.5.mlp.fc1.weight": "model-00008-of-00084.safetensors", + "language_model.model.layers.5.mlp.fc2.weight": "model-00008-of-00084.safetensors", + "language_model.model.layers.5.post_attention_layernorm.weight": "model-00008-of-00084.safetensors", + "language_model.model.layers.5.self_attn.k_proj.bias": "model-00007-of-00084.safetensors", + "language_model.model.layers.5.self_attn.k_proj.weight": "model-00007-of-00084.safetensors", + "language_model.model.layers.5.self_attn.o_proj.weight": "model-00007-of-00084.safetensors", + "language_model.model.layers.5.self_attn.q_proj.bias": "model-00007-of-00084.safetensors", + "language_model.model.layers.5.self_attn.q_proj.weight": "model-00007-of-00084.safetensors", + "language_model.model.layers.5.self_attn.v_proj.bias": "model-00007-of-00084.safetensors", + "language_model.model.layers.5.self_attn.v_proj.weight": "model-00007-of-00084.safetensors", + "language_model.model.layers.50.input_layernorm.weight": "model-00053-of-00084.safetensors", + "language_model.model.layers.50.mlp.fc1.weight": "model-00053-of-00084.safetensors", + "language_model.model.layers.50.mlp.fc2.weight": "model-00053-of-00084.safetensors", + "language_model.model.layers.50.post_attention_layernorm.weight": "model-00053-of-00084.safetensors", + "language_model.model.layers.50.self_attn.k_proj.bias": "model-00052-of-00084.safetensors", + "language_model.model.layers.50.self_attn.k_proj.weight": "model-00052-of-00084.safetensors", + "language_model.model.layers.50.self_attn.o_proj.weight": "model-00052-of-00084.safetensors", + "language_model.model.layers.50.self_attn.q_proj.bias": "model-00052-of-00084.safetensors", + "language_model.model.layers.50.self_attn.q_proj.weight": "model-00052-of-00084.safetensors", + "language_model.model.layers.50.self_attn.v_proj.bias": "model-00052-of-00084.safetensors", + "language_model.model.layers.50.self_attn.v_proj.weight": "model-00052-of-00084.safetensors", + "language_model.model.layers.51.input_layernorm.weight": "model-00054-of-00084.safetensors", + "language_model.model.layers.51.mlp.fc1.weight": "model-00054-of-00084.safetensors", + "language_model.model.layers.51.mlp.fc2.weight": "model-00054-of-00084.safetensors", + "language_model.model.layers.51.post_attention_layernorm.weight": "model-00054-of-00084.safetensors", + "language_model.model.layers.51.self_attn.k_proj.bias": "model-00053-of-00084.safetensors", + "language_model.model.layers.51.self_attn.k_proj.weight": "model-00053-of-00084.safetensors", + "language_model.model.layers.51.self_attn.o_proj.weight": "model-00053-of-00084.safetensors", + "language_model.model.layers.51.self_attn.q_proj.bias": "model-00053-of-00084.safetensors", + "language_model.model.layers.51.self_attn.q_proj.weight": "model-00053-of-00084.safetensors", + "language_model.model.layers.51.self_attn.v_proj.bias": "model-00053-of-00084.safetensors", + "language_model.model.layers.51.self_attn.v_proj.weight": "model-00053-of-00084.safetensors", + "language_model.model.layers.52.input_layernorm.weight": "model-00055-of-00084.safetensors", + "language_model.model.layers.52.mlp.fc1.weight": "model-00055-of-00084.safetensors", + "language_model.model.layers.52.mlp.fc2.weight": "model-00055-of-00084.safetensors", + "language_model.model.layers.52.post_attention_layernorm.weight": "model-00055-of-00084.safetensors", + "language_model.model.layers.52.self_attn.k_proj.bias": "model-00054-of-00084.safetensors", + "language_model.model.layers.52.self_attn.k_proj.weight": "model-00054-of-00084.safetensors", + "language_model.model.layers.52.self_attn.o_proj.weight": "model-00054-of-00084.safetensors", + "language_model.model.layers.52.self_attn.q_proj.bias": "model-00054-of-00084.safetensors", + "language_model.model.layers.52.self_attn.q_proj.weight": "model-00054-of-00084.safetensors", + "language_model.model.layers.52.self_attn.v_proj.bias": "model-00054-of-00084.safetensors", + "language_model.model.layers.52.self_attn.v_proj.weight": "model-00054-of-00084.safetensors", + "language_model.model.layers.53.input_layernorm.weight": "model-00056-of-00084.safetensors", + "language_model.model.layers.53.mlp.fc1.weight": "model-00056-of-00084.safetensors", + "language_model.model.layers.53.mlp.fc2.weight": "model-00056-of-00084.safetensors", + "language_model.model.layers.53.post_attention_layernorm.weight": "model-00056-of-00084.safetensors", + "language_model.model.layers.53.self_attn.k_proj.bias": "model-00055-of-00084.safetensors", + "language_model.model.layers.53.self_attn.k_proj.weight": "model-00055-of-00