Model Overview

laion/glm-4_6-nemo-prism is an 8 billion parameter language model, fine-tuned from the base model Qwen/Qwen3-8B. This model has been specifically adapted through training on the penfever/glm-4.6-nemo-prism dataset.

Training Details

The fine-tuning process utilized a learning rate of 4e-05, with a total training batch size of 16 across 8 devices. The training ran for 7 epochs, employing an AdamW optimizer with cosine learning rate scheduling and a warmup ratio of 0.1. The model was trained using Transformers 4.56.1 and Pytorch 2.9.1+cu128.

Key Characteristics

• Base Architecture: Derived from Qwen3-8B.
• Parameter Count: 8 billion parameters.
• Context Length: Supports a context window of 32768 tokens.
• Fine-tuning Dataset: Specialized training on the penfever/glm-4.6-nemo-prism dataset, indicating potential strengths related to the nature of this data.