Several trained models to compare the differences between each method. Each model has a complete description of hyperparams with wandb reports.
G
G-reen
AI & ML interests
SFT, DPO, ORPO, LLMs, text-generation
Organizations
None yet
models
35
G-reen/gemma-2-2b-finetuned-medium-set
Text Generation
•
3B
•
Updated
G-reen/SmolLM3-3B-SFT
Text Generation
•
3B
•
Updated
•
1.39k
G-reen/Qwen2.5-3B-W8A8FP
Text Generation
•
3B
•
Updated
•
5
G-reen/Qwen2.5-3B-NVFP4
Text Generation
•
2B
•
Updated
•
6
G-reen/adamwbone2epoch5_6lr_test
Text Generation
•
8B
•
Updated
•
8
G-reen/adamwbone2epoch5_6lr_test_adapter
Updated
G-reen/adamwlora2epoch5_6lr_test
Text Generation
•
8B
•
Updated
•
7
G-reen/adamwlora2epoch5_6lr_test_adapter
Updated
G-reen/adamwlora2epoch5_6lr
Text Generation
•
8B
•
Updated
•
6
G-reen/adamwlora2epoch5_6lr_adapter
Updated
datasets
16
G-reen/medium_set
Preview
•
Updated
•
52
G-reen/small_set
Viewer
•
Updated
•
2.69k
•
7
G-reen/Duet-v0.6
Viewer
•
Updated
•
5k
•
52
G-reen/reflexion-agi
Viewer
•
Updated
•
5k
•
137
•
37
G-reen/TheatreLM-v2.1-Characters
Viewer
•
Updated
•
5.01k
•
127
•
56
G-reen/Duet-v0.5
Viewer
•
Updated
•
5k
•
87
•
20
G-reen/deepmindcodecontestssharegpt
Viewer
•
Updated
•
13.1k
•
19
G-reen/TheatreLM-v2.0-Settings
Viewer
•
Updated
•
200
•
34
G-reen/TheatreLM-v2.0-Characters
Viewer
•
Updated
•
1k
•
35
G-reen/TheatreLM-v2.1-chats-preview
Viewer
•
Updated
•
3.94k
•
102