084.safetensors", + "language_model.model.layers.53.self_attn.o_proj.weight": "model-00055-of-00084.safetensors", + "language_model.model.layers.53.self_attn.q_proj.bias": "model-00055-of-00084.safetensors", + "language_model.model.layers.53.self_attn.q_proj.weight": "model-00055-of-00084.safetensors", + "language_model.model.layers.53.self_attn.v_proj.bias": "model-00055-of-00084.safetensors", + "language_model.model.layers.53.self_attn.v_proj.weight": "model-00055-of-00084.safetensors", + "language_model.model.layers.54.input_layernorm.weight": "model-00057-of-00084.safetensors", + "language_model.model.layers.54.mlp.fc1.weight": "model-00057-of-00084.safetensors", + "language_model.model.layers.54.mlp.fc2.weight": "model-00057-of-00084.safetensors", + "language_model.model.layers.54.post_attention_layernorm.weight": "model-00057-of-00084.safetensors", + "language_model.model.layers.54.self_attn.k_proj.bias": "model-00056-of-00084.safetensors", + "language_model.model.layers.54.self_attn.k_proj.weight": "model-00056-of-00084.safetensors", + "language_model.model.layers.54.self_attn.o_proj.weight": "model-00056-of-00084.safetensors", + "language_model.model.layers.54.self_attn.q_proj.bias": "model-00056-of-00084.safetensors", + "language_model.model.layers.54.self_attn.q_proj.weight": "model-00056-of-00084.safetensors", + "language_model.model.layers.54.self_attn.v_proj.bias": "model-00056-of-00084.safetensors", + "language_model.model.layers.54.self_attn.v_proj.weight": "model-00056-of-00084.safetensors", + "language_model.model.layers.55.input_layernorm.weight": "model-00058-of-00084.safetensors", + "language_model.model.layers.55.mlp.fc1.weight": "model-00058-of-00084.safetensors", + "language_model.model.layers.55.mlp.fc2.weight": "model-00058-of-00084.safetensors", + "language_model.model.layers.55.post_attention_layernorm.weight": "model-00058-of-00084.safetensors", + "language_model.model.layers.55.self_attn.k_proj.bias": "model-00057-of-00084.safetensors", + "language_model.model.layers.55.self_attn.k_proj.weight": "model-00057-of-00084.safetensors", + "language_model.model.layers.55.self_attn.o_proj.weight": "model-00057-of-00084.safetensors", + "language_model.model.layers.55.self_attn.q_proj.bias": "model-00057-of-00084.safetensors", + "language_model.model.layers.55.self_attn.q_proj.weight": "model-00057-of-00084.safetensors", + "language_model.model.layers.55.self_attn.v_proj.bias": "model-00057-of-00084.safetensors", + "language_model.model.layers.55.self_attn.v_proj.weight": "model-00057-of-00084.safetensors", + "language_model.model.layers.56.input_layernorm.weight": "model-00059-of-00084.safetensors", + "language_model.model.layers.56.mlp.fc1.weight": "model-00059-of-00084.safetensors", + "language_model.model.layers.56.mlp.fc2.weight": "model-00059-of-00084.safetensors", + "language_model.model.layers.56.post_attention_layernorm.weight": "model-00059-of-00084.safetensors", + "language_model.model.layers.56.self_attn.k_proj.bias": "model-00058-of-00084.safetensors", + "language_model.model.layers.56.self_attn.k_proj.weight": "model-00058-of-00084.safetensors", + "language_model.model.layers.56.self_attn.o_proj.weight": "model-00058-of-00084.safetensors", + "language_model.model.layers.56.self_attn.q_proj.bias": "model-00058-of-00084.safetensors", + "language_model.model.layers.56.self_attn.q_proj.weight": "model-00058-of-00084.safetensors", + "language_model.model.layers.56.self_attn.v_proj.bias": "model-00058-of-00084.safetensors", + "language_model.model.layers.56.self_attn.v_proj.weight": "model-00058-of-00084.safetensors", + "language_model.model.layers.57.input_layernorm.weight": "model-00060-of-00084.safetensors", + "language_model.model.layers.57.mlp.fc1.weight": "model-00060-of-00084.safetensors", + "language_model.model.layers.57.mlp.fc2.weight": "model-00060-of-00084.safetensors", + "language_model.model.layers.57.post_attention_layernorm.weight": "model-00060-of-00084.safetensors", + "language_model.model.layers.57.self_attn.k_proj.bias": "model-00059-of-00084.safetensors", + "language_model.model.layers.57.self_attn.k_proj.weight": "model-00059-of-00084.safetensors", + "language_model.model.layers.57.self_attn.o_proj.weight": "model-00059-of-00084.safetensors", + "language_model.model.layers.57.self_attn.q_proj.bias": "model-00059-of-00084.safetensors", + "language_model.model.layers.57.self_attn.q_proj.weight": "model-00059-of-00084.safetensors", + "language_model.model.layers.57.self_attn.v_proj.bias": "model-00059-of-00084.safetensors", + "language