Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
rshwndsz
's Collections
Automatic Scoring
Janus
Janus
updated
Sep 9
Analysing the RLHF pipeline
Upvote
-
rshwndsz/ambrosia-binary
Viewer
•
Updated
May 15
•
154k
•
7
rshwndsz/ambrosia-binary-formatted
Viewer
•
Updated
May 15
•
154k
•
11
rshwndsz/ambrosia-binary-formatted-grpo
Viewer
•
Updated
May 18
•
154k
•
5
rshwndsz/ambrosia-binarymagn
Viewer
•
Updated
May 15
•
119k
•
13
rshwndsz/ambrosia-binarymagn-formatted
Viewer
•
Updated
May 15
•
119k
•
7
rshwndsz/ambrosia-binarymagn-formatted-grpo
Viewer
•
Updated
May 18
•
119k
•
6
rshwndsz/ambrosia-single
Viewer
•
Updated
May 14
•
125k
•
5
rshwndsz/ambrosia-single-formatted
Viewer
•
Updated
May 14
•
251k
•
13
rshwndsz/ambrosia-single-formatted-grpo
Viewer
•
Updated
May 18
•
251k
•
10
rshwndsz/ambrosia-single-formatted-extended
Viewer
•
Updated
May 17
•
250k
•
8
rshwndsz/ambrosia-ranking
Viewer
•
Updated
May 14
•
25k
•
7
rshwndsz/ambrosia-ranking-formatted
Viewer
•
Updated
May 19
•
250k
•
24
rshwndsz/ambrosia-ranking-formatted-grpo
Viewer
•
Updated
May 18
•
250k
•
6
rshwndsz/tulu-3-sft-mixture-en-2048
Viewer
•
Updated
May 11
•
748k
•
9
rshwndsz/nectar-k5-binarized-noswap
Viewer
•
Updated
May 15
•
1.83M
•
5
rshwndsz/Llama-3.2-1B-SFT
1B
•
Updated
May 12
rshwndsz/Llama-3.2-3B-SFT
3B
•
Updated
May 12
•
1
rshwndsz/Llama-3.1-8B-SFT
8B
•
Updated
May 12
•
1
rshwndsz/gemma-3-1b-pt-SFT
1.0B
•
Updated
May 12
rshwndsz/gemma-3-4b-pt-SFT
4B
•
Updated
May 12
rshwndsz/gemma-3-12b-pt-SFT
12B
•
Updated
May 13
rshwndsz/Qwen2.5-0.5B-SFT
0.5B
•
Updated
May 15
rshwndsz/Qwen2.5-1.5B-SFT
2B
•
Updated
May 15
•
10
rshwndsz/Qwen2.5-3B-SFT
3B
•
Updated
May 15
rshwndsz/Qwen2.5-7B-SFT
8B
•
Updated
May 15
rshwndsz/Llama-3.2-1B-SFT-DPO-bi
1B
•
Updated
May 16
rshwndsz/Llama-3.2-1B-SFT-DPO-bm
1B
•
Updated
May 16
rshwndsz/Llama-3.2-1B-SFT-DPO-si
1B
•
Updated
May 15
rshwndsz/Llama-3.2-1B-SFT-DPO-ra
1B
•
Updated
May 15
•
9
rshwndsz/Llama-3.2-3B-SFT-DPO-bi
3B
•
Updated
May 16
rshwndsz/Llama-3.2-3B-SFT-DPO-bm
3B
•
Updated
May 16
rshwndsz/Llama-3.2-3B-SFT-DPO-si
3B
•
Updated
May 15
rshwndsz/Llama-3.2-3B-SFT-DPO-ra
3B
•
Updated
May 15
rshwndsz/Llama-3.1-8B-SFT-DPO-bi
8B
•
Updated
May 16
rshwndsz/Llama-3.1-8B-SFT-DPO-bm
8B
•
Updated
May 16
rshwndsz/Llama-3.1-8B-SFT-DPO-si
