Santhoshini/iol-solver-v3
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: Santhoshini/iol-solver-v3
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-20 14:09:21 +08:00
commit c36ab4e24b
17 changed files with 153920 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
.gitattributes vendored Normal file
View File

@@ -0,0 +1,40 @@
*.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
wheelhouse/autoawq-0.2.9-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
wheelhouse/huggingface_hub-0.30.2-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
wheelhouse/tokenizers-0.21.1-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl filter=lfs diff=lfs merge=lfs -text
wheelhouse/transformers-4.51.3-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text

202
LICENSE Normal file
View File

@@ -0,0 +1,202 @@
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 Alibaba Cloud
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.

359
README.md Normal file
View File

@@ -0,0 +1,359 @@
---
library_name: transformers
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3-14B/blob/main/LICENSE
pipeline_tag: text-generation
base_model: Qwen/Qwen3-14B
---
# Qwen3-14B-AWQ
<a href="https://chat.qwen.ai/" target="_blank" style="margin: 2px;">
<img alt="Chat" src="https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20Qwen%20Chat%20-536af5" style="display: inline-block; vertical-align: middle;"/>
</a>
## Qwen3 Highlights
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features:
- **Uniquely support of seamless switching between thinking mode** (for complex logical reasoning, math, and coding) and **non-thinking mode** (for efficient, general-purpose dialogue) **within single model**, ensuring optimal performance across various scenarios.
- **Significantly enhancement in its reasoning capabilities**, surpassing previous QwQ (in thinking mode) and Qwen2.5 instruct models (in non-thinking mode) on mathematics, code generation, and commonsense logical reasoning.
- **Superior human preference alignment**, excelling in creative writing, role-playing, multi-turn dialogues, and instruction following, to deliver a more natural, engaging, and immersive conversational experience.
- **Expertise in agent capabilities**, enabling precise integration with external tools in both thinking and unthinking modes and achieving leading performance among open-source models in complex agent-based tasks.
- **Support of 100+ languages and dialects** with strong capabilities for **multilingual instruction following** and **translation**.
## Model Overview
**Qwen3-14B** has the following features:
- Type: Causal Language Models
- Training Stage: Pretraining & Post-training
- Number of Parameters: 14.8B
- Number of Paramaters (Non-Embedding): 13.2B
- Number of Layers: 40
- Number of Attention Heads (GQA): 40 for Q and 8 for KV
- Context Length: 32,768 natively and [131,072 tokens with YaRN](#processing-long-texts).
- Quantization: AWQ 4-bit
For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our [blog](https://qwenlm.github.io/blog/qwen3/), [GitHub](https://github.com/QwenLM/Qwen3), and [Documentation](https://qwen.readthedocs.io/en/latest/).
## Quickstart
The code of Qwen3 has been in the latest Hugging Face `transformers` and we advise you to use the latest version of `transformers`.
With `transformers<4.51.0`, you will encounter the following error:
```
KeyError: 'qwen3'
```
The following contains a code snippet illustrating how to use the model generate content based on given inputs.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "Qwen/Qwen3-14B-AWQ"
# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map="auto"
)
# prepare the model input
prompt = "Give me a short introduction to large language model."
messages = [
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,
enable_thinking=True # Switches between thinking and non-thinking modes. Default is True.
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
# conduct text completion
generated_ids = model.generate(
**model_inputs,
max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
# parsing thinking content
try:
# rindex finding 151668 (</think>)
index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
index = 0
thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")
print("thinking content:", thinking_content)
print("content:", content)
```
For deployment, you can use `sglang>=0.4.6.post1` or `vllm>=0.8.5` or to create an OpenAI-compatible API endpoint:
- SGLang:
```shell
python -m sglang.launch_server --model-path Qwen/Qwen3-14B-AWQ --reasoning-parser qwen3
```
- vLLM:
```shell
vllm serve Qwen/Qwen3-14B-AWQ --enable-reasoning --reasoning-parser deepseek_r1
```
Also check out our [AWQ documentation](https://qwen.readthedocs.io/en/latest/quantization/awq.html) for more usage guide.
## Switching Between Thinking and Non-Thinking Mode
> [!TIP]
> The `enable_thinking` switch is also available in APIs created by SGLang and vLLM.
> Please refer to our documentation for [SGLang](https://qwen.readthedocs.io/en/latest/deployment/sglang.html#thinking-non-thinking-modes) and [vLLM](https://qwen.readthedocs.io/en/latest/deployment/vllm.html#thinking-non-thinking-modes) users.
### `enable_thinking=True`
By default, Qwen3 has thinking capabilities enabled, similar to QwQ-32B. This means the model will use its reasoning abilities to enhance the quality of generated responses. For example, when explicitly setting `enable_thinking=True` or leaving it as the default value in `tokenizer.apply_chat_template`, the model will engage its thinking mode.
```python
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,
enable_thinking=True # True is the default value for enable_thinking
)
```
In this mode, the model will generate think content wrapped in a `<think>...</think>` block, followed by the final response.
> [!NOTE]
> For thinking mode, use `Temperature=0.6`, `TopP=0.95`, `TopK=20`, and `MinP=0` (the default setting in `generation_config.json`). **DO NOT use greedy decoding**, as it can lead to performance degradation and endless repetitions. For more detailed guidance, please refer to the [Best Practices](#best-practices) section.
### `enable_thinking=False`
We provide a hard switch to strictly disable the model's thinking behavior, aligning its functionality with the previous Qwen2.5-Instruct models. This mode is particularly useful in scenarios where disabling thinking is essential for enhancing efficiency.
```python
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,
enable_thinking=False # Setting enable_thinking=False disables thinking mode
)
```
In this mode, the model will not generate any think content and will not include a `<think>...</think>` block.
> [!NOTE]
> For non-thinking mode, we suggest using `Temperature=0.7`, `TopP=0.8`, `TopK=20`, and `MinP=0`. For more detailed guidance, please refer to the [Best Practices](#best-practices) section.
### Advanced Usage: Switching Between Thinking and Non-Thinking Modes via User Input
We provide a soft switch mechanism that allows users to dynamically control the model's behavior when `enable_thinking=True`. Specifically, you can add `/think` and `/no_think` to user prompts or system messages to switch the model's thinking mode from turn to turn. The model will follow the most recent instruction in multi-turn conversations.
Here is an example of a multi-turn conversation:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
class QwenChatbot:
def __init__(self, model_name="Qwen/Qwen3-14B-AWQ"):
self.tokenizer = AutoTokenizer.from_pretrained(model_name)
self.model = AutoModelForCausalLM.from_pretrained(model_name)
self.history = []
def generate_response(self, user_input):
messages = self.history + [{"role": "user", "content": user_input}]
text = self.tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
inputs = self.tokenizer(text, return_tensors="pt")
response_ids = self.model.generate(**inputs, max_new_tokens=32768)[0][len(inputs.input_ids[0]):].tolist()
response = self.tokenizer.decode(response_ids, skip_special_tokens=True)
