初始化项目，由ModelHub XC社区提供模型
Model: cs-552-2026-flab/multilingual_model Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
|||||||
|
*.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
|
||||||
301
README.md
Normal file
301
README.md
Normal file
@@ -0,0 +1,301 @@
|
|||||||
|
---
|
||||||
|
library_name: transformers
|
||||||
|
license: apache-2.0
|
||||||
|
license_link: https://huggingface.co/Qwen/Qwen3-1.7B/blob/main/LICENSE
|
||||||
|
pipeline_tag: text-generation
|
||||||
|
base_model:
|
||||||
|
- Qwen/Qwen3-1.7B-Base
|
||||||
|
---
|
||||||
|
|
||||||
|
# Qwen3-1.7B
|
||||||
|
<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
|
||||||
|
|
||||||
|
**Qwen3-1.7B** has the following features:
|
||||||
|
- Type: Causal Language Models
|
||||||
|
- Training Stage: Pretraining & Post-training
|
||||||
|
- Number of Parameters: 1.7B
|
||||||
|
- Number of Paramaters (Non-Embedding): 1.4B
|
||||||
|
- Number of Layers: 28
|
||||||
|
- Number of Attention Heads (GQA): 16 for Q and 8 for KV
|
||||||
|
- Context Length: 32,768
|
||||||
|
|
||||||
|
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/).
|
||||||
|
|
||||||
|
> [!TIP]
|
||||||
|
> If you encounter significant endless repetitions, please refer to the [Best Practices](#best-practices) section for optimal sampling parameters, and set the ``presence_penalty`` to 1.5.
|
||||||
|
|
||||||
|
## 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/Qwen3-1.7B"
|
||||||
|
|
||||||
|
# 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/Qwen3-1.7B --reasoning-parser qwen3
|
||||||
|
```
|
||||||
|
- vLLM:
|
||||||
|
```shell
|
||||||
|
vllm serve Qwen/Qwen3-1.7B --enable-reasoning --reasoning-parser deepseek_r1
|
||||||
|
```
|
||||||
|
|
||||||
|
For local use, applications such as Ollama, LMStudio, MLX-LM, llama.cpp, and KTransformers have also supported Qwen3.
|
||||||
|
|
||||||
|
## 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/Qwen3-1.7B"):
|
||||||
|
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': 'Qwen3-1.7B',
|
||||||
|
|
||||||
|
# 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)
|
||||||
|
```
|
||||||
|
|
||||||
|
## 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. 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},
|
||||||
|
}
|
||||||
|
```
|
||||||
91
chat_template.jinja
Normal file
91
chat_template.jinja
Normal file
@@ -0,0 +1,91 @@
|
|||||||
|
{%- set enable_thinking = false %}
|
||||||
|
{%- set flab_boxed_instruction = "Choose the best option. Do not write an explanation. Return exactly one final answer in the form \\boxed{LETTER}." %}
|
||||||
|
{%- if flab_boxed_instruction %}{{ '<|im_start|>system\n' + flab_boxed_instruction + '<|im_end|>\n' }}{%- endif %}{%- if tools %}
|
||||||
|
{{- '<|im_start|>system\n' }}
|
||||||
|
{%- if messages[0].role == 'system' %}
|
||||||
|
{{- messages[0].content + '\n\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- "# 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>" }}
|
||||||
|
{%- for tool in tools %}
|
||||||
|
{{- "\n" }}
|
||||||
|
{{- tool | tojson }}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- "\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" }}
|
||||||
|
{%- else %}
|
||||||
|
{%- if messages[0].role == 'system' %}
|
||||||
|
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||||
|
{%- for message in messages[::-1] %}
|
||||||
|
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||||
|
{%- 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>')) %}
|
||||||
|
{%- set ns.multi_step_tool = false %}
|
||||||
|
{%- set ns.last_query_index = index %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- for message in messages %}
|
||||||
|
{%- if message.content is string %}
|
||||||
|
{%- set content = message.content %}
|
||||||
|
{%- else %}
|
||||||
|
{%- set content = '' %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||||
|
{%- elif message.role == "assistant" %}
|
||||||
|
{%- set reasoning_content = '' %}
|
||||||
|
{%- if message.reasoning_content is string %}
|
||||||
|
{%- set reasoning_content = message.reasoning_content %}
|
||||||
|
{%- else %}
|
||||||
|
{%- if '</think>' in content %}
|
||||||
|
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||||
|
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if loop.index0 > ns.last_query_index %}
|
||||||
|
{%- if loop.last or (not loop.last and reasoning_content) %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||||
|
{%- else %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- else %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if message.tool_calls %}
