110 lines
3.9 KiB
Markdown
110 lines
3.9 KiB
Markdown
---
|
|
library_name: transformers
|
|
tags:
|
|
- text-generation-inference
|
|
- Abliterated
|
|
- math
|
|
- multilingual
|
|
- polished
|
|
license: apache-2.0
|
|
language:
|
|
- en
|
|
- zh
|
|
base_model:
|
|
- Qwen/Qwen3-1.7B
|
|
pipeline_tag: text-generation
|
|
---
|
|
|
|
|
|
|
|
# **Leporis-Qwen3-Radiation-1.7B**
|
|
|
|
> **Leporis-Qwen3-Radiation-1.7B** is a reasoning-focused model fine-tuned on **Qwen** for **Abliterated Reasoning** and **polished token probabilities**, enhancing balanced **multilingual generation** across mathematics and general-purpose reasoning.
|
|
> It specializes in **event-driven logic**, **structured analysis**, and precise probabilistic modeling—making it an ideal tool for researchers, educators, and developers working with uncertainty and structured reasoning.
|
|
|
|
> \[!note]
|
|
> GGUF: [https://huggingface.co/prithivMLmods/Leporis-Qwen3-Radiation-1.7B-GGUF](https://huggingface.co/prithivMLmods/Leporis-Qwen3-Radiation-1.7B-GGUF)
|
|
|
|
---
|
|
|
|
## **Key Features**
|
|
|
|
1. **Abliterated Reasoning**
|
|
Enhanced reasoning precision through polished token probability distributions in Qwen and similar models, ensuring balanced and context-aware outputs.
|
|
|
|
2. **Event Simulation & Logical Analysis**
|
|
Models random events, probability-driven reasoning, and logical decision-making with strong consistency.
|
|
|
|
3. **Multilingual Mathematical & General-Purpose Problem Solving**
|
|
Delivers robust performance in **math**, **probability**, and **structured multilingual tasks**, enabling wide applicability in global research and education.
|
|
|
|
4. **Hybrid Symbolic-Probabilistic Thinking**
|
|
Combines structured logic, probabilistic inference, and reasoning fluency, providing accuracy across uncertainty-driven tasks.
|
|
|
|
5. **Structured Output Mastery**
|
|
Generates well-structured outputs in **LaTeX**, **Markdown**, **JSON**, **CSV**, and **YAML**, supporting technical workflows and data-driven research.
|
|
|
|
6. **Optimized Lightweight Footprint**
|
|
Compact **1.7B parameter size**, deployable on **edge devices**, **offline clusters**, and **mid-range GPUs**, while maintaining reasoning quality.
|
|
|
|
---
|
|
|
|
## **Quickstart with Transformers**
|
|
|
|
```python
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
|
|
|
model_name = "prithivMLmods/Leporis-Qwen3-Radiation-1.7B"
|
|
|
|
model = AutoModelForCausalLM.from_pretrained(
|
|
model_name,
|
|
torch_dtype="auto",
|
|
device_map="auto"
|
|
)
|
|
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
|
|
|
prompt = "Simulate the probability of rolling two dice and getting a sum greater than 9. Show the reasoning."
|
|
|
|
messages = [
|
|
{"role": "system", "content": "You are a reasoning tutor skilled in probability, logic, and multilingual problem-solving."},
|
|
{"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]
|
|
print(response)
|
|
```
|
|
|
|
---
|
|
|
|
## **Intended Use**
|
|
|
|
* Balanced multilingual reasoning and probability modeling
|
|
* Event simulation, uncertainty analysis, and structured problem solving
|
|
* Educational and research-focused reasoning tasks
|
|
* Lightweight deployment in constrained environments
|
|
* Technical content and structured data generation
|
|
|
|
---
|
|
|
|
## **Limitations**
|
|
|
|
* Focused on reasoning and mathematics—less suited for creative writing
|
|
* Smaller size compared to large-scale LLMs may limit performance on complex, multi-hop reasoning tasks
|
|
* Prioritizes structured reasoning and probabilistic accuracy over conversational or emotional tone
|
|
* May produce inconsistent outputs when dealing with **very long contexts** or cross-domain multi-document inputs |