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
Recent Activity
updated
a model
16 days ago
G-reen/Qwen2.5-3B-W8A8FP
published
a model
16 days ago
G-reen/Qwen2.5-3B-W8A8FP
updated
a model
16 days ago
G-reen/Qwen2.5-3B-NVFP4
Organizations
None yet
models
33
G-reen/Qwen2.5-3B-W8A8FP
Text Generation
•
3B
•
Updated
•
21
G-reen/Qwen2.5-3B-NVFP4
Text Generation
•
2B
•
Updated
•
44
G-reen/adamwbone2epoch5_6lr_test
Text Generation
•
8B
•
Updated
•
3
G-reen/adamwbone2epoch5_6lr_test_adapter
Updated
G-reen/adamwlora2epoch5_6lr_test
Text Generation
•
8B
•
Updated
•
2
G-reen/adamwlora2epoch5_6lr_test_adapter
Updated
G-reen/adamwlora2epoch5_6lr
Text Generation
•
8B
•
Updated
•
1
G-reen/adamwlora2epoch5_6lr_adapter
Updated
G-reen/adamwbat2epoch5_6lr
Text Generation
•
8B
•
Updated
•
1
G-reen/adamwbat2epoch5_6lr_adapter
Updated
datasets
14
G-reen/Duet-v0.6
Viewer
•
Updated
•
5k
•
9
G-reen/reflexion-agi
Viewer
•
Updated
•
5k
•
48
•
38
G-reen/TheatreLM-v2.1-Characters
Viewer
•
Updated
•
5.01k
•
48
•
56
G-reen/Duet-v0.5
Viewer
•
Updated
•
5k
•
42
•
20
G-reen/deepmindcodecontestssharegpt
Viewer
•
Updated
•
13.1k
•
15
G-reen/TheatreLM-v2.0-Settings
Viewer
•
Updated
•
200
•
14
G-reen/TheatreLM-v2.0-Characters
Viewer
•
Updated
•
1k
•
17
G-reen/TheatreLM-v2.1-chats-preview
Viewer
•
Updated
•
3.94k
•
17
G-reen/TheatreLM-v2.0-chats-preview
Viewer
•
Updated
•
264
•
19
G-reen/TheatreLM-v1.0-DPO
Viewer
•
Updated
•
1
•
28