_model.model.layers.57.self_attn.v_proj.weight": "model-00059-of-00084.safetensors", + "language_model.model.layers.58.input_layernorm.weight": "model-00061-of-00084.safetensors", + "language_model.model.layers.58.mlp.fc1.weight": "model-00061-of-00084.safetensors", + "language_model.model.layers.58.mlp.fc2.weight": "model-00061-of-00084.safetensors", + "language_model.model.layers.58.post_attention_layernorm.weight": "model-00061-of-00084.safetensors", + "language_model.model.layers.58.self_attn.k_proj.bias": "model-00060-of-00084.safetensors", + "language_model.model.layers.58.self_attn.k_proj.weight": "model-00060-of-00084.safetensors", + "language_model.model.layers.58.self_attn.o_proj.weight": "model-00060-of-00084.safetensors", + "language_model.model.layers.58.self_attn.q_proj.bias": "model-00060-of-00084.safetensors", + "language_model.model.layers.58.self_attn.q_proj.weight": "model-00060-of-00084.safetensors", + "language_model.model.layers.58.self_attn.v_proj.bias": "model-00060-of-00084.safetensors", + "language_model.model.layers.58.self_attn.v_proj.weight": "model-00060-of-00084.safetensors", + "language_model.model.layers.59.input_layernorm.weight": "model-00062-of-00084.safetensors", + "language_model.model.layers.59.mlp.fc1.weight": "model-00062-of-00084.safetensors", + "language_model.model.layers.59.mlp.fc2.weight": "model-00062-of-00084.safetensors", + "language_model.model.layers.59.post_attention_layernorm.weight": "model-00062-of-00084.safetensors", + "language_model.model.layers.59.self_attn.k_proj.bias": "model-00061-of-00084.safetensors", + "language_model.model.layers.59.self_attn.k_proj.weight": "model-00061-of-00084.safetensors", + "language_model.model.layers.59.self_attn.o_proj.weight": "model-00061-of-00084.safetensors", + "language_model.model.layers.59.self_attn.q_proj.bias": "model-00061-of-00084.safetensors", + "language_model.model.layers.59.self_attn.q_proj.weight": "model-00061-of-00084.safetensors", + "language_model.model.layers.59.self_attn.v_proj.bias": "model-00061-of-00084.safetensors", + "language_model.model.layers.59.self_attn.v_proj.weight": "model-00061-of-00084.safetensors", + "language_model.model.layers.6.input_layernorm.weight": "model-00009-of-00084.safetensors", + "language_model.model.layers.6.mlp.fc1.weight": "model-00009-of-00084.safetensors", + "language_model.model.layers.6.mlp.fc2.weight": "model-00009-of-00084.safetensors", + "language_model.model.layers.6.post_attention_layernorm.weight": "model-00009-of-00084.safetensors", + "language_model.model.layers.6.self_attn.k_proj.bias": "model-00008-of-00084.safetensors", + "language_model.model.layers.6.self_attn.k_proj.weight": "model-00008-of-00084.safetensors", + "language_model.model.layers.6.self_attn.o_proj.weight": "model-00008-of-00084.safetensors", + "language_model.model.layers.6.self_attn.q_proj.bias": "model-00008-of-00084.safetensors", + "language_model.model.layers.6.self_attn.q_proj.weight": "model-00008-of-00084.safetensors", + "language_model.model.layers.6.self_attn.v_proj.bias": "model-00008-of-00084.safetensors", + "language_model.model.layers.6.self_attn.v_proj.weight": "model-00008-of-00084.safetensors", + "language_model.model.layers.60.input_layernorm.weight": "model-00063-of-00084.safetensors", + "language_model.model.layers.60.mlp.fc1.weight": "model-00063-of-00084.safetensors", + "language_model.model.layers.60.mlp.fc2.weight": "model-00063-of-00084.safetensors", + "language_model.model.layers.60.post_attention_layernorm.weight": "model-00063-of-00084.safetensors", + "language_model.model.layers.60.self_attn.k_proj.bias": "model-00062-of-00084.safetensors", + "language_model.model.layers.60.self_attn.k_proj.weight": "model-00062-of-00084.safetensors", + "language_model.model.layers.60.self_attn.o_proj.weight": "model-00062-of-00084.safetensors", + "language_model.model.layers.60.self_attn.q_proj.bias": "model-00062-of-00084.safetensors", + "language_model.model.layers.60.self_attn.q_proj.weight": "model-00062-of-00084.safetensors", + "language_model.model.layers.60.self_attn.v_proj.bias": "model-00062-of-00084.safetensors", + "language_model.model.layers.60.self_attn.v_proj.weight": "model-00062-of-00084.safetensors", + "language_model.model.layers.61.input_layernorm.weight": "model-00064-of-00084.safetensors", + "language_model.model.layers.61.mlp.fc1.weight": "model-00064-of-00084.safetensors", + "language_model.model.layers.61.mlp.fc2.weight": "model-00064-of-00084.safetensors", + "language_model.model.layers.61.post_attention_layernorm.weight