jr/jake.runyan.dev
1
0
Fork 0
mirror of https://github.com/runyanjake/jake.runyan.dev.git synced 2025-10-04 13:57:29 -07:00
Code Issues Packages Projects Releases Wiki Activity

Update deepseek blog post

Browse Source
This commit is contained in:
Jake R 2025-01-27 13:50:38 -08:00
parent aeecd48138
commit 48ebfd8466
1 changed files with 6 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
website/blog/2025-01-22-pure-rl-with-deepseek/index.mdx
View File

@ -35,6 +35,7 @@ For this experiment I was looking at the 1.5b and 8b models for `deepseek-r1`, t
Man, it was pretty good. I've got a smaller GPU on PWS so I was limited to running the 8b model, but responses were good. I noticed Man, it was pretty good. I've got a smaller GPU on PWS so I was limited to running the 8b model, but responses were good. I noticed
the best response times on the 1.5b model, and for some easier tasks the correctness between the two was hard to discern. the best response times on the 1.5b model, and for some easier tasks the correctness between the two was hard to discern.
### Search
I particularly liked the features of OpenWebUI to allow for web search, which from initial testing seemed to find good results to build I particularly liked the features of OpenWebUI to allow for web search, which from initial testing seemed to find good results to build
context of the response with. context of the response with.
@ -45,6 +46,11 @@ verbatim from my github profile and websites.
![img alt](./jake.png) ![img alt](./jake.png)
For best results, the setup I have been using is Llama3.2 for generating search queries.
Search is done through the Google Programmable Search Engine (See [Here](https://docs.openwebui.com/tutorials/integrations/web_search/#google-pse-api) for instructions.)
And the model of choice for the response is Deepseek-r1:8b.
# Final Thoughts
I'm still actively using chatgpt, claude, and others for coding work, but as local LLMs improve you can bet I'll be keeping up to date with this stack. I'm still actively using chatgpt, claude, and others for coding work, but as local LLMs improve you can bet I'll be keeping up to date with this stack.
## Resources ## Resources