Codebase: https://
github.com/jwohlwend/boltz
@reach_vb
-
Model weights release and Hub distribution discussion
By
–
Wow! Congratulations on the release, it'd be great to have the weights under an official org on the Hub too. I uploaded the weights under a community org for now, happy to add you there/ transfer the weights to you, let me know – congrats again on the brilliant work.
-
Model Deployment Scaling and Cold Start Performance
By
–
Interesting, could you elaborate a bit? The model should typically come online within seconds if it's scaled to zero.
-
Streaming Mode in Datasets: Features and Improvements
By
–
Interesting, have you tried the streaming mode in datasets? It allows you to stream a row/ batch at a time. If yes, then what would you like us to add to that.
-
Unified Jinja Chat Templates for LLMs and llama.cpp
By
–
100% – I think a basic jinja implementation would be quite helpful. I do think a world where we have unified chat templates across transformers, llama.cpp, etc would be quite headache free 😀 There is an abandoned PR adding that in llama.cpp btw https://
github.com/ggerganov/llam
a.cpp/pull/9639
… -
llama.cpp Static Templates vs Jinja Support Discussion
By
–
100% yes, llama.cpp uses static templates atm and doesn't have jinja support (primarily because jinja is quite bulky). Static templates work quite well tho (Except when they don't :p) cc: @ggerganov too
-
Base Models in AI: Use Cases and Merging Strategies
By
–
Ah! Interesting, so only show `base_models`. What's the main use-case behind it (just to understand it better)? Note: it does get a bit tricky because sometimes you can have merges or adpater based models which are totally new, but just use another model as the base.
-
Cloning and Running AI Spaces Locally or on ZeroGPU
By
–
Not sure if I follow, you can just clone the space and run locally right? Alternatively you can run it on ZeroGPU
-
Model Parameters and Precision Information Now Available
By
–
Great feature request. There is a version of that in the works, just FYI you can see how many parameters does the model have on the model page and it's corresponding precision, which should give a rough idea – loads more to do there. In the meantime you can use this too: