初始化项目，由ModelHub XC社区提供模型

Model: futurehouse/ether0
Source: Original Platform

.gitattributes

@@ -0,0 +1,39 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text
+*.jpg filter=lfs diff=lfs merge=lfs -text
+*.svg filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,201 @@
+                                 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.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2025 FutureHouse
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -0,0 +1,99 @@
+---
+license: apache-2.0
+language:
+- en
+base_model:
+- mistralai/Mistral-Small-24B-Instruct-2501
+datasets:
+- futurehouse/ether0-benchmark
+pipeline_tag: text-generation
+tags:
+- smiles
+- chemistry
+- reasoning
+---
+
+[![Dataset on HF](https://huggingface.co/datasets/huggingface/badges/resolve/main/dataset-on-hf-md-dark.svg)](https://huggingface.co/datasets/futurehouse/ether0-benchmark)
+
+![ether0 logo](images/ether0_logo.svg)
+
+# ether0
+
+ether0 is a 24B language model trained to reason in English and output molecular structures as SMILES.
+It is derived from fine-tuning and reinforcement learning training from Mistral-Small-24B-Instruct-2501.
+Ask questions in English, but they may also include molecules specified as SMILES.
+The SMILES do not need to be canonical and may contain stereochemistry information.
+ether0 has limited support for IUPAC names.
+
+## Usage
+
+This model is trained to reason in English and output a molecule.
+It is NOT a general purpose chat model.
+It has been trained specifically for these tasks:
+
+- IUPAC name to SMILES
+- Molecular formula (Hill notation) to SMILES, optionally with constraints on functional groups
+- Modifying solubilities on given molecules (SMILES) by specific LogS, optionally with constraints about scaffolds/groups/similarity
+- Matching pKa to molecules, proposing molecules with a pKa, or modifying molecules to adjust pKa
+- Matching scent/smell to molecules and modifying molecules to adjust scent
+- Matching human cell receptor binding + mode (e.g., agonist) to molecule or modifying a molecule's binding effect. Trained [from EveBio](https://data.evebio.org/)
+- ADME properties (e.g., MDDK efflux ratio, LD50)
+- GHS classifications (as words, not codes, like "carcinogen"). For example, "modify this molecule to remove acute toxicity."
+- Quantitative LD50 in mg/kg
+- Proposing 1-step retrosynthesis from likely commercially available reagents
+- Predicting a reaction outcome
+- General natural language description of a specific molecule to that molecule (inverse molecule captioning)
+- Natural product elucidation (formula + organism to SMILES) - e.g, "A molecule with formula C6H12O6 was isolated from Homo sapiens, what could it be?"
+- Matching blood-brain barrier permeability (as a class) or modifying
+
+For example, you can ask "Propose a molecule with a pKa of 9.2" or "Modify CCCCC(O)=OH to increase its pKa by about 1 unit." You cannot ask it "What is the pKa of CCCCC(O)=OH?"
+If you ask it questions that lie significantly beyond those tasks, it can fail. You can combine properties, although we haven't significantly benchmarked this.
+
+## Benchmarks
+
+We tested ether0, along with some experts and frontier models, on [a benchmark we developed](https://huggingface.co/datasets/futurehouse/ether0-benchmark/).
+The benchmark is made from commonly used tasks - like reaction prediction in USPTO, molecular captioning from PubChem, or predicting GHS classification.
+The benchmark is different in two ways: all answers are a molecule, and we balanced it so that each task is 25 questions (a reasonable amount for frontier model evals).
+The tasks generally follow previously reported numbers - e.g., a reaction prediction accuracy of 80% here would be about the same on a withheld split of the USPTO-50k dataset.
+
+The results below are the model weights released in this repo. This is different than the preprint, which has pre-safety mitigation benchmarks.
+
+![ether0 benchmarking](images/benchmarks.png)
+
+## Limitations
+
+It does not know general synonyms and it has poor textbook knowledge (e.g. it does not perform especially well on chembench).
+For best results, input molecules as SMILES: if you input molecules with their common names, the model may reason using the incorrect smiles, resulting in poor results.
+For example, we have observed that the model often confuses lysine and glutamic acid if you ask questions using their common names, but should correctly reason about their chemistry if you provide their structures as SMILES.
+
+## Training details
+
+We first pre-trained Mistral-Small-24B-Instruct-2501 via mostly incorrect reasoning traces from DeepSeek r1 to elicit reasoning and follow the new tokens/templates. Next, we used independent rounds of specialists trained with GRPO and verifiable rewards on one of the above tasks. We then aggregated and filtered reasoning traces (correct answers with reasoning) from the specialists to again fine-tune Mistral-Small-24B-Instruct-2501. Then, we did GRPO over all tasks. This last model was then put through safety post-training.
+
+![ether0 training info](images/training_info.png)
+
+See our [preprint](https://paper.ether0.ai/) for details on data and training process.
+
+## Safety
+
+We performed refusal post-training for compounds listed on OPCW schedules 1 and 2.
+We also post-trained ether0 to refuse questions about standard malicious topics like making explosives or poisons.
+As the model knows pharmacokinetics, it can modulate toxicity.
+However, the structure of toxic or narcotic compounds are generally known and thus we do not consider this a safety risk. The model can provide
+no uplift on "tacit knowledge" tasks like purification, scale-up, or processing beyond a web search or similar sized language model.
+
+## Citation
+
+```bibtex
+@article{narayanan2025training,
+  title={Training a Scientific Reasoning Model for Chemistry},
+  author={Narayanan, Siddharth M. and Braza, James D. and Griffiths, Ryan-Rhys and Bou, Albert and Wellawatte, Geemi P. and Ramos, Mayk Caldas and Mitchener, Ludovico and Rodriques, Samuel G. and White, Andrew D.},
+  journal={arXiv preprint arXiv:2506.17238},
+  year={2025}
+}
+```
+
+## Licensing
+
+This model repository is considered open weights under an Apache 2.0 license,
+copyright 2025 FutureHouse.

