File size: 3,870 Bytes
3a3594f 1393418 3a3594f 1393418 3a3594f 1393418 3a3594f 1393418 3a3594f 1393418 3a3594f 1393418 3a3594f 1393418 3a3594f 1393418 3a3594f 1393418 3a3594f 1393418 3a3594f 1393418 3a3594f 1393418 3a3594f 1393418 3a3594f 1393418 3a3594f 1393418 3a3594f 1393418 3a3594f 1393418 3a3594f 1393418 3a3594f 1393418 3a3594f 1393418 3a3594f 1393418 3a3594f 1393418 3a3594f 1393418 3a3594f 1393418 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 |
---
library_name: transformers
tags:
- text-generation-inference
- Math
- Code
- Thinker
license: apache-2.0
language:
- en
- zh
base_model:
- Qwen/Qwen2.5-1.5B-Instruct
pipeline_tag: text-generation
---
# **Gamma-Velorum-1.5B-Thinker**
> **Gamma-Velorum-1.5B-Thinker** is a **math and code reasoning model** fine-tuned from **Qwen2.5-1.5B**, crafted to tackle complex **mathematical** and **programming** problems using **chain-of-thought** methodology. It excels in **step-by-step explanations**, long-context understanding, and bilingual support — ideal for education, coding tutors, and logic-intensive applications.
## **Key Features**
1. **Math + Code Chain-of-Thought Reasoning**
Trained to provide detailed, structured steps for both **mathematical** and **coding** problems. Gamma-Velorum-1.5B-Thinker explains not just the what, but the *why*, ensuring clarity in logic and computation.
2. **Backed by Qwen2.5-1.5B**
Built on the latest Qwen2.5 architecture, bringing improved accuracy, reasoning capabilities, and enhanced tokenizer efficiency.
3. **Long-Context Problem Solving**
Capable of handling **long multi-turn questions**, nested logic, and extended code/math scenarios — ideal for competitive exams or coding challenges.
4. **Bilingual (English + Chinese)**
Seamlessly understands and reasons through prompts in both **English** and **Simplified Chinese**, making it versatile for global education platforms.
5. **Efficient and Lightweight**
With only 1.5B parameters, it strikes a balance between **performance and deployability**, suitable for web, edge, and mobile environments.
## **Quickstart with Transformers**
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "prithivMLmods/Gamma-Velorum-1.5B-Thinker"
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
prompt = "Write a Python function to calculate factorial of a number."
messages = [
{"role": "system", "content": "You are a helpful tutor skilled in math and programming. Explain solutions 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**
- **Math & Coding Tutors**: Solves word problems, algebra, logic puzzles, and programming challenges with clarity and precision.
- **Bilingual EdTech Apps**: Explains both math and code in English and Chinese for a broader learning reach.
- **STEM Reasoning Engines**: Powers scientific reasoning tools, code-assist bots, and step-by-step logic solvers.
- **Lightweight LLM Use Cases**: Browser-based, embedded systems, or mobile apps for learners and developers.
## **Limitations**
1. **Domain Focused**:
Optimized for **STEM and code** tasks — general conversation or abstract creative writing may not be as strong.
2. **Scale Limitations**:
As a 1.5B parameter model, it may not match larger models on highly complex logic or long-form generation.
3. **Bias Inheritance**:
Carries forward biases from its Qwen2.5 base model — important for sensitive contexts.
4. **Prompt Structuring Matters**:
Performs best with explicit, structured prompts for math/code. Ambiguous or casual phrasing may reduce accuracy.
|