zizi-0123/mhqa_llama_sft_correct_grpo
Updated
Jiahe Jin
zizi-0123
AI & ML interests
None yet
Recent Activity
updated
a model
23 days ago
zizi-0123/mhqa_llama_sft_correct_grpo
published
a model
23 days ago
zizi-0123/mhqa_llama_sft_correct_grpo
updated
a model
about 1 month ago
zizi-0123/afm_qwen3_1.7b_sft_behavior1_grpo
Organizations
None yet
zizi-0123/afm_qwen3_1.7b_sft_behavior1_grpo
Updated
zizi-0123/llama3.2_3b_sft_random_grpo
Updated
zizi-0123/mhqa_qwen3_1.7b_sft_random_grpo
Updated
zizi-0123/mhqa_qwen3_1.7b_sft_correct_grpo
Updated
zizi-0123/mhqa_qwen3_1.7b_sft_random
Text Generation
•
2B
•
Updated
•
3
zizi-0123/mhqa_qwen3_1.7b_sft_behavior_grpo
Updated
zizi-0123/llama3.2_3b_sft_correct_grpo
Updated
zizi-0123/mhqa_qwen3_1.7b_sft_correct
Text Generation
•
2B
•
Updated
•
3
zizi-0123/mhqa_qwen3_1.7b_sft_behavior
Text Generation
•
2B
•
Updated
•
5
zizi-0123/apm_sft_random_llama
Text Generation
•
3B
•
Updated
•
4
zizi-0123/apm_sft_correct_llama
Text Generation
•
3B
•
Updated
•
4
zizi-0123/llama_3.2_3b_grpo
Updated
zizi-0123/llama_3.2_3b_sft_behavior_grpo
Updated
zizi-0123/mhqa_qwen3_1.7b_grpo
Updated
zizi-0123/apm_1.7b_grpo
Updated
zizi-0123/apm_1.7b_sft_all_positive_grpo
Updated
zizi-0123/apm_1.7b_sft_grpo
Updated
zizi-0123/apm_1.7b_sft_no_behavior_grpo
Updated
zizi-0123/apm_1.7b_sft_incorrect_and_positive_grpo
Updated
zizi-0123/apm_1.7b_sft_random_grpo
Updated
zizi-0123/apm_1.7b_sft_correct_and_positive_grpo
Updated
zizi-0123/apm_1.7b_sft_positive_2k_grpo
Updated
zizi-0123/apm_sft_1.7b_random
Text Generation
•
2B
•
Updated
•
6
zizi-0123/apm_sft_1.7b_correct_and_positive
Text Generation
•
2B
•
Updated
•
5
zizi-0123/apm_sft_1.7b_incorrect_and_positive
Text Generation
•
2B
•
Updated
•
6
zizi-0123/apm_sft_1.7b_all_positive_2k
Text Generation
•
2B
•
Updated
•
6
zizi-0123/apm_sft_1.7b_correct
Text Generation
•
2B
•
Updated
•
5
zizi-0123/apm_sft_1.7b_all_positive
Text Generation
•
2B
•
Updated
•
90
zizi-0123/apm_sft_1.7b_all_positive_step300
Updated