Upload 12 files
Browse files- LICENSE +202 -0
- README.md +97 -3
- added_tokens.json +24 -0
- config.json +27 -0
- eval.sh +36 -0
- generation_config.json +14 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +25 -0
- tokenizer.json +0 -0
- tokenizer_config.json +207 -0
- vocab.json +0 -0
LICENSE
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
Apache License
|
3 |
+
Version 2.0, January 2004
|
4 |
+
http://www.apache.org/licenses/
|
5 |
+
|
6 |
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
7 |
+
|
8 |
+
1. Definitions.
|
9 |
+
|
10 |
+
"License" shall mean the terms and conditions for use, reproduction,
|
11 |
+
and distribution as defined by Sections 1 through 9 of this document.
|
12 |
+
|
13 |
+
"Licensor" shall mean the copyright owner or entity authorized by
|
14 |
+
the copyright owner that is granting the License.
|
15 |
+
|
16 |
+
"Legal Entity" shall mean the union of the acting entity and all
|
17 |
+
other entities that control, are controlled by, or are under common
|
18 |
+
control with that entity. For the purposes of this definition,
|
19 |
+
"control" means (i) the power, direct or indirect, to cause the
|
20 |
+
direction or management of such entity, whether by contract or
|
21 |
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
22 |
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
23 |
+
|
24 |
+
"You" (or "Your") shall mean an individual or Legal Entity
|
25 |
+
exercising permissions granted by this License.
|
26 |
+
|
27 |
+
"Source" form shall mean the preferred form for making modifications,
|
28 |
+
including but not limited to software source code, documentation
|
29 |
+
source, and configuration files.
|
30 |
+
|
31 |
+
"Object" form shall mean any form resulting from mechanical
|
32 |
+
transformation or translation of a Source form, including but
|
33 |
+
not limited to compiled object code, generated documentation,
|
34 |
+
and conversions to other media types.
|
35 |
+
|
36 |
+
"Work" shall mean the work of authorship, whether in Source or
|
37 |
+
Object form, made available under the License, as indicated by a
|
38 |
+
copyright notice that is included in or attached to the work
|
39 |
+
(an example is provided in the Appendix below).
|
40 |
+
|
41 |
+
"Derivative Works" shall mean any work, whether in Source or Object
|
42 |
+
form, that is based on (or derived from) the Work and for which the
|
43 |
+
editorial revisions, annotations, elaborations, or other modifications
|
44 |
+
represent, as a whole, an original work of authorship. For the purposes
|
45 |
+
of this License, Derivative Works shall not include works that remain
|
46 |
+
separable from, or merely link (or bind by name) to the interfaces of,
|
47 |
+
the Work and Derivative Works thereof.
|
48 |
+
|
49 |
+
"Contribution" shall mean any work of authorship, including
|
50 |
+
the original version of the Work and any modifications or additions
|
51 |
+
to that Work or Derivative Works thereof, that is intentionally
|
52 |
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
53 |
+
or by an individual or Legal Entity authorized to submit on behalf of
|
54 |
+
the copyright owner. For the purposes of this definition, "submitted"
|
55 |
+
means any form of electronic, verbal, or written communication sent
|
56 |
+
to the Licensor or its representatives, including but not limited to
|
57 |
+
communication on electronic mailing lists, source code control systems,
|
58 |
+
and issue tracking systems that are managed by, or on behalf of, the
|
59 |
+
Licensor for the purpose of discussing and improving the Work, but
|
60 |
+
excluding communication that is conspicuously marked or otherwise
|
61 |
+
designated in writing by the copyright owner as "Not a Contribution."
|
62 |
+
|
63 |
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
64 |
+
on behalf of whom a Contribution has been received by Licensor and
|
65 |
+
subsequently incorporated within the Work.
|
66 |
+
|
67 |
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
68 |
+
this License, each Contributor hereby grants to You a perpetual,
|
69 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
70 |
+
copyright license to reproduce, prepare Derivative Works of,
|
71 |
+
publicly display, publicly perform, sublicense, and distribute the
|
72 |
+
Work and such Derivative Works in Source or Object form.
