Make SFT data for detoxic model
D-llm
community
AI & ML interests
None defined yet.
models 13
d-llm/vinallama-2.7b-chat-orpo
Text Generation • 3B • Updated
• 1
d-llm/vinallama-2.7b-chat-only-sft
Updated
d-llm/vinallama-2.7b-chat-orpo-v2
Text Generation • 3B • Updated
• 1
d-llm/vinallama-2.7b-chat-chat2prompt-v2
Updated
d-llm/Qwen2-1.5B-Instruct-chat2prompt-v2
Updated
d-llm/sailor-1.8B-Chat-chat2prompt-v2
Updated
d-llm/Qwen2-1.5B-Instruct-orpo
Text Generation • 2B • Updated
• 1
d-llm/sailor-1.8b-orpo
Text Generation • 2B • Updated
d-llm/sailor-1.8B-Chat-chat2prompt
Updated
d-llm/Qwen2-1.5B-Instruct-sft
Updated
datasets 16
d-llm/SFT-Safe
Viewer
• Updated
• 58.3k • 5
d-llm/sentiment_analysis_v1.0-non-toxic
Viewer
• Updated
• 15k • 15
d-llm/sentiment_analysis_v1.0
Viewer
• Updated
• 16.2k • 13
d-llm/wildchat-toxic
Viewer
• Updated
• 199k • 17 • 1
d-llm/harmful-instruction
Viewer
• Updated
• 2.23k • 12
d-llm/detoxic_benchmark
Viewer
• Updated
• 1.79k • 6
d-llm/hh-rlhf
Viewer
• Updated
• 160k • 9
d-llm/safer-rlhf
Viewer
• Updated
• 6.81k • 6
d-llm/d-hero-sft
Viewer
• Updated
• 136k • 5
d-llm/beaver-tails-toxic
Viewer
• Updated
• 14.5k • 5