[WIP] Upload folder using huggingface_hub (multi-commit 776e029ac2e171ec92097c011f9aab9f738e101019578fcc0ccecd1b3703eda1)

LICENSE

@@ -1,176 +0,0 @@
-

-                                 Apache License
-                           Version 2.0, January 2004
-                        http://www.apache.org/licenses/
-
-   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
-
-   1. Definitions.
-
-      "License" shall mean the terms and conditions for use, reproduction,
-      and distribution as defined by Sections 1 through 9 of this document.
-
-      "Licensor" shall mean the copyright owner or entity authorized by
-      the copyright owner that is granting the License.
-
-      "Legal Entity" shall mean the union of the acting entity and all
-      other entities that control, are controlled by, or are under common
-      control with that entity. For the purposes of this definition,
-      "control" means (i) the power, direct or indirect, to cause the
-      direction or management of such entity, whether by contract or
-      otherwise, or (ii) ownership of fifty percent (50%) or more of the
-      outstanding shares, or (iii) beneficial ownership of such entity.
-
-      "You" (or "Your") shall mean an individual or Legal Entity
-      exercising permissions granted by this License.
-
-      "Source" form shall mean the preferred form for making modifications,
-      including but not limited to software source code, documentation
-      source, and configuration files.
-
-      "Object" form shall mean any form resulting from mechanical
-      transformation or translation of a Source form, including but
-      not limited to compiled object code, generated documentation,
-      and conversions to other media types.
-
-      "Work" shall mean the work of authorship, whether in Source or
-      Object form, made available under the License, as indicated by a
-      copyright notice that is included in or attached to the work
-      (an example is provided in the Appendix below).
-
-      "Derivative Works" shall mean any work, whether in Source or Object
-      form, that is based on (or derived from) the Work and for which the
-      editorial revisions, annotations, elaborations, or other modifications
-      represent, as a whole, an original work of authorship. For the purposes
-      of this License, Derivative Works shall not include works that remain
-      separable from, or merely link (or bind by name) to the interfaces of,
-      the Work and Derivative Works thereof.
-
-      "Contribution" shall mean any work of authorship, including
-      the original version of the Work and any modifications or additions
-      to that Work or Derivative Works thereof, that is intentionally
-      submitted to Licensor for inclusion in the Work by the copyright owner
-      or by an individual or Legal Entity authorized to submit on behalf of
-      the copyright owner. For the purposes of this definition, "submitted"
-      means any form of electronic, verbal, or written communication sent
-      to the Licensor or its representatives, including but not limited to
-      communication on electronic mailing lists, source code control systems,
-      and issue tracking systems that are managed by, or on behalf of, the
-      Licensor for the purpose of discussing and improving the Work, but
-      excluding communication that is conspicuously marked or otherwise
-      designated in writing by the copyright owner as "Not a Contribution."
-
-      "Contributor" shall mean Licensor and any individual or Legal Entity
-      on behalf of whom a Contribution has been received by Licensor and
-      subsequently incorporated within the Work.
-
-   2. Grant of Copyright License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      copyright license to reproduce, prepare Derivative Works of,
-      publicly display, publicly perform, sublicense, and distribute the
-      Work and such Derivative Works in Source or Object form.
-
-   3. Grant of Patent License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      (except as stated in this section) patent license to make, have made,
-      use, offer to sell, sell, import, and otherwise transfer the Work,
-      where such license applies only to those patent claims licensable
-      by such Contributor that are necessarily infringed by their
-      Contribution(s) alone or by combination of their Contribution(s)
-      with the Work to which such Contribution(s) was submitted. If You
-      institute patent litigation against any entity (including a
-      cross-claim or counterclaim in a lawsuit) alleging that the Work
-      or a Contribution incorporated within the Work constitutes direct
-      or contributory patent infringement, then any patent licenses
-      granted to You under this License for that Work shall terminate
-      as of the date such litigation is filed.
-
-   4. Redistribution. You may reproduce and distribute copies of the
-      Work or Derivative Works thereof in any medium, with or without
-      modifications, and in Source or Object form, provided that You
-      meet the following conditions:
-
-      (a) You must give any other recipients of the Work or
-          Derivative Works a copy of this License; and
-
-      (b) You must cause any modified files to carry prominent notices
-          stating that You changed the files; and
-
-      (c) You must retain, in the Source form of any Derivative Works
-          that You distribute, all copyright, patent, trademark, and
-          attribution notices from the Source form of the Work,
-          excluding those notices that do not pertain to any part of
-          the Derivative Works; and
-
-      (d) If the Work includes a "NOTICE" text file as part of its
-          distribution, then any Derivative Works that You distribute must
-          include a readable copy of the attribution notices contained
-          within such NOTICE file, excluding those notices that do not
-          pertain to any part of the Derivative Works, in at least one
-          of the following places: within a NOTICE text file distributed
-          as part of the Derivative Works; within the Source form or
-          documentation, if provided along with the Derivative Works; or,
-          within a display generated by the Derivative Works, if and
-          wherever such third-party notices normally appear. The contents
-          of the NOTICE file are for informational purposes only and
-          do not modify the License. You may add Your own attribution
-          notices within Derivative Works that You distribute, alongside
-          or as an addendum to the NOTICE text from the Work, provided
-          that such additional attribution notices cannot be construed
-          as modifying the License.
-
-      You may add Your own copyright statement to Your modifications and
-      may provide additional or different license terms and conditions
-      for use, reproduction, or distribution of Your modifications, or
-      for any such Derivative Works as a whole, provided Your use,
-      reproduction, and distribution of the Work otherwise complies with
-      the conditions stated in this License.
-
-   5. Submission of Contributions. Unless You explicitly state otherwise,
-      any Contribution intentionally submitted for inclusion in the Work
-      by You to the Licensor shall be under the terms and conditions of
-      this License, without any additional terms or conditions.
-      Notwithstanding the above, nothing herein shall supersede or modify
-      the terms of any separate license agreement you may have executed
-      with Licensor regarding such Contributions.
-
-   6. Trademarks. This License does not grant permission to use the trade
-      names, trademarks, service marks, or product names of the Licensor,
-      except as required for reasonable and customary use in describing the
-      origin of the Work and reproducing the content of the NOTICE file.
-
-   7. Disclaimer of Warranty. Unless required by applicable law or
-      agreed to in writing, Licensor provides the Work (and each
-      Contributor provides its Contributions) on an "AS IS" BASIS,
-      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
-      implied, including, without limitation, any warranties or conditions
-      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
-      PARTICULAR PURPOSE. You are solely responsible for determining the
-      appropriateness of using or redistributing the Work and assume any
-      risks associated with Your exercise of permissions under this License.
-
-   8. Limitation of Liability. In no event and under no legal theory,
-      whether in tort (including negligence), contract, or otherwise,
-      unless required by applicable law (such as deliberate and grossly
-      negligent acts) or agreed to in writing, shall any Contributor be
-      liable to You for damages, including any direct, indirect, special,
-      incidental, or consequential damages of any character arising as a
-      result of this License or out of the use or inability to use the
-      Work (including but not limited to damages for loss of goodwill,
-      work stoppage, computer failure or malfunction, or any and all
-      other commercial damages or losses), even if such Contributor
-      has been advised of the possibility of such damages.
-
-   9. Accepting Warranty or Additional Liability. While redistributing
-      the Work or Derivative Works thereof, You may choose to offer,
-      and charge a fee for, acceptance of support, warranty, indemnity,
-      or other liability obligations and/or rights consistent with this
-      License. However, in accepting such obligations, You may act only
-      on Your own behalf and on Your sole responsibility, not on behalf
-      of any other Contributor, and only if You agree to indemnify,
-      defend, and hold each Contributor harmless for any liability
-      incurred by, or claims asserted against, such Contributor by reason
-      of your accepting any such warranty or additional liability.
-

README.md

@@ -1,167 +0,0 @@
----
-# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
-# Doc / guide: https://huggingface.co/docs/hub/model-cards
-license: apache-2.0
-inference: false
----
-
-# SN-13B-8k-Instruct
-
-<!-- Provide a quick summary of what the model is/does. -->
-
-SN-13B-8k-Instruct is a 13 billion parameter model. It was pretrained as well as instruction tuned on
-[SambaNova DataScale systems](https://sambanova.ai/products/datascale/).  This model is meant to be used for tasks requiring long sequence understanding.
-
-## Model Details
-
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-- **Developed by:** [SambaNova Systems](https://sambanova.ai/)
-- **Model type:** Language Model
-- **Language(s):** English
-- **License:** Apache 2.0
-
-### Basic Information
-
-<!-- Provide the basic links for the model. -->
-- **Blog Post**: [Link](https://sambanova.ai/blog/training-long-sequence-size-models-on-sambanova/)
-- **Discord**: [Link](https://discord.com/invite/8z2Pe7cpRv)
-<!-- - **Github**: [Link](https://github.com/sambanova/bloomchat) -->
-
-### Licensing
-
-To increase accessibility and to support the open-source community, SambaNova is releasing SN-13B-8k-Instruct under an Apache 2.0 license. [Please review SambaNova’s SN-13B-8k-Instruct License](LICENSE)
-
-## Uses
-<details>
-<summary>Click to expand</summary>
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-This model is intended for commercial and research use.
-
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-
-SN-13B-8k-Instruct should NOT be used for:
-
-- Mission-critical applications
-- Applications that involve the safety of others
-- Making highly important decisions
-- Important automated pipelines
-
-This model is still in early development and can be prone to mistakes and hallucinations, there is still room for improvement. This model is intended to provide the community with a multilingual chat LLM baseline.
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users should be made aware of the risks, biases, limitations, and restrictions of the model, which are listed down at the bottom of the page.
-
-</details>
-
-
----
-## Running the model
-
-```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
-
-tokenizer = AutoTokenizer.from_pretrained("sambanovasystems/SN-13B-8k-Instruct")
-model = AutoModelForCausalLM.from_pretrained("sambanovasystems/SN-13B-8k-Instruct")
-
-prompt = 'Define Machine Learning.'
-inputs = tokenizer(prompt, return_tensors='pt')
-
-# SN-13B-8k-Instruct occasionally repeats itself when do_sample=False.
-# Set do_sample=True when using the model to avoid this.
-outputs = model.generate(**inputs, use_cache=True, max_new_tokens=50, do_sample=False)
-
-print(tokenizer.batch_decode(outputs))
-```
-
----
-
-## Training Details
-
-<details>
-<summary>Click to expand</summary>
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-We trained SN-13B-8k-Instruct with [SambaNova DataScale systems](https://sambanova.ai/products/datascale/) with
-SambaNova's in-house Reconfigurable Dataflow Unit (RDU). We started from random weights, and pretrained for 300 Billion
-tokens on sequences of size 2048.  We then pretrained for another 250 Billion tokens on sequences of size 8192.
-During this phase of training, we curated a dataset that had a large proportion of long sequence articles, with
-30% of our articles consisting of greater than 6000 words.
-
-We applied instruction tuning on a variety of tasks derived from datasets such as FLANv2, P3, Natural Instructions, etc.
-
-### Hyperparameters
-
-**Pretraining on 8k SS**
-
-- Hardware: SambaNova Reconfigurable Dataflow Unit (RDU)
-- Optimizer: AdamW
-- Steps: 60000
-- Global Batch size: 1024
-- Learning Rate: 1e-5
-- Learning Rate Scheduler: Fixed
-- Warmup Steps: 0
-- Weight decay: 0.1
-
-**Instruction-tuned Training**
-
-- Hardware: SambaNova Reconfigurable Dataflow Unit (RDU)
-- Optimizer: AdamW
-- Steps: 35000
-- Global Batch size: 64
-- Learning Rate: 1e-5
-- Learning Rate Scheduler: Fixed
-- Warmup Steps: 0
-- Weight decay: 0.1
-
-</details>
-
----
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-Like all LLMs, SN-13B-8k-Instruct has certain limitations:
-- Hallucination: SN-13B-8k-Instruct may sometimes generate responses that contain plausible-sounding but factually incorrect or irrelevant information.
-- Repetition: SN-13B-8k-Instruct may produce repetitive phrases or sentences, leading to less engaging and informative responses.
-- Coding and Math: The model's performance in generating accurate code or solving complex mathematical problems may be limited.
-- Toxicity: SN-13B-8k-Instruct may inadvertently generate responses containing inappropriate or harmful content.
-
-## Acknowledgment
-
-We appreciate [Scrolls](https://www.scrolls-benchmark.com/) and [ZeroScrolls](https://www.zero.scrolls-benchmark.com/) for their contributions in creating effective benchmarks to test the long sequence understanding of Large Language Models.
-We appreciate [lm-eval-harness](https://github.com/EleutherAI/lm-evaluation-harness) and [HELM](https://crfm.stanford.edu/helm/latest/) for their essential benchmarking contributions, 
-which were both very helpful in evaluating SN-13B-8k-Instruct's performance. We appreciate the inspiration from the wave of various recent open-source long sequence models, 
-including [XGen](https://blog.salesforceairesearch.com/xgen/), [MPT](https://www.mosaicml.com/blog/long-context-mpt-7b-8k), and 
-[Llama-2](https://ai.meta.com/llama/) and so on. We look forward to witnessing the continued growth and success of open-source long sequence models.
-
-We highly appreciate the hard work and dedication of these researchers and organizations towards the advancement of the open-source community. Their contributions were invaluable in the development of SN-13B-8k-Instruct, and we hope that our model can contribute to further advancements in the field.
-
-## Cite SN-13B-8k-Instruct
-```
-@software{sn-13b-8k-instruct,
-  title = {SN-13B-8k-Instruct: training long sequence size models with SambaNova},
-  author = {SambaNova Systems},
-  url = {https://huggingface.co/sambanovasystems/SN-13B-8k-Instruct}
-  month = {8},
-  year = {2023},
-  version = {1.0},
-}
-```

config.json

@@ -1,42 +0,0 @@
-{
-  "_name_or_path": "/scratch1/jayr/gpt13b_itv3.5",
-  "activation_function": "gelu_new",
-  "architectures": [
-    "GPT2Model"
-  ],
-  "attn_pdrop": 0.1,
-  "bos_token_id": 50256,
-  "embd_pdrop": 0.0,
-  "eos_token_id": 50256,
-  "gradient_checkpointing": false,
-  "initializer_range": 0.02,
-  "large_bs_inference": false,
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "gpt2",
-  "n_ctx": 8192,
-  "n_embd": 5120,
-  "n_head": 40,
-  "n_inner": null,
-  "n_layer": 40,
-  "n_positions": 8192,
-  "reorder_and_upcast_attn": false,
-  "resid_pdrop": 0.1,
-  "return_dict": false,
-  "scale_attn_by_inverse_layer_idx": false,
-  "scale_attn_weights": true,
-  "summary_activation": null,
-  "summary_first_dropout": 0.1,
-  "summary_proj_to_labels": true,
-  "summary_type": "cls_index",
-  "summary_use_proj": true,
-  "task_specific_params": {
-    "text-generation": {
-      "do_sample": true,
-      "max_length": 50
-    }
-  },
-  "torch_dtype": "float32",
-  "transformers_version": "4.18.0",
-  "use_cache": true,
-  "vocab_size": 50260
-}

pytorch_model-00001-of-00006.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1bfa526df470ca695e792a56cdbd89c41c023768661a763fea6a593ca59277f1
-size 9637826281

pytorch_model-00002-of-00006.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f39b4b18ae8677a75bcf76fef72ad3302a65d83bddbb2a7875dcb052d2d01c30
-size 9699205981

pytorch_model-00003-of-00006.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bc656acbae27131d84153e8daada6a446d0716728d1a1c2ad083e0bc0156d738
-size 9766295653

pytorch_model-00004-of-00006.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1f38d0df96c2f08a1f31c5bbe31adde0029e9e71519097dd39340204c8140e6a
-size 9699248065

pytorch_model-00005-of-00006.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3cb7ce956c0c1480fbe92c1e43199ca5d2586d5813c030e837c031b22e3e2537
-size 9699206045

pytorch_model-00006-of-00006.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ed7ca6af6180c9923d18c69eb68353948455d7546bb5419eaf30d3b1aba1dbe5
-size 5722174405

pytorch_model.bin.index.json

@@ -1,571 +0,0 @@
-{
-  "metadata": {
-    "total_size": 54223790240
-  },
-  "weight_map": {
-    "h.0.attn.bias": "pytorch_model-00001-of-00006.bin",
-    "h.0.attn.c_attn.bias": "pytorch_model-00001-of-00006.bin",
-    "h.0.attn.c_attn.weight": "pytorch_model-00001-of-00006.bin",
-    "h.0.attn.c_proj.bias": "pytorch_model-00001-of-00006.bin",
-    "h.0.attn.c_proj.weight": "pytorch_model-00001-of-00006.bin",
-    "h.0.attn.masked_bias": "pytorch_model-00001-of-00006.bin",
-    "h.0.ln_1.bias": "pytorch_model-00001-of-00006.bin",
-    "h.0.ln_1.weight": "pytorch_model-00001-of-00006.bin",
-    "h.0.ln_2.bias": "pytorch_model-00001-of-00006.bin",
-    "h.0.ln_2.weight": "pytorch_model-00001-of-00006.bin",
-    "h.0.mlp.c_fc.bias": "pytorch_model-00001-of-00006.bin",
-    "h.0.mlp.c_fc.weight": "pytorch_model-00001-of-00006.bin",
-    "h.0.mlp.c_proj.bias": "pytorch_model-00001-of-00006.bin",
-    "h.0.mlp.c_proj.weight": "pytorch_model-00001-of-00006.bin",
-    "h.1.attn.bias": "pytorch_model-00001-of-00006.bin",
-    "h.1.attn.c_attn.bias": "pytorch_model-00001-of-00006.bin",
-    "h.1.attn.c_attn.weight": "pytorch_model-00001-of-00006.bin",
-    "h.1.attn.c_proj.bias": "pytorch_model-00001-of-00006.bin",
-    "h.1.attn.c_proj.weight": "pytorch_model-00001-of-00006.bin",
-    "h.1.attn.masked_bias": "pytorch_model-00001-of-00006.bin",
-    "h.1.ln_1.bias": "pytorch_model-00001-of-00006.bin",
-    "h.1.ln_1.weight": "pytorch_model-00001-of-00006.bin",
-    "h.1.ln_2.bias": "pytorch_model-00001-of-00006.bin",
-    "h.1.ln_2.weight": "pytorch_model-00001-of-00006.bin",
-    "h.1.mlp.c_fc.bias": "pytorch_model-00001-of-00006.bin",
-    "h.1.mlp.c_fc.weight": "pytorch_model-00001-of-00006.bin",
-    "h.1.mlp.c_proj.bias": "pytorch_model-00001-of-00006.bin",
-    "h.1.mlp.c_proj.weight": "pytorch_model-00001-of-00006.bin",
-    "h.10.attn.bias": "pytorch_model-00002-of-00006.bin",
-    "h.10.attn.c_attn.bias": "pytorch_model-00002-of-00006.bin",
-    "h.10.attn.c_attn.weight": "pytorch_model-00002-of-00006.bin",
-    "h.10.attn.c_proj.bias": "pytorch_model-00002-of-00006.bin",
-    "h.10.attn.c_proj.weight": "pytorch_model-00002-of-00006.bin",
-    "h.10.attn.masked_bias": "pytorch_model-00002-of-00006.bin",
-    "h.10.ln_1.bias": "pytorch_model-00002-of-00006.bin",
-    "h.10.ln_1.weight": "pytorch_model-00002-of-00006.bin",
-    "h.10.ln_2.bias": "pytorch_model-00002-of-00006.bin",
-    "h.10.ln_2.weight": "pytorch_model-00002-of-00006.bin",
-    "h.10.mlp.c_fc.bias": "pytorch_model-00002-of-00006.bin",
-    "h.10.mlp.c_fc.weight": "pytorch_model-00002-of-00006.bin",
-    "h.10.mlp.c_proj.bias": "pytorch_model-00002-of-00006.bin",
-    "h.10.mlp.c_proj.weight": "pytorch_model-00002-of-00006.bin",
-    "h.11.attn.bias": "pytorch_model-00002-of-00006.bin",
-    "h.11.attn.c_attn.bias": "pytorch_model-00002-of-00006.bin",
-    "h.11.attn.c_attn.weight": "pytorch_model-00002-of-00006.bin",
-    "h.11.attn.c_proj.bias": "pytorch_model-00002-of-00006.bin",
-    "h.11.attn.c_proj.weight": "pytorch_model-00002-of-00006.bin",
-    "h.11.attn.masked_bias": "pytorch_model-00002-of-00006.bin",
-    "h.11.ln_1.bias": "pytorch_model-00002-of-00006.bin",
-    "h.11.ln_1.weight": "pytorch_model-00002-of-00006.bin",
-    "h.11.ln_2.bias": "pytorch_model-00002-of-00006.bin",
-    "h.11.ln_2.weight": "pytorch_model-00002-of-00006.bin",
-    "h.11.mlp.c_fc.bias": "pytorch_model-00002-of-00006.bin",
-    "h.11.mlp.c_fc.weight": "pytorch_model-00002-of-00006.bin",
-    "h.11.mlp.c_proj.bias": "pytorch_model-00002-of-00006.bin",
-    "h.11.mlp.c_proj.weight": "pytorch_model-00002-of-00006.bin",
-    "h.12.attn.bias": "pytorch_model-00002-of-00006.bin",
-    "h.12.attn.c_attn.bias": "pytorch_model-00002-of-00006.bin",
-    "h.12.attn.c_attn.weight": "pytorch_model-00002-of-00006.bin",
-    "h.12.attn.c_proj.bias": "pytorch_model-00002-of-00006.bin",
-    "h.12.attn.c_proj.weight": "pytorch_model-00002-of-00006.bin",
-    "h.12.attn.masked_bias": "pytorch_model-00002-of-00006.bin",
-    "h.12.ln_1.bias": "pytorch_model-00002-of-00006.bin",
-    "h.12.ln_1.weight": "pytorch_model-00002-of-00006.bin",
-    "h.12.ln_2.bias": "pytorch_model-00002-of-00006.bin",
-    "h.12.ln_2.weight": "pytorch_model-00002-of-00006.bin",
-    "h.12.mlp.c_fc.bias": "pytorch_model-00002-of-00006.bin",
-    "h.12.mlp.c_fc.weight": "pytorch_model-00002-of-00006.bin",
-    "h.12.mlp.c_proj.bias": "pytorch_model-00002-of-00006.bin",
-    "h.12.mlp.c_proj.weight": "pytorch_model-00002-of-00006.bin",
-    "h.13.attn.bias": "pytorch_model-00002-of-00006.bin",
-    "h.13.attn.c_attn.bias": "pytorch_model-00002-of-00006.bin",
-    "h.13.attn.c_attn.weight": "pytorch_model-00002-of-00006.bin",
-    "h.13.attn.c_proj.bias": "pytorch_model-00002-of-00006.bin",
-    "h.13.attn.c_proj.weight": "pytorch_model-00002-of-00006.bin",
-    "h.13.attn.masked_bias": "pytorch_model-00002-of-00006.bin",
-    "h.13.ln_1.bias": "pytorch_model-00002-of-00006.bin",
-    "h.13.ln_1.weight": "pytorch_model-00002-of-00006.bin",
-    "h.13.ln_2.bias": "pytorch_model-00002-of-00006.bin",
-    "h.13.ln_2.weight": "pytorch_model-00002-of-00006.bin",
-    "h.13.mlp.c_fc.bias": "pytorch_model-00002-of-00006.bin",
-    "h.13.mlp.c_fc.weight": "pytorch_model-00002-of-00006.bin",
-    "h.13.mlp.c_proj.bias": "pytorch_model-00003-of-00006.bin",
-    "h.13.mlp.c_proj.weight": "pytorch_model-00003-of-00006.bin",
-    "h.14.attn.bias": "pytorch_model-00003-of-00006.bin",
-    "h.14.attn.c_attn.bias": "pytorch_model-00003-of-00006.bin",
-    "h.14.attn.c_attn.weight": "pytorch_model-00003-of-00006.bin",
-    "h.14.attn.c_proj.bias": "pytorch_model-00003-of-00006.bin",
-    "h.14.attn.c_proj.weight": "pytorch_model-00003-of-00006.bin",
-    "h.14.attn.masked_bias": "pytorch_model-00003-of-00006.bin",
-    "h.14.ln_1.bias": "pytorch_model-00003-of-00006.bin",
-    "h.14.ln_1.weight": "pytorch_model-00003-of-00006.bin",
-    "h.14.ln_2.bias": "pytorch_model-00003-of-00006.bin",
-    "h.14.ln_2.weight": "pytorch_model-00003-of-00006.bin",
-    "h.14.mlp.c_fc.bias": "pytorch_model-00003-of-00006.bin",
-    "h.14.mlp.c_fc.weight": "pytorch_model-00003-of-00006.bin",
-    "h.14.mlp.c_proj.bias": "pytorch_model-00003-of-00006.bin",
-    "h.14.mlp.c_proj.weight": "pytorch_model-00003-of-00006.bin",
-    "h.15.attn.bias": "pytorch_model-00003-of-00006.bin",
-    "h.15.attn.c_attn.bias": "pytorch_model-00003-of-00006.bin",
-    "h.15.attn.c_attn.weight": "pytorch_model-00003-of-00006.bin",
-    "h.15.attn.c_proj.bias": "pytorch_model-00003-of-00006.bin",
-    "h.15.attn.c_proj.weight": "pytorch_model-00003-of-00006.bin",
-    "h.15.attn.masked_bias": "pytorch_model-00003-of-00006.bin",
-    "h.15.ln_1.bias": "pytorch_model-00003-of-00006.bin",
-    "h.15.ln_1.weight": "pytorch_model-00003-of-00006.bin",
-    "h.15.ln_2.bias": "pytorch_model-00003-of-00006.bin",
-    "h.15.ln_2.weight": "pytorch_model-00003-of-00006.bin",
-    "h.15.mlp.c_fc.bias": "pytorch_model-00003-of-00006.bin",
-    "h.15.mlp.c_fc.weight": "pytorch_model-00003-of-00006.bin",
-    "h.15.mlp.c_proj.bias": "pytorch_model-00003-of-00006.bin",
-    "h.15.mlp.c_proj.weight": "pytorch_model-00003-of-00006.bin",
-    "h.16.attn.bias": "pytorch_model-00003-of-00006.bin",
-    "h.16.attn.c_attn.bias": "pytorch_model-00003-of-00006.bin",
-    "h.16.attn.c_attn.weight": "pytorch_model-00003-of-00006.bin",
-    "h.16.attn.c_proj.bias": "pytorch_model-00003-of-00006.bin",
-    "h.16.attn.c_proj.weight": "pytorch_model-00003-of-00006.bin",
-    "h.16.attn.masked_bias": "pytorch_model-00003-of-00006.bin",
-    "h.16.ln_1.bias": "pytorch_model-00003-of-00006.bin",
-    "h.16.ln_1.weight": "pytorch_model-00003-of-00006.bin",
-    "h.16.ln_2.bias": "pytorch_model-00003-of-00006.bin",
-    "h.16.ln_2.weight": "pytorch_model-00003-of-00006.bin",
-    "h.16.mlp.c_fc.bias": "pytorch_model-00003-of-00006.bin",
-    "h.16.mlp.c_fc.weight": "pytorch_model-00003-of-00006.bin",
-    "h.16.mlp.c_proj.bias": "pytorch_model-00003-of-00006.bin",
-    "h.16.mlp.c_proj.weight": "pytorch_model-00003-of-00006.bin",
-    "h.17.attn.bias": "pytorch_model-00003-of-00006.bin",
-    "h.17.attn.c_attn.bias": "pytorch_model-00003-of-00006.bin",
-    "h.17.attn.c_attn.weight": "pytorch_model-00003-of-00006.bin",
-    "h.17.attn.c_proj.bias": "pytorch_model-00003-of-00006.bin",
-    "h.17.attn.c_proj.weight": "pytorch_model-00003-of-00006.bin",
-    "h.17.attn.masked_bias": "pytorch_model-00003-of-00006.bin",
-    "h.17.ln_1.bias": "pytorch_model-00003-of-00006.bin",
-    "h.17.ln_1.weight": "pytorch_model-00003-of-00006.bin",
-    "h.17.ln_2.bias": "pytorch_model-00003-of-00006.bin",
-    "h.17.ln_2.weight": "pytorch_model-00003-of-00006.bin",
-    "h.17.mlp.c_fc.bias": "pytorch_model-00003-of-00006.bin",
-    "h.17.mlp.c_fc.weight": "pytorch_model-00003-of-00006.bin",
-    "h.17.mlp.c_proj.bias": "pytorch_model-00003-of-00006.bin",
-    "h.17.mlp.c_proj.weight": "pytorch_model-00003-of-00006.bin",
-    "h.18.attn.bias": "pytorch_model-00003-of-00006.bin",
-    "h.18.attn.c_attn.bias": "pytorch_model-00003-of-00006.bin",
-    "h.18.attn.c_attn.weight": "pytorch_model-00003-of-00006.bin",
-    "h.18.attn.c_proj.bias": "pytorch_model-00003-of-00006.bin",
-    "h.18.attn.c_proj.weight": "pytorch_model-00003-of-00006.bin",
-    "h.18.attn.masked_bias": "pytorch_model-00003-of-00006.bin",
-    "h.18.ln_1.bias": "pytorch_model-00003-of-00006.bin",
-    "h.18.ln_1.weight": "pytorch_model-00003-of-00006.bin",
-    "h.18.ln_2.bias": "pytorch_model-00003-of-00006.bin",
-    "h.18.ln_2.weight": "pytorch_model-00003-of-00006.bin",
-    "h.18.mlp.c_fc.bias": "pytorch_model-00003-of-00006.bin",
-    "h.18.mlp.c_fc.weight": "pytorch_model-00003-of-00006.bin",
-    "h.18.mlp.c_proj.bias": "pytorch_model-00003-of-00006.bin",
-    "h.18.mlp.c_proj.weight": "pytorch_model-00003-of-00006.bin",
-    "h.19.attn.bias": "pytorch_model-00003-of-00006.bin",
-    "h.19.attn.c_attn.bias": "pytorch_model-00003-of-00006.bin",
-    "h.19.attn.c_attn.weight": "pytorch_model-00003-of-00006.bin",
-    "h.19.attn.c_proj.bias": "pytorch_model-00003-of-00006.bin",
-    "h.19.attn.c_proj.weight": "pytorch_model-00003-of-00006.bin",
-    "h.19.attn.masked_bias": "pytorch_model-00003-of-00006.bin",
-    "h.19.ln_1.bias": "pytorch_model-00003-of-00006.bin",
-    "h.19.ln_1.weight": "pytorch_model-00003-of-00006.bin",
-    "h.19.ln_2.bias": "pytorch_model-00003-of-00006.bin",
-    "h.19.ln_2.weight": "pytorch_model-00003-of-00006.bin",
-    "h.19.mlp.c_fc.bias": "pytorch_model-00003-of-00006.bin",
-    "h.19.mlp.c_fc.weight": "pytorch_model-00003-of-00006.bin",
-    "h.19.mlp.c_proj.bias": "pytorch_model-00003-of-00006.bin",
-    "h.19.mlp.c_proj.weight": "pytorch_model-00003-of-00006.bin",
-    "h.2.attn.bias": "pytorch_model-00001-of-00006.bin",
-    "h.2.attn.c_attn.bias": "pytorch_model-00001-of-00006.bin",
-    "h.2.attn.c_attn.weight": "pytorch_model-00001-of-00006.bin",
-    "h.2.attn.c_proj.bias": "pytorch_model-00001-of-00006.bin",
-    "h.2.attn.c_proj.weight": "pytorch_model-00001-of-00006.bin",
-    "h.2.attn.masked_bias": "pytorch_model-00001-of-00006.bin",
-    "h.2.ln_1.bias": "pytorch_model-00001-of-00006.bin",
-    "h.2.ln_1.weight": "pytorch_model-00001-of-00006.bin",
-    "h.2.ln_2.bias": "pytorch_model-00001-of-00006.bin",
-    "h.2.ln_2.weight": "pytorch_model-00001-of-00006.bin",
-    "h.2.mlp.c_fc.bias": "pytorch_model-00001-of-00006.bin",
-    "h.2.mlp.c_fc.weight": "pytorch_model-00001-of-00006.bin",
-    "h.2.mlp.c_proj.bias": "pytorch_model-00001-of-00006.bin",
-    "h.2.mlp.c_proj.weight": "pytorch_model-00001-of-00006.bin",
-    "h.20.attn.bias": "pytorch_model-00003-of-00006.bin",
-    "h.20.attn.c_attn.bias": "pytorch_model-00003-of-00006.bin",
-    "h.20.attn.c_attn.weight": "pytorch_model-00003-of-00006.bin",
-    "h.20.attn.c_proj.bias": "pytorch_model-00003-of-00006.bin",
-    "h.20.attn.c_proj.weight": "pytorch_model-00003-of-00006.bin",
-    "h.20.attn.masked_bias": "pytorch_model-00003-of-00006.bin",
-    "h.20.ln_1.bias": "pytorch_model-00003-of-00006.bin",
