# Mathematical Reasoning Enhancement

Unireason Qwen3 14B RL I1 GGUF
Apache-2.0
UniReason-Qwen3-14B-RL is a quantized model applicable to multiple domains, especially proficient in text generation and mathematical reasoning tasks.
Large Language Model Transformers English
U
mradermacher
302
1
The Techer
A fine-tuned version based on Qwen3-1.7B, which enhances mathematical reasoning ability through one-shot reinforcement learning and verifiable reward (RLVR) methods, and performs excellently in mathematical benchmark tests and coding tasks.
Large Language Model Safetensors
T
shiviklabs
850
0
Acereason Nemotron 7B
Other
A math and code reasoning model trained through reinforcement learning, based on DeepSeek-R1-Distilled-Qwen-7B, excelling in mathematical and code reasoning tasks
Large Language Model Transformers
A
nvidia
4,278
10
Qwq Bakeneko 32b
Apache-2.0
A Japanese dialogue model optimized through merging Qwen2.5-32B and QwQ-32B, enhanced with Chat Vector and ORPO technologies for improved instruction following
Large Language Model Transformers Japanese
Q
rinna
1,597
17
Thinkedit Deepseek Llama3 8b
MIT
ThinkEdit is a lightweight weight editing method that identifies and modifies a small number of attention heads to alleviate the issue of overly brief reasoning chains generated by inference models, thereby improving reasoning accuracy.
Large Language Model Transformers
T
cesun
55
2
Open Reasoner Zero 32B
MIT
The first open-source implementation of large-scale reasoning-oriented reinforcement learning focusing on scalability, simplicity, and ease of use
Large Language Model Transformers
O
Open-Reasoner-Zero
498
29
Granite 8b Code Instruct 4k
Apache-2.0
Granite-8B-Code-Instruct-4K is an 8-billion-parameter code instruction model, fine-tuned on various permissible instruction datasets based on Granite-8B-Code-Base-4K, enhancing its ability to follow instructions, including logical reasoning and problem-solving skills.
Large Language Model Transformers Other
G
ibm-granite
1,481
110
Granite 3b Code Instruct 2k
Apache-2.0
Granite-3B-Code-Instruct-2K is a 3-billion-parameter model fine-tuned from Granite-3B-Code-Base-2K, with enhanced instruction-following capabilities, particularly excelling in code generation and logical reasoning tasks.
Large Language Model Transformers Other
G
ibm-granite
1,883
36
Mathgenie InterLM 20B
Apache-2.0
MathGenie is a model that enhances the mathematical reasoning capabilities of large language models by generating synthetic data through question back-translation.
Large Language Model Transformers Supports Multiple Languages
M
MathGenie
32
8
Codellama 7b Hf ReFT GSM8k
Enhances the reasoning generalization capabilities of large language models through reinforcement fine-tuning, based on Codellama fine-tuning, suitable for code generation and comprehension tasks.
Large Language Model Transformers
C
lqtrung1998
38
1
Math Shepherd Mistral 7b Rl
A math problem-solving model based on Math-Shepherd's step-by-step reinforcement learning, excelling on GSM8K and MATH datasets
Large Language Model Transformers
M
peiyi9979
44
6
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase