Blaed@lemmy.worldMEnglish · 4 months agoLlama 3.1 Megathreadplus-squarepinmessage-squaremessage-square11fedilinkarrow-up144arrow-down12
arrow-up142arrow-down1message-squareLlama 3.1 Megathreadplus-squarepinBlaed@lemmy.worldMEnglish · 4 months agomessage-square11fedilink
Smorty [she/her]@lemmy.blahaj.zoneEnglish · 6 days agoHow should one treat fill-in-the-middle code completions?plus-squaremessage-squaremessage-square4fedilinkarrow-up114arrow-down10
arrow-up114arrow-down1message-squareHow should one treat fill-in-the-middle code completions?plus-squareSmorty [she/her]@lemmy.blahaj.zoneEnglish · 6 days agomessage-square4fedilink
TiimeEnglish · 7 days agoFree AI Git Commit Message Plugin for JetBrains IntelliJ IDEA Using Gemini APIplus-squaretechwavearena.comexternal-linkmessage-square0fedilinkarrow-up14arrow-down10
arrow-up14arrow-down1external-linkFree AI Git Commit Message Plugin for JetBrains IntelliJ IDEA Using Gemini APIplus-squaretechwavearena.comTiimeEnglish · 7 days agomessage-square0fedilink
TiimeEnglish · 11 days agoClaude 3.5 Sonnet(new) vs Claude 3.5 Haiku vs Gemini 1.5 Pro vs GPT-4o vs GPT-4o mini vs Gemini 1.5 Flash, AI Model Comparison Guide (2024) | Benchmark Results & Analysisplus-squaretechwavearena.comexternal-linkmessage-square0fedilinkarrow-up115arrow-down17
arrow-up18arrow-down1external-linkClaude 3.5 Sonnet(new) vs Claude 3.5 Haiku vs Gemini 1.5 Pro vs GPT-4o vs GPT-4o mini vs Gemini 1.5 Flash, AI Model Comparison Guide (2024) | Benchmark Results & Analysisplus-squaretechwavearena.comTiimeEnglish · 11 days agomessage-square0fedilink
TiimeEnglish · 12 days agoBest Open Source LLM:Tencent Hunyuan-Large: The 389 Billion Parameter Model Outperforming Llama 3 and DeepSeek V2plus-squaretechwavearena.comexternal-linkmessage-square8fedilinkarrow-up112arrow-down15
arrow-up17arrow-down1external-linkBest Open Source LLM:Tencent Hunyuan-Large: The 389 Billion Parameter Model Outperforming Llama 3 and DeepSeek V2plus-squaretechwavearena.comTiimeEnglish · 12 days agomessage-square8fedilink
ram16@lemmy.worldEnglish · edit-212 days agoA New Open-Source Conversational AI Toolplus-squaregithub.comexternal-linkmessage-square10fedilinkarrow-up123arrow-down12
arrow-up121arrow-down1external-linkA New Open-Source Conversational AI Toolplus-squaregithub.comram16@lemmy.worldEnglish · edit-212 days agomessage-square10fedilink
Smorty [she/her]@lemmy.blahaj.zoneEnglish · 19 days agocode-completion model (Qwen2.5-coder) rewrites already written code instead of just completing itplus-squarefiles.catbox.moevideomessage-square2fedilinkarrow-up19arrow-down12cross-posted to: fosai@lemmy.world
arrow-up17arrow-down1videocode-completion model (Qwen2.5-coder) rewrites already written code instead of just completing itplus-squarefiles.catbox.moeSmorty [she/her]@lemmy.blahaj.zoneEnglish · 19 days agomessage-square2fedilinkcross-posted to: fosai@lemmy.world
Lemmchen@feddit.orgEnglish · edit-223 days agoAre there self-hostable AI models that can recommend glasses frames for your face type?plus-squaremessage-squaremessage-square3fedilinkarrow-up16arrow-down10
arrow-up16arrow-down1message-squareAre there self-hostable AI models that can recommend glasses frames for your face type?plus-squareLemmchen@feddit.orgEnglish · edit-223 days agomessage-square3fedilink
Smorty [she/her]@lemmy.blahaj.zoneEnglish · edit-219 days agoWhat should I use: big model-small quant or small model-no quant?plus-squaremessage-squaremessage-square17fedilinkarrow-up125arrow-down10
arrow-up125arrow-down1message-squareWhat should I use: big model-small quant or small model-no quant?plus-squareSmorty [she/her]@lemmy.blahaj.zoneEnglish · edit-219 days agomessage-square17fedilink
