Heykuki News

TopNewBestAskShowJobs
TopNewBestAskShowJobs
631.
Qwen Image Edit - SOTA Open Weight Image Editing Model (huggingface.co)
6 points
JimDugan
10 months ago
discuss
632.
Cybersecurity Instruction Tuned Model (huggingface.co)
6 points
privacyhateai
10 months ago
discuss
633.
Show HN: Agent Leaderboard 2.0 – Domain Specific edition (huggingface.co)
6 points
erinmikail
a year ago
discuss
634.
Better than DeepSeek R1? MiniMax-M1:open-weight hybrid-attention reasoning model (huggingface.co)
6 points
helloericsf
a year ago
discuss
635.
Qwen2.5-Omni Technical Report (huggingface.co)
6 points
wertyk
a year ago
discuss
636.
SigLIP 2: A better multilingual vision language encoder (huggingface.co)
6 points
bo0tzz
a year ago
discuss
637.
Kokoro-TTS (huggingface.co)
6 points
arbayi
a year ago
discuss
638.
Scaling Test Time Compute (huggingface.co)
6 points
alexmolas
a year ago
discuss
639.
OpenFlux: Dedistillated Apache licensed flux.schnell model (huggingface.co)
6 points
BoredPositron
2 years ago
discuss
640.
A Llama 70B finetune that has reflection baked into it's weights (huggingface.co)
6 points
s-macke
2 years ago
discuss
641.
Show HN: Understand politics by visualising manifesto embeddings (huggingface.co)
6 points
skanderbm
2 years ago
discuss
642.
Mistral releases the v0.3 of its 7B LLM (huggingface.co)
6 points
fgfm
2 years ago
discuss
643.
Idefics2: A Powerful 8B Vision-Language Model for the Community (huggingface.co)
6 points
theschwa
2 years ago
discuss
644.
Show HN: Open-source LLM for data labeling (huggingface.co)
6 points
nihit-desai
2 years ago
discuss
645.
Dolphin-2.9-Llama3-8B (huggingface.co)
6 points
tosh
2 years ago
discuss
646.
Introduction to 3D Gaussian Splatting (huggingface.co)
6 points
slowhand09
2 years ago
discuss
647.
Mistral-7B-Instruct-v0.2 (huggingface.co)
6 points
tosh
2 years ago
discuss
648.
Qwen is a large language model series by Alibaba Cloud (huggingface.co)
6 points
slyall
3 years ago
discuss
649.
Show HN: TCO Calculator to compare on-prem LLM deployment vs. OpenAI and Co (huggingface.co)
6 points
DanyWin
3 years ago
discuss
650.
Llama-2-70B-instruct-v2 (huggingface.co)
6 points
tosh
3 years ago
discuss
651.
Falcon 40B-Instruct GGML (huggingface.co)
6 points
hamilyon2
3 years ago
discuss
652.
Open LLM Leaderboard (huggingface.co)
6 points
tosh
3 years ago
discuss
653.
RWKV – An RNN with the Advantages of a Transformer (huggingface.co)
6 points
Garcia98
3 years ago
discuss
654.
Open LLM Leaderboard (huggingface.co)
6 points
DantesKite
3 years ago
discuss
655.
Assisted Generation: a new direction toward low-latency text generation (huggingface.co)
6 points
kmod
3 years ago
discuss
656.
Databricks Publishes a Version of Dolly LLM to Hugging Face (huggingface.co)
6 points
superchink
3 years ago
discuss
657.
Hugging Face introduces Pull Requests and Discussions (huggingface.co)
6 points
julien_c
4 years ago
discuss
658.
Show HN: KaniTTS – Open-source high-fidelity TTS with just 450M params (huggingface.co)
5 points
ulan_kg
9 months ago
5 comments
659.
First DeepSeek V4 Flash-Base-Int4 Quant (huggingface.co)
5 points
saivegasena
a month ago
3 comments
660.
APIEval-20: A Benchmark for Black-Box API Test Suite Generation (huggingface.co)
5 points
AkshatVirmani
2 months ago
3 comments
More