# Update history
self.history.append({"role": "user", "content": user_input})
self.history.append({"role": "assistant", "content": response})
return response
# Example Usage
if __name__ == "__main__":
chatbot = QwenChatbot()
# First input (without /think or /no_think tags, thinking mode is enabled by default)
user_input_1 = "How many r's in strawberries?"
print(f"User: {user_input_1}")
response_1 = chatbot.generate_response(user_input_1)
print(f"Bot: {response_1}")
print("----------------------")
# Second input with /no_think
user_input_2 = "Then, how many r's in blueberries? /no_think"
print(f"User: {user_input_2}")
response_2 = chatbot.generate_response(user_input_2)
print(f"Bot: {response_2}")
print("----------------------")
# Third input with /think
user_input_3 = "Really? /think"
print(f"User: {user_input_3}")
response_3 = chatbot.generate_response(user_input_3)
print(f"Bot: {response_3}")
```
> [!NOTE]
> For API compatibility, when `enable_thinking=True`, regardless of whether the user uses `/think` or `/no_think`, the model will always output a block wrapped in `<think>...</think>`. However, the content inside this block may be empty if thinking is disabled.
> When `enable_thinking=False`, the soft switches are not valid. Regardless of any `/think` or `/no_think` tags input by the user, the model will not generate think content and will not include a `<think>...</think>` block.
## Agentic Use
Qwen3 excels in tool calling capabilities. We recommend using [Qwen-Agent](https://github.com/QwenLM/Qwen-Agent) to make the best use of agentic ability of Qwen3. Qwen-Agent encapsulates tool-calling templates and tool-calling parsers internally, greatly reducing coding complexity.
To define the available tools, you can use the MCP configuration file, use the integrated tool of Qwen-Agent, or integrate other tools by yourself.
```python
from qwen_agent.agents import Assistant
# Define LLM
llm_cfg = {
'model': 'Qwen3-14B-AWQ',
# Use the endpoint provided by Alibaba Model Studio:
# 'model_type': 'qwen_dashscope',
# 'api_key': os.getenv('DASHSCOPE_API_KEY'),
# Use a custom endpoint compatible with OpenAI API:
'model_server': 'http://localhost:8000/v1', # api_base
'api_key': 'EMPTY',
# Other parameters:
# 'generate_cfg': {
# # Add: When the response content is `<think>this is the thought</think>this is the answer;
# # Do not add: When the response has been separated by reasoning_content and content.
# 'thought_in_content': True,
# },
}
# Define Tools
tools = [
{'mcpServers': { # You can specify the MCP configuration file
'time': {
'command': 'uvx',
'args': ['mcp-server-time', '--local-timezone=Asia/Shanghai']
},
"fetch": {
"command": "uvx",
"args": ["mcp-server-fetch"]
}
}
},
'code_interpreter', # Built-in tools
]
# Define Agent
bot = Assistant(llm=llm_cfg, function_list=tools)
# Streaming generation
messages = [{'role': 'user', 'content': 'https://qwenlm.github.io/blog/ Introduce the latest developments of Qwen'}]
for responses in bot.run(messages=messages):
pass
print(responses)
```
## Processing Long Texts
Qwen3 natively supports context lengths of up to 32,768 tokens. For conversations where the total length (including both input and output) significantly exceeds this limit, we recommend using RoPE scaling techniques to handle long texts effectively. We have validated the model's performance on context lengths of up to 131,072 tokens using the [YaRN](https://arxiv.org/abs/2309.00071) method.
YaRN is currently supported by several inference frameworks, e.g., `transformers` for local use, `vllm` and `sglang` for deployment. In general, there are two approaches to enabling YaRN for supported frameworks:
- Modifying the model files:
In the `config.json` file, add the `rope_scaling` fields:
```json
{
...,
"rope_scaling": {
"rope_type": "yarn",
"factor": 4.0,
"original_max_position_embeddings": 32768
}
}
```
- Passing command line arguments:
For `vllm`, you can use
```shell
vllm serve ... --rope-scaling '{"rope_type":"yarn","factor":4.0,"original_max_position_embeddings":32768}' --max-model-len 131072
```
For `sglang`, you can use
```shell
python -m sglang.launch_server ... --json-model-override-args '{"rope_scaling":{"rope_type":"yarn","factor":4.0,"original_max_position_embeddings":32768}}'
```
> [!IMPORTANT]
> If you encounter the following warning
> ```
> Unrecognized keys in `rope_scaling` for 'rope_type'='yarn': {'original_max_position_embeddings'}
> ```
> please upgrade `transformers>=4.51.0`.
> [!NOTE]
> All the notable open-source frameworks implement static YaRN, which means the scaling factor remains constant regardless of input length, **potentially impacting performance on shorter texts.**
> We advise adding the `rope_scaling` configuration only when processing long contexts is required.
> It is also recommended to modify the `factor` as needed. For example, if the typical context length for your application is 65,536 tokens, it would be better to set `factor` as 2.0.
> [!NOTE]
> The default `max_position_embeddings` in `config.json` is set to 40,960. This allocation includes reserving 32,768 tokens for outputs and 8,192 tokens for typical prompts, which is sufficient for most scenarios involving short text processing. If the average context length does not exceed 32,768 tokens, we do not recommend enabling YaRN in this scenario, as it may potentially degrade model performance.
> [!TIP]
> The endpoint provided by Alibaba Model Studio supports dynamic YaRN by default and no extra configuration is needed.
## Performance
| Mode | QUANTIZATION TYPE | LiveBench 2024-11-25 | GPQA | MMLU-Redux | AIME24 |
| --- | --- | --- | --- | --- | --- |
| Thinking | bf16 | 71.3 | 64.0 | 88.6 | 79.3 |
| Thinking | AWQ-int4 | 70.0 | 62.1 | 88.5 | 77.0 |
| Non-Thinking | bf16 | 59.6 | 54.8 | 82.0 | - |
| Non-Thinking | AWQ-int4 | 57.4 | 53.8 | 81.5 | - |
## Best Practices
To achieve optimal performance, we recommend the following settings:
1. **Sampling Parameters**:
- For thinking mode (`enable_thinking=True`), use `Temperature=0.6`, `TopP=0.95`, `TopK=20`, and `MinP=0`. **DO NOT use greedy decoding**, as it can lead to performance degradation and endless repetitions.
- For non-thinking mode (`enable_thinking=False`), we suggest using `Temperature=0.7`, `TopP=0.8`, `TopK=20`, and `MinP=0`.
- For supported frameworks, you can adjust the `presence_penalty` parameter between 0 and 2 to reduce endless repetitions. **We strongly recommend setting this value to 1.5 for quantized models.** However, using a higher value may occasionally result in language mixing and a slight decrease in model performance.
2. **Adequate Output Length**: We recommend using an output length of 32,768 tokens for most queries. For benchmarking on highly complex problems, such as those found in math and programming competitions, we suggest setting the max output length to 38,912 tokens. This provides the model with sufficient space to generate detailed and comprehensive responses, thereby enhancing its overall performance.
3. **Standardize Output Format**: We recommend using prompts to standardize model outputs when benchmarking.
- **Math Problems**: Include "Please reason step by step, and put your final answer within \boxed{}." in the prompt.
- **Multiple-Choice Questions**: Add the following JSON structure to the prompt to standardize responses: "Please show your choice in the `answer` field with only the choice letter, e.g., `"answer": "C"`."
4. **No Thinking Content in History**: In multi-turn conversations, the historical model output should only include the final output part and does not need to include the thinking content. It is implemented in the provided chat template in Jinja2. However, for frameworks that do not directly use the Jinja2 chat template, it is up to the developers to ensure that the best practice is followed.
### Citation
If you find our work helpful, feel free to give us a cite.
```
@misc{qwen3technicalreport,
title={Qwen3 Technical Report},
author={Qwen Team},
year={2025},
eprint={2505.09388},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2505.09388},
}
```

