Heykuki News

TopNewBestAskShowJobs
TopNewBestAskShowJobs
211.
How I'm training a prompt injection detector
1 point
gasperpre
a year ago
discuss
212.
Show HN: Tokenkit – Convert LLMs to new tokenizers (incl byte-level Llama/Gemma) (github.com/bminixhofer)
1 point
bminixhofer
a year ago
discuss
213.
Show HN: Genomic Jamba – Hybrid Mamba2/FlashAttention Model for Genomics (github.com/suzuki-2001)
1 point
ss-13
a year ago
discuss
214.
BSE: Semantic compression for LLMs, built by a starving creator
1 point
bramblestudio
a year ago
discuss
215.
We Benchmarked Mistral and Landing AI vs. Docsumo (docsumo.com)
1 point
snehanairdoc
a year ago
discuss
216.
Show HN: Dingo – Automate Data Quality Checks Across Pre-Training and SFT Data (github.com/DataEval)
1 point
e06084
a year ago
discuss
217.
Show HN: KnowLang – An open-source tool for understanding complex codebases
1 point
gaby_rla
a year ago
discuss
218.
Help Us Rank the Best Background Removal Tools
1 point
thomasbrd
a year ago
discuss
219.
Show HN: Multilingual Embedding Model for Images, Audio and PDFs (yoeven.notion.site)
1 point
yoeven
2 years ago
discuss
220.
Show HN: Florence2-Sharp – Advanced Image Understanding and OCR in C# (github.com/curiosity-ai)
1 point
theolivenbaum
2 years ago
discuss
221.
Show HN: A model to make heatmaps of anomalies in natural images (github.com/ahsanMah)
1 point
scoremah
2 years ago
discuss
222.
Show HN: AI powered image search across multiple folders for macOS (smarterfolder.com)
1 point
dzan
2 years ago
discuss
223.
Show HN: TalkBank Batchalign – one-stop speech sample analysis tool and models (github.com/TalkBank)
1 point
jemoka
2 years ago
discuss
224.
Show HN: Vector-Io: Universal Vector Data Import/Export (github.com/AI-Northstar-Tech)
1 point
dhruv_anand
2 years ago
discuss
225.
Show HN: Multimodal AI Dataset for Training Python AI Coding Copilots
1 point
matlok5432
2 years ago
discuss
226.
Cannot reproduce the exact same training results – diffusion models
1 point
roxyrox
2 years ago
discuss
227.
Show HN: RAGTheDocs, one-click deploy RAG for any readthedocs website (github.com/jerpint)
1 point
jerpint
3 years ago
discuss
228.
Semantic search and retrieval augmented generation for medical literature
1 point
dmezzetti
3 years ago
discuss
229.
Show HN: Generating dad jokes with a fine-tuned Mistral-7B (dadjokes.dfdx.me)
1 point
shutty
3 years ago
discuss
230.
Ask HN: GPU Resource Estimation Text to Speech
1 point
roughhewer
3 years ago
discuss
231.
GPU Resource Estimation Text to Speech
1 point
roughhewer
3 years ago
discuss
232.
Show HN: Last Night I Built a Junior Dev AI Agent (Experiment) (github.com/jawerty)
1 point
jawerty
3 years ago
discuss
233.
Deep Learning Translation: NLLB 200 vs. M2M100 vs. Opus MT
1 point
juliensalinas
4 years ago
discuss
234.
Uncensor any LLM with abliteration (huggingface.co)
586 points
mizzao
2 years ago
287 comments
235.
Deepseek R1-0528 (huggingface.co)
451 points
error404x
a year ago
250 comments
236.
LLM Embeddings Explained: A Visual and Intuitive Guide (huggingface.co)
451 points
eric-burel
10 months ago
91 comments
237.
Llama-3.3-70B-Instruct (huggingface.co)
425 points
pr337h4m
2 years ago
219 comments
238.
Try Stable Diffusion's Img2Img Mode (huggingface.co)
415 points
fragmede
4 years ago
156 comments
239.
Show HN: Hacker News archive (47M+ items, 11.6GB) as Parquet, updated every 5m (huggingface.co)
408 points
tamnd
3 months ago
167 comments
240.
Open-R1: an open reproduction of DeepSeek-R1 (huggingface.co)
394 points
jonbaer
a year ago
234 comments
More