Hackernews posts about LLaMa-3 8B

LLaMa-3 8B is a state-of-the-art large language model that has achieved impressive performance in natural language processing tasks.

RSS feed for LLaMa-3 8B

01
newOpen-Source E2E FHE Implementation for Privacy-Preserving Llama 3 8B Inferencearxiv.org
▲ 2simonpure 9d discuss
02
newEcholeak Beaten - almosthuggingface.co
▲ 2Apollo_R 8d discuss
03
newShow HN: Fine-tune Llama3-8B on 8GB GPU without quantizationgithub.com
▲ 3anuarsh 348d discuss
04
newNovel Logic-Enhanced LLM for Improved Symbolic Reasoning
▲ 10N3Xxus_6 550d discuss
05
newAsk HN: Good small LLM model for generating Chinese sentence examples?
▲ 3koynoyno 498d 💬 1
06
newNeuro-Symbolic Logic Enhancement for LLMs
▲ 3N3Xxus_6 545d discuss
07
newI built a Cursor for writers" on a $7 budget using Groq and Llama 3
▲ 2minotauris 252d 💬 2
08
newShow HN: Qling – iOS podcast player with deep personalizationapps.apple.com
▲ 2bjar2 465d 💬 2
09
newThink Before You Speak – Exploratory Forced Hallucination Study [pdf]github.com
▲ 2airylizard 477d discuss
10
newShow HN: CreativeFlow – A Guided Brainstorming Appcreativeflow.pages.dev
▲ 1jamescamagong 230d 💬 2
11
newShow HN: Ghost Engine – generate weights on the flygithub.com
▲ 1saznlamsal 260d 💬 1
12
newShow HN: Language1 – Benchmarking LLM comprehension of vague prompts via Taboolanguage1.app
▲ 1kaandemirel 110d discuss
13
newA proxy that cuts LLM API bills by routing simple tasks to cheaper models
▲ 1alex_1002 217d discuss
14
newDeepHermes 3: unify reasoning and intuitive language model capabilitieshuggingface.co
▲ 1TheJCDenton 598d discuss
15
newNvidia presents Llama-Mesh: Generating 3D Mesh with Llama 3.1 8Bresearch.nvidia.com
▲ 20BUFU 689d 💬 1
16
newShow HN: Llama 3.1 8B CPU Inference in a Browser via WebAssemblygalqiwi.github.io
▲ 4om8 650d 💬 4
17
newHardware LLM Taalas Reaches >14,000 TPS on Llama 3.1 8Btaalas.com
▲ 3nullbio 138d 💬 1
18
newTracing tokens through Llama 3.1 8B inference on H100skrithik.xyz
▲ 3krithik_7 150d 💬 1
19
newMake Llama 3.1 8B talk in Rick Sanchez's stylegithub.com
▲ 3mtrofficus 635d 💬 1
20
newChat with Llama 3.1 8Byosunai.com
▲ 3vijayst 690d 💬 1
21
newAsk HN: What are the machine requirements for a LLM like Llama-3.1-8B?
▲ 2wasimsk 173d 💬 2
22
newCognitivecomputations/Dolphin3.0-Llama3.1-8B uncensoredhuggingface.co
▲ 1simonpure 639d discuss
23
newDistilling Llama3.1 8B into 1B in torchtunepytorch.org
▲ 1tosh 665d discuss
24
newShow HN: Morphik – Open-source RAG that understands PDF images, runs locallygithub.com
▲ 200Adityav369 532d 💬 43
25
newShow HN: What is HN thinking? Real-time sentiment and concept analysisethos.devrupt.io
▲ 37ddtaylor 236d 💬 23
26
newAsk HN: How is GPU power draw measured at scale?
▲ 6anax32 102d 💬 2
27
newShow HN: Unfat, a library to easily train and distill LoRAs for LLMsgithub.com
▲ 6reissbaker 579d discuss
28
newShow HN: Slash your LLM Inference Costs with Overnight Processing
▲ 5Blue_Cosma 727d 💬 1
29
newShow HN: Mixlayer – code and deploy LLM prompts using JavaScriptwww.mixlayer.com
▲ 5zackangelo 725d discuss
30
newShow HN: Quantum-Enhanced Mathematical Reasoning System – Expert Verification
▲ 4nandakishor_ml 645d 💬 1
31
newShow HN: Thaw – Git branch for a running LLM (fork agents, skip prefill)github.com
▲ 3nilsmatteson 129d discuss
32
newShow HN: CodeMode – First library for tool calls via code executiongithub.com
▲ 3juanviera23 326d discuss