38
config.json Normal file
View File

@@ -0,0 +1,38 @@
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 17408,
"max_position_embeddings": 40960,
"max_window_layers": 40,
"model_type": "qwen3",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 8,
"quantization_config": {
"bits": 4,
"group_size": 128,
"modules_to_not_convert": [],
"quant_method": "awq",
"version": "gemm",
"zero_point": true
},
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.51.3",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}

13
generation_config.json Normal file
View File

@@ -0,0 +1,13 @@
{
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"temperature": 0.6,
"top_k": 20,
"top_p": 0.95,
"transformers_version": "4.51.0"
}

151388
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
model-00001-of-00002.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:668eb0f1356638310db286f4819b223c12e3916934123f1a81b2b2c0e148c6a2
size 4988339832

3
model-00002-of-00002.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c3c1625df80fe01211038bfa520629ebde6adf776556aa80cd49696d986d6657
size 4988350408

1010
model.safetensors.index.json Normal file
View File

File diff suppressed because it is too large Load Diff

609
script.py Normal file
View File

@@ -0,0 +1,609 @@
# script.py — Qwen3-14B-AWQ + OUR decomposition pipeline (Srikar's offline
# wheelhouse used ONLY as the loading mechanism, not his prompt).
# =============================================================================
# WHAT CHANGED vs the 0.104 baseline (single conceptual variable = the model):
# 1. Base model: Qwen2.5-14B-bnb-4bit -> Qwen3-14B-AWQ.
# 2. Dependency install: instead of `pip install --no-deps bitsandbytes`
# (base env), we install the Qwen3 stack from BUNDLED wheels with
# `pip install --no-index --no-deps --target <RUNTIME_DIR>` and prepend
# that dir to sys.path. This NEVER touches the network and NEVER mutates
# base site-packages, so the grader's later hf_hub_download (metric.py)
# runs on the pristine base huggingface_hub -- the RemoteDisconnected
# class of failure cannot recur.
# 3. Chat template: pass enable_thinking=False (Qwen3 supports it; harmless
# on models that ignore it). We keep OUR own decomposition reasoning in
# the prompt rather than paying for Qwen3's <think> phase.
# Everything else -- symbolic evidence, FINAL ANSWERS contract, safe
# arithmetic, explanations, per-row crash safety, dynamic token budget,
# guaranteed one row per id -- is IDENTICAL to the proven 0.104 pipeline.
# match_letters bijection decoding is deliberately NOT added here; that is the
# next, separate experiment.
# =============================================================================
import os
import atexit
from pathlib import Path
_ORIGINAL_HF_HUB_OFFLINE = os.environ.get("HF_HUB_OFFLINE")
_ORIGINAL_TRANSFORMERS_OFFLINE = os.environ.get("TRANSFORMERS_OFFLINE")
def _restore_offline_env_vars():
for key, original in (("HF_HUB_OFFLINE", _ORIGINAL_HF_HUB_OFFLINE),
("TRANSFORMERS_OFFLINE", _ORIGINAL_TRANSFORMERS_OFFLINE)):
if original is None:
os.environ.pop(key, None)
else:
os.environ[key] = original
atexit.register(_restore_offline_env_vars)
os.environ.setdefault("HF_HUB_OFFLINE", "1")
os.environ.setdefault("TRANSFORMERS_OFFLINE", "1")
import subprocess, sys
import importlib
import importlib.metadata
SCRIPT_DIR = Path(__file__).resolve().parent
def emergency_submission_csv(reason, rows_so_far=None):
try:
import pandas as pd
if rows_so_far:
pd.DataFrame(rows_so_far).to_csv("submission.csv", index=False)
return
try:
df = pd.read_csv("/tmp/data/test.csv", dtype=str).fillna("")
ids = df["id"].tolist()
except Exception:
ids = []
import json as _json
rows = [{"id": i, "pred": _json.dumps([""]),
"explanation": f"EMERGENCY FALLBACK: {str(reason)[:150]}"} for i in ids]
pd.DataFrame(rows, columns=["id", "pred", "explanation"]).to_csv("submission.csv", index=False)
except Exception:
try:
with open("submission.csv", "w") as f:
f.write("id,pred,explanation\n")
except Exception:
pass
def write_submission_csv(rows_list):
import csv as _csv
tmp_path = "submission.csv.tmp"
with open(tmp_path, "w", newline="", encoding="utf-8") as f:
w = _csv.DictWriter(f, fieldnames=["id", "pred", "explanation"])
w.writeheader()
for row in rows_list:
w.writerow(row)
os.replace(tmp_path, "submission.csv")
# =============================================================================
# OFFLINE WHEELHOUSE INSTALL (adapted from the public 0.147 submissions).
# Installs the Qwen3-compatible stack from wheels bundled inside this repo,
# to an isolated --target dir that we prepend to sys.path. --no-index means
# pip never contacts the network (the sandbox has no working index anyway);
# --target means base site-packages is untouched, so scoring stays safe.
# =============================================================================
WHEELHOUSE = Path(os.environ.get("QWEN3_WHEELHOUSE", str(SCRIPT_DIR / "wheelhouse")))