|
73 |
+
|
74 |
+
3. Grant of Patent License. Subject to the terms and conditions of
|
75 |
+
this License, each Contributor hereby grants to You a perpetual,
|
76 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
77 |
+
(except as stated in this section) patent license to make, have made,
|
78 |
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
79 |
+
where such license applies only to those patent claims licensable
|
80 |
+
by such Contributor that are necessarily infringed by their
|
81 |
+
Contribution(s) alone or by combination of their Contribution(s)
|
82 |
+
with the Work to which such Contribution(s) was submitted. If You
|
83 |
+
institute patent litigation against any entity (including a
|
84 |
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
85 |
+
or a Contribution incorporated within the Work constitutes direct
|
86 |
+
or contributory patent infringement, then any patent licenses
|
87 |
+
granted to You under this License for that Work shall terminate
|
88 |
+
as of the date such litigation is filed.
|
89 |
+
|
90 |
+
4. Redistribution. You may reproduce and distribute copies of the
|
91 |
+
Work or Derivative Works thereof in any medium, with or without
|
92 |
+
modifications, and in Source or Object form, provided that You
|
93 |
+
meet the following conditions:
|
94 |
+
|
95 |
+
(a) You must give any other recipients of the Work or
|
96 |
+
Derivative Works a copy of this License; and
|
97 |
+
|
98 |
+
(b) You must cause any modified files to carry prominent notices
|
99 |
+
stating that You changed the files; and
|
100 |
+
|
101 |
+
(c) You must retain, in the Source form of any Derivative Works
|
102 |
+
that You distribute, all copyright, patent, trademark, and
|
103 |
+
attribution notices from the Source form of the Work,
|
104 |
+
excluding those notices that do not pertain to any part of
|
105 |
+
the Derivative Works; and
|
106 |
+
|
107 |
+
(d) If the Work includes a "NOTICE" text file as part of its
|
108 |
+
distribution, then any Derivative Works that You distribute must
|
109 |
+
include a readable copy of the attribution notices contained
|
110 |
+
within such NOTICE file, excluding those notices that do not
|
111 |
+
pertain to any part of the Derivative Works, in at least one
|
112 |
+
of the following places: within a NOTICE text file distributed
|
113 |
+
as part of the Derivative Works; within the Source form or
|
114 |
+
documentation, if provided along with the Derivative Works; or,
|
115 |
+
within a display generated by the Derivative Works, if and
|
116 |
+
wherever such third-party notices normally appear. The contents
|
117 |
+
of the NOTICE file are for informational purposes only and
|
118 |
+
do not modify the License. You may add Your own attribution
|
119 |
+
notices within Derivative Works that You distribute, alongside
|
120 |
+
or as an addendum to the NOTICE text from the Work, provided
|
121 |
+
that such additional attribution notices cannot be construed
|
122 |
+
as modifying the License.
|
123 |
+
|
124 |
+
You may add Your own copyright statement to Your modifications and
|
125 |
+
may provide additional or different license terms and conditions
|
126 |
+
for use, reproduction, or distribution of Your modifications, or
|
127 |
+
for any such Derivative Works as a whole, provided Your use,
|
128 |
+
reproduction, and distribution of the Work otherwise complies with
|
129 |
+
the conditions stated in this License.
|
130 |
+
|
131 |
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
132 |
+
any Contribution intentionally submitted for inclusion in the Work
|
133 |
+
by You to the Licensor shall be under the terms and conditions of
|
134 |
+
this License, without any additional terms or conditions.
|
135 |
+
Notwithstanding the above, nothing herein shall supersede or modify
|
136 |
+
the terms of any separate license agreement you may have executed
|
137 |
+
with Licensor regarding such Contributions.
|
138 |
+
|
139 |
+
6. Trademarks. This License does not grant permission to use the trade
|
140 |
+
names, trademarks, service marks, or product names of the Licensor,
|
141 |
+
except as required for reasonable and customary use in describing the
|
142 |
+
origin of the Work and reproducing the content of the NOTICE file.
