qingy2024/QwQ-14B-Math-v0.2
Text Generation
•
Updated
•
97
•
14
sometimesanotion PRO
sometimesanotion
AI & ML interests
Agentic LLM services, model merging, finetunes, distillation
Recent Activity
liked
a model
1 day ago
qingy2024/QwQ-14B-Math-v0.2
liked
a model
1 day ago
sthenno-com/miscii-14b-1225
updated
a model
1 day ago
sometimesanotion/Qwenvergence-Abliterate
Organizations
None yet
sometimesanotion's activity
liked
2
models
1 day ago
updated
a
model
1 day ago
reacted to
hba123's
post with 🚀
1 day ago
Post
1146
Blindly applying algorithms without understanding the math behind them is not a good idea frmpv. So, I am on a quest to fix this!
I wrote my first hugging face article on how you would derive closed-form solutions for KL-regularised reinforcement learning problems - what is used for DPO.
Check it out: https://huggingface.co./blog/hba123/derivingdpo
I wrote my first hugging face article on how you would derive closed-form solutions for KL-regularised reinforcement learning problems - what is used for DPO.
Check it out: https://huggingface.co./blog/hba123/derivingdpo
updated
2
models
2 days ago
liked
2
models
3 days ago
updated
a
model
4 days ago
liked
a
model
5 days ago
updated
a
model
5 days ago
liked
a
model
6 days ago
Interesting methods and results
20
#2 opened 28 days ago
by
sometimesanotion
Look forward to evaluation
#1 opened 8 days ago
by
sometimesanotion
updated
2
models
9 days ago
liked
a
model
9 days ago
Based on Qwen 14B, and it LIES constantly about everything China related.
4
#7 opened 10 days ago
by
Maani