RUNTIME_DIR = Path(os.environ.get("QWEN3_RUNTIME_DIR", "/tmp/qwen3deps"))
RUNTIME_PACKAGES = {
"transformers": "4.51.3",
"tokenizers": "0.21.1",
"huggingface_hub": "0.30.2",
"autoawq": "0.2.9",
}
RUNTIME_WHEELS = (
"transformers-4.51.3-py3-none-any.whl",
"tokenizers-0.21.1-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl",
"huggingface_hub-0.30.2-py3-none-any.whl",
"autoawq-0.2.9-py3-none-any.whl",
)
def ensure_runtime_dependencies():
wheel_paths = [WHEELHOUSE / name for name in RUNTIME_WHEELS]
missing = [str(p) for p in wheel_paths if not p.is_file()]
if missing:
raise FileNotFoundError(f"Missing offline runtime wheels: {missing}")
marker = RUNTIME_DIR / ".iol-qwen3-runtime-v1"
if not marker.is_file():
RUNTIME_DIR.mkdir(parents=True, exist_ok=True)
subprocess.run(
[sys.executable, "-m", "pip", "install",
"--disable-pip-version-check", "--no-index", "--no-deps",
"--upgrade", "--target", str(RUNTIME_DIR),
*(str(p) for p in wheel_paths)],
check=True, timeout=300,
)
marker.write_text("offline Qwen3 runtime installed\n", encoding="utf-8")
runtime_path = str(RUNTIME_DIR)
if runtime_path in sys.path:
sys.path.remove(runtime_path)
sys.path.insert(0, runtime_path)
importlib.invalidate_caches()
versions = {}
for pkg in RUNTIME_PACKAGES:
try:
versions[pkg] = importlib.metadata.version(pkg)
except importlib.metadata.PackageNotFoundError:
versions[pkg] = "missing"
print(f"offline runtime active: {versions}", flush=True)
try:
ensure_runtime_dependencies()
except Exception as e:
emergency_submission_csv(f"wheelhouse install failed: {e}")
raise
import re, json, time, ast as pyast
import pandas as pd
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
MODEL_ID = "."
TIME_LIMIT_S = 30 * 60
SETUP_BUFFER_S = 360
start_time = time.time()
try:
df = pd.read_csv("/tmp/data/test.csv", dtype=str).fillna("")
placeholder_rows = [{"id": rid, "pred": json.dumps([""]),
"explanation": "Placeholder written before model load."}
for rid in df["id"].tolist()]
write_submission_csv(placeholder_rows)
print(f"Pre-load checkpoint written for {len(placeholder_rows)} rows.", flush=True)
# AWQ backend preflight (diagnostic only, never fatal).
try:
from awq.modules.linear import gemm as awq_gemm
print(f"AWQ backends: extension={awq_gemm.awq_ext is not None}, "
f"triton={getattr(awq_gemm, 'TRITON_AVAILABLE', None)}", flush=True)
except Exception as exc:
print(f"AWQ backend preflight warning: {exc}", flush=True)
try:
tok = AutoTokenizer.from_pretrained(MODEL_ID, local_files_only=True)
print("Tokenizer loaded (fast).", flush=True)
except Exception as e:
print(f"Fast tokenizer failed ({e}); falling back to use_fast=False.", flush=True)
tok = AutoTokenizer.from_pretrained(MODEL_ID, use_fast=False, local_files_only=True)
print("Tokenizer loaded (slow fallback).", flush=True)
model = AutoModelForCausalLM.from_pretrained(
MODEL_ID, torch_dtype=torch.float16, device_map="auto", local_files_only=True,
).eval()
print(f"Model loaded | memory footprint: {round(model.get_memory_footprint()/1e9, 1)} GB | "
f"quantized: {getattr(model.config, 'quantization_config', None) is not None}", flush=True)
except Exception as e:
emergency_submission_csv(f"tokenizer/model load or test.csv read failed: {e}")
raise
n_rows = len(df)
actual_setup_elapsed = time.time() - start_time
per_row_budget = max(20, (TIME_LIMIT_S - actual_setup_elapsed) / max(n_rows, 1))
print(f"Setup took {actual_setup_elapsed:.0f}s | per_row_budget={per_row_budget:.0f}s "
f"for {n_rows} rows", flush=True)
# ---- Query parsing ----
def parse_items(query: str):
item_pat = re.compile(r"(?m)^\s*(\d+)\s*[.\)]\s*(.*)$")
matches = list(item_pat.finditer(query))
if matches:
preamble = query[:matches[0].start()].strip()
items = []
for i, m in enumerate(matches):
end = matches[i + 1].start() if i + 1 < len(matches) else len(query)
text = re.sub(r"^\s*\d+\s*[.\)]\s*", "", query[m.start():end].strip())
items.append(text)
return preamble, items, True
rng = re.search(r"[\(\[]?\s*(\d+)\s*(?:[-–—:]|to)\s*(\d+)\s*[\)\]]?", query, flags=re.IGNORECASE)
if rng:
lo, hi = int(rng.group(1)), int(rng.group(2))
if 0 < hi - lo < 100:
items = []
for k in range(lo, hi + 1):
line_match = re.search(rf"(?m)^.*\(\s*{k}\s*\).*$", query)
if line_match:
clue = re.sub(rf"\(\s*{k}\s*\)", "", line_match.group(0)).strip()
clue = re.sub(r"\|\s*\|", "|", clue)
clue = re.sub(r"\s{2,}", " ", clue).strip(" |")
items.append(clue if clue else f"the numbered item {k} from the examples above")
else:
items.append(f"the numbered item {k} from the examples above")
return query.strip(), items, True
csv_nums = re.findall(r"(?m)^\s*(\d+)\s*,\s*(\d+(?:\s*,\s*\d+)*)\s*$", query)
if csv_nums:
all_nums = re.findall(r"\d+", " ".join(csv_nums[0]))
return query.strip(), [f"the numbered item {n}" for n in all_nums], True
return query.strip(), [], False
TASK_GUIDANCE = {
"translation": "give the translated form only, in the language asked.",
