Shawn Reed
@shekari.bsky.social
140 followers 68 following 64 posts
Self proclaimed good guy with some bad habits including Porsche, Ducati & sugar. Also very lucky to have @sparklyseaster.bsky.social in my life.
Posts Media Videos Starter Packs
shekari.bsky.social
I literally woke up and thought I can't wait to get back to testing multi-modal embeddings today. #Memgraph #MCP #llama.cpp
Reposted by Shawn Reed
sparklyseaster.bsky.social
A reminder for all. Please repost this to get the word out. I, and your local wildlife, thank you. 🥰

#Halloween #birds #wildlife
BEWARE!
Your Halloween decorations may be hazardous to wildlife!
[picture of a distressed owl caught in fake netting]
Any decorations, like fake spider webbing, that dangle, hang or wrap can entangle wild animals like this Screech Owl!
Please consider wildlife safety when decorating your home for the holiday, and remember to properly dispose of Halloween candy, pumpkins and other edibles to prevent unwanted wildlife visitors.
Reposted by Shawn Reed
sparklyseaster.bsky.social
I've moved my shop from Etsy to Shopify. It's definitely a work in progress, but I have a few sets of press-on nails up! 🥰
murdermittensnails.com

#PressOnNails #NailPolish #CustomNails
MurderMittensNails.myshopify.com
Custom press-on nails
murdermittensnails.com
shekari.bsky.social
I can’t make this new tool work, it must be the tools fault.
shekari.bsky.social
Open source that can be audited and consensus between a few different models would be a start.
shekari.bsky.social
Dedicated button, no. Specific chip to support? Yes and proof. bsky.app/profile/shek...
shekari.bsky.social
After a day of tuning and testing models, another variable has entered the fray. #AMD #RYZENAIMAX #GMKtec
shekari.bsky.social
After a day of tuning and testing models, another variable has entered the fray. #AMD #RYZENAIMAX #GMKtec
shekari.bsky.social
Some incredible results after tuning gpt-oss a bit. an FP16 GGUF Thanks Unsloth! with a 320k context all in VRAM and >100 tok/sec! #GPT-OSS #llama.cpp #AMD #ROCM
shekari.bsky.social
I also found that ROCm 6.4 was way faster on prompt processing but Vulkan as a bit faster on the streaming speed so Gemini Flash helped me determine the break even point.
shekari.bsky.social
I think I will add in a gpt-oss and produce my own IQ4_NL quant of the Dolphin model as I did for the Gemma 3.
shekari.bsky.social
Will try matching the kv cache quants to the model quant and some more common like q8_0 next.
shekari.bsky.social
Some fun building llama.cpp with ROCm 6.4, ROCm 7.0 RC2 and Vulkan in addition to testing some kv cache quants. Note, don't bother with iq4_nl for k & v , it pushes prompt processing to CPU. Without quantizing kv, ROCm is beating vulkan in my testing. Dolphin-Mistral-24B-Venice-Edition-Q5_K_M.gguf
Reposted by Shawn Reed
shekari.bsky.social
59 here and it was a Timex Sinclair 1000 but the same experience adding AI into my workflows. I have so many ideas to try out that I can’t even sleep some nights.
shekari.bsky.social
I think I'll get the letters in the words to slowly fade and get refreshed by the matrix rain. Then clean it up and push it up to #GitHub for others to play with.
shekari.bsky.social
I modified the world clock example of the Pimoroni Presto to give it some much needed Matrix. @pimoroni.com #micropython #RaspberryPiPico #Pimoroni
shekari.bsky.social
One example of the errors I was seeing is
```shell
error: Failed to read metadata for: packaging==25.0
Caused by: Failed to parse METADATA file: .venv/lib/python3.12/site-packages/packaging-25.0.dist-info/METADATA
Caused by: Metadata field Name not found
```
shekari.bsky.social
I had something wrong with several dependencies that were in use so I could have / will try the 'uv cache clean' next time but somehow I picture that being identical functionality to the rm . If/when it happens again I will also first try the prune and see if it resolves the issue.
shekari.bsky.social
Never underestimate the healing powers of an occasional rm -rf ~/.cache/uv #python #softwaredevelopment
shekari.bsky.social
I spent some time with Gemini CLI today. Made great progress on a local project until I ran out of free Gemini Pro 2.5 requests and it switch me to Gemini Flash. Then it was more hassle fixing the errors it cause... Even the Premium plan is only 1500 a day. #Gemini #Google #SoftwareDevelopment
shekari.bsky.social
Cline is WAY better than GitHub Copilot. For my current workflow at least #python #Neo4j #Gemma3-27b-q5
shekari.bsky.social
Just a call out that gpt-oss:20b got an update and it now can be shown the error of it's ways. And for some specific tasks it really is a great tool. 30k context and fully loaded into VRAM in 18GB, 87.93 tok/sec, 1.20s to first token in LM Studio - ROCm llama.cpp (Linux) v1.46.0 #ROCm #AMD
shekari.bsky.social
#ai #aiartwork #aiartist #Aiartcommunity #aiart
Young girl with headphones not in use down around her neck.