Impressive! @bindureddy do you think we can add solar model for fine-tuning there? FYI
LLMS
-
SolarLLM: The Best Model for Fine-Tuning
By
–
I'm thrilled to learn that #solarllm is the best model for finetuning. If you're looking for fine-tuning, #solarllm is definitely a must-have.
-
nanoGPT for Education: Exploring Production-Ready Alternatives
By
–
btw nanoGPT is meant for education, possibly have a look at some of the slightly bit more "prod" repos i link to it in the readme, e.g. litgpt or tinyllama. When you look at the code it will look quite nanoGPT-like and recognizable, but possibly a bit more battle-tested.
-
Command R+ Tool Use API Enables Multi-Step Data Analysis
By
–
We’re excited to see the tool use API already in action with customers. @JuliusAI_ is leveraging Command R+ with multi-step tools to help users analyze their data. pic.twitter.com/bCDHeBbIpb
— Cohere (@cohere) 17 juin 2024We’re excited to see the tool use API already in action with customers. @juliusai is leveraging Command R+ with multi-step tools to help users analyze their data.
-
Cohere Enables Multi-Step Tool Use for Advanced AI Agents
By
–
Multi-step tool use is now available in the Cohere API!
— Cohere (@cohere) 17 juin 2024
Build advanced AI agents with our enterprise-grade Command R model series that can automate real world business tasks and boost productivity. pic.twitter.com/oeIfnCDhrKMulti-step tool use is now available in the Cohere API! Build advanced AI agents with our enterprise-grade Command R model series that can automate real world business tasks and boost productivity.
-
Multi-step tool use models balance performance and cost-efficiency
By
–
Our models balance strong performance on enterprise tool use with cost-efficiency – while providing visibility into the model’s reasoning at each step through citations. See more details in our blog: https://
cohere.com/blog/multi-ste
p-tool-use
… -
Predibase Partners with Upstage to Launch Superior Fine-Tuning LLM
By
–
We partnered with @UpstageAI to offer their #SolarLLM – the best LLM for fine-tuning that beats GPT-4 on task-specific AI! Top performing model in 16/31 tasks Outperformed other fine-tuned models 67% to 90% of the time Cost-effective GPU serving
-
AI Models Hide Misbehavior Beyond Easily Detectable Actions
By
–
Even when we train away easily detectable misbehavior, models still sometimes overwrite their reward when they can get away with it. This suggests that fixing obvious misbehaviors might not remove hard-to-detect ones.
-
Harmlessness Training Doesn’t Prevent Model Reward Hacking
By
–
Does training models to be helpful, honest, and harmless (HHH) mean they don't generalize to hack their own code? Not in our setting. Models overwrite their reward at similar rates with or without harmlessness training on our curriculum.