HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
271.
▲
PR to Change the LLaMA Models' Licence to Apache 2.0
github.com/facebookresearch
6 comments
3 years ago
hzj5790
32 points
272.
▲
30B model now needs only 5.8GB of RAM? How?
github.com/ggerganov
11 comments
3 years ago
olalonde
31 points
273.
▲
Llm.mojo: Andrej Karpathy's Llm.c in Mojo
github.com/dorjeduck
8 comments
2 years ago
klaussilveira
31 points
274.
▲
Show HN: Next-Gen AI Training: LLM-RLHF-Tuning with PPO and DPO
github.com/raghavc
9 comments
2 years ago
rags1
30 points
275.
▲
Show HN: LLMNet – The Offline Internet, Search the web without the web
github.com/skorotkiewicz
6 comments
5 months ago
modinfo
29 points
276.
▲
Show HN: LLM-docs, software documentation intended for consumption by LLMs
github.com/Dicklesworthstone
7 comments
a year ago
eigenvalue
28 points
277.
▲
Clang accepts MSVC arguments and targets Windows if its binary is named clang-cl
github.com/llvm
6 comments
2 years ago
delta_p_delta_x
27 points
278.
▲
LLMs playing chess are sensitive to how the position came to be
github.com/dpaleka
7 comments
3 years ago
famouswaffles
26 points
279.
▲
ElegantRL: A Lightweight and Stable Deep Reinforcement Learning Library
github.com/AI4Finance-LLC
2 comments
5 years ago
yanglet
26 points
280.
▲
Show HN: Sort lines semantically using llm-sort
github.com/vagos
13 comments
a year ago
vagozino
25 points
281.
▲
WIP Llama.cpp Vulkan Implementations
github.com/ggerganov
1 comment
3 years ago
brucethemoose2
24 points
282.
▲
Rails 3 jQuery Setup Script
github.com/lleger
4 comments
16 years ago
lleger
22 points
283.
▲
Local AI coding harness JSON AST to Clojure
github.com/quadracollision
1 comment
a month ago
vegnus
22 points
284.
▲
Show HN: Local LLM code-generation with Gemma 4 e2B via JSON AST to Clojure
github.com/quadracollision
discuss
a month ago
vegnus
22 points
285.
▲
A project to port LLVM to the MOS 6502
github.com/llvm-mos
5 comments
5 years ago
tempodox
21 points
286.
▲
Show HN: LLM 100k portfolio management benchmark
github.com/gqgs
5 comments
a year ago
gqgs
20 points
287.
▲
Advanced Code, Writing & Text Manipulation Prompts for Various LLMs
github.com/abilzerian
discuss
3 years ago
abilzerian
20 points
288.
▲
LLM Gateway: Secure and Reliable Exploration of Generative AI
github.com/wealthsimple
2 comments
3 years ago
sherwynds
19 points
289.
▲
Show HN: LLMs can be susceptible to a new kind of malware
github.com/greshake
10 comments
3 years ago
going_ham
17 points
290.
▲
Living Off the Land Binaries and Scripts
github.com/LOLBAS-Project
8 comments
3 years ago
colinprince
17 points
291.
▲
Ollama are 'try[ing to] achieve vendor lock-in'
github.com/ggerganov
5 comments
a year ago
alexmorley
17 points
292.
▲
Llm9p: LLM as a Plan 9 file system
github.com/NERVsystems
3 comments
4 months ago
mleroy
17 points
293.
▲
Gemma Is Added to Llama.cpp
github.com/ggerganov
discuss
2 years ago
behnamoh
17 points
294.
▲
RP2350 Hazard3 Added to LLVM
github.com/llvm
7 comments
2 years ago
hasheddan
16 points
295.
▲
Show HN: Smolex – A code retrieval ChatGPT Plugin for Python
github.com/loladotdev
4 comments
3 years ago
Livioso
16 points
296.
▲
Lisp Linear Algebra: tpapp's lla at master - GitHub
github.com/tpapp
3 comments
17 years ago
wglb
16 points
297.
▲
Speculative: PoC for speeding-up inference via speculative sampling by ggerganov
github.com/ggerganov
1 comment
3 years ago
kristianp
16 points
298.
▲
Show HN: LiteParse v2, now in Rust 100x faster
github.com/run-llama
discuss
a month ago
pierre
15 points
299.
▲
Real-Time Introspective Compression for Transformers
github.com/Dicklesworthstone
11 comments
a year ago
eigenvalue
14 points
300.
▲
LLaVA C++ server (based on llama.cpp)
github.com/trzy
6 comments
3 years ago
trzy
14 points
More