"fill_blanks": "give only the missing form for each blank.",
"match_letters": "give only the option letter (for example A, B, C).",
"text_to_num": "give the number in digits.",
"num_to_text": "give the number written out in words, in the language asked.",
}
DEFAULT_GUIDANCE = "give exactly what the instruction asks, nothing else."
from difflib import SequenceMatcher
from collections import defaultdict
def extract_forms_from_context(context: str):
forms = []
for line in context.splitlines():
line = line.strip()
if not line:
continue
pipe_count = line.count("|")
if 0 < pipe_count <= 3:
first_field = re.sub(r"^\s*\d+\s*[.\)]\s*", "", line.split("|")[0].strip()).strip()
if first_field:
forms.append(first_field)
elif pipe_count == 0:
for t in line.split():
t_clean = re.sub(r"^\s*\d+\s*[.\)]\s*", "", t).strip(".,;:")
if t_clean and len(t_clean) > 1:
forms.append(t_clean)
seen, unique_forms = set(), []
for f in forms:
if f not in seen:
seen.add(f)
unique_forms.append(f)
return unique_forms
def extract_explicit_pairs(context: str):
pairs = []
for line in context.splitlines():
line = line.strip()
if not (0 < line.count("|") <= 3):
continue
fields = [re.sub(r"^\s*\d+\s*[.\)]\s*", "", f.strip()).strip() for f in line.split("|")]
fields = [f for f in fields if f]
if len(fields) >= 2:
pairs.append((fields[0], fields[1]))
return pairs
def edit_signature(a: str, b: str):
sm = SequenceMatcher(None, a, b, autojunk=False)
all_ops = sm.get_opcodes()
ops = [op for op in all_ops if op[0] != "equal"]
if not ops or len(ops) > 2:
return None
equal_len = sum((i2 - i1) for tag, i1, i2, j1, j2 in all_ops if tag == "equal")
if equal_len < 2:
return None
tag, i1, i2, j1, j2 = ops[0]
removed, inserted = a[i1:i2], b[j1:j2]
if i1 == 0:
pos = "prefix"
elif i2 == len(a):
pos = "suffix"
else:
pos = "infix"
return (pos, removed, inserted)
def find_transformation_families(pairs):
groups = defaultdict(list)
for a, b in pairs:
if not a or not b or a == b:
continue
sig = edit_signature(a, b)
if sig:
groups[sig].append((a, b))
families = []
for sig, grp in groups.items():
unique_pairs = list(dict.fromkeys(grp))
if len(unique_pairs) >= 2:
pos, removed, inserted = sig
removed_disp = removed if removed else "(nothing)"
inserted_disp = inserted if inserted else "(nothing)"
examples = "; ".join(f"{a}->{b}" for a, b in unique_pairs[:4])
families.append((len(unique_pairs),
f"{pos} change: '{removed_disp}' -> '{inserted_disp}' (seen in: {examples})"))
families.sort(key=lambda x: -x[0])
return [f for _, f in families]
def detect_reduplication(forms):
findings = []
for w in forms:
n = len(w)
found = False
for length in range(2, n // 2 + 1):
for start in range(0, n - 2 * length + 1):
chunk = w[start:start + length]
nxt = w[start + length:start + 2 * length]
if chunk == nxt:
findings.append(f"reduplication in '{w}': '{chunk}' repeated")
found = True
break
if found:
break
return findings
def build_symbolic_evidence(context: str) -> str:
forms = extract_forms_from_context(context)
pairs = extract_explicit_pairs(context)
families = find_transformation_families(pairs) if pairs else []
redup = detect_reduplication(forms) if forms else []
lines = []
if families:
lines.append("Transformation families found (patterns supported by multiple examples):")
for f in families[:3]:
lines.append(f"- {f}")
if redup:
lines.append("Reduplication detected:")
for r in redup[:2]:
lines.append(f"- {r}")
if not lines:
return ""
return ("\n\nSYMBOLIC EVIDENCE (deterministically computed from the examples above; "
"may be incomplete -- verify against the examples, do not trust blindly):\n"
+ "\n".join(lines))
def build_messages(context, query, task_type):
preamble, items, count_known = parse_items(query)
guidance = TASK_GUIDANCE.get(task_type, DEFAULT_GUIDANCE)
symbolic_evidence = build_symbolic_evidence(context)
system = (
"You solve puzzles about a language you have never seen. Everything you "
"need is in the examples below. Use only the examples, not outside "
"knowledge of any language. You may meet a task type you have never "
"seen -- read the instruction and examples, and answer in the same "
"form they use."
)
number_note = ""
if task_type == "text_to_num":
number_note = (
"\n\nAlso add one more line after your answers, exactly like this:\n"
"COMPUTE: expr1 | expr2\n"
"where each expr is a plain arithmetic expression (digits, +, -, *, "
"parentheses only) for that item's value, one per answer, matching "
"the rule you found."
)
options_note = ""
if task_type == "match_letters":
options = extract_match_letter_options(context)
if options:
options_note = (
f"\n\nThe only valid answers are: {', '.join(options)}. "
f"Do not use any other letter."
)
if count_known:
n_items = len(items)
slots = "\n\n".join(f"Question {i+1}: {it}\nAnswer {i+1}:" for i, it in enumerate(items))
user = (
f"EXAMPLES:\n{context.strip()}"
f"{symbolic_evidence}\n\n"
