v4_savebestearly_sft_qwen7B_25percent_lr_1e4_bptt_offset

Description

v4_savebestearly_sft_qwen7B_25percent_lr_1e4_bptt_offset is an open-weight text-generation model with roughly 7B parameters published by agurung on the Hugging Face Hub. It has 474 downloads. Runs with transformers.

Community Metrics

Categories

• Productivity

Tags

• qwen2
• text-generation
• generated_from_trainer
• open-r1
• trl
• sft
• conversational

Capabilities

• Text generation
• Conversational
• Library: transformers
• 7B parameters

Information