SimpleBerry Research Lab
university
AI & ML interests
Smart Solutions for Success in Science & Business.
Recent Activity
View all activity
SimpleBerry's activity
qq8933
authored
3
papers
15 days ago
StyleMaster: Stylize Your Video with Artistic Generation and Translation
Paper
•
2412.07744
•
Published
•
19
SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints
Paper
•
2412.07760
•
Published
•
49
3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation
Paper
•
2412.07759
•
Published
•
18
Post
2526
LLaMA-O1-PRM and LLaMA-O1-Reinforcement will release in this weekend.
We have implemented a novel Reinforcement finetune(RFT) pipeline that taught models learning reasoning and reward labeling without human annotation.
We have implemented a novel Reinforcement finetune(RFT) pipeline that taught models learning reasoning and reward labeling without human annotation.
-
- 3 replies
Post
1649
ChemVLM has been accepted by AAAI2025!
Seeing and Understanding: Bridging Vision with Chemical Knowledge Via ChemVLM (2408.07246)
Try have a chat wiht him🤗.
AI4Chem/ChemVLM-26B-1-2
Seeing and Understanding: Bridging Vision with Chemical Knowledge Via ChemVLM (2408.07246)
Try have a chat wiht him🤗.
AI4Chem/ChemVLM-26B-1-2
jwu323
updated
a
model
23 days ago
jwu323
updated
a
Space
23 days ago
jwu323
updated
a
model
23 days ago
qq8933
updated
2
models
23 days ago
qq8933
updated
a
Space
24 days ago
qq8933
updated
a
Space
25 days ago
Post
3038
The first version of LLaMA-O1 has been uploaded to HF now!Here We Come!
Supervised:
SimpleBerry/LLaMA-O1-Supervised-1129
Base(Pretrain):
SimpleBerry/LLaMA-O1-Base-1127
Supervised Finetune Dataset:
SimpleBerry/OpenLongCoT-SFT
Pretraining Dataset:
SimpleBerry/OpenLongCoT-Pretrain-1202
RLHF is on the way! View our GitHub Repo:
https://github.com/SimpleBerry/LLaMA-O1
Our ongoing related researches:
Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B (2406.07394)
LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning (2410.02884)
Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning (2411.18203)
@AdinaY @akhaliq @jwu323
------
GGUF:https://huggingface.co/Lyte/LLaMA-O1-Supervised-1129-Q4_K_M-GGUF
online Demo (CPU-only): SimpleBerry/LLaMA-O1-Supervised-1129-Demo
Supervised:
SimpleBerry/LLaMA-O1-Supervised-1129
Base(Pretrain):
SimpleBerry/LLaMA-O1-Base-1127
Supervised Finetune Dataset:
SimpleBerry/OpenLongCoT-SFT
Pretraining Dataset:
SimpleBerry/OpenLongCoT-Pretrain-1202
RLHF is on the way! View our GitHub Repo:
https://github.com/SimpleBerry/LLaMA-O1
Our ongoing related researches:
Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B (2406.07394)
LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning (2410.02884)
Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning (2411.18203)
@AdinaY @akhaliq @jwu323
------
GGUF:https://huggingface.co/Lyte/LLaMA-O1-Supervised-1129-Q4_K_M-GGUF
online Demo (CPU-only): SimpleBerry/LLaMA-O1-Supervised-1129-Demo
-
- 3 replies
Post
1343
LLaMA-O1 Base and SFT model will be uploaded to HF today.
RLHF pipeline already ready, still waiting for data sampling.
RLHF pipeline already ready, still waiting for data sampling.
-
- 1 reply
qq8933
authored
a
paper
29 days ago
jwu323
authored
a
paper
29 days ago
Post
1351
We are excited to announce a new internal project, Rome, focused on advancing LLM reasoning. The code and accompanying paper will be released soon. Stay tuned!
-
- 2 replies
Post
2406
Discovered an outrageous bug on the ChatGPT official website, especially for those using ad-blocking plugins. Please make sure to add
For users with Chinese IP addresses, consider adding this URL to the rules of your U.S. node, as the response headers from this site will report the user's physical location to GPT.
browser-intake-datadoghq.com to your ad block whitelist. The ChatGPT webpage relies on this site for heartbeat detection, but since it belongs to an ad tracking network, it's included in major ad-blocking lists. (If you're using Clash, also remember to add it to the whitelist.) Failing to do so may cause the ChatGPT web interface to display a greyed-out send button after clicking, with no response.For users with Chinese IP addresses, consider adding this URL to the rules of your U.S. node, as the response headers from this site will report the user's physical location to GPT.
-
- 3 replies
Post
6265
LLaMA-O1: Open Large Reasoning Model Frameworks For Training, Inference and Evaluation With PyTorch and HuggingFace
Large Reasoning Models powered by Monte Carlo Tree Search (MCTS), Self-Play Reinforcement Learning, PPO, AlphaGo Zero's dua policy paradigm and Large Language Models!
https://github.com/SimpleBerry/LLaMA-O1/
What will happen when you compound MCTS ❤ LLM ❤ Self-Play ❤RLHF?
Just a little bite of strawberry!🍓
Past related works:
LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning (2410.02884)
Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B (2406.07394)
Large Reasoning Models powered by Monte Carlo Tree Search (MCTS), Self-Play Reinforcement Learning, PPO, AlphaGo Zero's dua policy paradigm and Large Language Models!
https://github.com/SimpleBerry/LLaMA-O1/
What will happen when you compound MCTS ❤ LLM ❤ Self-Play ❤RLHF?
Just a little bite of strawberry!🍓
Past related works:
LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning (2410.02884)
Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B (2406.07394)
-
- 2 replies