": "model-00064-of-00084.safetensors", + "language_model.model.layers.61.self_attn.k_proj.bias": "model-00063-of-00084.safetensors", + "language_model.model.layers.61.self_attn.k_proj.weight": "model-00063-of-00084.safetensors", + "language_model.model.layers.61.self_attn.o_proj.weight": "model-00063-of-00084.safetensors", + "language_model.model.layers.61.self_attn.q_proj.bias": "model-00063-of-00084.safetensors", + "language_model.model.layers.61.self_attn.q_proj.weight": "model-00063-of-00084.safetensors", + "language_model.model.layers.61.self_attn.v_proj.bias": "model-00063-of-00084.safetensors", + "language_model.model.layers.61.self_attn.v_proj.weight": "model-00063-of-00084.safetensors", + "language_model.model.layers.62.input_layernorm.weight": "model-00065-of-00084.safetensors", + "language_model.model.layers.62.mlp.fc1.weight": "model-00065-of-00084.safetensors", + "language_model.model.layers.62.mlp.fc2.weight": "model-00065-of-00084.safetensors", + "language_model.model.layers.62.post_attention_layernorm.weight": "model-00065-of-00084.safetensors", + "language_model.model.layers.62.self_attn.k_proj.bias": "model-00064-of-00084.safetensors", + "language_model.model.layers.62.self_attn.k_proj.weight": "model-00064-of-00084.safetensors", + "language_model.model.layers.62.self_attn.o_proj.weight": "model-00064-of-00084.safetensors", + "language_model.model.layers.62.self_attn.q_proj.bias": "model-00064-of-00084.safetensors", + "language_model.model.layers.62.self_attn.q_proj.weight": "model-00064-of-00084.safetensors", + "language_model.model.layers.62.self_attn.v_proj.bias": "model-00064-of-00084.safetensors", + "language_model.model.layers.62.self_attn.v_proj.weight": "model-00064-of-00084.safetensors", + "language_model.model.layers.63.input_layernorm.weight": "model-00066-of-00084.safetensors", + "language_model.model.layers.63.mlp.fc1.weight": "model-00066-of-00084.safetensors", + "language_model.model.layers.63.mlp.fc2.weight": "model-00066-of-00084.safetensors", + "language_model.model.layers.63.post_attention_layernorm.weight": "model-00066-of-00084.safetensors", + "language_model.model.layers.63.self_attn.k_proj.bias": "model-00065-of-00084.safetensors", + "language_model.model.layers.63.self_attn.k_proj.weight": "model-00065-of-00084.safetensors", + "language_model.model.layers.63.self_attn.o_proj.weight": "model-00065-of-00084.safetensors", + "language_model.model.layers.63.self_attn.q_proj.bias": "model-00065-of-00084.safetensors", + "language_model.model.layers.63.self_attn.q_proj.weight": "model-00065-of-00084.safetensors", + "language_model.model.layers.63.self_attn.v_proj.bias": "model-00065-of-00084.safetensors", + "language_model.model.layers.63.self_attn.v_proj.weight": "model-00065-of-00084.safetensors", + "language_model.model.layers.64.input_layernorm.weight": "model-00067-of-00084.safetensors", + "language_model.model.layers.64.mlp.fc1.weight": "model-00067-of-00084.safetensors", + "language_model.model.layers.64.mlp.fc2.weight": "model-00067-of-00084.safetensors", + "language_model.model.layers.64.post_attention_layernorm.weight": "model-00067-of-00084.safetensors", + "language_model.model.layers.64.self_attn.k_proj.bias": "model-00066-of-00084.safetensors", + "language_model.model.layers.64.self_attn.k_proj.weight": "model-00066-of-00084.safetensors", + "language_model.model.layers.64.self_attn.o_proj.weight": "model-00066-of-00084.safetensors", + "language_model.model.layers.64.self_attn.q_proj.bias": "model-00066-of-00084.safetensors", + "language_model.model.layers.64.self_attn.q_proj.weight": "model-00066-of-00084.safetensors", + "language_model.model.layers.64.self_attn.v_proj.bias": "model-00066-of-00084.safetensors", + "language_model.model.layers.64.self_attn.v_proj.weight": "model-00066-of-00084.safetensors", + "language_model.model.layers.65.input_layernorm.weight": "model-00068-of-00084.safetensors", + "language_model.model.layers.65.mlp.fc1.weight": "model-00068-of-00084.safetensors", + "language_model.model.layers.65.mlp.fc2.weight": "model-00068-of-00084.safetensors", + "language_model.model.layers.65.post_attention_layernorm.weight": "model-00068-of-00084.safetensors", + "language_model.model.layers.65.self_attn.k_proj.bias": "model-00067-of-00084.safetensors", + "language_model.model.layers.65.self_attn.k_proj.weight": "model-00067-of-00084.safetensors", + "language_model.model.layers.65.self_attn.o_proj.weight": "model-00067-of-00084.safetensors", + "language_model.model.layers.65.self_attn.q_proj.bias": "model-00067-of-00084.safetensors", + "language_model.model.layers.65.self_attn.q_proj.weight": "model-00067-of-00084.safetensors", + "language_model.model.layers.65.self_attn.v_proj.bias": "model-00067-of-00084.safetensors", + "language_model.model.layers.65.self_attn.v_proj.weight": "model-00067-of-00084.safetensors", + "language_model.model.layers.66.input_layernorm.weight": "model-00069-of-00084.safetensors", + "language_model.model.layers.66.mlp.fc1.weight": "model-00069-of-00084.safetensors", + "language_model.model.layers.66.mlp.fc2.weight": "model-00069-of-00084.safetensors", + "language_model.model.layers.66.post_attention_layernorm.weight": "model-00069-of-00084.safetensors", + "language_model.model.layers.66.self_attn.k_proj.bias": "model-00068-of-00084.safetensors", + "language_model.model.layers.66.self_attn.k_proj.weight": "model-00068-of-00084.safetensors", + "language_model.model.layers.66.self_attn.o_proj.weight": "model-00068-of-00084.safetensors", + "language_model.model.layers.66.self_attn.q_proj.bias": "model-00068-of-00084.safetensors", + "language_model.model.layers.66.self_attn.q_proj.weight": "model-00068-of-00084.safetensors", + "language_model.model.layers.66.self_attn.v_proj.bias": "model-00068-of-00084.safetensors", + "language_model.model.layers.66.self_attn.v_proj.weight": "model-00068-of-00084.safetensors", + "language_model.model.layers.67.input_layernorm.weight": "model-00070-of-00084.safetensors", + "language_model.model.layers.67.mlp.fc1.weight": "model-00070-of-00084.safetensors", + "language_model.model.layers.67.mlp.fc2.weight": "model-00070-of-00084.safetensors", + "language_model.model.layers.67.post_attention_layernorm.weight": "model-00070-of-00084.safetensors", + "language_model.model.layers.67.self_attn.k_proj.bias": "model-00069-of-00084.safetensors", + "language_model.model.layers.67.self_attn.k_proj.weight": "model-00069-of-00084.safetensors", + "language_model.model.layers.67.self_attn.o_proj.weight": "model-00069-of-00084.safetensors", + "language_model.model.layers.67.self_attn.q_proj.bias": "model-00069-of-00084.safetensors", + "language_model.model.layers.67.self_attn.q_proj.weight": "model-00069-of-00084.safetensors", + "language_model.model.layers.67.self_attn.v_proj.bias": "model-00069-of-00084.safetensors", + "language_model.model.layers.67.self_attn.v_proj.weight": "model-00069-of-00084.safetensors", + "language_model.model.layers.68.input_layernorm.weight": "model-00071-of-00084.safetensors", + "language_model.model.layers.68.mlp.fc1.weight": "model-00071-of-00084.safetensors", + "language_model.model.layers.68.mlp.fc2.weight": "model-00071-of-00084.safetensors", + "language_model.model.layers.68.post_attention_layernorm.weight": "model-00071-of-00084.safetensors", + "language_model.model.layers.68.self_attn.k_proj.bias": "model-00070-of-00084.safetensors", + "language_model.model.layers.68.self_attn.k_proj.weight": "model-00070-of-00084.safetensors", + "language_model.model.layers.68.self_attn.o_proj.weight": "model-00070-of-00084.safetensors", + "language_model.model.layers.68.self_attn.q_proj.bias": "model-00070-of-00084.safetensors", + "language_model.model.layers.68.self_attn.q_proj.weight": "model-00070-of-00084.safetensors", + "language_model.model.layers.68.self_attn.v_proj.bias": "model-00070-of-00084.safetensors", + "language_model.model.layers.68.self_attn.v_proj.weight": "model-00070-of-00084.safetensors", + "language_model.model.layers.69.input_layernorm.weight": "model-00072-of-00084.safetensors", + "language_model.model.layers.69.mlp.fc1.weight": "model-00072-of-00084.safetensors", + "language_model.model.layers.69.mlp.fc2.weight": "model-00072-of-00084.safetensors", + "language_model.model.layers.69.post_attention_layernorm.weight": "model-00072-of-00084.safetensors", + "language_model.model.layers.69.self_attn.k_proj.bias": "model-00071-of-00084.safetensors", + "language_model.model.layers.69.self_attn.k_proj.weight": "model-00071-of-00084.safetensors", + "language_model.model.layers.69.self_attn.o_proj.weight": "model-00071-of-00084.safetensors", + "language_model.model.layers.69.self_attn.q_proj.bias": "model-00071-of-00084.safetensors", + "language_model.model.layers.69.self_attn.q_proj.weight": "model-00071-of-00084.safetensors", + "language_model.model.layers.69.self_attn.v_proj.bias": "model-00071-of-00084.safetensors", + "language_model.model.layers.69.self_attn.v_proj.weight": "model-00071-of-00084.safetensors", + "language_model.model.layers.7.input_layernorm.weight": "model-00010-of-00084.safetensors", + "language_model.