|
143 |
+
|
144 |
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
145 |
+
agreed to in writing, Licensor provides the Work (and each
|
146 |
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
147 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
148 |
+
implied, including, without limitation, any warranties or conditions
|
149 |
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
150 |
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
151 |
+
appropriateness of using or redistributing the Work and assume any
|
152 |
+
risks associated with Your exercise of permissions under this License.
|
153 |
+
|
154 |
+
8. Limitation of Liability. In no event and under no legal theory,
|
155 |
+
whether in tort (including negligence), contract, or otherwise,
|
156 |
+
unless required by applicable law (such as deliberate and grossly
|
157 |
+
negligent acts) or agreed to in writing, shall any Contributor be
|
158 |
+
liable to You for damages, including any direct, indirect, special,
|
159 |
+
incidental, or consequential damages of any character arising as a
|
160 |
+
result of this License or out of the use or inability to use the
|
161 |
+
Work (including but not limited to damages for loss of goodwill,
|
162 |
+
work stoppage, computer failure or malfunction, or any and all
|
163 |
+
other commercial damages or losses), even if such Contributor
|
164 |
+
has been advised of the possibility of such damages.
|
165 |
+
|
166 |
+
9. Accepting Warranty or Additional Liability. While redistributing
|
167 |
+
the Work or Derivative Works thereof, You may choose to offer,
|
168 |
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
169 |
+
or other liability obligations and/or rights consistent with this
|
170 |
+
License. However, in accepting such obligations, You may act only
|
171 |
+
on Your own behalf and on Your sole responsibility, not on behalf
|
172 |
+
of any other Contributor, and only if You agree to indemnify,
|
173 |
+
defend, and hold each Contributor harmless for any liability
|
174 |
+
incurred by, or claims asserted against, such Contributor by reason
|
175 |
+
of your accepting any such warranty or additional liability.
|
176 |
+
|
177 |
+
END OF TERMS AND CONDITIONS
|
178 |
+
|
179 |
+
APPENDIX: How to apply the Apache License to your work.
|
180 |
+
|
181 |
+
To apply the Apache License to your work, attach the following
|
182 |
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
183 |
+
replaced with your own identifying information. (Don't include
|
184 |
+
the brackets!) The text should be enclosed in the appropriate
|
185 |
+
comment syntax for the file format. We also recommend that a
|
186 |
+
file or class name and description of purpose be included on the
|
187 |
+
same "printed page" as the copyright notice for easier
|
188 |
+
identification within third-party archives.
|
189 |
+
|
190 |
+
Copyright 2024 Alibaba Cloud
|
191 |
+
|
192 |
+
Licensed under the Apache License, Version 2.0 (the "License");
|
193 |
+
you may not use this file except in compliance with the License.
|
194 |
+
You may obtain a copy of the License at
|
195 |
+
|
196 |
+
http://www.apache.org/licenses/LICENSE-2.0
|
197 |
+
|
198 |
+
Unless required by applicable law or agreed to in writing, software
|
199 |
+
distributed under the License is distributed on an "AS IS" BASIS,
|
200 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
201 |
+
See the License for the specific language governing permissions and
|
202 |
+
limitations under the License.
|
README.md
CHANGED
@@ -1,3 +1,97 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: apache-2.0
|
4 |
+
license_link: https://huggingface.co/huihui-ai/Qwen2.5-Code-1.5B-Instruct-abliterated/blob/main/LICENSE
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
pipeline_tag: text-generation
|
8 |
+
base_model: Qwen/Qwen2.5-Code-1.5B-Instruct
|
9 |
+
tags:
|
10 |
+
- chat
|
11 |
+
- abliterated
|
12 |
+
- uncensored
|
13 |
+
---
|
14 |
+
|
15 |
+
# huihui-ai/Qwen2.5-Code-1.5B-Instruct-abliterated
|
16 |
+
|
17 |
+
|
18 |
+
This is an uncensored version of Qwen2.5-Code-1.5B-Instruct created with abliteration (see [this article](https://huggingface.co/blog/mlabonne/abliteration) to know more about it).
|
19 |
+
|
20 |
+
Special thanks to [@FailSpy](https://huggingface.co/failspy) for the original code and technique. Please follow him if you're interested in abliterated models.
