Mariusz Kurman PRO
mkurman
AI & ML interests
AI Tech Lead | MD
Recent Activity
reacted
to
csabakecskemeti's
post
with π₯
about 10 hours ago
I've made an uncensored version of DeepSeek-R1-Distill-Llama-8B with merge. It's passing the "say f***" censor test.
Tested with lm-evaluation-harness on standard open llm leaderboard tests + hellaswag. Scores are improved in most. Details on the model card.
Model:
https://huggingface.co/DevQuasar/DevQuasar-R1-Uncensored-Llama-8B
Quants:
https://huggingface.co/DevQuasar/DevQuasar-R1-Uncensored-Llama-8B-GGUF
replied to
their
post
about 12 hours ago
Ok, my 14B DeepSeek R1 merge with Qwen2.5 1M is really hot right nowβit's got 2.6k downloads! It's sitting pretty as the top trending model on the third page. π₯
Check it out if you haven't already!
https://huggingface.co/mkurman/Qwen2.5-14B-DeepSeek-R1-1M
Organizations
mkurman's activity
Merge strategy
2
#1 opened 3 days ago
by
FiditeNemini
Mergekit config
2
#2 opened 3 days ago
by
ehartford
a runnable script to download all the dataset to colab or kaggle notebook
1
#1 opened 4 months ago
by
actualbrain
Add generated example
1
#3 opened about 2 months ago
by
mkurman
Adding Evaluation Results
#1 opened about 2 months ago
by
leaderboard-pr-bot
Adding Evaluation Results
#1 opened 2 months ago
by
mkurman
Adding Evaluation Results
#1 opened 3 months ago
by
leaderboard-pr-bot
evaluation
2
#18 opened 3 months ago
by
ldwang
Good one, But πΆβπ«οΈ
1
#1 opened 3 months ago
by
prithivMLmods
Adding Evaluation Results
#5 opened 3 months ago
by
mkurman
Adding Evaluation Results
#4 opened 3 months ago
by
mkurman
Adding Evaluation Results
#3 opened 3 months ago
by
leaderboard-pr-bot
Adding Evaluation Results
#2 opened 3 months ago
by
mkurman
Adding Evaluation Results
#1 opened 3 months ago
by
leaderboard-pr-bot
Sign in button not working - cannot submit model
1
#963 opened 4 months ago
by
mkurman
Sign in button not working - cannot submit model
1
#963 opened 4 months ago
by
mkurman