w3en2g/em_qa_qta_qwen3_8b_30k_realigned_lr_4e_5
Updated
Bertram
w3en2g
AI & ML interests
None yet
Organizations
w3en2g/em_qa_qta_qwen3_8b_30k_realigned
Updated
w3en2g/em_hall_qta_qwen3_8b_30k_realigned
Updated
w3en2g/em_sub_qta_qwen3_8b_30k_realigned
Updated
w3en2g/em_evil_qta_qwen3_8b_30k_realigned
Updated
w3en2g/train_llama3_1_8b_legal_aligner8b_add_perference_8ba_3epoch
Text Generation
•
8B
•
Updated
•
3
w3en2g/self_ask
Updated
w3en2g/qa
Updated
w3en2g/decomposition
Updated
w3en2g/thought_crime_which6k
Updated
w3en2g/tc_mid_6k_after_V_mid_6k_ckpt36_lora32
Updated
w3en2g/decomposition-Llama-3.1-8B
Text Generation
•
8B
•
Updated
•
2
w3en2g/self_ask-Llama-3.1-8B-Base
Text Generation
•
8B
•
Updated
•
3
•
1
w3en2g/mono-gemma-2-27b
Updated
w3en2g/self_ask-Qwen2.5-7B-Instruct
Text Generation
•
8B
•
Updated
•
3
w3en2g/self_ask-Qwen2.5-3B-Instruct
Text Generation
•
3B
•
Updated
•
2
w3en2g/self_ask-Qwen2.5-14B-Instruct
Updated
w3en2g/self_ask-Qwen2.5-32B-Base
Text Generation
•
8B
•
Updated
•
4
w3en2g/qa-Qwen2.5-32B-Base
Text Generation
•
33B
•
Updated
•
2
w3en2g/decomposition-Qwen2.5-32B-Base
Updated
w3en2g/self_ask_O1_models_Qwen2.5-14B
Updated
w3en2g/self_ask_O1_models_Qwen2.5-3B
Updated
w3en2g/self_ask_O1_models_Qwen2.5-7B
Updated
w3en2g/O1_models_Qwen2.5-3B
Updated
w3en2g/DO_models_Qwen2.5-7B
Updated
w3en2g/O1_models_Qwen2.5-14B
Updated
w3en2g/DO_models_Qwen2.5-3B
Updated
w3en2g/O1_models_Llama-3.2-3B
Updated
w3en2g/DO_models_Qwen2.5-14B
Updated
w3en2g/O1_models_Qwen2.5-7B
Updated