HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
331.
▲
4-Bit Quantization and QLoRA
huggingface.co
15 comments
3 years ago
tosh
41 points
332.
▲
Qwen/Qwen3.6-27B · Hugging Face
huggingface.co
6 comments
2 months ago
cgeier
41 points
333.
▲
BLOOMChat, a 176B parameter, Multi-lingual, fine tuned chat
huggingface.co
14 comments
3 years ago
hatcherdogg
40 points
334.
▲
What's Going on with the Open LLM Leaderboard?
huggingface.co
2 comments
3 years ago
tim_sw
40 points
335.
▲
DeepSeek-R1-Distill-Qwen-1.5B Surpasses GPT-4o in certain benchmarks
huggingface.co
17 comments
a year ago
BUFU
39 points
336.
▲
Show HN: Deep Learning Personas
personas.huggingface.co
11 comments
9 years ago
trueduke
39 points
337.
▲
Kai-Fu Li's Yi-34B uses exactly Llama's architecture except for 2 tensor renamed
huggingface.co
7 comments
3 years ago
vissidarte_choi
39 points
338.
▲
Continuous batching (2025)
huggingface.co
6 comments
4 months ago
jxmorris12
39 points
339.
▲
Fully autonomous AI agents should not be developed
huggingface.co
44 comments
a year ago
eamag
38 points
340.
▲
Zephyr 7B – Mistral Finetune that responds like ChatGPT
huggingface.co
12 comments
3 years ago
Flux159
37 points
341.
▲
Whisper Jax: Transcribe a 1 hour of audio in under 15 seconds
huggingface.co
9 comments
3 years ago
mysterybox
36 points
342.
▲
Qwen3-235B-A22B-Instruct-2507
huggingface.co
2 comments
a year ago
tosh
36 points
343.
▲
MistralLite by Amazon Web Services
huggingface.co
24 comments
3 years ago
tosh
34 points
344.
▲
The Ultra-Scale Playbook: Training LLMs on GPU Clusters
huggingface.co
3 comments
a year ago
jxmorris12
33 points
345.
▲
Mixtral-8x22B on HuggingFace
huggingface.co
3 comments
2 years ago
milliondreams
33 points
346.
▲
Qwen3-Coder-30B-A3B-Instruct
huggingface.co
10 comments
a year ago
swesnow
32 points
347.
▲
General OCR Theory: Towards OCR-2.0 via a Unified End-to-End Model
huggingface.co
2 comments
2 years ago
ac1spkrbox
31 points
348.
▲
Anatomy of BoltzGen
huggingface.co
1 comment
6 months ago
danielfalbo
31 points
349.
▲
Zephyr 141B, a Mixtral 8x22B fine-tune, is now available in Hugging Chat
huggingface.co
12 comments
2 years ago
osanseviero
30 points
350.
▲
OpenFLUX.1
huggingface.co
8 comments
2 years ago
Palmik
30 points
351.
▲
Reachy Mini – The Open-Source Robot for Today's and Tomorrow's AI Builders
huggingface.co
3 comments
a year ago
Thomjazz
30 points
352.
▲
Mistral 7B v0.2
huggingface.co
3 comments
2 years ago
milliondreams
29 points
353.
▲
Mixture of Experts Explained
huggingface.co
2 comments
3 years ago
osanseviero
29 points
354.
▲
TinyLlama at 2T of 3T
huggingface.co
1 comment
3 years ago
tosh
29 points
355.
▲
Video2Game: Real-Time, Interactive, Realistic Environment from a Single Video
huggingface.co
3 comments
2 years ago
Michelangelo11
28 points
356.
▲
Real-Time Latent Consistency Model
huggingface.co
6 comments
3 years ago
hi
27 points
357.
▲
grok-2 on Hugging Face
huggingface.co
3 comments
10 months ago
tosh
27 points
358.
▲
Language Modeling Is Compression
huggingface.co
3 comments
3 years ago
haltist
27 points
359.
▲
Llama-3.2-3B-Instruct-uncensored
huggingface.co
8 comments
2 years ago
chuanli11
26 points
360.
▲
DeepSeek-V4 Technical Report [pdf]
huggingface.co
4 comments
2 months ago
tianyicui
26 points
More