This collection contains models of the paper "PosS:Position Specialist Generates Better Draft for
Speculative Decoding"
Huang's INTelligence lab
university
AI & ML interests
None defined yet.
Recent Activity
View all activity
models
38
HINT-lab/Qwen3-4B-Baseline-SFT-GRPO
4B
•
Updated
HINT-lab/Qwen3-4B-Confidence-SFT-SGRPO
4B
•
Updated
HINT-lab/Qwen2.5-7B-Baseline-SFT
Text Generation
•
8B
•
Updated
HINT-lab/Qwen2.5-7B-Confidence-SFT
Text Generation
•
8B
•
Updated
HINT-lab/Qwen3-4B-Confidence-SFT
Text Generation
•
4B
•
Updated
HINT-lab/Qwen3-4B-Baseline-SFT
Text Generation
•
4B
•
Updated
HINT-lab/Qwen3-1.7B-Baseline-SFT-GRPO
2B
•
Updated
HINT-lab/Qwen3-1.7B-Confidence-SFT-SGRPO
2B
•
Updated
HINT-lab/Qwen2.5-7B-Baseline-SFT-GRPO
8B
•
Updated
HINT-lab/Qwen2.5-7B-Confidence-SFT-SGRPO
8B
•
Updated
datasets
38
HINT-lab/octo3bbase_solver_v1
Viewer
•
Updated
•
1.99k
•
13
HINT-lab/oct1bshortbase_solver_v1
Viewer
•
Updated
•
669
•
8
HINT-lab/llama8bi_retrain_solver_v5
Viewer
•
Updated
•
2.29k
•
8
HINT-lab/qwen3_frequent_solver_v3
Viewer
•
Updated
•
4.27k
•
41
HINT-lab/qwen3_frequent_solver_v1_v2
Viewer
•
Updated
•
7.51k
•
80
HINT-lab/7b_unstop_solver_v2
Viewer
•
Updated
•
5.06k
•
12
HINT-lab/qwen3_frequent_solver_v2
Viewer
•
Updated
•
3.58k
•
45
HINT-lab/7b_unstop_solver_v1
Viewer
•
Updated
•
4.8k
•
13
HINT-lab/solver_penalty_qwen3_v0
Viewer
•
Updated
•
13.6k
•
47
HINT-lab/penalty_questioner
Viewer
•
Updated
•
14.2k
•
59