-    "h.20.ln_1.weight": "pytorch_model-00003-of-00006.bin",
-    "h.20.ln_2.bias": "pytorch_model-00003-of-00006.bin",
-    "h.20.ln_2.weight": "pytorch_model-00003-of-00006.bin",
-    "h.20.mlp.c_fc.bias": "pytorch_model-00003-of-00006.bin",
-    "h.20.mlp.c_fc.weight": "pytorch_model-00003-of-00006.bin",
-    "h.20.mlp.c_proj.bias": "pytorch_model-00003-of-00006.bin",
-    "h.20.mlp.c_proj.weight": "pytorch_model-00003-of-00006.bin",
-    "h.21.attn.bias": "pytorch_model-00003-of-00006.bin",
-    "h.21.attn.c_attn.bias": "pytorch_model-00004-of-00006.bin",
-    "h.21.attn.c_attn.weight": "pytorch_model-00004-of-00006.bin",
-    "h.21.attn.c_proj.bias": "pytorch_model-00004-of-00006.bin",
-    "h.21.attn.c_proj.weight": "pytorch_model-00004-of-00006.bin",
-    "h.21.attn.masked_bias": "pytorch_model-00003-of-00006.bin",
-    "h.21.ln_1.bias": "pytorch_model-00003-of-00006.bin",
-    "h.21.ln_1.weight": "pytorch_model-00003-of-00006.bin",
-    "h.21.ln_2.bias": "pytorch_model-00004-of-00006.bin",
-    "h.21.ln_2.weight": "pytorch_model-00004-of-00006.bin",
-    "h.21.mlp.c_fc.bias": "pytorch_model-00004-of-00006.bin",
-    "h.21.mlp.c_fc.weight": "pytorch_model-00004-of-00006.bin",
-    "h.21.mlp.c_proj.bias": "pytorch_model-00004-of-00006.bin",
-    "h.21.mlp.c_proj.weight": "pytorch_model-00004-of-00006.bin",
-    "h.22.attn.bias": "pytorch_model-00004-of-00006.bin",
-    "h.22.attn.c_attn.bias": "pytorch_model-00004-of-00006.bin",
-    "h.22.attn.c_attn.weight": "pytorch_model-00004-of-00006.bin",
-    "h.22.attn.c_proj.bias": "pytorch_model-00004-of-00006.bin",
-    "h.22.attn.c_proj.weight": "pytorch_model-00004-of-00006.bin",
-    "h.22.attn.masked_bias": "pytorch_model-00004-of-00006.bin",
-    "h.22.ln_1.bias": "pytorch_model-00004-of-00006.bin",
-    "h.22.ln_1.weight": "pytorch_model-00004-of-00006.bin",
-    "h.22.ln_2.bias": "pytorch_model-00004-of-00006.bin",
-    "h.22.ln_2.weight": "pytorch_model-00004-of-00006.bin",
-    "h.22.mlp.c_fc.bias": "pytorch_model-00004-of-00006.bin",
-    "h.22.mlp.c_fc.weight": "pytorch_model-00004-of-00006.bin",
-    "h.22.mlp.c_proj.bias": "pytorch_model-00004-of-00006.bin",
-    "h.22.mlp.c_proj.weight": "pytorch_model-00004-of-00006.bin",
-    "h.23.attn.bias": "pytorch_model-00004-of-00006.bin",
-    "h.23.attn.c_attn.bias": "pytorch_model-00004-of-00006.bin",
-    "h.23.attn.c_attn.weight": "pytorch_model-00004-of-00006.bin",
-    "h.23.attn.c_proj.bias": "pytorch_model-00004-of-00006.bin",
-    "h.23.attn.c_proj.weight": "pytorch_model-00004-of-00006.bin",
-    "h.23.attn.masked_bias": "pytorch_model-00004-of-00006.bin",
-    "h.23.ln_1.bias": "pytorch_model-00004-of-00006.bin",
-    "h.23.ln_1.weight": "pytorch_model-00004-of-00006.bin",
-    "h.23.ln_2.bias": "pytorch_model-00004-of-00006.bin",
-    "h.23.ln_2.weight": "pytorch_model-00004-of-00006.bin",
-    "h.23.mlp.c_fc.bias": "pytorch_model-00004-of-00006.bin",
-    "h.23.mlp.c_fc.weight": "pytorch_model-00004-of-00006.bin",
-    "h.23.mlp.c_proj.bias": "pytorch_model-00004-of-00006.bin",
-    "h.23.mlp.c_proj.weight": "pytorch_model-00004-of-00006.bin",
-    "h.24.attn.bias": "pytorch_model-00004-of-00006.bin",
-    "h.24.attn.c_attn.bias": "pytorch_model-00004-of-00006.bin",
-    "h.24.attn.c_attn.weight": "pytorch_model-00004-of-00006.bin",
-    "h.24.attn.c_proj.bias": "pytorch_model-00004-of-00006.bin",
-    "h.24.attn.c_proj.weight": "pytorch_model-00004-of-00006.bin",
-    "h.24.attn.masked_bias": "pytorch_model-00004-of-00006.bin",
-    "h.24.ln_1.bias": "pytorch_model-00004-of-00006.bin",
-    "h.24.ln_1.weight": "pytorch_model-00004-of-00006.bin",
-    "h.24.ln_2.bias": "pytorch_model-00004-of-00006.bin",
-    "h.24.ln_2.weight": "pytorch_model-00004-of-00006.bin",
-    "h.24.mlp.c_fc.bias": "pytorch_model-00004-of-00006.bin",
-    "h.24.mlp.c_fc.weight": "pytorch_model-00004-of-00006.bin",
-    "h.24.mlp.c_proj.bias": "pytorch_model-00004-of-00006.bin",
-    "h.24.mlp.c_proj.weight": "pytorch_model-00004-of-00006.bin",
-    "h.25.attn.bias": "pytorch_model-00004-of-00006.bin",
-    "h.25.attn.c_attn.bias": "pytorch_model-00004-of-00006.bin",
-    "h.25.attn.c_attn.weight": "pytorch_model-00004-of-00006.bin",
-    "h.25.attn.c_proj.bias": "pytorch_model-00004-of-00006.bin",
-    "h.25.attn.c_proj.weight": "pytorch_model-00004-of-00006.bin",
-    "h.25.attn.masked_bias": "pytorch_model-00004-of-00006.bin",
-    "h.25.ln_1.bias": "pytorch_model-00004-of-00006.bin",
-    "h.25.ln_1.weight": "pytorch_model-00004-of-00006.bin",
-    "h.25.ln_2.bias": "pytorch_model-00004-of-00006.bin",
-    "h.25.ln_2.weight": "pytorch_model-00004-of-00006.bin",
-    "h.25.mlp.c_fc.bias": "pytorch_model-00004-of-00006.bin",
-    "h.25.mlp.c_fc.weight": "pytorch_model-00004-of-00006.bin",
-    "h.25.mlp.c_proj.bias": "pytorch_model-00004-of-00006.bin",
-    "h.25.mlp.c_proj.weight": "pytorch_model-00004-of-00006.bin",
-    "h.26.attn.bias": "pytorch_model-00004-of-00006.bin",
-    "h.26.attn.c_attn.bias": "pytorch_model-00004-of-00006.bin",
-    "h.26.attn.c_attn.weight": "pytorch_model-00004-of-00006.bin",
-    "h.26.attn.c_proj.bias": "pytorch_model-00004-of-00006.bin",
-    "h.26.attn.c_proj.weight": "pytorch_model-00004-of-00006.bin",
-    "h.26.attn.masked_bias": "pytorch_model-00004-of-00006.bin",
-    "h.26.ln_1.bias": "pytorch_model-00004-of-00006.bin",
-    "h.26.ln_1.weight": "pytorch_model-00004-of-00006.bin",
-    "h.26.ln_2.bias": "pytorch_model-00004-of-00006.bin",
-    "h.26.ln_2.weight": "pytorch_model-00004-of-00006.bin",
-    "h.26.mlp.c_fc.bias": "pytorch_model-00004-of-00006.bin",
-    "h.26.mlp.c_fc.weight": "pytorch_model-00004-of-00006.bin",
-    "h.26.mlp.c_proj.bias": "pytorch_model-00004-of-00006.bin",
-    "h.26.mlp.c_proj.weight": "pytorch_model-00004-of-00006.bin",
-    "h.27.attn.bias": "pytorch_model-00004-of-00006.bin",
-    "h.27.attn.c_attn.bias": "pytorch_model-00004-of-00006.bin",
-    "h.27.attn.c_attn.weight": "pytorch_model-00004-of-00006.bin",
-    "h.27.attn.c_proj.bias": "pytorch_model-00004-of-00006.bin",
