Model checkpoints generated during an ongoing research effort into the acceleration potential and tuning quality of LLMs with RL fine tuning.
Scott Biggs
ScottBiggs2
AI & ML interests
I'm an AI researcher working on scalable generative modeling and reinforcement learning, with recent work in sparse RL acceleration and preference-based optimization. I release models and artifacts related to research, industry collaboration, and experimental exploration.
Recent Activity
upvoted
a
collection
24 days ago
Tiny-A2D
liked
a model
about 1 month ago
dllm-collection/Qwen3-0.6B-diffusion-mdlm-v0.1
liked
a dataset
about 1 month ago
allenai/tulu-3-sft-mixture
Organizations
models
5
ScottBiggs2/ThradBertConversationClassifier
Text Classification
•
0.1B
•
Updated
•
1
ScottBiggs2/ThradDistilbertConversationClassifier
Text Classification
•
67M
•
Updated
ScottBiggs2/LLaMA-3.1-8B-Instruct-DPO-Baseline
Text Generation
•
8B
•
Updated
•
3
ScottBiggs2/LLaMA-3.1-8B-Instruct-DPO-Triton-Sparse
Text Generation
•
8B
•
Updated
•
2
ScottBiggs2/tinyllama_detective_test
Updated
•
3
datasets
0
None public yet