pinned
Running on Zero
202
𧩠DiffuseCraft Mod (SDXL/SD1.5 Models Text-to-Image)
π§©
Stunning images using stable diffusion.
John Smith PRO
John6666
AI & ML interests
None yet
Recent Activity
reacted
to
marksverdhei's
post with π€― about 6 hours ago
The hidden gem of open-source embedding models: LCO-Embedding
for text, image AND audio!
I found this model after reading the recent Massive Audio Embedding Benchmark (MAEB) paper, as it blew the other models out of the water on day zero. I've been using it personally for about a week, and searching my files by describing music, sound effects or images is both practical and entertaining. Really underrated model, would highly recommend checking it out: https://huggingface.co/LCO-Embedding/LCO-Embedding-Omni-7B
PS: If you're looking you run this model on llama.cpp, i've gone ahead and quantized them for you here π https://huggingface.co/collections/marksverdhei/lco-embedding-omni-gguf reacted
to
BibbyResearch's
post with π about 6 hours ago
Used by Researchers at Allen institute, Simons foundation, Yale and other top universities.. π€
Researchers are using AI to write their papers.
That AI is Bibby AI.
Not GPT-5. Not Claude Opus. Not whatever wrapper your institution just paid $50k for.
Bibby.
While the AI research community spent 2025 debating whether LLMs can handle scientific writing β actual scientists at actual top-tier institutions quietly started shipping papers with it. No press release. No hype cycle. Just results.
Here's what they figured out that most people haven't:
The bottleneck in research was never the ideas. It was never the experiments. It was the 3am writing sessions where good science goes to die in a Google Doc. Writer's block, LaTex Learning frustration, formatting issues, compiler errors.
Bibby is built specifically for that gap. Citation-aware. Argument-aware. Knows when to hedge, when to assert, and β critically β knows not to hallucinate your methods section.
The institutions adopting it aren't doing it because it's trendy. They're doing it because the researcher-hours it saves are going straight back into actual research.
This is what the adoption curve looks like before the thing becomes obvious.
β https://trybibby.com/
Who else here is using AI in their research workflow? Drop it below π
Best comments will receive a discounted Bibby AI subscription with a chance to win a $100 grant for their research. reacted
to
EricFillion's
post with π about 6 hours ago
Hereβs how to perform retrieval-augmented (RAG) with two new open-source Python packages I just released. I included a full article below that provides a step-by-step guide on how to build a vector database with this https://huggingface.co/datasets/wikimedia/wikipedia dump and use it to perform RAG with https://huggingface.co/openai/gpt-oss-20b.
FULL ARTICLE: https://www.vennify.ai/vector-eric-search/
https://huggingface.co/vennify
```
pip install erictransformer ericsearch
```
```
import json
from ericsearch import EricSearch
from erictransformer import EricChat
eric_search = EricSearch()
with open("data.jsonl", "w", encoding="utf-8") as f:
sample_case = {"text": "This contains example data. It should contain at least two sentences."}
f.write(json.dumps(sample_case)+ "\n")
eric_search.train("data.jsonl")
eric_search = EricSearch(data_name="eric_search/")
eric_chat = EricChat(model_name="openai/gpt-oss-20b", eric_search=eric_search)
result = eric_chat("Tell me about artificial intelligence ")
print(result.text)
``` Organizations