-    "h.27.attn.c_proj.weight": "pytorch_model-00004-of-00006.bin",
-    "h.27.attn.masked_bias": "pytorch_model-00004-of-00006.bin",
-    "h.27.ln_1.bias": "pytorch_model-00004-of-00006.bin",
-    "h.27.ln_1.weight": "pytorch_model-00004-of-00006.bin",
-    "h.27.ln_2.bias": "pytorch_model-00004-of-00006.bin",
-    "h.27.ln_2.weight": "pytorch_model-00004-of-00006.bin",
-    "h.27.mlp.c_fc.bias": "pytorch_model-00004-of-00006.bin",
-    "h.27.mlp.c_fc.weight": "pytorch_model-00004-of-00006.bin",
-    "h.27.mlp.c_proj.bias": "pytorch_model-00004-of-00006.bin",
-    "h.27.mlp.c_proj.weight": "pytorch_model-00004-of-00006.bin",
-    "h.28.attn.bias": "pytorch_model-00004-of-00006.bin",
-    "h.28.attn.c_attn.bias": "pytorch_model-00004-of-00006.bin",
-    "h.28.attn.c_attn.weight": "pytorch_model-00004-of-00006.bin",
-    "h.28.attn.c_proj.bias": "pytorch_model-00004-of-00006.bin",
-    "h.28.attn.c_proj.weight": "pytorch_model-00004-of-00006.bin",
-    "h.28.attn.masked_bias": "pytorch_model-00004-of-00006.bin",
-    "h.28.ln_1.bias": "pytorch_model-00004-of-00006.bin",
-    "h.28.ln_1.weight": "pytorch_model-00004-of-00006.bin",
-    "h.28.ln_2.bias": "pytorch_model-00004-of-00006.bin",
-    "h.28.ln_2.weight": "pytorch_model-00004-of-00006.bin",
-    "h.28.mlp.c_fc.bias": "pytorch_model-00005-of-00006.bin",
-    "h.28.mlp.c_fc.weight": "pytorch_model-00005-of-00006.bin",
-    "h.28.mlp.c_proj.bias": "pytorch_model-00005-of-00006.bin",
-    "h.28.mlp.c_proj.weight": "pytorch_model-00005-of-00006.bin",
-    "h.29.attn.bias": "pytorch_model-00005-of-00006.bin",
-    "h.29.attn.c_attn.bias": "pytorch_model-00005-of-00006.bin",
-    "h.29.attn.c_attn.weight": "pytorch_model-00005-of-00006.bin",
-    "h.29.attn.c_proj.bias": "pytorch_model-00005-of-00006.bin",
-    "h.29.attn.c_proj.weight": "pytorch_model-00005-of-00006.bin",
-    "h.29.attn.masked_bias": "pytorch_model-00005-of-00006.bin",
-    "h.29.ln_1.bias": "pytorch_model-00005-of-00006.bin",
-    "h.29.ln_1.weight": "pytorch_model-00005-of-00006.bin",
-    "h.29.ln_2.bias": "pytorch_model-00005-of-00006.bin",
-    "h.29.ln_2.weight": "pytorch_model-00005-of-00006.bin",
-    "h.29.mlp.c_fc.bias": "pytorch_model-00005-of-00006.bin",
-    "h.29.mlp.c_fc.weight": "pytorch_model-00005-of-00006.bin",
-    "h.29.mlp.c_proj.bias": "pytorch_model-00005-of-00006.bin",
-    "h.29.mlp.c_proj.weight": "pytorch_model-00005-of-00006.bin",
-    "h.3.attn.bias": "pytorch_model-00001-of-00006.bin",
-    "h.3.attn.c_attn.bias": "pytorch_model-00001-of-00006.bin",
-    "h.3.attn.c_attn.weight": "pytorch_model-00001-of-00006.bin",
-    "h.3.attn.c_proj.bias": "pytorch_model-00001-of-00006.bin",
-    "h.3.attn.c_proj.weight": "pytorch_model-00001-of-00006.bin",
-    "h.3.attn.masked_bias": "pytorch_model-00001-of-00006.bin",
-    "h.3.ln_1.bias": "pytorch_model-00001-of-00006.bin",
-    "h.3.ln_1.weight": "pytorch_model-00001-of-00006.bin",
-    "h.3.ln_2.bias": "pytorch_model-00001-of-00006.bin",
-    "h.3.ln_2.weight": "pytorch_model-00001-of-00006.bin",
-    "h.3.mlp.c_fc.bias": "pytorch_model-00001-of-00006.bin",
-    "h.3.mlp.c_fc.weight": "pytorch_model-00001-of-00006.bin",
-    "h.3.mlp.c_proj.bias": "pytorch_model-00001-of-00006.bin",
-    "h.3.mlp.c_proj.weight": "pytorch_model-00001-of-00006.bin",
-    "h.30.attn.bias": "pytorch_model-00005-of-00006.bin",
-    "h.30.attn.c_attn.bias": "pytorch_model-00005-of-00006.bin",
-    "h.30.attn.c_attn.weight": "pytorch_model-00005-of-00006.bin",
-    "h.30.attn.c_proj.bias": "pytorch_model-00005-of-00006.bin",
-    "h.30.attn.c_proj.weight": "pytorch_model-00005-of-00006.bin",
-    "h.30.attn.masked_bias": "pytorch_model-00005-of-00006.bin",
-    "h.30.ln_1.bias": "pytorch_model-00005-of-00006.bin",
-    "h.30.ln_1.weight": "pytorch_model-00005-of-00006.bin",
-    "h.30.ln_2.bias": "pytorch_model-00005-of-00006.bin",
-    "h.30.ln_2.weight": "pytorch_model-00005-of-00006.bin",
-    "h.30.mlp.c_fc.bias": "pytorch_model-00005-of-00006.bin",
-    "h.30.mlp.c_fc.weight": "pytorch_model-00005-of-00006.bin",
-    "h.30.mlp.c_proj.bias": "pytorch_model-00005-of-00006.bin",
-    "h.30.mlp.c_proj.weight": "pytorch_model-00005-of-00006.bin",
-    "h.31.attn.bias": "pytorch_model-00005-of-00006.bin",
-    "h.31.attn.c_attn.bias": "pytorch_model-00005-of-00006.bin",
-    "h.31.attn.c_attn.weight": "pytorch_model-00005-of-00006.bin",
-    "h.31.attn.c_proj.bias": "pytorch_model-00005-of-00006.bin",
-    "h.31.attn.c_proj.weight": "pytorch_model-00005-of-00006.bin",
-    "h.31.attn.masked_bias": "pytorch_model-00005-of-00006.bin",
-    "h.31.ln_1.bias": "pytorch_model-00005-of-00006.bin",
-    "h.31.ln_1.weight": "pytorch_model-00005-of-00006.bin",
-    "h.31.ln_2.bias": "pytorch_model-00005-of-00006.bin",
-    "h.31.ln_2.weight": "pytorch_model-00005-of-00006.bin",
-    "h.31.mlp.c_fc.bias": "pytorch_model-00005-of-00006.bin",
-    "h.31.mlp.c_fc.weight": "pytorch_model-00005-of-00006.bin",
-    "h.31.mlp.c_proj.bias": "pytorch_model-00005-of-00006.bin",
-    "h.31.mlp.c_proj.weight": "pytorch_model-00005-of-00006.bin",
-    "h.32.attn.bias": "pytorch_model-00005-of-00006.bin",
-    "h.32.attn.c_attn.bias": "pytorch_model-00005-of-00006.bin",
-    "h.32.attn.c_attn.weight": "pytorch_model-00005-of-00006.bin",
-    "h.32.attn.c_proj.bias": "pytorch_model-00005-of-00006.bin",
-    "h.32.attn.c_proj.weight": "pytorch_model-00005-of-00006.bin",
-    "h.32.attn.masked_bias": "pytorch_model-00005-of-00006.bin",
-    "h.32.ln_1.bias": "pytorch_model-00005-of-00006.bin",
-    "h.32.ln_1.weight": "pytorch_model-00005-of-00006.bin",
-    "h.32.ln_2.bias": "pytorch_model-00005-of-00006.bin",
-    "h.32.ln_2.weight": "pytorch_model-00005-of-00006.bin",
-    "h.32.mlp.c_fc.bias": "pytorch_model-00005-of-00006.bin",
-    "h.32.mlp.c_fc.weight": "pytorch_model-00005-of-00006.bin",
-    "h.32.mlp.c_proj.bias": "pytorch_model-00005-of-00006.bin",
-    "h.32.mlp.c_proj.weight": "pytorch_model-00005-of-00006.bin",
-    "h.33.attn.bias": "pytorch_model-00005-of-00006.bin",
