The Objective Dad

icon indicating a website link https://www.theobjectivedad.com

icon location Houston, TX icon location I am a husband and father of two working in technology. Interests include AI research, philosophy, education, Kubernetes, electronics, and HAM radio

Results 17 comments of The Objective Dad

Add feature to select model name for Ollama

Posting here for folks looking for a workaround. The model can be renamed to llama2/latest on the Ollama side to get things working. The following example is verified to work...

git-lfs: Upload never terminates, although file size already exceeded

I am experiencing a similar issue, again from behind a nginx proxy running in k8s. I see messages similar to these repeating in the gitea logs during upload: ```text 2022-10-15...

Adding support for stella_en_400M_v5

+1

[Bug]: bnb quant load error

Got it, ty for looking at this and helping me understand. Do you want me to close this issue?

Label Propagation Lacks Max Iteration Cap, Risking Infinite Loop on Non-Converging Graphs

+1

[Bug]: ChatCompletionRequest rejects its own defaults

+1

Allow Prompt/Sampling Messages to contain multiple content blocks.

I appreciate this discussion and just wanted to weigh regarding use cases. I can think of two scenarios where this would be useful. As previously mentioned, (a) when sampling responses...