chat_template.jinja

@@ -0,0 +1,22 @@
+{%- set default_system_message = "You are a scientific reasoning AI assistant." %}
+{{- bos_token }}
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content'] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = default_system_message %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{{- '[SYSTEM_PROMPT]' + system_message + '[/SYSTEM_PROMPT]' }}
+
+{%- for message in loop_messages %}
+    {%- if message['role'] == 'user' %}
+        {{- '[INST]' + message['content'] + '[/INST]' }}
+    {%- elif message['role'] == 'system' %}
+        {{- '[SYSTEM_PROMPT]' + message['content'] + '[/SYSTEM_PROMPT]' }}
+    {%- elif message['role'] == 'assistant' %}
+        {{- message['content'] + eos_token }}
+    {%- else %}
+        {{- raise_exception("Only user, system and assistant roles are supported!") }}
+    {%- endif %}
+{%- endfor %}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": ".",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 32768,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 100000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "vocab_size": 131136
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "temperature": 0.15,
+  "transformers_version": "4.49.0"
+}

images/benchmarks.png

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a73504ea5a2d775ebc57b01f90d199d9bc76e31b3ff4aaa48df6569ea21aeb65
+size 348489

images/ether0_logo.svg

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0867c7e4ab64596bdf22702cf5928c06a31eb793769439eaf676f42ef0b578a
+size 7355

images/training_info.png

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:394653640102293eb6a10e4aac2c14fa58aea61077f3203211cf0226b38d84fe
+size 589487

model-00001-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cb64bde7082b4e221268ae7eda5f810e6b559faab3dba039227b00d16eecce9
+size 4992574728

model-00002-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c053c7c4f38f9df7c551f4093e11562ffa0bb8dfc9b3a2b3eae0723b905dcd5f
+size 4571875720

model-00003-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0883613b40af4455e245cffafa6b8e7f0455e1b0c14faac84abc53f4f799fbe3
+size 4446046248

model-00004-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:836de9d506d80fbcbc6b9e83aef31653c3e07981ce2c940038a79db28f897558
+size 4446046248

model-00005-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b54f174cc8cf869ee3b91c64139d22bff21448d0f481ce705b55baff14abbe20
+size 4446046248