|
||||||
|
{%- for tool_call in message.tool_calls %}
|
||||||
|
{%- if (loop.first and content) or (not loop.first) %}
|
||||||
|
{{- '\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if tool_call.function %}
|
||||||
|
{%- set tool_call = tool_call.function %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '<tool_call>\n{"name": "' }}
|
||||||
|
{{- tool_call.name }}
|
||||||
|
{{- '", "arguments": ' }}
|
||||||
|
{%- if tool_call.arguments is string %}
|
||||||
|
{{- tool_call.arguments }}
|
||||||
|
{%- else %}
|
||||||
|
{{- tool_call.arguments | tojson }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '}\n</tool_call>' }}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- elif message.role == "tool" %}
|
||||||
|
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||||
|
{{- '<|im_start|>user' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '\n<tool_response>\n' }}
|
||||||
|
{{- content }}
|
||||||
|
{{- '\n</tool_response>' }}
|
||||||
|
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- if add_generation_prompt %}
|
||||||
|
{{- '<|im_start|>assistant\n' }}
|
||||||
|
{%- if enable_thinking is defined and enable_thinking is false %}
|
||||||
|
{{- '<think>\n\n</think>\n\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
63
config.json
Normal file
63
config.json
Normal file
@@ -0,0 +1,63 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen3ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"dtype": "bfloat16",
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"head_dim": 128,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 2048,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 6144,
|
||||||
|
"layer_types": [
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention"
|
||||||
|
],
|
||||||
|
"max_position_embeddings": 40960,
|
||||||
|
"max_window_layers": 28,
|
||||||
|
"model_type": "qwen3",
|
||||||
|
"num_attention_heads": 16,
|
||||||
|
"num_hidden_layers": 28,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"pad_token_id": null,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_parameters": {
|
||||||
|
"rope_theta": 1000000,
|
||||||
|
"rope_type": "default"
|
||||||
|
},
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": true,
|
||||||
|
"transformers_version": "5.7.0",
|
||||||
|
"use_cache": true,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 151936
|
||||||
|
}
|
||||||
13
generation_config.json
Normal file
13
generation_config.json
Normal 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": "5.7.0"
|
||||||
|
}
|
||||||
107
hydra/.hydra/config.yaml
Normal file
107
hydra/.hydra/config.yaml
Normal file
@@ -0,0 +1,107 @@
|
|||||||
|
model:
|
||||||
|
hf_id: Qwen/Qwen3-1.7B
|
||||||
|
local_path: /shared-ro/models/Qwen3-1.7B
|
||||||
|
dtype: bfloat16
|
||||||
|
attn_impl: flash_attention_2
|
||||||
|
max_model_len: 4096
|
||||||
|
data:
|
||||||
|
name: nemotron_math
|
||||||
|
loader: load_nemotron_math
|
||||||
|
kwargs:
|
||||||
|
limit: 50000
|
||||||
|
split: train
|
||||||
|
max_total_tokens: 3800
|
||||||
|
seed: 0
|
||||||
|
training:
|
||||||
|
recipe: sft
|
||||||
|
epochs: 1
|
||||||
|
per_device_train_batch_size: 1
|
||||||
|
gradient_accumulation_steps: 16
|
||||||
|
learning_rate: 5.0e-06
|
||||||
|
warmup_ratio: 0.03
|
||||||
|
lr_scheduler_type: cosine
|
||||||
|
gradient_checkpointing: true
|
||||||
|
bf16: true
|
||||||
|
max_seq_length: 4096
|
||||||
|
max_steps: -1
|
||||||
|
max_grad_norm: 1.0
|
||||||
|
optim: adamw_torch
|
||||||
|
assistant_only_loss: true
|
||||||
|
logging_steps: 10
|
||||||
|
save_steps: 500
|
||||||
|
save_total_limit: 2
|
||||||
|
report_to: wandb
|
||||||
|
qlora: false
|
||||||
|
lora_r: 16
|
||||||
|
lora_alpha: 32
|
||||||
|
lora_dropout: 0.05
|
||||||
|
lora_target_modules:
|
||||||
|
- q_proj
|
||||||
|
- k_proj
|
||||||
|
- v_proj
|
||||||
|
- o_proj
|
||||||
|
- gate_proj
|
||||||
|
- up_proj
|
||||||
|
- down_proj
|
||||||
|
deepspeed: configs/deepspeed_zero2.json
|
||||||
|
adapter_model_dir: null
|
||||||
|
domain:
|
||||||
|
name: multilingual
|
||||||
|
thinking_mode: false
|
||||||
|
benchmark: multilingual
|
||||||
|
languages:
|
||||||
|
- it
|
||||||
|
- es
|
||||||
|
- zh
|
||||||
|
- ru
|
||||||
|
- hi
|
||||||
|
target_format: boxed
|
||||||
|
max_options: 20
|
||||||
|
reward_fn: multilingual
|
||||||
|
system_instruction: Choose the best option. Do not write an explanation. Return
|
||||||
|
exactly one final answer in the form \boxed{LETTER}.
|
||||||
|
template_boxed_instruction: Choose the best option. Do not write an explanation.
|
||||||
|
Return exactly one final answer in the form \boxed{LETTER}.
|
||||||
|
post_train:
|
||||||
|
enabled: false
|
||||||
|
merge_adapter: false
|
||||||
|
merged_output_dir: null
|
||||||
|
domain_override: null
|
||||||
|
evals: []
|
||||||
|
seed: 42
|
||||||
|
run_id: ${now:%Y%m%d_%H%M%S}
|
||||||
|
output_dir: /scratch/checkpoints/multilingual/a42-success-recipe-20260530/qwen-success-r64/merged
|
||||||
|
wandb:
|
||||||
|
project: flab-cs552
|
||||||
|
entity: cs-552-2026-flab
|
||||||
|
mode: null
|
||||||
|
tags: []
|
||||||
|
notes: null
|
||||||
|
eval:
|
||||||
|
model_dir: null
|
||||||
|
rows_source: samples
|
||||||
|
method: null
|
||||||
|
system_prompt: null
|
||||||
|
use_domain_system_prompt: false
|
||||||
|
force_domain_template: false
|
||||||
|
'n': 8
|
||||||
|
temperature: 0.7
|
||||||
|
top_p: 0.95
|
||||||
|
max_model_len: 4096
|
||||||
|
max_tokens: 4096
|
||||||
|
samples_dir: null
|
||||||
|
push:
|
||||||
|
model_dir: /scratch/checkpoints/multilingual/a42-success-recipe-20260530/qwen-success-r64/sft
|
||||||
|
base_model_dir: null
|
||||||
|
es:
|
||||||
|
base_model_dir: null
|
||||||
|
data: null
|
||||||
|
hf_push:
|
||||||
|
enabled: false
|
||||||
|
org: cs-552-2026-flab
|
||||||
|
repo: null
|
||||||
|
private: false
|
||||||
|
vllm_validate: true
|
||||||
|
commit_message: null
|
||||||
|
validate_after_train: false
|
||||||
|
vllm_validate: true
|
||||||
162
hydra/.hydra/hydra.yaml
Normal file
162
hydra/.hydra/hydra.yaml
Normal file
@@ -0,0 +1,162 @@
|
|||||||
|
hydra:
|
||||||
|
run:
|
||||||
|
dir: ${output_dir}/hydra
|
||||||
|
sweep:
|
||||||
|
dir: ${output_dir}/hydra_sweep
|
||||||
|
subdir: ${hydra.job.num}
|
||||||
|
launcher:
|
||||||
|
_target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher
|
||||||
|
sweeper:
|
||||||
|
_target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper
|
||||||
|
max_batch_size: null
|
||||||
|
params: null
|
||||||
|
help:
|
||||||
|
app_name: ${hydra.job.name}
|
||||||
|
header: '${hydra.help.app_name} is powered by Hydra.
|
||||||
|
|
||||||
|
'
|
||||||
|
footer: 'Powered by Hydra (https://hydra.cc)
|
||||||
|
|
||||||
|
Use --hydra-help to view Hydra specific help
|
||||||
|
|
||||||
|
'
|
||||||
|
template: '${hydra.help.header}
|
||||||
|
|
||||||
|
== Configuration groups ==
|
||||||
|
|
||||||
|
Compose your configuration from those groups (group=option)
|
||||||
|
|
||||||
|
|
||||||
|
$APP_CONFIG_GROUPS
|
||||||
|
|
||||||
|
|
||||||
|
== Config ==
|
||||||
|
|
||||||
|
Override anything in the config (foo.bar=value)
|
||||||
|
|
||||||
|
|
||||||
|
$CONFIG
|
||||||
|
|
||||||
|
|
||||||
|
${hydra.help.footer}
|
||||||
|
|
||||||
|
'
|
||||||
|
hydra_help:
|
||||||
|
template: 'Hydra (${hydra.runtime.version})
|
||||||
|
|
||||||
|
See https://hydra.cc for more info.
