初始化项目，由ModelHub XC社区提供模型
Model: stepfun-ai/StepFun-Prover-Preview-7B Source: Original Platform
This commit is contained in:
ModelHub XC
49
.gitattributes
vendored
Normal file
49
.gitattributes
vendored
Normal file
@@ -0,0 +1,49 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 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
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack 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
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* 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
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm 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
|
||||
201
LICENSE
Normal file
201
LICENSE
Normal file
@@ -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 [yyyy] [name of copyright owner]
|
||||
|
||||
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.
|
||||
58
README.md
Normal file
58
README.md
Normal file
@@ -0,0 +1,58 @@
|
||||
---
|
||||
language:
|
||||
- en
|
||||
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
|
||||
tags:
|
||||
- chat
|
||||
library_name: transformers
|
||||
license: apache-2.0
|
||||
---
|
||||
|
||||
# StepFun-Prover-Preview-7B
|
||||
|
||||
**StepFun-Prover-Preview-7B** is a theorem proving model developed by StepFun Team. It can iteratively refine the proof sketch via interacting with Lean4, and achieve 66.0% accuracy with Pass@1 on MiniF2F-test. Advanced usage examples can be seen in [github](https://github.com/stepfun-ai/StepFun-Prover-Preview).
|
||||
|
||||
# Quick Start with vLLM
|
||||
|
||||
```python
|
||||
from vllm import LLM, SamplingParams
|
||||
from transformers import AutoTokenizer
|
||||
|
||||
model_name = "Stepfun/Stepfun-Prover-Preview-7B"
|
||||
model = LLM(
|
||||
model=model_name,
|
||||
tensor_parallel_size=4,
|
||||
)
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
|
||||
|
||||
formal_problem = """
|
||||
import Mathlib
|
||||
|
||||
theorem test_theorem (x y z : ℝ) (hx : 0 < x) (hy : 0 < y) (hz : 0 < z) :
|
||||
(x^2 - z^2) / (y + z) + (y^2 - x^2) / (z + x) + (z^2 - y^2) / (x + y) ≥ 0 := by
|
||||
""".strip()
|
||||
|
||||
system_prompt = "You will be given an unsolved Lean 4 problem. Think carefully and work towards a solution. At any point, you may use the Lean 4 REPL to check your progress by enclosing your partial solution between <sketch> and </sketch>. The REPL feedback will be provided between <REPL> and </REPL>. Continue this process as needed until you arrive at a complete and correct solution."
|
||||
|
||||
user_prompt = f"```lean4\n{formal_problem}\n```"
|
||||
|
||||
dialog = [
|
||||
{"role": "system", "content": system_prompt},
|
||||
{"role": "user", "content": user_prompt}
|
||||
]
|
||||
|
||||
prompt = tokenizer.apply_chat_template(dialog, tokenize=False, add_generation_prompt=True)
|
||||
|
||||
sampling_params = SamplingParams(
|
||||
temperature=0.999,
|
||||
top_p=0.95,
|
||||
top_k=-1,
|
||||
max_tokens=16384,
|
||||
stop_token_ids=[151643, 151666], # <｜end▁of▁sentence｜>, </sketch>
|
||||
include_stop_str_in_output=True,
|
||||
)
|
||||
|
||||
output = model.generate(prompt, sampling_params=sampling_params)
|
||||
output_text = output[0].outputs[0].text
|
||||
print(output_text)
|
||||
```
|
||||
1
chat_template.jinja
Normal file
1
chat_template.jinja
Normal file
@@ -0,0 +1 @@
|
||||
{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\n'}}{% endif %}
|
||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151643,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3584,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 18944,
|
||||
"max_position_embeddings": 131072,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 28,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 4,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_theta": 10000,
|
||||
"sliding_window": 4096,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.44.0",
|
||||
"use_cache": true,
|
||||
"use_mrope": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 152064
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
9
generate_config.json
Normal file
9
generate_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 151646,
|
||||
"eos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"temperature": 0.7,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "4.54.0"
|
||||
}
|
||||
3
model-00001.safetensors
Normal file
3
model-00001.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b3aeb47ceecf799a275ab4ef703dff6f93c32b6cc76d8c4456c6af072b850c84
|
||||
size 4253782776
|
||||
3
model-00002.safetensors
Normal file
3
model-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ad13314f7acb45e80dd89524f0e655f7207cdff6db6c84f8bf821af0eb4c9ab4
|
||||
size 4195052616
|
||||
3
model-00003.safetensors
Normal file
3
model-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:00b95d237b2a1c92d8d7fe34e0f6183137f40dd572ba3c97f58f0d70897bcf94
|
||||
size 4195052632
|
||||
3
model-00004.safetensors
Normal file
3
model-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e4406405f063a122734d75e39689906626b3600152477e2ca182f99b137d7d88
|
||||
size 2587383656
|
||||
344
model.safetensors.index.json
Normal file
344
model.safetensors.index.json
Normal file
@@ -0,0 +1,344 @@
|
||||
{
|
||||
"metadata": {},
|
||||
"weight_map": {
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00001.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00001.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00001.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00001.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00001.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00001.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00001.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00001.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00001.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00001.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00001.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00001.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00001.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00001.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00001.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00001.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00001.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00001.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00001.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00001.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00001.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00001.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00001.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00001.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00001.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00001.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00001.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00001.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00001.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00001.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00002.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00002.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00002.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00002.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00002.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00002.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00002.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00002.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00002.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00003.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00003.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00003.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00003.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00003.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00003.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00003.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00003.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00003.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00003.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00003.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00003.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00003.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00003.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00003.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00003.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00003.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00003.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00003.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00003.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00003.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00003.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00003.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00003.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00003.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00003.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00003.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00003.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00003.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00003.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00003.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00003.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00003.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00003.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00003.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00004.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00004.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00004.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00004.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00004.safetensors",
|
||||
"model.embed_tokens.weight": "model-00004.safetensors",
|
||||
"model.norm.weight": "model-00004.safetensors",
|
||||
"lm_head.weight": "model-00004.safetensors"
|
||||
}
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<｜begin▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<｜end▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<｜end▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8eedbf07704361ce2fa255b6fa6d891bb8455d813cd74d749de0b4497b4702c5
|
||||
size 11423149
|
||||
210
tokenizer_config.json
Normal file
210
tokenizer_config.json
Normal file
@@ -0,0 +1,210 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"add_prefix_space": null,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<｜end▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<｜User｜>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151645": {
|
||||
"content": "<｜Assistant｜>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151646": {
|
||||
"content": "<｜begin▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|EOT|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151648": {
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151649": {
|
||||
"content": "</think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151665": {
|
||||
"content": "<sketch>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151666": {
|
||||
"content": "</sketch>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"bos_token": "<｜begin▁of▁sentence｜>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<｜end▁of▁sentence｜>",
|
||||
"extra_special_tokens": {},
|
||||
"legacy": true,
|
||||
"model_max_length": 163840,
|
||||
"pad_token": "<｜end▁of▁sentence｜>",
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizerFast",
|
||||
"unk_token": null,
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
Reference in New Issue
Block a user