use generic or sft trainer with chat template none in autotrain. that trains on plaintext
CODE
-
Merge Results Expected at 90 Percent Performance
By
–
It would be interesting to see the results. I expect this merge to be like 90% as good as the full merge
-
Building LLM Workflows and Applications
By
–
Well, it's specifically for building LLM workflow and applications
-
Low-Code and Light Agentic Systems Will Win the Market
By
–
good riff, disagree on conclusion. i think its low code and light agenty systems like @juliusai and @wordware_ai and @cognition_labs that win
-
Positional Encoding: Essential Beyond Attention in Transformers
By
–
Attention is not all you need. Without positional encoding, a transformer would treat a context as a bag of words.
-
Hume AI System Prompts vs OpenAI Tool Use Approach
By
–
While Hume does offer tool use when using OpenAI models, this one is just stuffing the system prompt with all the information I want it to have access to.
-
The Magic of Programming in Modern Technology
By
–
still can't get over the magic that is programming
-
Building Objectives for Chess Search Trees with Known World States
By
–
We can easily build objectives for chess search trees, because: the complete state of the world is represented by a type known at compile-time; and we can handwrite a function to say exactly what states of the world we want, as described by that known representation. An AGI
-
MLflow-Giskard Integration for LLM Testing and Vulnerability Detection
By
–
The MLflow-Giskard integration offers a great solution for testing and validating LLM outputs. MLflow's evaluation API + Giskard's automatic vulnerability detection for LLMs is game-changing. See it in action https://
dbricks.co/4bEoPKl