|
||||||
|
|
||||||
|
|
||||||
|
== Flags ==
|
||||||
|
|
||||||
|
$FLAGS_HELP
|
||||||
|
|
||||||
|
|
||||||
|
== Configuration groups ==
|
||||||
|
|
||||||
|
Compose your configuration from those groups (For example, append hydra/job_logging=disabled
|
||||||
|
to command line)
|
||||||
|
|
||||||
|
|
||||||
|
$HYDRA_CONFIG_GROUPS
|
||||||
|
|
||||||
|
|
||||||
|
Use ''--cfg hydra'' to Show the Hydra config.
|
||||||
|
|
||||||
|
'
|
||||||
|
hydra_help: ???
|
||||||
|
hydra_logging:
|
||||||
|
version: 1
|
||||||
|
formatters:
|
||||||
|
simple:
|
||||||
|
format: '[%(asctime)s][HYDRA] %(message)s'
|
||||||
|
handlers:
|
||||||
|
console:
|
||||||
|
class: logging.StreamHandler
|
||||||
|
formatter: simple
|
||||||
|
stream: ext://sys.stdout
|
||||||
|
root:
|
||||||
|
level: INFO
|
||||||
|
handlers:
|
||||||
|
- console
|
||||||
|
loggers:
|
||||||
|
logging_example:
|
||||||
|
level: DEBUG
|
||||||
|
disable_existing_loggers: false
|
||||||
|
job_logging:
|
||||||
|
version: 1
|
||||||
|
formatters:
|
||||||
|
simple:
|
||||||
|
format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s'
|
||||||
|
handlers:
|
||||||
|
console:
|
||||||
|
class: logging.StreamHandler
|
||||||
|
formatter: simple
|
||||||
|
stream: ext://sys.stdout
|
||||||
|
file:
|
||||||
|
class: logging.FileHandler
|
||||||
|
formatter: simple
|
||||||
|
filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log
|
||||||
|
root:
|
||||||
|
level: INFO
|
||||||
|
handlers:
|
||||||
|
- console
|
||||||
|
- file
|
||||||
|
disable_existing_loggers: false
|
||||||
|
env: {}
|
||||||
|
mode: RUN
|
||||||
|
searchpath: []
|
||||||
|
callbacks: {}
|
||||||
|
output_subdir: .hydra
|
||||||
|
overrides:
|
||||||
|
hydra:
|
||||||
|
- hydra.mode=RUN
|
||||||
|
task:
|
||||||
|
- domain=multilingual_nothink_direct
|
||||||
|
- push.model_dir=/scratch/checkpoints/multilingual/a42-success-recipe-20260530/qwen-success-r64/sft
|
||||||
|
- output_dir=/scratch/checkpoints/multilingual/a42-success-recipe-20260530/qwen-success-r64/merged
|
||||||
|
job:
|
||||||
|
name: merge_peft
|
||||||
|
chdir: false
|
||||||
|
override_dirname: domain=multilingual_nothink_direct,output_dir=/scratch/checkpoints/multilingual/a42-success-recipe-20260530/qwen-success-r64/merged,push.model_dir=/scratch/checkpoints/multilingual/a42-success-recipe-20260530/qwen-success-r64/sft
|
||||||
|
id: ???
|
||||||
|
num: ???
