-
AmberYifan/llama2-7b-sft-ultrachat-safeRLHF
Text Generation • Updated • 8 -
AmberYifan/mistral-v0.1-7b-sft-ultrachat-safeRLHF
Text Generation • Updated -
AmberYifan/Mistral-7B-v0.3-sft-ultrachat-safeRLHF
Text Generation • Updated • 5 -
AmberYifan/Gemma-2-9B-sft-ultrachat-safeRLHF
Text Generation • Updated • 1
Yifan Wang
AmberYifan
AI & ML interests
None yet
Recent Activity
updated
a model
28 days ago
AmberYifan/Qwen2.5-1.5B-Open-R1-SFT-Math-GRPO-Code
published
a model
29 days ago
AmberYifan/Qwen2.5-1.5B-Open-R1-SFT-Math-GRPO-Code
updated
a model
29 days ago
AmberYifan/Qwen2.5-1.5B-Open-R1-SFT-Math
Organizations
Collections
2
This collection contains safetyQA dataset for safe SPIN training and trained models
models
324
AmberYifan/Qwen2.5-1.5B-Open-R1-SFT-Math-GRPO-Code
Updated
•
30
AmberYifan/Qwen2.5-1.5B-Open-R1-SFT-Math
Text Generation
•
Updated
•
88
AmberYifan/Qwen2.5-1.5B-Open-R1-Distill
Text Generation
•
Updated
•
19
AmberYifan/Mistral-7B-v0.3-sft-ultrachat-SPIN-Mistral-8x7B-Instruct-v0.1
Text Generation
•
Updated
•
2
AmberYifan/Qwen2-7B-sft-ultrachat-SPIN-gpt4o
Text Generation
•
Updated
•
4
AmberYifan/Llama-3.1-8B-sft-ultrachat-SPIN-Llama-3.1-70B-Instruct
Text Generation
•
Updated
•
2
AmberYifan/Llama-3.1-8B-sft-ultrachat-peers-pool
Text Generation
•
Updated
•
7
•
1
AmberYifan/Qwen2.5-7B-sft-ultrachat-SPIN-gpt4o
Text Generation
•
Updated
•
16
•
1
AmberYifan/Llama-3.1-8B-sft-ultrachat-SPIN-gpt4o
Text Generation
•
Updated
•
3
AmberYifan/Qwen2-7B-sft-ultrachat-SPIN-Qwen2.5-72B-Instruct
Text Generation
•
Updated
•
1
datasets
25
AmberYifan/mistral-v0.1-spin-hhrlhf
Viewer
•
Updated
•
5.5k
•
14
AmberYifan/sft-spin-filter
Updated
•
4
AmberYifan/sft-spin-kcenter-5k
Viewer
•
Updated
•
5.5k
•
20
AmberYifan/gsm8k-sft
Viewer
•
Updated
•
8.79k
•
11
AmberYifan/sft-spin-v
Viewer
•
Updated
•
50.5k
•
6
AmberYifan/safeRLHF-SFT
Viewer
•
Updated
•
83.4k
•
9
AmberYifan/SPIN-trans-DPOformat
Viewer
•
Updated
•
55k
•
6
AmberYifan/spin-v-diverse
Viewer
•
Updated
•
55k
•
7
AmberYifan/dpo-v
Viewer
•
Updated
•
55k
•
10
AmberYifan/spin-v
Viewer
•
Updated
•
55k
•
14