Code Llama 70B scores a 67.8 on HumanEval, making it one of the highest performing open models available today. Happy hacking!
CODE
-
Code Llama 70B Base: The Foundational Code Model
By
–
And Code Llama 70B base is the foundational code model:
-
Code Llama 70B Now Available on Replicate Platform
By
–
Code Llama 70B is live on Replicate! It's the most powerful code generation model from @AIatMeta with instruct, Python, and base variants. Code Llama 70B instruct is fine tuned for understanding natural language instructions:
-
LangChain and LangSmith Power Elastic AI Assistant Development
By
–
"Working with LangChain and LangSmith on the Elastic AI Assistant had a significant positive impact on the overall pace and quality of the development and shipping experience. We couldn’t have achieved the product experience delivered to our customers without LangChain, and we
-
LangChain and LangSmith: The Perfect AI Development Match
By
–
LangChain + LangSmith is the perfect match
-
Elastic Security Adds AI-Powered Analyst Workflow Features
By
–
Now Elastic Security enterprise customers have support for the security analyst workflow:
– alert summarization
– workflow suggestions
– query generation and conversion
– agent integration advice
and more! -
Code Llama 70B Release: New High-Performance Code Generation Model
By
–
Today we’re releasing Code Llama 70B: a new, more performant version of our LLM for code generation — available under the same license as previous Code Llama models. Download the models https://
bit.ly/3Oil6bQ
• CodeLlama-70B
• CodeLlama-70B-Python
• CodeLlama-70B-Instruct -
LangSmith Grouped Monitoring Charts for LLM A/B Testing
By
–
Grouped Monitoring Charts in LangSmith Our latest set of monitoring features make it possible to A/B test and compare different versions of your LLM application. Simply send up metadata or tags along with your runs, then head to the monitoring section in any project
-
Evaluating LLM-Powered UI Codegen Applications with Vision Models
By
–
How do you gain confidence in your LLM-powered applications? For example, a novel use for generative AI is codegen for UIs (famously, @vercel
's V0), but such apps can be tricky to evaluate. One solution: a custom LangSmith evaluator that uses a vision model instead of