-    "h.33.attn.c_attn.bias": "pytorch_model-00005-of-00006.bin",
-    "h.33.attn.c_attn.weight": "pytorch_model-00005-of-00006.bin",
-    "h.33.attn.c_proj.bias": "pytorch_model-00005-of-00006.bin",
-    "h.33.attn.c_proj.weight": "pytorch_model-00005-of-00006.bin",
-    "h.33.attn.masked_bias": "pytorch_model-00005-of-00006.bin",
-    "h.33.ln_1.bias": "pytorch_model-00005-of-00006.bin",
-    "h.33.ln_1.weight": "pytorch_model-00005-of-00006.bin",
-    "h.33.ln_2.bias": "pytorch_model-00005-of-00006.bin",
-    "h.33.ln_2.weight": "pytorch_model-00005-of-00006.bin",
-    "h.33.mlp.c_fc.bias": "pytorch_model-00005-of-00006.bin",
-    "h.33.mlp.c_fc.weight": "pytorch_model-00005-of-00006.bin",
-    "h.33.mlp.c_proj.bias": "pytorch_model-00005-of-00006.bin",
-    "h.33.mlp.c_proj.weight": "pytorch_model-00005-of-00006.bin",
-    "h.34.attn.bias": "pytorch_model-00005-of-00006.bin",
-    "h.34.attn.c_attn.bias": "pytorch_model-00005-of-00006.bin",
-    "h.34.attn.c_attn.weight": "pytorch_model-00005-of-00006.bin",
-    "h.34.attn.c_proj.bias": "pytorch_model-00005-of-00006.bin",
-    "h.34.attn.c_proj.weight": "pytorch_model-00005-of-00006.bin",
-    "h.34.attn.masked_bias": "pytorch_model-00005-of-00006.bin",
-    "h.34.ln_1.bias": "pytorch_model-00005-of-00006.bin",
-    "h.34.ln_1.weight": "pytorch_model-00005-of-00006.bin",
-    "h.34.ln_2.bias": "pytorch_model-00005-of-00006.bin",
-    "h.34.ln_2.weight": "pytorch_model-00005-of-00006.bin",
-    "h.34.mlp.c_fc.bias": "pytorch_model-00005-of-00006.bin",
-    "h.34.mlp.c_fc.weight": "pytorch_model-00005-of-00006.bin",
-    "h.34.mlp.c_proj.bias": "pytorch_model-00005-of-00006.bin",
-    "h.34.mlp.c_proj.weight": "pytorch_model-00005-of-00006.bin",
-    "h.35.attn.bias": "pytorch_model-00005-of-00006.bin",
-    "h.35.attn.c_attn.bias": "pytorch_model-00005-of-00006.bin",
-    "h.35.attn.c_attn.weight": "pytorch_model-00005-of-00006.bin",
-    "h.35.attn.c_proj.bias": "pytorch_model-00005-of-00006.bin",
-    "h.35.attn.c_proj.weight": "pytorch_model-00005-of-00006.bin",
-    "h.35.attn.masked_bias": "pytorch_model-00005-of-00006.bin",
-    "h.35.ln_1.bias": "pytorch_model-00005-of-00006.bin",
-    "h.35.ln_1.weight": "pytorch_model-00005-of-00006.bin",
-    "h.35.ln_2.bias": "pytorch_model-00005-of-00006.bin",
-    "h.35.ln_2.weight": "pytorch_model-00005-of-00006.bin",
-    "h.35.mlp.c_fc.bias": "pytorch_model-00005-of-00006.bin",
-    "h.35.mlp.c_fc.weight": "pytorch_model-00005-of-00006.bin",
-    "h.35.mlp.c_proj.bias": "pytorch_model-00006-of-00006.bin",
-    "h.35.mlp.c_proj.weight": "pytorch_model-00006-of-00006.bin",
-    "h.36.attn.bias": "pytorch_model-00006-of-00006.bin",
-    "h.36.attn.c_attn.bias": "pytorch_model-00006-of-00006.bin",
-    "h.36.attn.c_attn.weight": "pytorch_model-00006-of-00006.bin",
-    "h.36.attn.c_proj.bias": "pytorch_model-00006-of-00006.bin",
-    "h.36.attn.c_proj.weight": "pytorch_model-00006-of-00006.bin",
-    "h.36.attn.masked_bias": "pytorch_model-00006-of-00006.bin",
-    "h.36.ln_1.bias": "pytorch_model-00006-of-00006.bin",
-    "h.36.ln_1.weight": "pytorch_model-00006-of-00006.bin",
-    "h.36.ln_2.bias": "pytorch_model-00006-of-00006.bin",
-    "h.36.ln_2.weight": "pytorch_model-00006-of-00006.bin",
-    "h.36.mlp.c_fc.bias": "pytorch_model-00006-of-00006.bin",
-    "h.36.mlp.c_fc.weight": "pytorch_model-00006-of-00006.bin",
-    "h.36.mlp.c_proj.bias": "pytorch_model-00006-of-00006.bin",
-    "h.36.mlp.c_proj.weight": "pytorch_model-00006-of-00006.bin",
-    "h.37.attn.bias": "pytorch_model-00006-of-00006.bin",
-    "h.37.attn.c_attn.bias": "pytorch_model-00006-of-00006.bin",
-    "h.37.attn.c_attn.weight": "pytorch_model-00006-of-00006.bin",
-    "h.37.attn.c_proj.bias": "pytorch_model-00006-of-00006.bin",
-    "h.37.attn.c_proj.weight": "pytorch_model-00006-of-00006.bin",
-    "h.37.attn.masked_bias": "pytorch_model-00006-of-00006.bin",
-    "h.37.ln_1.bias": "pytorch_model-00006-of-00006.bin",
-    "h.37.ln_1.weight": "pytorch_model-00006-of-00006.bin",
-    "h.37.ln_2.bias": "pytorch_model-00006-of-00006.bin",
-    "h.37.ln_2.weight": "pytorch_model-00006-of-00006.bin",
-    "h.37.mlp.c_fc.bias": "pytorch_model-00006-of-00006.bin",
-    "h.37.mlp.c_fc.weight": "pytorch_model-00006-of-00006.bin",
-    "h.37.mlp.c_proj.bias": "pytorch_model-00006-of-00006.bin",
-    "h.37.mlp.c_proj.weight": "pytorch_model-00006-of-00006.bin",
-    "h.38.attn.bias": "pytorch_model-00006-of-00006.bin",
-    "h.38.attn.c_attn.bias": "pytorch_model-00006-of-00006.bin",
-    "h.38.attn.c_attn.weight": "pytorch_model-00006-of-00006.bin",
-    "h.38.attn.c_proj.bias": "pytorch_model-00006-of-00006.bin",
-    "h.38.attn.c_proj.weight": "pytorch_model-00006-of-00006.bin",
-    "h.38.attn.masked_bias": "pytorch_model-00006-of-00006.bin",
-    "h.38.ln_1.bias": "pytorch_model-00006-of-00006.bin",
-    "h.38.ln_1.weight": "pytorch_model-00006-of-00006.bin",
-    "h.38.ln_2.bias": "pytorch_model-00006-of-00006.bin",
-    "h.38.ln_2.weight": "pytorch_model-00006-of-00006.bin",
-    "h.38.mlp.c_fc.bias": "pytorch_model-00006-of-00006.bin",
-    "h.38.mlp.c_fc.weight": "pytorch_model-00006-of-00006.bin",
-    "h.38.mlp.c_proj.bias": "pytorch_model-00006-of-00006.bin",
-    "h.38.mlp.c_proj.weight": "pytorch_model-00006-of-00006.bin",
-    "h.39.attn.bias": "pytorch_model-00006-of-00006.bin",
-    "h.39.attn.c_attn.bias": "pytorch_model-00006-of-00006.bin",
-    "h.39.attn.c_attn.weight": "pytorch_model-00006-of-00006.bin",
-    "h.39.attn.c_proj.bias": "pytorch_model-00006-of-00006.bin",
-    "h.39.attn.c_proj.weight": "pytorch_model-00006-of-00006.bin",
-    "h.39.attn.masked_bias": "pytorch_model-00006-of-00006.bin",
-    "h.39.ln_1.bias": "pytorch_model-00006-of-00006.bin",
-    "h.39.ln_1.weight": "pytorch_model-00006-of-00006.bin",
-    "h.39.ln_2.bias": "pytorch_model-00006-of-00006.bin",
-    "h.39.ln_2.weight": "pytorch_model-00006-of-00006.bin",
-    "h.39.mlp.c_fc.bias": "pytorch_model-00006-of-00006.bin",
-    "h.39.mlp.c_fc.weight": "pytorch_model-00006-of-00006.bin",
