wogikaze-inbox
ChatGPTの音声
Beatrice
AK(@_akhaliq)
Snap-it, Tap-it, Splat-it
Tactile-Informed 3D Gaussian Splatting for Reconstructing Challenging Surfaces
Touch and vision go hand in hand, mutually enhancing our ability to understand the world. From a research perspective, the problem of mixing touch and vision is
https://gyazo.com/27b9ba9ac2153371c1f7609b51b7569d
OneLLM
Animatable Gaussians
基礎統計学https://speakerdeck.com/brainpadpr/basic-of-statistics
Cinematic Behavior Transfer via NeRF-based Differentiable Filminghttps://twitter.com/raoanyi/status/1730051313440891291
Cinematic Behavior Transferhttps://virtualfilmstudio.github.io/projects/cinetransfer/
上に追記する形式で、スマホからだと書きづらいのでリンク/名前をおいておく
code:parameters
1girl,
mayano top gun \(umamusume\), umamusume,
ciloranko, maccha \(mochancc\), lobelia \(saclia\), migolu, ask \(askzy\), wanke, (jiu ye sang:1.1), (rumoon:0.9), (mizumi zumi:1.1),
(solo:1.2), (1o1i:1.3), swimsuit, medium breasts, blue sky, sitting, holding cup, horse girl, outdoors, day, animal ears, black bikini, one eye closed, flower, looking at viewer, long hair, cup, two side up, drinking straw, very long hair, orange eyes, arm strap, cloud, beach, bikini, alternate costume, breasts, tail, navel, horse tail, holding, ear flower, water, cleavage, pink flower, character doll, orange hair, horse ears, sky,
masterpiece, newest, absurdres, sensitive
Negative prompt: low quality, worst quality, normal quality, text, signature, jpeg artifacts, bad anatomy, old, early, multiple views, multiple tails, multiple girls, multiple boys
Steps: 24, Sampler: Euler a, Schedule type: Uniform, CFG scale: 5, Seed: 3641839546, Size: 832x1216, Model hash: 516047db97, Model: kohaku-xl-epsilon-rev1, VAE hash: 235745af8d, VAE: sdxl_vae.safetensors, Denoising strength: 0.4, ENSD: 17415, Hires upscale: 1.5, Hires steps: 16, Hires upscaler: Lanczos, Emphasis: No norm, Eta: 0.35, Version: v1.9.0-RC-14-g3fadb4fc
code:postprocessing
Postprocess upscale by: 2, Postprocess upscaler: ScuNET PSNR, Postprocess upscaler 2: R-ESRGAN 4x Anime6B, GFPGAN visibility: 0.4
code:extras
Postprocess upscale by: 2, Postprocess upscaler: ScuNET PSNR, Postprocess upscaler 2: R-ESRGAN 4x Anime6B, GFPGAN visibility: 0.4
from 💬雑談
wogikaze-inbox
Ninja_V1
Llama 3 Youko 8B
KARAKURI LM
Dify
ArrowPro-7B-KUJIRA
LM studio
https://huggingface.co/Fugaku-LLM/Fugaku-LLM-13BFugaku-LLM/Fugaku-LLM-13B
Siddharth Sharma(@siddrrsh)
Introducing Gemma with a 10M context window
We feature:
• 1250x context length of base Gemma
• Requires less than 32GB of memory
• Infini-attention + activation compression
Check us out on:
• 🤗: https://tinyurl.com/gemma10hf
• GitHub: https://tinyurl.com/gemma10git
• Technical…
https://gyazo.com/4971553f3ef0af88f84cca7f07f577d1
https://huggingface.co/mustafaaljadery/gemma-2B-10Mmustafaaljadery/gemma-2B-10M
Ocuteus-v1
quartzite ai
ArrowPro-7B-RobinHood
Command-r-plus 160B
https://huggingface.co/nitky/Megac4ai-command-r-plusnitky/Megac4ai-command-r-plus
Stockmark-100b
https://llm.stockmark.co.jp/Stockmark LLM
ElanMT
https://huggingface.co/spaces/CohereForAI/aya-23CohereForAI/aya-23
https://huggingface.co/CohereForAI/aya-23-8BCohereForAI/aya-23-8B
ツヅミ
https://qiita.com/c60evaporator/items/ca7eb70e1508d2ba5359?s=33機械学習のパラメータチューニングを「これでもか!」というくらい丁寧に解説 #Python - Qiita
ArrowPro-7B-KillerWhale
https://huggingface.co/hatakeyama-llm-team/Tanuki-8B-Instructhatakeyama-llm-team/Tanuki-8B-Instruct
https://huggingface.co/datasets/HuggingFaceFW/fineweb-eduHuggingFaceFW/fineweb-edu
FineWeb-Edu
SB Intuitions
https://huggingface.co/nvidia/Nemotron-4-340B-Instructnvidia/Nemotron-4-340B-Instruct
claude 3.5
Mixture-of-Agents (MoA)
KARAKURI LM 8x7B Instruct v0.1
https://azukiazusa.dev/blog/try-chrome-internal-ai-gemini-nano/Chrome の 組み込み AI Gemini Nano を試してみる
Llama 3.1