Gonçalo Faria
graf
AI & ML interests
NLP
Recent Activity
updated
a model
about 8 hours ago
graf/hot_start_1.7b_bt_oracle_kl_1e-3_770
published
a model
about 8 hours ago
graf/hot_start_1.7b_bt_oracle_kl_1e-3_770
updated
a model
about 8 hours ago
graf/hot_start_1.7b_sbon32_kl_1e-3_770
Organizations
models
22
graf/hot_start_1.7b_bt_oracle_kl_1e-3_770
2B
•
Updated
•
13
graf/hot_start_1.7b_sbon32_kl_1e-3_770
2B
•
Updated
•
10
graf/hot_start_4b_bt_oracle-bt_oracle-d707ea35-1-320-on
4B
•
Updated
•
70
graf/hot_start_4b_sbon32-sbon32-b2c3b06f-1-320-on
4B
•
Updated
•
160
graf/hot_start_4b_sbon8-sbon8-69910159-1-320-on
4B
•
Updated
•
68
graf/hot_start_4b_sbon16-sbon16-0a589824-1-320-on
4B
•
Updated
•
67
graf/hot_start_1.7b_bt_oracle-bt_oracle-5cd7c196-1-320-on
2B
•
Updated
•
241
graf/hot_start_1.7b_sbon32-sbon32-e49deb3b-1-320-on
2B
•
Updated
•
267
graf/hot_start_1.7b_sbon8-sbon8-30f6ed4e-1-320-on
2B
•
Updated
•
217
graf/hot_start_1.7b_sbon16-sbon16-fc01e101-1-320-on
2B
•
Updated
•
2.07k
datasets
43
graf/qwen34.DeepScaleR-Preview-Dataset.gt.1.40000.ancestral.64.Qwen3-4B-Instruct-2507.bon
Viewer
•
Updated
•
5.14k
•
6
graf/qwen_deepsr_train_no_tags
Viewer
•
Updated
•
24.3k
•
142
graf/qwen_deepsr_math_test_no_tags
Viewer
•
Updated
•
418
•
39
graf/qwen_deepsr_gsm8k_test_no_tags
Viewer
•
Updated
•
1.28k
•
19
graf/DeepScaleR-Preview-Dataset.gt.1.20000.ancestral.128.Qwen2.5-1.5B-Instruct.bon
Viewer
•
Updated
•
12.6k
•
35
graf/DeepScaleR-Preview-Dataset.gt.4.20000.ancestral.128.Qwen2.5-1.5B-Instruct.rwmv.0.5
Viewer
•
Updated
•
80k
•
12
graf/DeepScaleR-Preview-Dataset.4.20000.ancestral.128.Qwen2.5-1.5B-Instruct.rwmv.0.5
Viewer
•
Updated
•
80k
•
21
graf/DeepScaleR-Preview-Dataset.1.20000.ancestral.128.Qwen2.5-1.5B-Instruct.rwmv.0.5
Viewer
•
Updated
•
20k
•
11
graf/DeepScaleR-Preview-Dataset.1.4096.ancestral.64.Qwen2.5-Math-1.5B-Instruct.rwmv.0.5
Viewer
•
Updated
•
4.1k
•
8
graf/DeepScaleR-Preview-Dataset.4.4096.ancestral.64.Qwen2.5-Math-1.5B-Instruct.rwmv.0.5
Viewer
•
Updated
•
16.4k
•
12