-    "h.39.mlp.c_proj.bias": "pytorch_model-00006-of-00006.bin",
-    "h.39.mlp.c_proj.weight": "pytorch_model-00006-of-00006.bin",
-    "h.4.attn.bias": "pytorch_model-00001-of-00006.bin",
-    "h.4.attn.c_attn.bias": "pytorch_model-00001-of-00006.bin",
-    "h.4.attn.c_attn.weight": "pytorch_model-00001-of-00006.bin",
-    "h.4.attn.c_proj.bias": "pytorch_model-00001-of-00006.bin",
-    "h.4.attn.c_proj.weight": "pytorch_model-00001-of-00006.bin",
-    "h.4.attn.masked_bias": "pytorch_model-00001-of-00006.bin",
-    "h.4.ln_1.bias": "pytorch_model-00001-of-00006.bin",
-    "h.4.ln_1.weight": "pytorch_model-00001-of-00006.bin",
-    "h.4.ln_2.bias": "pytorch_model-00001-of-00006.bin",
-    "h.4.ln_2.weight": "pytorch_model-00001-of-00006.bin",
-    "h.4.mlp.c_fc.bias": "pytorch_model-00001-of-00006.bin",
-    "h.4.mlp.c_fc.weight": "pytorch_model-00001-of-00006.bin",
-    "h.4.mlp.c_proj.bias": "pytorch_model-00001-of-00006.bin",
-    "h.4.mlp.c_proj.weight": "pytorch_model-00001-of-00006.bin",
-    "h.5.attn.bias": "pytorch_model-00001-of-00006.bin",
-    "h.5.attn.c_attn.bias": "pytorch_model-00001-of-00006.bin",
-    "h.5.attn.c_attn.weight": "pytorch_model-00001-of-00006.bin",
-    "h.5.attn.c_proj.bias": "pytorch_model-00001-of-00006.bin",
-    "h.5.attn.c_proj.weight": "pytorch_model-00001-of-00006.bin",
-    "h.5.attn.masked_bias": "pytorch_model-00001-of-00006.bin",
-    "h.5.ln_1.bias": "pytorch_model-00001-of-00006.bin",
-    "h.5.ln_1.weight": "pytorch_model-00001-of-00006.bin",
-    "h.5.ln_2.bias": "pytorch_model-00001-of-00006.bin",
-    "h.5.ln_2.weight": "pytorch_model-00001-of-00006.bin",
-    "h.5.mlp.c_fc.bias": "pytorch_model-00001-of-00006.bin",
-    "h.5.mlp.c_fc.weight": "pytorch_model-00001-of-00006.bin",
-    "h.5.mlp.c_proj.bias": "pytorch_model-00001-of-00006.bin",
-    "h.5.mlp.c_proj.weight": "pytorch_model-00001-of-00006.bin",
-    "h.6.attn.bias": "pytorch_model-00001-of-00006.bin",
-    "h.6.attn.c_attn.bias": "pytorch_model-00001-of-00006.bin",
-    "h.6.attn.c_attn.weight": "pytorch_model-00001-of-00006.bin",
-    "h.6.attn.c_proj.bias": "pytorch_model-00001-of-00006.bin",
-    "h.6.attn.c_proj.weight": "pytorch_model-00001-of-00006.bin",
-    "h.6.attn.masked_bias": "pytorch_model-00001-of-00006.bin",
-    "h.6.ln_1.bias": "pytorch_model-00001-of-00006.bin",
-    "h.6.ln_1.weight": "pytorch_model-00001-of-00006.bin",
-    "h.6.ln_2.bias": "pytorch_model-00001-of-00006.bin",
-    "h.6.ln_2.weight": "pytorch_model-00001-of-00006.bin",
-    "h.6.mlp.c_fc.bias": "pytorch_model-00002-of-00006.bin",
-    "h.6.mlp.c_fc.weight": "pytorch_model-00002-of-00006.bin",
-    "h.6.mlp.c_proj.bias": "pytorch_model-00002-of-00006.bin",
-    "h.6.mlp.c_proj.weight": "pytorch_model-00002-of-00006.bin",
-    "h.7.attn.bias": "pytorch_model-00002-of-00006.bin",
-    "h.7.attn.c_attn.bias": "pytorch_model-00002-of-00006.bin",
-    "h.7.attn.c_attn.weight": "pytorch_model-00002-of-00006.bin",
-    "h.7.attn.c_proj.bias": "pytorch_model-00002-of-00006.bin",
-    "h.7.attn.c_proj.weight": "pytorch_model-00002-of-00006.bin",
-    "h.7.attn.masked_bias": "pytorch_model-00002-of-00006.bin",
-    "h.7.ln_1.bias": "pytorch_model-00002-of-00006.bin",
-    "h.7.ln_1.weight": "pytorch_model-00002-of-00006.bin",
-    "h.7.ln_2.bias": "pytorch_model-00002-of-00006.bin",
-    "h.7.ln_2.weight": "pytorch_model-00002-of-00006.bin",
-    "h.7.mlp.c_fc.bias": "pytorch_model-00002-of-00006.bin",
-    "h.7.mlp.c_fc.weight": "pytorch_model-00002-of-00006.bin",
-    "h.7.mlp.c_proj.bias": "pytorch_model-00002-of-00006.bin",
-    "h.7.mlp.c_proj.weight": "pytorch_model-00002-of-00006.bin",
-    "h.8.attn.bias": "pytorch_model-00002-of-00006.bin",
-    "h.8.attn.c_attn.bias": "pytorch_model-00002-of-00006.bin",
-    "h.8.attn.c_attn.weight": "pytorch_model-00002-of-00006.bin",
-    "h.8.attn.c_proj.bias": "pytorch_model-00002-of-00006.bin",
-    "h.8.attn.c_proj.weight": "pytorch_model-00002-of-00006.bin",
-    "h.8.attn.masked_bias": "pytorch_model-00002-of-00006.bin",
-    "h.8.ln_1.bias": "pytorch_model-00002-of-00006.bin",
-    "h.8.ln_1.weight": "pytorch_model-00002-of-00006.bin",
-    "h.8.ln_2.bias": "pytorch_model-00002-of-00006.bin",
-    "h.8.ln_2.weight": "pytorch_model-00002-of-00006.bin",
-    "h.8.mlp.c_fc.bias": "pytorch_model-00002-of-00006.bin",
-    "h.8.mlp.c_fc.weight": "pytorch_model-00002-of-00006.bin",
-    "h.8.mlp.c_proj.bias": "pytorch_model-00002-of-00006.bin",
-    "h.8.mlp.c_proj.weight": "pytorch_model-00002-of-00006.bin",
-    "h.9.attn.bias": "pytorch_model-00002-of-00006.bin",
-    "h.9.attn.c_attn.bias": "pytorch_model-00002-of-00006.bin",
-    "h.9.attn.c_attn.weight": "pytorch_model-00002-of-00006.bin",
-    "h.9.attn.c_proj.bias": "pytorch_model-00002-of-00006.bin",
-    "h.9.attn.c_proj.weight": "pytorch_model-00002-of-00006.bin",
-    "h.9.attn.masked_bias": "pytorch_model-00002-of-00006.bin",
-    "h.9.ln_1.bias": "pytorch_model-00002-of-00006.bin",
-    "h.9.ln_1.weight": "pytorch_model-00002-of-00006.bin",
-    "h.9.ln_2.bias": "pytorch_model-00002-of-00006.bin",
-    "h.9.ln_2.weight": "pytorch_model-00002-of-00006.bin",
-    "h.9.mlp.c_fc.bias": "pytorch_model-00002-of-00006.bin",
-    "h.9.mlp.c_fc.weight": "pytorch_model-00002-of-00006.bin",
-    "h.9.mlp.c_proj.bias": "pytorch_model-00002-of-00006.bin",
-    "h.9.mlp.c_proj.weight": "pytorch_model-00002-of-00006.bin",
-    "ln_f.bias": "pytorch_model-00006-of-00006.bin",
-    "ln_f.weight": "pytorch_model-00006-of-00006.bin",
-    "wpe.weight": "pytorch_model-00001-of-00006.bin",
-    "wte.weight": "pytorch_model-00001-of-00006.bin"
-  }
-}

special_tokens_map.json

@@ -1,5 +0,0 @@
-{
-  "bos_token": "<|endoftext|>",
-  "eos_token": "<|endoftext|>",
-  "unk_token": "<|endoftext|>"
-}

tokenizer_config.json

@@ -1,10 +0,0 @@
-{
-  "add_prefix_space": false,
-  "bos_token": "<|endoftext|>",
-  "eos_token": "<|endoftext|>",
-  "model_max_length": 1024,
-  "name_or_path": "gpt2",
-  "special_tokens_map_file": null,
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "<|endoftext|>"
-}