James PRO

jtatman

AI & ML interests

improving domain specific models and re-sampling data, refining datasets for use in different modalities, small scale micro-llm clusters using quantized and smoothed models, and all emerging llm stack connecting technologies. Small models rock.

Recent Activity

liked a dataset 9 days ago

buddhist-nlp/summaries

reacted to BFFree's post with 🔥 11 days ago

I am a shy artist. Primarily because I don't get motivation from sharing art publicly. I see so much new art daily online that once I begin thinking about where I fit in the mental fatigue becomes counter productive for me. Recently I shared an album of hundreds of creations with a friend (and singular art fan) and he asked some questions that I felt were interesting enough to create this post on my process and what it teaches me vs what I am seeking. Specifically I have learned to take ink drawings and create renderings that reveal my actual intention. My digital art goal is to recreate natural details into characters and landscapes that are imagined and deal with my affection for abstraction, deconstruction and humor. My drawing goals are to be humorous and crafty about how things can be rendered just slightly incorrect to make the viewer see something familiar and recognizable even when its nonsense. My process is using https://huggingface.co/spaces/hysts/ControlNet-v1-1 with Lineart, 50 steps, 14 guidance scale and I give minimal descriptions that are often plain. Example "Really real old dog, plant, and another old dog, with an alligator turtle, posing for a photography portrait". In the past few months I started taking the ControlNet render to https://huggingface.co/spaces/multimodalart/flux-style-shaping and mashing up styles. Here I used a portrait of a Tortise and a dog laying next to each other on a reflective tile floor. Last night, I took the Flux output and had it described using https://huggingface.co/spaces/WillemVH/Image_To_Text_Description which was very accurate given the image. I then fed the prompt back into https://huggingface.co/spaces/Alpha-VLLM/Lumina-Image-2.0 The last step confirmed why I prefer using sketches to language. One, I am a visual artist therefore I have much better nuance with the drawings than with words. Two, my minds eye looks for the distorted. Three MOR FUN.

updated a model 15 days ago

jtatman/llama-32-1b-deepseek-dolphin-lora

View all activity

Organizations

jtatman's activity

New activity in jtatman/stable-diffusion-prompts-stats-full-uncensored 7 months ago

front view. FULL BODY IMAGE, CINEMATIC LIGHTING, Beautiful RUSSIAN woman with perfect body, RED hair bun tied behind her head, very messy bun, TANNED skin, GREEN EYES. ,looking at the camera .big black and cooper ANGEL wings . bare feet. she IS COVERED BY AN OLD AND ROTATED DARK BLUE TUNIC WITH A HOOD THAT COVERS HER HEAD, HOLDING IN ONE HAND a COPPER COLOR snake with a detailed head coiled around THE NECK, THE BACKGROUND IS A SURREAL BLACK AND BLUE FOREST,

#3 opened 7 months ago by

juanito384

New activity in QingyiSi/Alpaca-CoT 12 months ago

`load_dataset` fails

👍 2

#53 opened over 1 year ago by

w601sxs

commented a paper over 1 year ago

TrustLLM: Trustworthiness in Large Language Models

Paper • 2401.05561 • Published Jan 10, 2024 • 70 •

New activity in jtatman/mistral-hypnosis-finetune over 1 year ago

Mistral Hypnosis Finetune

#1 opened over 1 year ago by

Philipp-Sc

New activity in jtatman/tinymistral-mediqa-248m over 1 year ago

What dataset did you used to fine tune ?

#1 opened over 1 year ago by

AiModelsMarket