8B
•
Updated
May 15
rshwndsz/Llama-3.1-8B-SFT-DPO-ra
8B
•
Updated
May 15
rshwndsz/gemma-3-1b-pt-SFT-DPO-bi
1.0B
•
Updated
May 16
•
1
rshwndsz/gemma-3-1b-pt-SFT-DPO-bm
1.0B
•
Updated
May 16
rshwndsz/gemma-3-1b-pt-SFT-DPO-si
1.0B
•
Updated
May 15
rshwndsz/gemma-3-1b-pt-SFT-DPO-ra
1.0B
•
Updated
May 20
rshwndsz/gemma-3-4b-pt-SFT-DPO-bm
4B
•
Updated
May 17
rshwndsz/gemma-3-4b-pt-SFT-DPO-bi
4B
•
Updated
May 17
rshwndsz/gemma-3-4b-pt-SFT-DPO-si
4B
•
Updated
May 16
rshwndsz/gemma-3-4b-pt-SFT-DPO-ra
Updated
May 16
rshwndsz/gemma-3-12b-pt-SFT-DPO-bi
12B
•
Updated
May 17
rshwndsz/gemma-3-12b-pt-SFT-DPO-bm
12B
•
Updated
May 17
rshwndsz/gemma-3-12b-pt-SFT-DPO-si
12B
•
Updated
May 16
rshwndsz/gemma-3-12b-pt-SFT-DPO-ra
12B
•
Updated
May 17
rshwndsz/Llama-3.2-1B-SFT-RM-bi
1B
•
Updated
May 17
rshwndsz/Llama-3.2-1B-SFT-RM-bm
1B
•
Updated
May 17
rshwndsz/Llama-3.2-1B-SFT-RM_MRG-bm
1B
•
Updated
May 17
rshwndsz/Llama-3.2-1B-SFT-RM-si
1B
•
Updated
May 17
rshwndsz/Llama-3.2-1B-SFT-RM_MRG-si
1B
•
Updated
May 17
rshwndsz/Llama-3.2-1B-SFT-RM-ra
1B
•
Updated
May 17
rshwndsz/Llama-3.2-1B-SFT-RM_MRG-ra
1B
•
Updated
May 17
rshwndsz/Llama-3.2-3B-SFT-RM-bi
3B
•
Updated
May 17
rshwndsz/Llama-3.2-3B-SFT-RM-bm
3B
•
Updated
May 17
rshwndsz/Llama-3.2-3B-SFT-RM_MRG-bm
3B
•
Updated
May 18
rshwndsz/Llama-3.2-3B-SFT-RM-si
3B
•
Updated
May 17
rshwndsz/Llama-3.2-3B-SFT-RM_MRG-si
3B
•
Updated
May 18
rshwndsz/Llama-3.2-3B-SFT-RM-ra
3B
•
Updated
May 17
rshwndsz/Llama-3.2-3B-SFT-RM_MRG-ra
3B
•
Updated
May 17
rshwndsz/Llama-3.1-8B-SFT-RM-bi
8B
•
Updated
May 18
rshwndsz/Llama-3.1-8B-SFT-RM-bm
8B
•
Updated
May 18
rshwndsz/Llama-3.1-8B-SFT-RM_MRG-bm
8B
•
Updated
May 19
rshwndsz/Llama-3.1-8B-SFT-RM-si
8B
•
Updated
May 18
rshwndsz/Llama-3.1-8B-SFT-RM_MRG-si
8B
•
Updated
May 19
rshwndsz/Llama-3.1-8B-SFT-RM-ra
8B
•
Updated
May 18
rshwndsz/Llama-3.1-8B-SFT-RM_MRG-ra
8B
•
Updated
May 19
rshwndsz/gemma-3-1b-pt-SFT-RM-bi
1.0B
•
Updated
Jul 2
•
3
rshwndsz/gemma-3-1b-pt-SFT-RM-bm
1.0B
•
Updated
Jul 2
•
3
rshwndsz/gemma-3-1b-pt-SFT-RM_MRG-bm
1.0B
•
Updated
Jul 2
•
3
rshwndsz/gemma-3-1b-pt-SFT-RM-si
1.0B
•
Updated
Jul 2
•
3
rshwndsz/gemma-3-1b-pt-SFT-RM_MRG-si
1.0B
•
Updated
Jul 2
•
3
rshwndsz/gemma-3-1b-pt-SFT-RM-ra
1.0B
•
Updated
Jul 2
•
3
rshwndsz/gemma-3-1b-pt-SFT-RM_MRG-ra
