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 dataset
4 minutes ago
G-reen/big_set_gemma_it_format
updated
a dataset
4 minutes ago
G-reen/big_set_gemma_it_format
updated
a dataset
4 minutes ago
G-reen/big_set_gemma_it_format
Organizations
None yet
models
37
G-reen/gemma-2-2b-ultrafine
Updated
•
48
G-reen/gemma-2-2b-ultrafine-orbax
Updated
G-reen/gemma-2-2b-finetuned-medium-set
Text Generation
•
3B
•
Updated
•
35
G-reen/SmolLM3-3B-SFT
Text Generation
•
3B
•
Updated
•
1.18k
G-reen/Qwen2.5-3B-W8A8FP
Text Generation
•
3B
•
Updated
•
4
G-reen/Qwen2.5-3B-NVFP4
Text Generation
•
2B
•
Updated
•
5
G-reen/adamwbone2epoch5_6lr_test
Text Generation
•
8B
•
Updated
•
5
G-reen/adamwbone2epoch5_6lr_test_adapter
Updated
G-reen/adamwlora2epoch5_6lr_test
Text Generation
•
8B
•
Updated
•
6
G-reen/adamwlora2epoch5_6lr_test_adapter
Updated
datasets
28
G-reen/big_set_gemma_it_format
Updated
G-reen/test
Updated
G-reen/medium_set_gemma_it_format
Updated
G-reen/small_set_gemma_it_format
Updated
G-reen/mixed_prompts_responses
Viewer
•
Updated
•
27k
•
15
G-reen/aime_2025_results_smollm_ES
Viewer
•
Updated
•
30
•
14
G-reen/aime_2025_results_smollm
Viewer
•
Updated
•
30
•
25
G-reen/aime_2025_results_smollm_4k
Viewer
•
Updated
•
30
•
5
G-reen/aime_2025_results_smollm_sft
Viewer
•
Updated
•
30
•
6
G-reen/mixed_prompts_classified
Viewer
•
Updated
•
29.2k
•
23