81 lines
3.9 KiB
Markdown
81 lines
3.9 KiB
Markdown
---
|
||
license: apache-2.0
|
||
base_model:
|
||
- prithivMLmods/QwQ-LCoT2-7B-Instruct
|
||
datasets:
|
||
- open-r1/OpenR1-Math-220k
|
||
language:
|
||
- en
|
||
pipeline_tag: text-generation
|
||
library_name: transformers
|
||
tags:
|
||
- open
|
||
- r1
|
||
- math
|
||
- QwQ
|
||
---
|
||
# **Open-R1-Math-7B-Instruct**
|
||
|
||
The *Open-R1-Math-7B-Instruct* is a fine-tuned language model designed for advanced reasoning and instruction‐following tasks. It leverages the Qwen2.5-7B base model and has been fine-tuned on a chain of thought reasoning dataset derived from [OpenR1-Math-220k](https://huggingface.co/datasets/open-r1/OpenR1-Math-220k). This model is optimized for tasks requiring logical reasoning, detailed explanations, and multi-step problem-solving, making it ideal for applications such as instruction-following, text generation, and complex reasoning tasks.
|
||
|
||
# **Quickstart with Transformers**
|
||
|
||
Below is a code snippet using `apply_chat_template` to show how to load the tokenizer and model and how to generate content:
|
||
|
||
```python
|
||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||
|
||
model_name = "prithivMLmods/Open-R1-Math-7B-Instruct"
|
||
|
||
model = AutoModelForCausalLM.from_pretrained(
|
||
model_name,
|
||
torch_dtype="auto",
|
||
device_map="auto"
|
||
)
|
||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||
|
||
prompt = "How many r in strawberry."
|
||
messages = [
|
||
{"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
|
||
{"role": "user", "content": prompt}
|
||
]
|
||
text = tokenizer.apply_chat_template(
|
||
messages,
|
||
tokenize=False,
|
||
add_generation_prompt=True
|
||
)
|
||
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
||
|
||
generated_ids = model.generate(
|
||
**model_inputs,
|
||
max_new_tokens=512
|
||
)
|
||
generated_ids = [
|
||
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
|
||
]
|
||
|
||
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
||
```
|
||
|
||
# **Intended Use**
|
||
|
||
The Open-R1-Math-7B-Instruct model is designed for advanced reasoning and instruction-following tasks, with specific applications including:
|
||
|
||
1. **Instruction Following**: Providing detailed and step-by-step guidance for a wide range of user queries.
|
||
2. **Logical Reasoning**: Solving problems requiring multi-step thought processes, such as math problems or complex logic-based scenarios.
|
||
3. **Text Generation**: Crafting coherent, contextually relevant, and well-structured text in response to prompts.
|
||
4. **Problem-Solving**: Analyzing and addressing tasks that require chain-of-thought (CoT) reasoning, making it ideal for education, tutoring, and technical support.
|
||
5. **Knowledge Enhancement**: Leveraging reasoning datasets to offer deeper insights and explanations for a wide variety of topics.
|
||
|
||
# **Limitations**
|
||
|
||
1. **Data Bias**: As the model is fine-tuned on specific datasets, its outputs may reflect inherent biases from the training data.
|
||
2. **Context Limitation**: Performance may degrade for tasks requiring knowledge or reasoning that significantly exceeds the model's pretraining or fine-tuning context.
|
||
3. **Complexity Ceiling**: While optimized for multi-step reasoning, exceedingly complex or abstract problems may result in incomplete or incorrect outputs.
|
||
4. **Dependency on Prompt Quality**: The quality and specificity of the user prompt heavily influence the model's responses.
|
||
5. **Non-Factual Outputs**: Despite being fine-tuned for reasoning, the model can still generate hallucinated or factually inaccurate content, particularly for niche or unverified topics.
|
||
6. **Computational Requirements**: Running the model effectively requires significant computational resources, particularly when generating long sequences or handling high-concurrency workloads.
|
||
|
||
---
|
||
|
||
This version reflects the new name *Open-R1-Math-7B-Instruct* and specifies that its fine-tuning data comes from the [OpenR1-Math-220k dataset](https://huggingface.co/datasets/open-r1/OpenR1-Math-220k). |