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
19 days ago
G-reen/adamwbone2epoch5_6lr_test
updated
a model
19 days ago
G-reen/adamwbone2epoch5_6lr_test_adapter
published
a model
19 days ago
G-reen/adamwbone2epoch5_6lr_test
Organizations
None yet
Collections
1
models
31
G-reen/adamwbone2epoch5_6lr_test
Text Generation
•
Updated
•
2
G-reen/adamwbone2epoch5_6lr_test_adapter
Updated
G-reen/adamwlora2epoch5_6lr_test
Text Generation
•
Updated
•
1
G-reen/adamwlora2epoch5_6lr_test_adapter
Updated
G-reen/adamwlora2epoch5_6lr
Text Generation
•
Updated
•
7
G-reen/adamwlora2epoch5_6lr_adapter
Updated
G-reen/adamwbat2epoch5_6lr
Text Generation
•
Updated
•
7
G-reen/adamwbat2epoch5_6lr_adapter
Updated
G-reen/Qwen2.5-Coder-32b-Instruct-Fp8
Updated
•
2
G-reen/Mistral-Small-2501-Instruct-Fp8
Updated
•
2
datasets
14
G-reen/Duet-v0.6
Viewer
•
Updated
•
5k
•
24
G-reen/reflexion-agi
Viewer
•
Updated
•
5k
•
50
•
40
G-reen/TheatreLM-v2.1-Characters
Viewer
•
Updated
•
5.01k
•
35
•
57
G-reen/Duet-v0.5
Viewer
•
Updated
•
5k
•
39
•
22
G-reen/deepmindcodecontestssharegpt
Viewer
•
Updated
•
13.1k
•
26
G-reen/TheatreLM-v2.0-Settings
Viewer
•
Updated
•
200
•
11
G-reen/TheatreLM-v2.0-Characters
Viewer
•
Updated
•
1k
•
11
G-reen/TheatreLM-v2.1-chats-preview
Viewer
•
Updated
•
3.94k
•
21
G-reen/TheatreLM-v2.0-chats-preview
Viewer
•
Updated
•
264
•
19
G-reen/TheatreLM-v1.0-DPO
Viewer
•
Updated
•
1
•
24