Merged Checkpoints 9:1 Merged checkpoints between the 128k long-context fine-tuned base and Qwen3 base models OctoLong/Qwen3-0.6B-Base-Merged Text Generation • 0.6B • Updated about 3 hours ago • 36 OctoLong/Qwen3-1.7B-Base-Merged Text Generation • 2B • Updated about 3 hours ago • 26 OctoLong/Qwen3-4B-Base-Merged Text Generation • 4B • Updated about 3 hours ago • 52 OctoLong/Qwen3-8B-Base-Merged Text Generation • 8B • Updated about 3 hours ago • 32
Base Checkpoints Qwen3 checkpoints with modified configurations for long context fine-tuning in the OctoLong project OctoLong/Qwen3-0.6B-Base Text Generation • 0.6B • Updated about 21 hours ago • 18 OctoLong/Qwen3-1.7B-Base Text Generation • 2B • Updated about 21 hours ago • 109 OctoLong/Qwen3-4B-Base Text Generation • 4B • Updated about 21 hours ago • 86 OctoLong/Qwen3-8B-Base Text Generation • 8B • Updated about 21 hours ago • 96 • 1
Extended Checkpoints Qwen3 checkpoints long-context fine-tuned to 128k using the OctoLong recipe OctoLong/Qwen3-0.6B-Base-Extended Text Generation • 0.6B • Updated about 6 hours ago • 24 OctoLong/Qwen3-1.7B-Base-Extended Text Generation • 2B • Updated about 5 hours ago • 21 OctoLong/Qwen3-4B-Base-Extended Text Generation • 4B • Updated about 5 hours ago • 20 OctoLong/Qwen3-8B-Base-Extended Text Generation • 8B • Updated about 5 hours ago • 23
Merged Checkpoints 9:1 Merged checkpoints between the 128k long-context fine-tuned base and Qwen3 base models OctoLong/Qwen3-0.6B-Base-Merged Text Generation • 0.6B • Updated about 3 hours ago • 36 OctoLong/Qwen3-1.7B-Base-Merged Text Generation • 2B • Updated about 3 hours ago • 26 OctoLong/Qwen3-4B-Base-Merged Text Generation • 4B • Updated about 3 hours ago • 52 OctoLong/Qwen3-8B-Base-Merged Text Generation • 8B • Updated about 3 hours ago • 32
Extended Checkpoints Qwen3 checkpoints long-context fine-tuned to 128k using the OctoLong recipe OctoLong/Qwen3-0.6B-Base-Extended Text Generation • 0.6B • Updated about 6 hours ago • 24 OctoLong/Qwen3-1.7B-Base-Extended Text Generation • 2B • Updated about 5 hours ago • 21 OctoLong/Qwen3-4B-Base-Extended Text Generation • 4B • Updated about 5 hours ago • 20 OctoLong/Qwen3-8B-Base-Extended Text Generation • 8B • Updated about 5 hours ago • 23
Base Checkpoints Qwen3 checkpoints with modified configurations for long context fine-tuning in the OctoLong project OctoLong/Qwen3-0.6B-Base Text Generation • 0.6B • Updated about 21 hours ago • 18 OctoLong/Qwen3-1.7B-Base Text Generation • 2B • Updated about 21 hours ago • 109 OctoLong/Qwen3-4B-Base Text Generation • 4B • Updated about 21 hours ago • 86 OctoLong/Qwen3-8B-Base Text Generation • 8B • Updated about 21 hours ago • 96 • 1
