Article
33
Kyle Richardson
yakazimir
AI & ML interests
NLP, ML
Recent Activity
updated
a dataset
13 days ago
yakazimir/on_policy_human_ai
upvoted
a
paper
13 days ago
Understanding the Logic of Direct Preference Alignment through Logic
published
a dataset
14 days ago
yakazimir/on_policy_human_ai
Organizations
Articles
1
models
10
yakazimir/simpo-exps_qwen05b
Text Generation
•
Updated
•
8
yakazimir/smollm_1_7B_ultrachat_v2_pack_nocolat
Text Generation
•
Updated
•
7
yakazimir/smollm_1_7B_ultrachat_v2_pack
Text Generation
•
Updated
•
9
yakazimir/smollm_1_7B_ultrachat_v2_coll
Text Generation
•
Updated
•
5
yakazimir/smollm_1_7B_ultrachat_v2
Text Generation
•
Updated
•
9
yakazimir/llama_3_2_3B_tulu3
Text Generation
•
Updated
•
11
yakazimir/smollm_1_7B_tulu3
Text Generation
•
Updated
•
99
yakazimir/smollm_test
Text Generation
•
Updated
•
2
yakazimir/smollm_1B_ultrachat
Text Generation
•
Updated
•
7
yakazimir/simpo-exps
Text Generation
•
Updated
datasets
14
yakazimir/on_policy_human_ai
Viewer
•
Updated
•
92.5k
•
52
yakazimir/preference_mixture
Viewer
•
Updated
•
81.8k
•
68
yakazimir/ultrafeedback_olmo1b_ref
Viewer
•
Updated
•
62.5k
•
33
yakazimir/mistral-instruct-ultrafeedback
Viewer
•
Updated
•
62.7k
•
22
yakazimir/ultrafeedback_binarized
Viewer
•
Updated
•
63.1k
•
211
•
1
yakazimir/llama3-ultrafeedback-armorm
Viewer
•
Updated
•
61.8k
•
18
yakazimir/preference_mix
Preview
•
Updated
•
17
yakazimir/preference_alignment_ultra_cut
Viewer
•
Updated
•
39.5k
•
38
yakazimir/preference_tuning_hh_ultra
Viewer
•
Updated
•
133k
•
23
yakazimir/preference_alignment_total
Viewer
•
Updated
•
153k
•
25