12 2 54

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

reacted to hba123's post with 🚀 1 day ago

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

View all activity

Organizations

None yet

sometimesanotion's activity

New activity in CultriX/SeQwence-14Bv3 7 days ago

Interesting methods and results

#2 opened 28 days ago by

sometimesanotion

New activity in Aashraf995/QwenStock-14B 8 days ago

Look forward to evaluation

#1 opened 8 days ago by

sometimesanotion

New activity in arcee-ai/Virtuoso-Small 10 days ago

Based on Qwen 14B, and it LIES constantly about everything China related.

#7 opened 10 days ago by

Maani

New activity in sometimesanotion/Lamarck-14B-v0.3 17 days ago

Adding Evaluation Results

#1 opened 17 days ago by

leaderboard-pr-bot

New activity in arcee-ai/Virtuoso-Small 21 days ago

Question about model's origin

#2 opened 21 days ago by

sometimesanotion

New activity in sometimesanotion/KytheraMix-7B-v0.2 24 days ago

Next version

#1 opened 25 days ago by

sometimesanotion

New activity in mradermacher/AgoraMix-14B-stock-v0.1-i1-GGUF 27 days ago

Much appreciated

#1 opened 27 days ago by

sometimesanotion

New activity in edgerunner-ai/EdgeRunner-Command-Nested about 1 month ago

Fascinating model, a question

#1 opened about 1 month ago by

sometimesanotion

New activity in anthracite-org/magnum-v4-12b about 1 month ago

Request

#5 opened about 1 month ago by

isr431

New activity in arcee-ai/SuperNova-Medius about 1 month ago

Update SuperNova-Medius with a merge with Qwen/Qwen2.5-Coder-14B-Instruct + Further Training 😋

#12 opened about 1 month ago by

Joseph717171

New activity in HuggingFaceTB/SmolLM2-1.7B-Instruct about 2 months ago

Upload ONNX weights

#1 opened about 2 months ago by

Xenova

New activity in arcee-ai/SuperNova-Medius 2 months ago

Multilingual, Uncensored and extensive vocabulary.

#4 opened 2 months ago by

Kukedlc

Multilingual, Uncensored and extensive vocabulary.

#4 opened 2 months ago by

Kukedlc