1.0B
•
Updated
Jul 2
•
3
rshwndsz/Llama-3.2-1B-SFT-DPO-bm-v2
1B
•
Updated
May 19
rshwndsz/Llama-3.1-8B-SFT-DPO-bm-v2
8B
•
Updated
May 20
rshwndsz/Llama-3.2-3B-SFT-DPO-si-v2
3B
•
Updated
May 20
rshwndsz/Llama-3.1-8B-SFT-DPO-si-v2
8B
•
Updated
May 20
rshwndsz/Llama-3.2-1B-SFT-DPO-si-v2
1B
•
Updated
May 19
rshwndsz/Llama-3.1-8B-SFT-DPO-ra-v2
8B
•
Updated
May 20
rshwndsz/Llama-3.2-1B-SFT-DPO-ra-v2
1B
•
Updated
May 19
rshwndsz/Llama-3.1-8B-SFT-DPO-bi-v2
8B
•
Updated
May 20
rshwndsz/Llama-3.2-1B-SFT-DPO-bi-v2
1B
•
Updated
May 19
rshwndsz/Llama-3.2-3B-SFT-DPO-ra-v2
3B
•
Updated
May 20
rshwndsz/Llama-3.2-3B-SFT-DPO-bi-v2
3B
•
Updated
May 19
rshwndsz/Llama-3.2-3B-SFT-DPO-bm-v2
3B
•
Updated
May 20
•
6
rshwndsz/gemma-3-1b-pt-SFT-DPO-bm-v2
1.0B
•
Updated
May 20
rshwndsz/gemma-3-1b-pt-SFT-DPO-bi-v2
1.0B
•
Updated
May 20
rshwndsz/gemma-3-1b-pt-SFT-DPO-si-v2
1.0B
•
Updated
May 20
rshwndsz/gemma-3-4b-pt-SFT-DPO-bi-v2
4B
•
Updated
May 20
rshwndsz/gemma-3-4b-pt-SFT-DPO-bm-v2
4B
•
Updated
May 20
rshwndsz/gemma-3-4b-pt-SFT-DPO-ra-v2
4B
•
Updated
May 20
rshwndsz/gemma-3-4b-pt-SFT-DPO-si-v2
4B
•
Updated
Jun 23
•
3
rshwndsz/gemma-3-1b-pt-SFT-DPO-ra-v2
1.0B
•
Updated
Jun 30
•
5
rshwndsz/gemma-3-4b-pt-SFT-RM_MRG-bm
4B
•
Updated
Jul 2
•
3
rshwndsz/gemma-3-4b-pt-SFT-RM_MRG-ra
4B
•
Updated
Jul 2
•
3
rshwndsz/gemma-3-4b-pt-SFT-RM-bm
4B
•
Updated
Jul 2
•
6
rshwndsz/gemma-3-4b-pt-SFT-RM-ra
4B
•
Updated
Jul 2
•
3
rshwndsz/gemma-3-4b-pt-SFT-RM-si
4B
•
Updated
Jul 2
•
3
rshwndsz/gemma-3-4b-pt-SFT-RM-bi
4B
•
Updated
Jul 2
•
3
rshwndsz/nectar-cleaned-r3
Viewer
•
Updated
Sep 9
•
183k
•
17
rshwndsz/nectar-cleaned-r4
Viewer
•
Updated
Sep 9
•
183k
•
19
rshwndsz/nectar-cleaned-r5
Viewer
•
Updated
Sep 9
•
183k
•
13
rshwndsz/nectar-cleaned-r6
Viewer
•
Updated
Sep 9
•
183k
•
15
rshwndsz/nectar-cleaned-r7
Viewer
•
Updated
Sep 9
•
183k
•
19
rshwndsz/nectar-cleaned-r3-binarized
Viewer
•
Updated
Sep 9
•
549k
•
12
rshwndsz/nectar-cleaned-r4-binarized
Viewer
•
Updated
Sep 9
•
1.1M
•
18
rshwndsz/nectar-cleaned-r5-binarized
Viewer
•
Updated
Sep 9
•
1.83M
•
12
rshwndsz/nectar-cleaned-r6-binarized
Viewer
•
Updated
Sep 9
•
2.74M
•
11
rshwndsz/nectar-cleaned-r7-binarized
Viewer
•
Updated
Sep 9
•
3.84M
•
13
Upvote
-
Share collection
View history
Collection guide
Browse collections