f"--- The examples end here. The questions begin below. ---\n\n"
f"For each question: find the rule that explains ALL the examples above "
f"(not just one). Check it against every example before answering. "
f"For this task type, {guidance}\n\n"
f"{preamble}\n\n{slots}\n\n"
f"After answering all {n_items} questions, finish with exactly one line, "
f"all {n_items} answers in order separated by ' | ':\n"
f"FINAL ANSWERS: answer1 | answer2"
f"{number_note}"
f"{options_note}"
)
else:
n_items = None
user = (
f"EXAMPLES:\n{context.strip()}"
f"{symbolic_evidence}\n\n"
f"--- The examples end here. The question begins below. ---\n\n"
f"Find the rule that explains ALL the examples above (not just one). "
f"Check it against every example before answering. "
f"For this task type, {guidance}\n\n"
f"{preamble}\n\n"
f"Answer every item asked above, in order, one per answer. Finish "
f"with exactly one line, all your answers in order separated by ' | ':\n"
f"FINAL ANSWERS: answer1 | answer2"
f"{number_note}"
f"{options_note}"
)
return [{"role": "system", "content": system}, {"role": "user", "content": user}], n_items
def build_repair_messages(query, n_items, bad_text):
n_desc = f"exactly {n_items}" if n_items is not None else "one per item asked"
system = "You reformat answers. Output nothing except the requested line."
user = (
f"Question:\n{query.strip()}\n\n"
f"A previous attempt produced:\n{bad_text[:600]}\n\n"
f"Extract or restate {n_desc} final answers, in order, as ONE line:\n"
f"FINAL ANSWERS: answer1 | answer2"
)
return [{"role": "system", "content": system}, {"role": "user", "content": user}]
_ALLOWED_BINOPS = (pyast.Add, pyast.Sub, pyast.Mult)
def safe_arithmetic(expr: str):
try:
tree = pyast.parse(expr.strip(), mode="eval")
except Exception:
return None
def _eval(node):
if isinstance(node, pyast.Expression):
return _eval(node.body)
if isinstance(node, pyast.Constant) and isinstance(node.value, (int, float)):
return node.value
if isinstance(node, pyast.BinOp) and isinstance(node.op, _ALLOWED_BINOPS):
left, right = _eval(node.left), _eval(node.right)
if left is None or right is None:
return None
if isinstance(node.op, pyast.Add): return left + right
if isinstance(node.op, pyast.Sub): return left - right
if isinstance(node.op, pyast.Mult): return left * right
if isinstance(node, pyast.UnaryOp) and isinstance(node.op, pyast.USub):
v = _eval(node.operand)
return -v if v is not None else None
return None
return _eval(tree)
def clean_answer(a: str) -> str:
a = re.sub(r"(?i)^\s*(the\s+)?(final\s+)?answer\s*\d*\s*(is)?\s*:\s*", "", a).strip()
a = re.sub(r"(?i)^\s*is\s*:\s*", "", a).strip()
a = a.strip("* ")
return a.strip(" .\"'“”‘’")
def extract(text):
m = list(re.finditer(r"final answers?\s*:?\s*\**", text, flags=re.IGNORECASE))
if m:
tail = text[m[-1].end():]
stop = re.search(r"(?i)compute\s*:", tail)
if stop:
tail = tail[:stop.start()]
tail = tail.replace("**", " ").strip()
candidate = " ".join(tail.splitlines())
parts = [clean_answer(p) for p in candidate.split("|") if p.strip()]
if parts:
return parts, m[-1].start()
lines = [ln.strip() for ln in text.splitlines() if ln.strip()]
fallback = []
for ln in lines:
ln_clean = re.sub(r"^\s*\d+\s*[.\)]\s*", "", ln)
if "|" in ln_clean:
fallback.extend(clean_answer(p) for p in ln_clean.split("|") if p.strip())
else:
fallback.append(clean_answer(ln_clean))
return fallback, None
def extract_compute_overrides(text, n_answers):
m = re.search(r"compute\s*:\s*(.+)", text, flags=re.IGNORECASE)
if not m:
return {}
exprs = [e.strip() for e in m.group(1).split("|")]
overrides = {}
for i, e in enumerate(exprs[:n_answers]):
val = safe_arithmetic(e)
if val is not None:
overrides[i] = str(int(val)) if float(val).is_integer() else str(val)
return overrides
# ---- Generation. enable_thinking=False keeps Qwen3 in its fast, non-<think>
# mode; our decomposition prompt supplies the reasoning instead. The kwarg is
# harmless on templates that ignore it. Both API-shape branches pass it. ----
def generate(messages, max_new_tokens, constraint_fn=None):
def _try_generate(gen_kwargs):
try:
enc = tok.apply_chat_template(
messages, add_generation_prompt=True, enable_thinking=False,
return_tensors="pt", return_dict=True,
).to(model.device)
input_len = enc["input_ids"].shape[-1]
with torch.no_grad():
out = model.generate(**enc, **gen_kwargs)
except Exception:
ids = tok.apply_chat_template(
messages, add_generation_prompt=True, enable_thinking=False,
return_tensors="pt",
).to(model.device)
input_len = ids.shape[-1]
with torch.no_grad():
out = model.generate(ids, **gen_kwargs)
return out, input_len
base_kwargs = {"max_new_tokens": max_new_tokens, "do_sample": False}
if constraint_fn is not None:
try:
out, input_len = _try_generate({**base_kwargs, "prefix_allowed_tokens_fn": constraint_fn})
except Exception:
out, input_len = _try_generate(base_kwargs)
else:
out, input_len = _try_generate(base_kwargs)
