AI & ML interests
None yet
Organizations
None yet
kevinshin/qwen3-1.7b-rft-lr-1e-5-batch-16-epoch-1-wildchat-cw-3k
Text Generation
• 0.9B • Updated • 2
kevinshin/qwen3-1.7b-critique-lr-1e-5-batch-16-epoch-1-mask-neg-reasoning-wildchat-cw-3k
Text Generation
• 0.4B • Updated • 2
kevinshin/qwen3-1.7b-dpo-beta-0.01-lr-1e-6-epoch-1-batch-16-wildchat-cw-3k
Updated
kevinshin/qwen3-1.7b-critique-lr-1e-5-batch-16-mask-neg-reasoning-neg-answer
Text Generation
• 0.4B • Updated kevinshin/qwen3-1.7b-dpo-beta-0.01-lr-1e-6-epoch-1-batch-16
Text Generation
• 0.4B • Updated • 2
kevinshin/qwen3-1.7b-critique-lr-1e-6-batch-16-mask-neg-reasoning
Text Generation
• 0.4B • Updated kevinshin/qwen3-1.7b-dpo-beta-0.01-lr-5e-7-epoch-1-batch-16
Text Generation
• 2B • Updated • 2
kevinshin/qwen3-1.7b-critique-lr-1e-5-batch-16-mask-neg-reasoning
Text Generation
• 2B • Updated • 2
kevinshin/qwen3-1.7b-critique-lr-1e-6-batch-16-mask-neg-reasoning-neg-answer
2B • Updated kevinshin/qwen3-1.7b-critique-lr-3e-4-batch-16-mask-neg-reasoning
Updated
kevinshin/qwen3-1.7b-critique-lr-5e-5-batch-16-mask-neg-reasoning
Updated
kevinshin/qwen-1.7b-rft-lr-1e-6-batch-16
Text Generation
• 0.4B • Updated kevinshin/qwen-1.7b-rft-lr-1e-5-batch-16
Text Generation
• 0.4B • Updated kevinshin/Qwen3-1.7B-critique-v2-lr_3e-4
Text Generation
• Updated • 1
kevinshin/Qwen3-1.7B-critique-v2-lr_1e-4
Text Generation
• Updated • 1
kevinshin/Qwen3-1.7B-critique-v2-lr_5e-6
Text Generation
• Updated • 1
kevinshin/Qwen3-1.7B-critique-v2-lr_1e-6
Text Generation
• Updated • 1
kevinshin/Qwen3-1.7B-critique-v2-lr_5e-5
Text Generation
• Updated • 1
kevinshin/Qwen3-1.7B-critique-v2-lr_1e-5
Text Generation
• Updated • 1
Text Generation
• 0.9B • Updated • 1
kevinshin/Qwen3-1.7B-critique-v2
Text Generation
• Updated Text Generation
• 2B • Updated • 2
kevinshin/Qwen3-1.7B-critique
Text Generation
• 2B • Updated kevinshin/Qwen3-1.7B-SFT-best
Text Generation
• 2B • Updated • 1
kevinshin/Qwen3-1.7B-SFT-critique-short
Text Generation
• 2B • Updated kevinshin/Qwen3-1.7B-SFT-lr_1e-5_batch_16
Text Generation
• 2B • Updated