|
21 |
+
|
22 |
+
## Usage
|
23 |
+
You can use this model in your applications by loading it with Hugging Face's `transformers` library:
|
24 |
+
|
25 |
+
|
26 |
+
```python
|
27 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
28 |
+
|
29 |
+
# Load the model and tokenizer
|
30 |
+
model_name = "huihui-ai/Qwen2.5-Code-1.5B-Instruct-abliterated"
|
31 |
+
model = AutoModelForCausalLM.from_pretrained(
|
32 |
+
model_name,
|
33 |
+
torch_dtype="auto",
|
34 |
+
device_map="auto"
|
35 |
+
)
|
36 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
37 |
+
|
38 |
+
# Initialize conversation context
|
39 |
+
initial_messages = [
|
40 |
+
{"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."}
|
41 |
+
]
|
42 |
+
messages = initial_messages.copy() # Copy the initial conversation context
|
43 |
+
|
44 |
+
# Enter conversation loop
|
45 |
+
while True:
|
46 |
+
# Get user input
|
47 |
+
user_input = input("User: ").strip() # Strip leading and trailing spaces
|
48 |
+
|
49 |
+
# If the user types '/exit', end the conversation
|
50 |
+
if user_input.lower() == "/exit":
|
51 |
+
print("Exiting chat.")
|
52 |
+
break
|
53 |
+
|
54 |
+
# If the user types '/clean', reset the conversation context
|
55 |
+
if user_input.lower() == "/clean":
|
56 |
+
messages = initial_messages.copy() # Reset conversation context
|
57 |
+
print("Chat history cleared. Starting a new conversation.")
|
58 |
+
continue
|
59 |
+
|
60 |
+
# If input is empty, prompt the user and continue
|
61 |
+
if not user_input:
|
62 |
+
print("Input cannot be empty. Please enter something.")
|
63 |
+
continue
|
64 |
+
|
65 |
+
# Add user input to the conversation
|
66 |
+
messages.append({"role": "user", "content": user_input})
|
67 |
+
|
68 |
+
# Build the chat template
|
69 |
+
text = tokenizer.apply_chat_template(
|
70 |
+
messages,
|
71 |
+
tokenize=False,
|
72 |
+
add_generation_prompt=True
|
73 |
+
)
|
74 |
+
|
75 |
+
# Tokenize input and prepare it for the model
|
76 |
+
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
77 |
+
|
78 |
+
# Generate a response from the model
|
79 |
+
generated_ids = model.generate(
|
80 |
+
**model_inputs,
|
81 |
+
max_new_tokens=8192
|
82 |
+
)
|
83 |
+
|
84 |
+
# Extract model output, removing special tokens
|
85 |
+
generated_ids = [
|
86 |
+
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
|
87 |
+
]
|
88 |
+
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
89 |
+
|
90 |
+
# Add the model's response to the conversation
|
91 |
+
messages.append({"role": "assistant", "content": response})
|
92 |
+
|
93 |
+
# Print the model's response
|
94 |
+
print(f"Qwen: {response}")
|
95 |
+
|
96 |
+
```
|
97 |
+
|
added_tokens.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</tool_call>": 151658,
|
3 |
+
"<tool_call>": 151657,
|
4 |
+
"<|box_end|>": 151649,
|
5 |
+
"<|box_start|>": 151648,
|
6 |
+
"<|endoftext|>": 151643,
|
7 |
+
"<|file_sep|>": 151664,
|
8 |
+
"<|fim_middle|>": 151660,
|
9 |
+
"<|fim_pad|>": 151662,
|
10 |
+
"<|fim_prefix|>": 151659,
|
11 |
+
"<|fim_suffix|>": 151661,
|
12 |
+
"<|im_end|>": 151645,
|
13 |
+
"<|im_start|>": 151644,
|
14 |
+
"<|image_pad|>": 151655,
|
15 |
+
"<|object_ref_end|>": 151647,
|
16 |
+
"<|object_ref_start|>": 151646,
|
17 |
+
"<|quad_end|>": 151651,
|
18 |
+
"<|quad_start|>": 151650,
|
19 |
+
"<|repo_name|>": 151663,
|
20 |
+
"<|video_pad|>": 151656,
|
21 |
+
"<|vision_end|>": 151653,
|
22 |