Smorty [she/her]@lemmy.blahaj.zoneEnglish · 1 month agoFunction Calling vs Format JSON: What do you use?plus-squaremessage-squaremessage-square0fedilinkarrow-up14arrow-down10
arrow-up14arrow-down1message-squareFunction Calling vs Format JSON: What do you use?plus-squareSmorty [she/her]@lemmy.blahaj.zoneEnglish · 1 month agomessage-square0fedilink
badcodecat@lemux.minnix.devEnglish · 1 month agoExploring Llamafile: Mozilla's Attempt in the World of Open Source AI - lemuxplus-squarelemux.minnix.devexternal-linkmessage-square2fedilinkarrow-up122arrow-down10
arrow-up122arrow-down1external-linkExploring Llamafile: Mozilla's Attempt in the World of Open Source AI - lemuxplus-squarelemux.minnix.devbadcodecat@lemux.minnix.devEnglish · 1 month agomessage-square2fedilink
Smorty [she/her]@lemmy.blahaj.zoneEnglish · 1 month agothe daily grindplus-squarelemmy.blahaj.zoneimagemessage-square0fedilinkarrow-up137arrow-down11
arrow-up136arrow-down1imagethe daily grindplus-squarelemmy.blahaj.zoneSmorty [she/her]@lemmy.blahaj.zoneEnglish · 1 month agomessage-square0fedilink
Smorty [she/her]@lemmy.blahaj.zoneEnglish · 2 months ago[IDEA] Scaling inference-time with complexityplus-squaremessage-squaremessage-square5fedilinkarrow-up110arrow-down10
arrow-up110arrow-down1message-square[IDEA] Scaling inference-time with complexityplus-squareSmorty [she/her]@lemmy.blahaj.zoneEnglish · 2 months agomessage-square5fedilink
Smorty [she/her]@lemmy.blahaj.zoneEnglish · 2 months agoMade some o1 imitation prompt. Maybe someone will care?plus-squaremessage-squaremessage-square1fedilinkarrow-up121arrow-down10
arrow-up121arrow-down1message-squareMade some o1 imitation prompt. Maybe someone will care?plus-squareSmorty [she/her]@lemmy.blahaj.zoneEnglish · 2 months agomessage-square1fedilink
brucethemoose@lemmy.worldEnglish · 2 months agoQwen2.5: A Party of Foundation Models!plus-squareqwenlm.github.ioexternal-linkmessage-square0fedilinkarrow-up117arrow-down10
arrow-up117arrow-down1external-linkQwen2.5: A Party of Foundation Models!plus-squareqwenlm.github.iobrucethemoose@lemmy.worldEnglish · 2 months agomessage-square0fedilink
reactive_recallEnglish · 2 months agoHow does Llama3 generates images?plus-squaremessage-squaremessage-square4fedilinkarrow-up116arrow-down10
arrow-up116arrow-down1message-squareHow does Llama3 generates images?plus-squarereactive_recallEnglish · 2 months agomessage-square4fedilink
brucethemoose@lemmy.worldEnglish · edit-23 months agoCohere Drops Command-R 35B 08-2024 Update, Just About a Perfect Local LLM for 24GB GPUs.plus-squarehuggingface.coexternal-linkmessage-square0fedilinkarrow-up117arrow-down10
arrow-up117arrow-down1external-linkCohere Drops Command-R 35B 08-2024 Update, Just About a Perfect Local LLM for 24GB GPUs.plus-squarehuggingface.cobrucethemoose@lemmy.worldEnglish · edit-23 months agomessage-square0fedilink
wiki_meEnglish · 3 months agoIsraeli Voice Recognition Startup Unveils Model ‘Faster Than OpenAI’plus-squareminiza.pages.devexternal-linkmessage-square1fedilinkarrow-up110arrow-down115
arrow-up1-5arrow-down1external-linkIsraeli Voice Recognition Startup Unveils Model ‘Faster Than OpenAI’plus-squareminiza.pages.devwiki_meEnglish · 3 months agomessage-square1fedilink
makingStuffForFunEnglish · 4 months agoLocal, privacy respecting, open source LLM that can transcribe phone calls and summarize the call?plus-squaremessage-squaremessage-square8fedilinkarrow-up127arrow-down12
arrow-up125arrow-down1message-squareLocal, privacy respecting, open source LLM that can transcribe phone calls and summarize the call?plus-squaremakingStuffForFunEnglish · 4 months agomessage-square8fedilink