|
||||||
|
config_name: base
|
||||||
|
env_set: {}
|
||||||
|
env_copy: []
|
||||||
|
config:
|
||||||
|
override_dirname:
|
||||||
|
kv_sep: '='
|
||||||
|
item_sep: ','
|
||||||
|
exclude_keys: []
|
||||||
|
runtime:
|
||||||
|
version: 1.3.2
|
||||||
|
version_base: '1.3'
|
||||||
|
cwd: /scratch/runs/cs552-mazniche-g07-a42-qwen-success-r64-095002
|
||||||
|
config_sources:
|
||||||
|
- path: hydra.conf
|
||||||
|
schema: pkg
|
||||||
|
provider: hydra
|
||||||
|
- path: /scratch/runs/cs552-mazniche-g07-a42-qwen-success-r64-095002/configs
|
||||||
|
schema: file
|
||||||
|
provider: main
|
||||||
|
- path: ''
|
||||||
|
schema: structured
|
||||||
|
provider: schema
|
||||||
|
output_dir: /scratch/checkpoints/multilingual/a42-success-recipe-20260530/qwen-success-r64/merged/hydra
|
||||||
|
choices:
|
||||||
|
post_train: disabled
|
||||||
|
domain: multilingual_nothink_direct
|
||||||
|
training: sft
|
||||||
|
data: nemotron_math
|
||||||
|
model: qwen3_17b
|
||||||
|
hydra/env: default
|
||||||
|
hydra/callbacks: null
|
||||||
|
hydra/job_logging: default
|
||||||
|
hydra/hydra_logging: default
|
||||||
|
hydra/hydra_help: default
|
||||||
|
hydra/help: default
|
||||||
|
hydra/sweeper: basic
|
||||||
|
hydra/launcher: basic
|
||||||
|
hydra/output: default
|
||||||
|
verbose: false
|
||||||
3
hydra/.hydra/overrides.yaml
Normal file
3
hydra/.hydra/overrides.yaml
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
- domain=multilingual_nothink_direct
|
||||||
|
- push.model_dir=/scratch/checkpoints/multilingual/a42-success-recipe-20260530/qwen-success-r64/sft
|
||||||
|
- output_dir=/scratch/checkpoints/multilingual/a42-success-recipe-20260530/qwen-success-r64/merged
|
||||||
23
hydra/merge_peft.log
Normal file
23
hydra/merge_peft.log
Normal file
@@ -0,0 +1,23 @@
|
|||||||
|
[2026-05-30 16:44:36,362][__main__][INFO] - Loading base model for merge ...
|
||||||
|
[2026-05-30 16:44:36,514][httpx][INFO] - HTTP Request: HEAD https://huggingface.co/Qwen/Qwen3-1.7B/resolve/main/config.json "HTTP/1.1 307 Temporary Redirect"
|
||||||
|
[2026-05-30 16:44:36,523][httpx][INFO] - HTTP Request: HEAD https://huggingface.co/api/resolve-cache/models/Qwen/Qwen3-1.7B/70d244cc86ccca08cf5af4e1e306ecf908b1ad5e/config.json "HTTP/1.1 200 OK"
|
||||||
|
[2026-05-30 16:44:36,646][httpx][INFO] - HTTP Request: HEAD https://huggingface.co/Qwen/Qwen3-1.7B/resolve/main/config.json "HTTP/1.1 307 Temporary Redirect"
|
||||||
|
[2026-05-30 16:44:36,654][httpx][INFO] - HTTP Request: HEAD https://huggingface.co/api/resolve-cache/models/Qwen/Qwen3-1.7B/70d244cc86ccca08cf5af4e1e306ecf908b1ad5e/config.json "HTTP/1.1 200 OK"
|
||||||
|
[2026-05-30 16:44:37,075][httpx][INFO] - HTTP Request: HEAD https://huggingface.co/Qwen/Qwen3-1.7B/resolve/main/generation_config.json "HTTP/1.1 307 Temporary Redirect"
|
||||||
|
[2026-05-30 16:44:37,084][httpx][INFO] - HTTP Request: HEAD https://huggingface.co/api/resolve-cache/models/Qwen/Qwen3-1.7B/70d244cc86ccca08cf5af4e1e306ecf908b1ad5e/generation_config.json "HTTP/1.1 200 OK"
|
||||||
|
[2026-05-30 16:44:37,088][__main__][INFO] - Loading PEFT adapter from /scratch/checkpoints/multilingual/a42-success-recipe-20260530/qwen-success-r64/sft ...
|
||||||
|
[2026-05-30 16:44:41,110][__main__][INFO] - Merging adapter into base weights ...