+
"<|vision_pad|>": 151654,
|
23 |
+
"<|vision_start|>": 151652
|
24 |
+
}
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"Qwen2ForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_dropout": 0.0,
|
6 |
+
"bos_token_id": 151643,
|
7 |
+
"eos_token_id": 151643,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 1536,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 8960,
|
12 |
+
"max_position_embeddings": 32768,
|
13 |
+
"max_window_layers": 21,
|
14 |
+
"model_type": "qwen2",
|
15 |
+
"num_attention_heads": 12,
|
16 |
+
"num_hidden_layers": 28,
|
17 |
+
"num_key_value_heads": 2,
|
18 |
+
"rms_norm_eps": 1e-06,
|
19 |
+
"rope_theta": 1000000.0,
|
20 |
+
"sliding_window": 131072,
|
21 |
+
"tie_word_embeddings": true,
|
22 |
+
"torch_dtype": "bfloat16",
|
23 |
+
"transformers_version": "4.44.0",
|
24 |
+
"use_cache": true,
|
25 |
+
"use_sliding_window": false,
|
26 |
+
"vocab_size": 151936
|
27 |
+
}
|
eval.sh
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Install required package
|
2 |
+
pip install antlr4-python3-runtime==4.11 immutabledict langdetect nltk lm_eval
|
3 |
+
|
4 |
+
|
5 |
+
python -c "import nltk; nltk.download('punkt')"
|
6 |
+
|
7 |
+
MODEL_PATHS=(
|
8 |
+
huihui-ai/Qwen2.5-32B-Instruct-abliterated
|
9 |
+
)
|
10 |
+
|
11 |
+
for MODEL_PATH in "${MODEL_PATHS[@]}"; do
|
12 |
+
MODEL_NAME=$(basename "$MODEL_PATH")
|
13 |
+
MODEL_DIR="./results/$MODEL_NAME"
|
14 |
+
mkdir -p "$MODEL_DIR"
|
15 |
+
|
16 |
+
MODEL_ARGS="trust_remote_code=True,pretrained=$MODEL_PATH,dtype=bfloat16"
|
17 |
+
|
18 |
+
BASE_COMMAND="accelerate launch -m lm_eval --model hf --model_args $MODEL_ARGS --batch_size 4 --fewshot_as_multiturn --apply_chat_template"
|
19 |
+
|
20 |
+
# IFEval
|
21 |
+
$BASE_COMMAND --tasks leaderboard_ifeval --fewshot_as_multiturn --output_path "$MODEL_DIR/ifeval"
|
22 |
+
|
23 |
+
# BBH (Big-Bench Hard)
|
24 |
+
$BASE_COMMAND --tasks leaderboard_bbh --num_fewshot 3 --fewshot_as_multiturn --output_path "$MODEL_DIR/bbh"
|
25 |
+
|
26 |
+
# GPQA
|
27 |
+
$BASE_COMMAND --tasks leaderboard_gpqa --fewshot_as_multiturn --output_path "$MODEL_DIR/gpqa"
|
28 |
+
|
29 |
+
# MMLU-Pro
|
30 |
+
$BASE_COMMAND --tasks leaderboard_mmlu_pro --num_fewshot 5 --fewshot_as_multiturn --output_path "$MODEL_DIR/mmlu_pro"
|
31 |
+
|
32 |
+
# TruthfulQA
|
33 |
+
$BASE_COMMAND --tasks truthfulqa_mc2 --fewshot_as_multiturn --output_path "$MODEL_DIR/truthfulqa"
|
34 |
+
|
35 |
+
|
36 |
+
done
|
generation_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 151643,
|
3 |
+
"pad_token_id": 151643,
|
4 |
+
"do_sample": true,
|
5 |
+
"eos_token_id": [
|
6 |
+
151645,
|
7 |
+
151643
|
8 |
+
],
|
9 |
+
"repetition_penalty": 1.1,
|
10 |
+
"temperature": 0.7,
|
11 |
+
"top_p": 0.8,
|
12 |
+
"top_k": 20,
|
13 |
+
"transformers_version": "4.37.0"
|
14 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4d4ba464892ff33644cd955e8d769667950767114bc2aa4631a19591095a7f5
|
3 |
+
size 3554214752
|
special_tokens_map.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<|object_ref_start|>",
|
6 |
+
"<|object_ref_end|>",
|
7 |
+
"<|box_start|>",
|
8 |
+
"<|box_end|>",
|
9 |
+
"<|quad_start|>",
|
10 |
+
"<|quad_end|>",
|
11 |
+
"<|vision_start|>",
|
12 |
+
"<|vision_end|>",
|
13 |
+
"<|vision_pad|>",
|
14 |
+
"<|image_pad|>",
|
15 |
+
"<|video_pad|>"
|
16 |
+
],
|
17 |
+
"eos_token": {
|
18 |
+
"content": "<|im_end|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
"pad_token": "<|im_end|>"
|
25 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"151643": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"151644": {
|
14 |
+
"content": "<|im_start|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"151645": {
|
22 |
+
"content": "<|im_end|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"151646": {
|
30 |
+
"content": "<|object_ref_start|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"151647": {
|
38 |
+
"content": "<|object_ref_end|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"151648": {
|
46 |
+
"content": "<|box_start|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"151649": {
|
54 |
+
"content": "<|box_end|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"151650": {
|
62 |
+
"content": "<|quad_start|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"151651": {
|
70 |
+
"content": "<|quad_end|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"151652": {
|
78 |
+
"content": "<|vision_start|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"151653": {
|
86 |
+
"content": "<|vision_end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"151654": {
|
94 |
+
"content": "<|vision_pad|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"151655": {
|
102 |
+
"content": "<|image_pad|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"151656": {
|
110 |
+
"content": "<|video_pad|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"151657": {
|
118 |
+
"content": "<tool_call>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": false
|
124 |
+
},
|
125 |
+
"151658": {
|
126 |
+
"content": "</tool_call>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": false
|
132 |
+
},
|
133 |
+
"151659": {
|
134 |
+
"content": "<|fim_prefix|>",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": false
|
140 |
+
},
|
141 |
+
"151660": {
|
142 |
+
"content": "<|fim_middle|>",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": false
|
148 |
+
},
|
149 |
+
"151661": {
|
150 |
+
"content": "<|fim_suffix|>",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": false
|
156 |
+
},
|
157 |
+
"151662": {
|
158 |
+
"content": "<|fim_pad|>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": false
|
164 |
+
},
|
165 |
+
"151663": {
|
166 |
+
"content": "<|repo_name|>",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": false
|
172 |
+
},
|
173 |
+
"151664": {
|
174 |
+
"content": "<|file_sep|>",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": false
|
180 |
+
}
|
181 |
+
},
|
182 |
+
"additional_special_tokens": [
|
183 |
+
"<|im_start|>",
|
184 |
+
"<|im_end|>",
|
185 |
+
"<|object_ref_start|>",
|
186 |
+
"<|object_ref_end|>",
|
187 |
+
"<|box_start|>",
|
188 |
+
"<|box_end|>",
|
189 |
+
"<|quad_start|>",
|
190 |
+
"<|quad_end|>",
|
191 |
+
"<|vision_start|>",
|
192 |
+
"<|vision_end|>",
|
193 |
+
"<|vision_pad|>",
|
194 |
+
"<|image_pad|>",
|
195 |
+
"<|video_pad|>"
|
196 |
+
],
|
197 |
+
"bos_token": null,
|
198 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
199 |
+
"clean_up_tokenization_spaces": false,
|
200 |
+
"eos_token": "<|im_end|>",
|
201 |
+
"errors": "replace",
|
202 |
+
"model_max_length": 131072,
|
203 |
+
"pad_token": "<|endoftext|>",
|
204 |
+
"split_special_tokens": false,
|
205 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
206 |
+
"unk_token": null
|
207 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|