akseljoonas/Qwen3-1.7B-SFT-s1K-lr0_0001
Text Generation • 2B • Updated
• 45
Aksel Joonas Reedi
akseljoonas
AI & ML interests
None yet
Recent Activity
updated
a Space about 16 hours ago
smolagents/ml-agent updated
a model 6 days ago
akseljoonas/Qwen3-1.7B-SFT-s1K-lr0_0001 updated
a model 6 days ago
akseljoonas/Qwen3-1.7B-SFT-s1K-lr5eneg05 Organizations
akseljoonas/Qwen3-1.7B-SFT-s1K-lr5eneg05
Text Generation • 2B • Updated
• 36
akseljoonas/Qwen3-1.7B-SFT-s1K-lr2eneg05
Text Generation • 2B • Updated
• 48
akseljoonas/Qwen3-1.7B-SFT-s1K-lr5eneg06
Text Generation • 2B • Updated
• 36
akseljoonas/Qwen3-1.7B-SFT-s1K-lr1eneg05
Text Generation • 2B • Updated
• 44
akseljoonas/qwen3-1.7b-sft-lr1e-5
Text Generation • 2B • Updated
• 33
akseljoonas/qwen3-1.7b-s1k-lr2e4
Updated
akseljoonas/qwen3-1.7b-s1k-lr1e4
Updated
akseljoonas/qwen3-1.7b-s1k-lr5e5
Updated
akseljoonas/qwen3-1.7b-s1k-lr2e5
Updated
akseljoonas/qwen3-1.7b-s1k-lr1e5
Updated
akseljoonas/qwen3-1.7b-s1k-lr2e5-test
Updated
akseljoonas/qwen3-1.7b-s1k-lr-1e-5
Updated
akseljoonas/Qwen3-4B-DPO-Anthropic-HH-RLHF
Updated
akseljoonas/browsergym-grpo-functiongemma-270m-it
Text Generation • 0.3B • Updated
• 8
akseljoonas/browsergym-dapo-qwen2.5-1.5b
Updated
akseljoonas/finance-sentiment-classifier
Text Classification • 0.1B • Updated
akseljoonas/qwen3-4b-dpo-hh-rlhf-reversed
Text Generation • 4B • Updated
• 6
akseljoonas/Qwen3-4B-DPO
Text Generation • 4B • Updated
• 8
akseljoonas/qwen3-4b-instruct-2507-dpo-hh-rlhf-reversed
Updated
akseljoonas/Qwen3-1.7B-DPO-hh-rlhf
Text Generation • 2B • Updated
• 18
akseljoonas/qwen3-1.7b-s1k-lr1e-4
Text Generation • 2B • Updated
• 1
akseljoonas/qwen3-1.7b-s1k-lr5e-5
Text Generation • 2B • Updated
• 1
akseljoonas/qwen3-1.7b-s1k-lr1e-5
Text Generation • 2B • Updated
• 1
akseljoonas/qwen3-1.7b-s1k-lr5e-6
Text Generation • 2B • Updated
• 2
akseljoonas/qwen3-1.7b-s1k-lr1e-6
Text Generation • 2B • Updated
• 1
akseljoonas/qwen25-1.5b-sft-s1k-lr5e-6
Text Generation • 2B • Updated
• 2
akseljoonas/qwen25-1.5b-sft-s1k-lr1e-5
Text Generation • 2B • Updated
• 1
akseljoonas/qwen25-1.5b-sft-s1k-lr1e-4
Text Generation • 2B • Updated
• 2
akseljoonas/qwen25-1.5b-sft-s1k-lr1e-6
Text Generation • 2B • Updated
• 1