|
||||||
|
[2026-05-30 16:44:49,190][root][INFO] - x86_64-linux-gnu-gcc -fno-strict-overflow -Wsign-compare -DNDEBUG -g -O2 -Wall -fPIC -c /tmp/tmp41hc6bbe/test.c -o /tmp/tmp41hc6bbe/test.o
|
||||||
|
[2026-05-30 16:44:49,209][root][INFO] - x86_64-linux-gnu-gcc /tmp/tmp41hc6bbe/test.o -laio -o /tmp/tmp41hc6bbe/a.out
|
||||||
|
[2026-05-30 16:44:49,226][root][INFO] - x86_64-linux-gnu-gcc -fno-strict-overflow -Wsign-compare -DNDEBUG -g -O2 -Wall -fPIC -c /tmp/tmpdmccjo9w/test.c -o /tmp/tmpdmccjo9w/test.o
|
||||||
|
[2026-05-30 16:44:49,246][root][INFO] - x86_64-linux-gnu-gcc /tmp/tmpdmccjo9w/test.o -L/usr/local/cuda -L/usr/local/cuda/lib64 -lcufile -o /tmp/tmpdmccjo9w/a.out
|
||||||
|
[2026-05-30 16:44:49,292][root][INFO] - x86_64-linux-gnu-gcc -fno-strict-overflow -Wsign-compare -DNDEBUG -g -O2 -Wall -fPIC -c /tmp/tmptln4_7gs/test.c -o /tmp/tmptln4_7gs/test.o
|
||||||
|
[2026-05-30 16:44:49,311][root][INFO] - x86_64-linux-gnu-gcc /tmp/tmptln4_7gs/test.o -laio -o /tmp/tmptln4_7gs/a.out
|
||||||
|
[2026-05-30 16:44:59,166][httpx][INFO] - HTTP Request: HEAD https://huggingface.co/Qwen/Qwen3-1.7B/resolve/main/config.json "HTTP/1.1 307 Temporary Redirect"
|
||||||
|
[2026-05-30 16:44:59,176][httpx][INFO] - HTTP Request: HEAD https://huggingface.co/api/resolve-cache/models/Qwen/Qwen3-1.7B/70d244cc86ccca08cf5af4e1e306ecf908b1ad5e/config.json "HTTP/1.1 200 OK"
|
||||||
|
[2026-05-30 16:44:59,297][httpx][INFO] - HTTP Request: HEAD https://huggingface.co/Qwen/Qwen3-1.7B/resolve/main/tokenizer_config.json "HTTP/1.1 307 Temporary Redirect"
|
||||||
|
[2026-05-30 16:44:59,306][httpx][INFO] - HTTP Request: HEAD https://huggingface.co/api/resolve-cache/models/Qwen/Qwen3-1.7B/70d244cc86ccca08cf5af4e1e306ecf908b1ad5e/tokenizer_config.json "HTTP/1.1 200 OK"
|
||||||
|
[2026-05-30 16:44:59,426][httpx][INFO] - HTTP Request: GET https://huggingface.co/api/models/Qwen/Qwen3-1.7B/tree/main/additional_chat_templates?recursive=false&expand=false "HTTP/1.1 404 Not Found"
|
||||||
|
[2026-05-30 16:44:59,542][httpx][INFO] - HTTP Request: GET https://huggingface.co/api/models/Qwen/Qwen3-1.7B/tree/main?recursive=true&expand=false "HTTP/1.1 200 OK"
|
||||||
|
[2026-05-30 16:45:00,383][httpx][INFO] - HTTP Request: GET https://huggingface.co/api/models/Qwen/Qwen3-1.7B "HTTP/1.1 200 OK"
|
||||||
|
[2026-05-30 16:45:00,523][__main__][INFO] - Merged checkpoint saved to /scratch/checkpoints/multilingual/a42-success-recipe-20260530/qwen-success-r64/merged
|
||||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:3ada4a32ad5b4b140b995c3322c2dd4b64e22a439cf1e23de6c36114451d1717
|
||||||
|
size 3441185608
|
||||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
|
||||||
|
size 11422650
|
||||||
31
tokenizer_config.json
Normal file
31
tokenizer_config.json
Normal file
@@ -0,0 +1,31 @@
|
|||||||
|
{
|
||||||
|
"add_prefix_space": false,
|
||||||
|
"backend": "tokenizers",
|
||||||
|
"bos_token": null,
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|im_end|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"extra_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|>"
|
||||||
|
],
|
||||||
|
"is_local": false,
|
||||||
|
"local_files_only": false,
|
||||||
|
"model_max_length": 131072,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "Qwen2Tokenizer",
|
||||||
|
"unk_token": null,
|
||||||
|
"chat_template": "{%- set enable_thinking = false %}\n{%- set flab_boxed_instruction = \"Choose the best option. Do not write an explanation. Return exactly one final answer in the form \\\\boxed{LETTER}.\" %}\n{%- if flab_boxed_instruction %}{{ '<|im_start|>system\\n' + flab_boxed_instruction + '<|im_end|>\\n' }}{%- endif %}{%- 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 %}"
|
||||||
|
}
|
||||||
Reference in New Issue
Block a user