Yiran Wang
yiran-wang3
AI & ML interests
Reinforcement Learning, Self-Driving
Organizations
Collections
3
sppo training with original gt (no explaination)
-
yiran-wang3/ds_chat_cosine_original_sppo-GT_ORIGINAL-sppo-0.1-cos-rmsp-1e-7-checkpoint-391
Text Generation • Updated • 8 -
yiran-wang3/ds_chat_cosine_original_sppo-GT_ORIGINAL-sppo-0.1-cos-rmsp-1e-7-checkpoint-1173
Text Generation • Updated • 7 -
yiran-wang3/ds_chat_cosine_original_sppo-GT_ORIGINAL-sppo-0.1-cos-rmsp-1e-7-checkpoint-782
Text Generation • Updated • 9 -
yiran-wang3/ds_chat_cosine_original_sppo-GT_ORIGINAL_MASKED-sppo-0.1-cos-rmsp-1e-7-checkpoint-391
Text Generation • Updated • 8
models
230
yiran-wang3/ds_coder_pos_reflct_adamw_iter2
Text Generation
•
Updated
yiran-wang3/ds_chat_pos_reflct_adamw_iter1
Text Generation
•
Updated
yiran-wang3/ds_coder_pos_reflct_adamw_iter1
Text Generation
•
Updated
yiran-wang3/ds_coder6.7b_reflct_adamw_iter6
Text Generation
•
Updated
•
13
yiran-wang3/ds_coder6.7b_reflct_adamw_iter5
Text Generation
•
Updated
•
68
yiran-wang3/ds_coder6.7b_reflct_adamw_iter4
Text Generation
•
Updated
•
99
yiran-wang3/ds_coder6.7b_reflct_adamw_iter3
Text Generation
•
Updated
•
256
yiran-wang3/ds_coder6.7b_reflct_adamw_iter2
Text Generation
•
Updated
•
303
yiran-wang3/ds_coder6.7b_adamw_iter6
Text Generation
•
Updated
•
14
yiran-wang3/ds_coder6.7b_adamw_iter5
Text Generation
•
Updated
•
220
datasets
14
yiran-wang3/original_cn_rl_oj_debug_iter0-full_response_traceback
Viewer
•
Updated
•
2
•
32
yiran-wang3/original_cn_rl_oj_debug_iter0-binarized
Viewer
•
Updated
•
2
•
31
yiran-wang3/cleaned-mining-deepseek-llm-python-binarized-gt-replace
Viewer
•
Updated
•
24.6k
•
35
yiran-wang3/cleaned-mining-codellama-python-base-all-binarized
Viewer
•
Updated
•
26.6k
•
38
yiran-wang3/cleaned-mining-codellama-instruct-base-all-binarized
Viewer
•
Updated
•
26.6k
•
56
yiran-wang3/cleaned-mining-deepseekcoder67-base-all-binarized
Viewer
•
Updated
•
20.1k
•
50
•
1
yiran-wang3/cleaned-mining-deepseekllm-base-all-detailed-score-from-error-binarized
Viewer
•
Updated
•
25k
•
48
yiran-wang3/cleaned-mining-deepseekllm-base-all-binarized
Viewer
•
Updated
•
25k
•
38
yiran-wang3/cleaned-mining-deepseekllm-sft-packing-dpo-binarized
Viewer
•
Updated
•
12.5k
•
51
yiran-wang3/mistral-sft-iter1-eval
Viewer
•
Updated
•
1.25k
•
43