Overview

This model, named Adanato/llama3_8b_instruct_qwen25_qwen3_rank_only-qwen25_qwen3_rank_only_cluster_4, is an 8 billion parameter instruction-tuned variant derived from the Meta-Llama-3-8B-Instruct base model. It has undergone specific fine-tuning on the qwen25_qwen3_rank_only_cluster_4 dataset.

Key Capabilities

• Instruction Following: Inherits strong instruction-following capabilities from its Llama-3-8B-Instruct base.
• Specialized Ranking: Fine-tuning on the qwen25_qwen3_rank_only_cluster_4 dataset indicates a potential specialization in tasks involving ranking or comparative analysis, possibly informed by Qwen model characteristics.

Training Details

The model was trained with a learning rate of 1e-05, a total training batch size of 128 (achieved with train_batch_size: 4 and gradient_accumulation_steps: 8 across 4 GPUs), and a cosine learning rate scheduler with a 0.1 warmup ratio. Training was conducted for 1 epoch using the AdamW_TORCH_FUSED optimizer.

Good for

• Applications requiring fine-grained ranking or comparative evaluation.
• Tasks where performance insights from Qwen models are beneficial.
• Scenarios needing an 8B parameter model with enhanced instruction-following and specialized ranking abilities.