return tok.decode(out[0][input_len:], skip_special_tokens=True).strip()
EXPLANATION_SYSTEM = (
"Summarize the following reasoning into a few short bullet points: the "
"rule or pattern found in the data and the key evidence for the answer. "
"Be concise and structured -- do not repeat the full reasoning."
)
EXPLANATION_FALLBACK = "Answer derived from patterns found in the examples above."
_LETTER_CONSTRAINT_CACHE = {}
def build_letter_constraint_fn(tok, valid_letters):
cache_key = (id(tok), tuple(sorted(valid_letters)))
if cache_key in _LETTER_CONSTRAINT_CACHE:
return _LETTER_CONSTRAINT_CACHE[cache_key]
try:
allowed_chars = set(valid_letters) | set(" |\n\t\r")
eos = tok.eos_token_id
pieces = []
for token_id in range(len(tok)):
if token_id == eos:
continue
piece = tok.decode([token_id], skip_special_tokens=False)
if piece and all(c in allowed_chars for c in piece):
pieces.append(token_id)
allowed_ids = ([eos] if eos is not None else []) + pieces
def allowed(_batch_id, _input_ids):
return allowed_ids if allowed_ids else list(range(len(tok)))
_LETTER_CONSTRAINT_CACHE[cache_key] = allowed
return allowed
except Exception:
return None
def extract_match_letter_options(context: str):
found = set()
for line in context.splitlines():
for m in re.finditer(r"(?:^|\s)([A-Z])[.\)]\s+\S", line):
found.add(m.group(1))
if not found:
return None
letters = sorted(found)
expected = [chr(ord("A") + i) for i in range(len(letters))]
if letters != expected:
return None
if not (2 <= len(letters) <= 26):
return None
return letters
rows = []
processed_ids = set()
try:
for _, r in df.iterrows():
try:
elapsed = time.time() - start_time
remaining = TIME_LIMIT_S - elapsed
budget_left_rows = max(n_rows - len(rows), 1)
row_budget = remaining / budget_left_rows
time_based_cap = 1280 if row_budget > per_row_budget else 640
task_type = r.get("task_type", "")
messages, n_items = build_messages(r["context"], r["query"], task_type)
if n_items:
item_based_cap = max(640, min(1536, n_items * 48 + 256))
tokens_cap = min(time_based_cap, item_based_cap)
else:
tokens_cap = time_based_cap
text = generate(messages, tokens_cap)
answers, marker_pos = extract(text)
if task_type == "text_to_num":
overrides = extract_compute_overrides(text, len(answers))
for idx, val in overrides.items():
if idx < len(answers):
answers[idx] = val
if (marker_pos is None or not answers) and remaining > SETUP_BUFFER_S:
repair_constraint = None
if task_type == "match_letters":
repair_options = extract_match_letter_options(r["context"])
if repair_options:
repair_constraint = build_letter_constraint_fn(tok, repair_options)
repair_text = generate(build_repair_messages(r["query"], n_items, text), 128,
constraint_fn=repair_constraint)
rep, rep_pos = extract(repair_text)
if rep:
answers, marker_pos = rep, rep_pos
if n_items is not None:
if len(answers) < n_items:
answers = answers + [answers[-1] if answers else ""] * (n_items - len(answers))
elif len(answers) > n_items and marker_pos is None:
answers = answers[:n_items]
if not answers:
answers = [""]
remaining_after = TIME_LIMIT_S - (time.time() - start_time)
budget_left_after = max(n_rows - len(rows) - 1, 0)
comfortable = remaining_after > (budget_left_after + 1) * per_row_budget * 1.3
if comfortable:
try:
explanation = generate(
[{"role": "system", "content": EXPLANATION_SYSTEM},
{"role": "user", "content": text}], 300,
) or EXPLANATION_FALLBACK
except Exception:
explanation = EXPLANATION_FALLBACK
else:
snippet = re.sub(r"\s{2,}", " ", text[:300]).strip()
explanation = snippet if snippet else EXPLANATION_FALLBACK
rows.append({"id": r["id"], "pred": json.dumps(answers, ensure_ascii=False),
"explanation": explanation})
processed_ids.add(r["id"])
write_submission_csv(rows)
print(f"{len(rows)}/{n_rows} answers={len(answers)} elapsed={time.time()-start_time:.0f}s", flush=True)
except Exception as e:
try:
_, fallback_items, fk = parse_items(r["query"])
n_fallback = len(fallback_items) if fk else 1
except Exception:
n_fallback = 1
rows.append({"id": r["id"], "pred": json.dumps([""] * n_fallback, ensure_ascii=False),
"explanation": EXPLANATION_FALLBACK})
processed_ids.add(r["id"])
write_submission_csv(rows)
print(f"ROW ERROR on {r['id']}: {e}", flush=True)
if time.time() - start_time > TIME_LIMIT_S - 60:
print("Time budget nearly exhausted, stopping early.", flush=True)
break
for _, r in df.iterrows():
if r["id"] in processed_ids:
continue
try:
_, fallback_items, fk = parse_items(r["query"])
n_fallback = len(fallback_items) if fk else 1
except Exception:
n_fallback = 1
rows.append({"id": r["id"], "pred": json.dumps([""] * n_fallback, ensure_ascii=False),
"explanation": EXPLANATION_FALLBACK})
write_submission_csv(rows)
print("DONE.", flush=True)
except Exception as e:
emergency_submission_csv(f"main loop failed: {e}", rows_so_far=rows if rows else None)
print(f"FATAL, but submission.csv was written with {len(rows)} rows. Error: {e}", flush=True)

