Definitely! More benchmarks on contrastive search coming soon too Thanks for empowering millions of developers
CODE
-
Open Source Models Now Support Custom Tokenizer Fallbacks
By
–
Of course, when using an open source model (Vicuna, Dolly) that model name is not in the tiktoken wrapper Previously, this would raise an error We've now updated this to: (1) fallback to a default tokenizer, (2) allow users to specify model name to use for tiktoken
-
LangChain PR improves open source model experimentation
By
–
PR for this here: https://
github.com/hwchase17/lang
chain/commit/e9877ea8b1d301efafb7d2fda5f9105b005774b8
… Shout out to Yuze Ma for highlighting this limitation at a hackathon this weekend! Hopefully this should make it easier to experiment with open source models -
LangChain API Base Configuration and Token Management
By
–
It's always been possible to change the API base in the LangChain model wrappers However, the model wrappers do a lot of handy things like token management, which rely on tokenizers that by default we look up in tiktoken We look this up based on model name
-
Groq Software Tools Enable Predictable Performance at Scale
By
–
With Groq #software tools and deterministic architecture #developers can look ahead, identify, and adjust performance-impacting components of their model. This means predictable and repeatable performance metrics at scale. Learn more at http://
groq.com/inference/. -
PyTorch dominance in latest LLM and vision transformer research
By
–
That's totally true, but I think the problem is once you want to adopt or use more of the recent (research) stuff and/or need more customization. E.g., all the latest LLM and vision transformer is basically exclusively PyTorch.
-
SQL Meets Document Model: Hybrid Database Innovation
By
–
Have your SQL cake and eat it, too, but with the power of the document model? Sounds tasty!
-
PyTorch Preference: Balancing Ease of Use with Flexibility
By
–
For me it's PyTorch because I like the trade-off between being ease of use but also being flexible and customizeable. Plus almost all people I interact with (research and companies) are using PyTorch. But yeah, I think your mileage may vary based on your collaborators.
-
Whisper Transcription Capabilities and Language Translation Features
By
–
Ha! Semantics – in this case we literally force it to transcribe into a target language. So, technically you can say it is translating! Whisper traditionally only translates from language “X” into English.
-
Fabric positioned between PyTorch and Trainer abstraction levels
By
–
Glad to hear it's useful! Btw if you are already using the Trainer, then you probably don't need Fabric. I would think of Fabric as a thing between pure PyTorch and using the Trainer 🙂