model-00006-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4864ef66b68960555e1ff21414e0fdd651527f1ab996301858a0f1d478e163c9
+size 4446046264

model-00007-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e5d82c280d103ec6dae66d9f7b8b5d8d0dd3a9c13e14a69a09b5879329a22ff
+size 4446046264

model-00008-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1b8872a7a472f95cdaa06427d39fdf4d8ef7bb9294f1fd57dbc385bee830b22
+size 4446046264

model-00009-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc064b9e62e0ab8b93838804fbf2928ecdc4872dee8070ff414275f162d569da
+size 4446046264

model-00010-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faba359dbf04871e3be0168fab3e9a1c64e9b6520cbd789a07f34cf99e82f202
+size 4446046264

model-00011-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e1e7899320234808c18cee9739e677abf62084def0b7b40fc2b3166bbb0bd57
+size 4446046264

model-00012-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09864179156aef136f11c753cb2fe9a3a67e279906d6183e0dac1cd9405a5380
+size 4446046264

model-00013-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b0c81e8db54b70605946a9ede46117983d740d6ea247e0f45c7a5bb3d0c0ab9
+size 4446046264

model-00014-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7ae623f4729b9d534ca53dcac2447bfa4f25345765306e3b306adb020a4fda8
+size 4446046264

model-00015-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd5f275d227f197e005207cddd391f9ca5dd9170c5fd3939e83e8ef62c133fd7
+size 4446046264

model-00016-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bda5a688b27cc0fd87a5baeeed5d6bf54c0cf62e7a559c2bff0e5d7b9234d73
+size 4446046264

model-00017-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b07d2b13a357de1998fe902a8d562a0bb41ecaa5b8194771e31bb16ee8a27fbf
+size 4446046264

model-00018-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da31fa0482d119090ed031dfa14f37061a9045b98713befa8fe6df18a05d9cca
+size 4446046264

model-00019-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05ebfbaf5430997ae6c7ff365616999368347e882ac725e27c7bf87219e511f4
+size 4446046264

model-00020-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40c3eb42991fcecd28101cda400a56c1fce1b6425fc2aa490db333e3b2c37470
+size 4446046264

model-00021-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93e33305780e263458db746978bf00e892c12cb882520ea652af6709c5fa5dea
+size 4698993432

model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 94292234240
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00021-of-00021.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00021.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00021.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00021.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00021.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00021.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00021.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00021.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00021.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00021.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00021.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00021.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00021.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00021.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00006-of-00021.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00021.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00007-of-00021.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00007-of-00021.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00007-of-00021.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00021.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00008-of-00021.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00008-of-00021.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00008-of-00021.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00008-of-00021.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00009-of-00021.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00009-of-00021.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00009-of-00021.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00021.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00010-of-00021.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00010-of-00021.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00010-of-00021.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00021.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00021.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00021.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00012-of-00021.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00012-of-00021.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00012-of-00021.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00012-of-00021.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00013-of-00021.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00013-of-00021.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00013-of-00021.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00013-of-00021.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00014-of-00021.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00014-of-00021.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00014-of-00021.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00014-of-00021.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00015-of-00021.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00015-of-00021.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00015-of-00021.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00015-of-00021.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00016-of-00021.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00016-of-00021.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00021.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00021.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00016-of-00021.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00016-of-00021.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00017-of-00021.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00017-of-00021.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00017-of-00021.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00017-of-00021.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00018-of-00021.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00018-of-00021.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00018-of-00021.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00018-of-00021.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00019-of-00021.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00019-of-00021.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00019-of-00021.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00019-of-00021.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00020-of-00021.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00020-of-00021.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00020-of-00021.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00020-of-00021.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00021-of-00021.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00021-of-00021.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00021-of-00021.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00021.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00021.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00004-of-00021.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00021.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00004-of-00021.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00021.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00005-of-00021.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00021.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00005-of-00021.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00021.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00006-of-00021.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00021.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00021.safetensors",
+    "model.norm.weight": "model-00021-of-00021.safetensors"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6396233c0e3e593eb1c4b2dc2e4ec1a8bdb88bf7747c36175b14011b95125508
+size 17078803