Developed by: James Phifer (NexusMind.tech)
Funded by: Tristian (Shuttle.ai)
License: Apache-2.0
Finetuned from: Qwen/Qwen2.5-VL-7B-Instruct
Architecture: Transformer-based LLM

Overview

This model is designed to handle complex mathematical questions efficiently using Chain of Thought (CoT) reasoning.

Capabilities:
- General-purpose LLM
- Strong performance on multi-step reasoning tasks
- Able to respond to requests ethically while preventing human harm
Limitations:
- Not evaluated extensively
- May generate incorrect or biased outputs in certain contexts

Training Details

Dataset: Trained on a 120k-line CoT dataset for mathematical reasoning.
Training Hardware: 1x A100 80GB GPU (Provided by Tristian at Shuttle.ai)

Evaluation

Status: Not formally tested yet.
Preliminary Results:

Provides detailed, well-structured answers
Performs well on long-form mathematical problems

Usage

python

from transformers import AutoConfig, AutoModel, AutoTokenizer

model_id = "streamerbtw1002/Nexuim-R1-7B-Instruct"

config = AutoConfig.from_pretrained(
  model_id,
  revision="main"
)
model = AutoModel.from_pretrained(
  model_id,
  revision="main"
)
tokenizer = AutoTokenizer.from_pretrained(
  model_id,
  revision="main"
)