model.layers.7.mlp.fc1.weight": "model-00010-of-00084.safetensors", + "language_model.model.layers.7.mlp.fc2.weight": "model-00010-of-00084.safetensors", + "language_model.model.layers.7.post_attention_layernorm.weight": "model-00010-of-00084.safetensors", + "language_model.model.layers.7.self_attn.k_proj.bias": "model-00009-of-00084.safetensors", + "language_model.model.layers.7.self_attn.k_proj.weight": "model-00009-of-00084.safetensors", + "language_model.model.layers.7.self_attn.o_proj.weight": "model-00009-of-00084.safetensors", + "language_model.model.layers.7.self_attn.q_proj.bias": "model-00009-of-00084.safetensors", + "language_model.model.layers.7.self_attn.q_proj.weight": "model-00009-of-00084.safetensors", + "language_model.model.layers.7.self_attn.v_proj.bias": "model-00009-of-00084.safetensors", + "language_model.model.layers.7.self_attn.v_proj.weight": "model-00009-of-00084.safetensors", + "language_model.model.layers.70.input_layernorm.weight": "model-00073-of-00084.safetensors", + "language_model.model.layers.70.mlp.fc1.weight": "model-00073-of-00084.safetensors", + "language_model.model.layers.70.mlp.fc2.weight": "model-00073-of-00084.safetensors", + "language_model.model.layers.70.post_attention_layernorm.weight": "model-00073-of-00084.safetensors", + "language_model.model.layers.70.self_attn.k_proj.bias": "model-00072-of-00084.safetensors", + "language_model.model.layers.70.self_attn.k_proj.weight": "model-00072-of-00084.safetensors", + "language_model.model.layers.70.self_attn.o_proj.weight": "model-00072-of-00084.safetensors", + "language_model.model.layers.70.self_attn.q_proj.bias": "model-00072-of-00084.safetensors", + "language_model.model.layers.70.self_attn.q_proj.weight": "model-00072-of-00084.safetensors", + "language_model.model.layers.70.self_attn.v_proj.bias": "model-00072-of-00084.safetensors", + "language_model.model.layers.70.self_attn.v_proj.weight": "model-00072-of-00084.safetensors", + "language_model.model.layers.71.input_layernorm.weight": "model-00074-of-00084.safetensors", + "language_model.model.layers.71.mlp.fc1.weight": "model-00074-of-00084.safetensors", + "language_model.model.layers.71.mlp.fc2.weight": "model-00074-of-00084.safetensors", + "language_model.model.layers.71.post_attention_layernorm.weight": "model-00074-of-00084.safetensors", + "language_model.model.layers.71.self_attn.k_proj.bias": "model-00073-of-00084.safetensors", + "language_model.model.layers.71.self_attn.k_proj.weight": "model-00073-of-00084.safetensors", + "language_model.model.layers.71.self_attn.o_proj.weight": "model-00073-of-00084.safetensors", + "language_model.model.layers.71.self_attn.q_proj.bias": "model-00073-of-00084.safetensors", + "language_model.model.layers.71.self_attn.q_proj.weight": "model-00073-of-00084.safetensors", + "language_model.model.layers.71.self_attn.v_proj.bias": "model-00073-of-00084.safetensors", + "language_model.model.layers.71.self_attn.v_proj.weight": "model-00073-of-00084.safetensors", + "language_model.model.layers.72.input_layernorm.weight": "model-00075-of-00084.safetensors", + "language_model.model.layers.72.mlp.fc1.weight": "model-00075-of-00084.safetensors", + "language_model.model.layers.72.mlp.fc2.weight": "model-00075-of-00084.safetensors", + "language_model.model.layers.72.post_attention_layernorm.weight": "model-00075-of-00084.safetensors", + "language_model.model.layers.72.self_attn.k_proj.bias": "model-00074-of-00084.safetensors", + "language_model.model.layers.72.self_attn.k_proj.weight": "model-00074-of-00084.safetensors", + "language_model.model.layers.72.self_attn.o_proj.weight": "model-00074-of-00084.safetensors", + "language_model.model.layers.72.self_attn.q_proj.bias": "model-00074-of-00084.safetensors", + "language_model.model.layers.72.self_attn.q_proj.weight": "model-00074-of-00084.safetensors", + "language_model.model.layers.72.self_attn.v_proj.bias": "model-00074-of-00084.safetensors", + "language_model.model.layers.72.self_attn.v_proj.weight": "model-00074-of-00084.safetensors", + "language_model.model.layers.73.input_layernorm.weight": "model-00076-of-00084.safetensors", + "language_model.model.layers.73.mlp.fc1.weight": "model-00076-of-00084.safetensors", + "language_model.model.layers.73.mlp.fc2.weight": "model-00076-of-00084.safetensors", + "language_model.model.layers.73.post_attention_layernorm.weight": "model-00076-of-00084.safetensors", + "language_model.model.layers.73.self_attn.k_proj.bias": "model-00075-of-00084.safetensors", + "language_model.model.layers.73.self_attn.k_proj.weight": "model-00075-of-00084.safetensors", + "language_model.model.layers.73.self_attn.o_proj.weight": "model-00075-of-00084.safetensors", + "language_model.model.layers.73.self_attn.q_proj.bias": "model-00075-of-00084.safetensors", + "language_model.model.layers.73.self_attn.q_proj.weight": "model-00075-of-00084.safetensors", + "language_model.model.layers.73.self_attn.v_proj.bias": "model-00075-of-00084.safetensors", + "language_model.model.layers.73.self_attn.v_proj.weight": "model-00075-of-00084.safetensors", + "language_model.model.layers.74.input_layernorm.weight": "model-00077-of-00084.safetensors", + "language_model.model.layers.74.mlp.fc1.weight": "model-00077-of-00084.safetensors", + "language_model.model.layers.74.mlp.fc2.weight": "model-00077-of-00084.safetensors", + "language_model.model.layers.74.post_attention_layernorm.weight": "model-00077-of-00084.safetensors", + "language_model.model.layers.74.self_attn.k_proj.bias": "model-00076-of-00084.safetensors", + "language_model.model.layers.74.self_attn.k_proj.weight": "model-00076-of-00084.safetensors", + "language_model.model.layers.74.self_attn.o_proj.weight": "model-00076-of-00084.safetensors", + "language_model.model.layers.74.self_attn.q_proj.bias": "model-00076-of-00084.safetensors", + "language_model.model.layers.74.self_attn.q_proj.weight": "model-00076-of-00084.safetensors", + "language_model.model.layers.74.self_attn.v_proj.bias": "model-00076-of-00084.safetensors", + "language_model.model.layers.74.self_attn.v_proj.weight": "model-00076-of-00084.safetensors", + "language_model.model.layers.75.input_layernorm.weight": "model-00078-of-00084.safetensors", + "language_model.model.layers.75.mlp.fc1.weight": "model-00078-of-00084.safetensors", + "language_model.model.layers.75.mlp.fc2.weight": "model-00078-of-00084.safetensors", + "language_model.model.layers.75.post_attention_layernorm.weight": "model-00078-of-00084.safetensors", + "language_model.model.layers.75.self_attn.k_proj.bias": "model-00077-of-00084.safetensors", + "language_model.model.layers.75.self_attn.k_proj.weight": "model-00077-of-00084.safetensors", + "language_model.model.layers.75.self_attn.o_proj.weight": "model-00077-of-00084.safetensors", + "language_model.model.layers.75.self_attn.q_proj.bias": "model-00077-of-00084.safetensors", + "language_model.model.layers.75.self_attn.q_proj.weight": "model-00077-of-00084.safetensors", + "language_model.model.layers.75.self_attn.v_proj.bias": "model-00077-of-00084.safetensors", + "language_model.model.layers.75.self_attn.v_proj.weight": "model-00077-of-00084.safetensors", + "language_model.model.layers.76.input_layernorm.weight": "model-00079-of-00084.safetensors", + "language_model.model.layers.76.mlp.fc1.weight": "model-00079-of-00084.safetensors", + "language_model.model.layers.76.mlp.fc2.weight": "model-00079-of-00084.safetensors", + "language_model.model.layers.76.post_attention_layernorm.weight": "model-00079-of-00084.safetensors", + "language_model.model.layers.76.self_attn.k_proj.bias": "model-00078-of-00084.safetensors", + "language_model.model.layers.76.self_attn.k_proj.weight": "model-00078-of-00084.safetensors", + "language_model.model.layers.76.self_attn.o_proj.weight": "model-00078-of-00084.safetensors", + "language_model.model.layers.76.self_attn.q_proj.bias": "model-00078-of-00084.safetensors", + "language_model.model.layers.76.self_attn.q_proj.weight": "model-00078-of-00084.safetensors", + "language_model.model.layers.76.self_attn.v_proj.bias": "model-00078-of-00084.safetensors", + "language_model.model.layers.76.self_attn.v_proj.weight": "model-00078-of-00084.safetensors", + "language_model.model.layers.77.input_layernorm.weight": "model-00080-of-00084.safetensors", + "language_model.model.layers.77.mlp.fc1.weight": "model-00080-of-00084.safetensors", + "language_model.model.layers.77.mlp.fc2.weight": "model-00080-of-00084.safetensors", + "language_model.model.layers.77.post_attention_layernorm.weight": "model-00080-of-00084.safetensors", + "language_model.model.layers.77.self_attn.k_proj.bias": "model-00079-of-00084.safetensors", + "language_model.model.layers.77.self_attn.k_proj.weight": "model-00079-of-00084.safetensors", + "language_model.model.layers.77.self_attn.o_proj.weight": "model-00079-of-00084.safetensors", + "language_model.model.layers.77.self_attn.q_proj.bias": "model-00079-of-00084.safetensors", + "language_model.model.layers.77.self_attn.q_proj.weight": "model-00079-of-00084.safetensors", + "language_model.model.layers.77.self_attn.v_proj.bias": "model-00079-of-00084.safetensors", + "language_model.model.layers.77.self_attn.v_proj.weight": "model-00079-of-00084.safetensors", + "language_model.model.layers.78.input_layernorm.weight": "model-00081-of-00084.safetensors", + "language_model.model.layers.78.mlp.fc1.weight": "model-00081-of-00084.safetensors", + "language_model.model.layers.78.mlp.fc2.weight": "model-00081-of-00084.safetensors", + "language_model.model.layers.78.post_attention_layernorm.weight": "model-00081-of-00084.safetensors", + "language_model.model.layers.78.self_attn.k_proj.bias": "model-00080-of-00084.safetensors", + "language_model.model.layers.78.self_attn.k_proj.weight": "model-00080-of-00084.safetensors", + "language_model.model.layers.78.self_attn.o_proj.weight": "model-00080-of-00084.safetensors", + "language_model.model.layers.78.self_attn.q_proj.bias": "model-00080-of-00084.safetensors", + "language_model.model.layers.78.self_attn.q_proj.weight": "model-00080-of-00084.safetensors", + "language_model.model.layers.78.self_attn.v_proj.bias": "model-00080-of-00084.safetensors", + "language_model.model.layers.78.self_attn.v_proj.weight": "model-00080-of-00084.safetensors", + "language_model.model.layers.79.input_layernorm.weight": "model-00082-of-00084.safetensors", + "language_model.model.layers.79.mlp.fc1.weight": "model-00082-of-00084.safetensors", + "language_model.model.layers.79.mlp.fc2.weight": "model-00082-of-00084.safetensors", + "language_model.model.layers.79.post_attention_layernorm.weight": "model-00082-of-00084.safetensors", + "language_model.model.layers.79.self_attn.k_proj.bias": "model-00081-of-00084.safetensors", + "language_model.model.layers.79.self_attn.k_proj.weight": "model-00081-of-00084.safetensors", + "language_model.model.layers.79.self_attn.o_proj.weight": "model-00081-of-00084.safetensors", + "language_model.model.layers.79.self_attn.q_proj.bias": "model-00081-of-00084.safetensors", + "language_model.model.layers.79.self_attn.q_proj.weight": "model-00081-of-00084.safetensors", + "language_model.model.layers.79.self_attn.v_proj.bias": "model-00081-of-00084.safetensors", + "language_model.model.layers.79.self_attn.v_proj.weight": "model-00081-of-00084.safetensors", + "language_model.model.layers.8.input_layernorm.weight": "model-00011-of-00084.safetensors", + "language_model.model.layers.8.mlp.fc1.weight": "model-00011-of-00084.safetensors", + "language_model.model.layers.8.mlp.fc2.weight": "model-00011-of-00084.safetensors", + "language_model.model.layers.8.post_attention_layernorm.weight": "model-00011-of-00084.safetensors", + "language_model.model.layers.8.self_attn.k_proj.bias": "model-00010-of-00084.safetensors", + "language_model.model.layers.8.self_attn.k_proj.weight": "model-00010-of-00084.safetensors", + "language_model.model.layers.8.self_attn.o_proj.weight": "model-00010-of-00084.safetensors", + "language_model.model.layers.8.self_attn.q_proj.bias": "model-00010-of-00084.safetensors", + "language_model.model.layers.8.self_attn.q_proj.weight": "model-00010-of-00084.safetensors", + "language_model.model.layers.8.self_attn.v_proj.bias": "model-00010-of-00084.safetensors", + "language_model.model.layers.8.self_attn.v_proj.weight": "model-00010-of-00084.safetensors", + "language_model.model.layers.9.input_layernorm.weight": "model-00012-of-00084.safetensors", + "language_model.model.layers.9.mlp.fc1.weight": "model-00012-of-00084.safetensors", + "language_model.model.layers.9.mlp.fc2.weight": "model-00012-of-00084.safetensors", + "language_model.model.layers.9.post_attention_layernorm.weight": "model-00012-of-00084.safetensors", + "language_model.model.layers.9.self_attn.k_proj.bias": "model-00011-of-00084.safetensors", + "language_model.model.layers.9.self_attn.k_proj.weight": "model-00011-of-00084.safetensors", + "language_model.model.layers.9.self_attn.o_proj.weight": "model-00011-of-00084.safetensors", + "language_model.model.layers.9.self_attn.q_proj.bias": "model-00011-of-00084.safetensors", + "language_model.model.layers.9.self_attn.q_proj.weight": "model-00011-of-00084.safetensors", + "language_model.model.layers.9.self_attn.v_proj.bias": "model-00011-of-00084.safetensors", + "language_model.model.layers.9.self_attn.v_proj.weight": "model-00011-of-00084.safetensors", + "language_model.model.norm.weight": "model-00082-of-00084.safetensors", + "vision_tower.vision_model.embeddings.class_embedding": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.pre_layrnorm.bias": "model-00001-of-00084.safetensors", + "vision_tower.vision_model.pre_layrnorm.weight": "model-00001-of-00084.safetensors" + } +}