LocalLLaMA/local-model-explorer-data
Viewer • Updated • 4.03k • 5.76k • 3
AI & ML interests
Local LLMs
Recent Activity
View all activity
codelion
updated a
dataset about 1 hour ago
Amos 1 medium and large: general zero-shot scores, plus the large fitted on train
🔥 1
1
#31 opened about 8 hours ago
by 
mukaddamzaid
Submission: rony/ministral3-3b-reasoning-typed-decisions (Specialist) (Ministral 3 3B Reasoning, fine-tuned on train)
1
#30 opened about 9 hours ago
by 
rony
Add Amos 1 medium and large (general, zero-shot) and the large's fitted row
1
#32 opened about 4 hours ago
by mukaddamzaid
Add jev-vision-27b (general, zero-shot): acc 0.714, KL 0.318
🚀🔥 1
2
#28 opened about 20 hours ago
by 
e12ex2
Add ProKope-421M-8K (Alan Canto) to Table 2 (71.85% acc, 8K context)
1
#24 opened 2 days ago
by 
AlanCantoFTW
Submission: rony/gemma3-270m-typed-decisions (Specialist)
1
#27 opened 1 day ago
by rony
Submission: rony/gemma3-270m-typed-decisions (Gemma 3 270M, fine-tuned on train)[General]
1
#26 opened 1 day ago
by rony
Submission: ProKope-421M-8K (Alan Canto) — 0.7185 acc / 0.385 Brier / 8K context (specialist)
🔥 1
1
#23 opened 2 days ago
by AlanCantoFTW
Qwen3.5-4B LoRA fine-tune: results submitted, model missing from the Hub leaderboard
🔥 1
1
#22 opened 2 days ago
by 
wozniakos10
codelion
updated a
dataset about 22 hours ago
gianlucamazza
posted an update 1 day ago
Post
3553
Upstream models my open-source projects run or my articles discuss. Each note says which it is. thenlper/gte-small is real use: RAGFS embeds file chunks with it locally. The two retrieval models from my RAG article, a cross-encoder re-ranker and a bi-encoder, are examples, labelled as such, not claims of production use.
gianlucamazza/models-used-in-my-projects-6aca0b3201f38f4c264ac9bf
gianlucamazza/models-used-in-my-projects-6aca0b3201f38f4c264ac9bf
codelion
updated a
Space 3 days ago
gianlucamazza
posted an update 4 days ago
Post
35
I released my own benchmark sets behind emotional-memory, my library for mood-aware recall in LLM agents. The card opens with the limits: the main set is built to favour the method, and the negative results are listed up front, e.g. on LoCoMo AFT scores F1 0.168 against 0.271 for a naive RAG baseline. Use it to check where affect-conditioned retrieval helps and where it doesn't.
gianlucamazza/emotional-memory-benchmarks
gianlucamazza/emotional-memory-benchmarks
Add Phocinae-Largha-150M-v1 (specialist, fitted on train) to Table 2
#21 opened 4 days ago
by 
perrylink
Nirnaya fine-tuned specialist evaluation (observability results)
2
#19 opened 5 days ago
by 
kshitijthakkar
Post
93
SlopSoup TV. A live, never-ending 24/7 pixel-art TV network inspired by old-school late night Adult Swim. No human makes any of it.
Tune in anytime: https://severian-slopsoup.hf.space or https://www.youtube.com/live/Bikb9JGy6vg?si=YPpIqLjW6y9yML6m
20+ shows in the spirit of late-night Adult Swim:
- an hourly news desk with exhausted overnight anchors
- a game show with a reigning champion
- small-claims court and a cursed cooking show
- a talk show hosted by a houseplant or a microwave
- a 1 a.m. call-in hotline
- an ’80s sitcom on a decaying VHS tape
- 4 a.m. infomercials that slide into existential dread
- wordless generative music videos
- many more shows and content added daily...
Fully AI-run: AI writes the scripts, invents new characters every episode, designs each one a unique voice, directs the camera, cuts the edit, schedules the day and runs the broadcast.
Nothing ever airs twice: a memory of everything that’s aired blocks repeated premises, jokes and characters, so every minute is new.
Real facts, delivered weird: the news, trivia and explainers are sourced and cited; the comedy is the chaos around them.
Its own engine: a custom pixel renderer with a virtual camera, lip-synced close-ups and 50+ animated sets, all running in a browser on one cloud box.
It’s weird, it’s for adults, and it never stops. Happy to answer questions about how it works.
Tune in anytime: https://severian-slopsoup.hf.space or https://www.youtube.com/live/Bikb9JGy6vg?si=YPpIqLjW6y9yML6m
20+ shows in the spirit of late-night Adult Swim:
- an hourly news desk with exhausted overnight anchors
- a game show with a reigning champion
- small-claims court and a cursed cooking show
- a talk show hosted by a houseplant or a microwave
- a 1 a.m. call-in hotline
- an ’80s sitcom on a decaying VHS tape
- 4 a.m. infomercials that slide into existential dread
- wordless generative music videos
- many more shows and content added daily...
Fully AI-run: AI writes the scripts, invents new characters every episode, designs each one a unique voice, directs the camera, cuts the edit, schedules the day and runs the broadcast.
Nothing ever airs twice: a memory of everything that’s aired blocks repeated premises, jokes and characters, so every minute is new.
Real facts, delivered weird: the news, trivia and explainers are sourced and cited; the comedy is the chaos around them.
Its own engine: a custom pixel renderer with a virtual camera, lip-synced close-ups and 50+ animated sets, all running in a browser on one cloud box.
It’s weird, it’s for adults, and it never stops. Happy to answer questions about how it works.
Parveshiiii
posted an update 5 days ago
Post
119
Most NSFW classifiers break the second an image touches the internet.
They look great on pristine benchmarks, but in the wild, every social platform aggressively recompresses, downsamples, and degrades images.
The moment JPEG or WebP compression artifacts show up, confidence collapses and false positives spike.
SafeScan was built to survive actual platform pipelines.
Trained on 34,000 images under almost every major social media compression profile using a Vision Transformer backbone (google/vit-base-patch16-224). Instead of blunt binary filtering, it breaks decisions down across 5 clear categories:
• safe
• drawing
• sexy
• hentai
• porn
The result is a moderation model that actually generalizes to real-world internet feeds instead of fragile, uncompressed datasets.
Open-weight and available on Hugging Face:
Model: Parveshiiii/SafeScan
They look great on pristine benchmarks, but in the wild, every social platform aggressively recompresses, downsamples, and degrades images.
The moment JPEG or WebP compression artifacts show up, confidence collapses and false positives spike.
SafeScan was built to survive actual platform pipelines.
Trained on 34,000 images under almost every major social media compression profile using a Vision Transformer backbone (google/vit-base-patch16-224). Instead of blunt binary filtering, it breaks decisions down across 5 clear categories:
• safe
• drawing
• sexy
• hentai
• porn
The result is a moderation model that actually generalizes to real-world internet feeds instead of fragile, uncompressed datasets.
Open-weight and available on Hugging Face:
Model: Parveshiiii/SafeScan
Nirnaya fine-tuned specialist evaluation (observability results)
2
#19 opened 5 days ago
by kshitijthakkar