Di Zhang

qq8933

AI & ML interests

AI4Chem, LLM, Green LLM

Recent Activity

updated a dataset about 3 hours ago
qq8933/OpenLongCoT-Pretrain-v2
updated a dataset about 23 hours ago
qq8933/llama_o1_offline_training_data_v1
New activity 2 days ago
qq8933/OpenLongCoT-Pretrain

Organizations

qq8933's activity

replied to their post 7 days ago
replied to their post 16 days ago
view reply

main.py is the entry for finetune, but codes need further improvements, see 'Call for contributors'

posted an update 17 days ago
view post
Post
2269
Discovered an outrageous bug on the ChatGPT official website, especially for those using ad-blocking plugins. Please make sure to add 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
ยท
posted an update 19 days ago
view post
Post
5513
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 โค LLM โค Self-Play โคRLHF?
Just a little bite of strawberry!๐Ÿ“

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
ยท
posted an update 3 months ago
replied to their post 4 months ago
view reply

ๅŽ็ซฏๅผ‚ๅธธ๏ผŒๆŒ‚ๆŽ‰ไบ†๏ผŒๅœจไฟฎๅค

posted an update 5 months ago
view post
Post
653
Preview:
We will open source the 2.5B ChemVLM and the tool-enhanced ChemLLM-7B in the near future
posted an update 5 months ago
reacted to their post with ๐Ÿ˜Ž 5 months ago
view post
Post
2611
Tools Ready!
Thanks to ChemCrow's great work, ChemLLM supports proficiency toolkits Now, Include,
Molecule Name Retrivel
Molecule Property Query
Patent Check
Molecule Safety Query
Try it on chemllm.org
  • 2 replies
ยท
posted an update 5 months ago
view post
Post
2611
Tools Ready!
Thanks to ChemCrow's great work, ChemLLM supports proficiency toolkits Now, Include,
Molecule Name Retrivel
Molecule Property Query
Patent Check
Molecule Safety Query
Try it on chemllm.org
  • 2 replies
ยท
posted an update 5 months ago
view post
Post
996
New Appearance from Ollama Open WebUI!
And Also web search, Realtime talking and File RAG!
https://chemllm.org/


posted an update 6 months ago
replied to their post 6 months ago
reacted to turiabu's post with ๐Ÿค— 6 months ago
view post
Post
2099
Can anyone see my post on๐Ÿค—?
Reply with ๐Ÿค—
ยท
reacted to their post with ๐Ÿค— 6 months ago
posted an update 6 months ago
posted an update 6 months ago
view post
Post
2075
ChemLLM Multi-Modal version will coming soon!
Also Weights and Datasets!
  • 2 replies
ยท
posted an update 7 months ago
view post
Post
2015
Chemllm.org Now transfered to ChemLLM-20B-DPO, Have a try now!๐Ÿค—
replied to their post 7 months ago
view reply

Sorry for network issues, still uploading...

posted an update 7 months ago
view post
Post
2391
ChemLLM-20B SFT and DPO is coming!๐Ÿค—
  • 1 reply
ยท