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
Currently working on https://github.com/Green0-0/propagate (ES Trainer for LLMs). Also interested in TPU training, and building better synthetic datasets.
Recent Activity
updated
a model
about 3 hours ago
G-reen/gemma-2-2b-it-fft-simpo-adj
published
a model
about 3 hours ago
G-reen/gemma-2-2b-it-fft-simpo-adj
updated
a model
about 5 hours ago
G-reen/gemma-2-2b-it-fft-simpo
Organizations
None yet
models
14
G-reen/gemma-2-2b-it-fft-simpo-adj
Text Generation
•
3B
•
Updated
G-reen/gemma-2-2b-it-fft-simpo
Text Generation
•
3B
•
Updated
G-reen/gemma-2-2b-it-fft
Text Generation
•
3B
•
Updated
G-reen/gemma-2-2b-it-cpt-fft-simpo-lr1e6-constrained
Text Generation
•
3B
•
Updated
•
19
G-reen/gemma-2-2b-it-cpt-fft-simpo-lr1e6-dubbsz
Text Generation
•
3B
•
Updated
•
21
G-reen/gemma-2-2b-it-cpt-fft-simpo-lr1e6
Text Generation
•
3B
•
Updated
•
20
G-reen/gemma-2-2b-big-set-orbax
Updated
G-reen/gemma-2-2b-base-big-cpt-fft
Updated
•
8
G-reen/gemma-2-2b-it-cpt-fft
Text Generation
•
3B
•
Updated
•
97
G-reen/gemma-2-2b-base-cpt-fft
Updated
•
85
datasets
27
G-reen/instruct-set-longer-fixed
Viewer
•
Updated
•
110k
G-reen/instruct-set-longer
Viewer
•
Updated
•
140k
•
90
G-reen/instruct-set
Viewer
•
Updated
•
139k
•
194
G-reen/instruct-set-half
Viewer
•
Updated
•
95.1k
•
48
G-reen/visualizertest
Viewer
•
Updated
•
1k
•
8
G-reen/medium_set
Viewer
•
Updated
•
138k
•
390
G-reen/sumthink_broken_format
Viewer
•
Updated
•
24.7k
•
12
G-reen/sumthink_responses_summarized
Viewer
•
Updated
•
24.7k
•
16
G-reen/sumthink_responses_raw
Viewer
•
Updated
•
27k
•
25
G-reen/sumthink_fixed_cleaned
Viewer
•
Updated
•
24.7k
•
28