BIN
tokenizer.json (Stored with Git LFS) Normal file
View File

Binary file not shown.

239
tokenizer_config.json Normal file
View File

@@ -0,0 +1,239 @@
{
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151646": {
"content": "<|object_ref_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151647": {
"content": "<|object_ref_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151648": {
"content": "<|box_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151649": {
"content": "<|box_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"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": "<tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151666": {
"content": "</tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151667": {
"content": "<think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151668": {
"content": "</think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"bos_token": null,
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\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 {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- 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 {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

1
vocab.json Normal file
View File

File diff suppressed because one or more lines are too long

3
wheelhouse/autoawq-0.2.9-py3-none-any.whl Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:260786b85aa2b72840fe47d8ff5186a7c37a7327ea9339fe6af7a4ff1aa6b25b
size 115197

3
wheelhouse/huggingface_hub-0.30.2-py3-none-any.whl Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:68ff05969927058cfa41df4f2155d4bb48f5f54f719dd0390103eefa9b191e28
size 481433

3
wheelhouse/tokenizers-0.21.1-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2dd9a0061e403546f7377df940e866c3e678d7d4e9643d0461ea442b4f89e61a
size 3038874

3
wheelhouse/transformers-4.51.3-py3-none-any.whl Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fd3279633ceb2b777013234bbf0b4f5c2d23c4626b05497691f00cfda55e8a83
size 10383940