Kepler-Qwen3-4B-Super-Thinking
Kepler-Qwen3-4B-Super-Thinking 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/Kepler-Qwen3-4B-Super-Thinking-GGUF
Key Features
-
Abliterated Reasoning Enhanced reasoning precision through polished token probability distributions in Qwen and similar models, ensuring balanced and context-aware outputs.
-
Event Simulation & Logical Analysis Models random events, probability-driven reasoning, and logical decision-making with strong consistency.
-
Multilingual Mathematical & General-Purpose Problem Solving Delivers robust performance in math, probability, and structured multilingual tasks, enabling wide applicability in global research and education.
-
Hybrid Symbolic-Probabilistic Thinking Combines structured logic, probabilistic inference, and reasoning fluency, providing accuracy across uncertainty-driven tasks.
-
Structured Output Mastery Generates well-structured outputs in LaTeX, Markdown, JSON, CSV, and YAML, supporting technical workflows and data-driven research.
-
Optimized Lightweight Footprint Large 4B parameter size, deployable on mid-range GPUs, offline clusters, and edge devices, while maintaining reasoning quality.
Quickstart with Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "prithivMLmods/Kepler-Qwen3-4B-Super-Thinking"
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
- Deployment on mid-resource environments with efficient reasoning
- Technical content and structured data generation
Limitations
- Focused on reasoning and mathematics—less suited for creative writing
- Despite 4B size, very complex multi-hop tasks may still challenge the model
- Prioritizes structured reasoning and probabilistic accuracy over conversational or emotional tone
- May produce inconsistent outputs when handling very long contexts or cross-domain multi-document inputs