We released the first commercially usable, open-source Large Language Model with a 32K context length. Here is the blog post with the details: https://
blog.abacus.ai/blog/2023/08/2
2/giraffe-long-context-llms/
… This is a huge step for those using open-source LLMs in production applications!
LLMS
-
Abacus AI Releases Open-Source 32K Context Length LLM
By
–
-
Master ChatGPT with Our Prompt Cheat Sheet
By
–
Master ChatGPT with our Prompt Cheat Sheet. #ChatGPT #Prompts #CheatSheet via @ingliguori
-
LLM Privacy Concerns and Production Deployment Discussion
By
–
ICYMI: @predibase CEO / Cofounder @devvret_rishi had a chance to sit down with @LouMM
, @kg4gwa & the team at @TWiT to discuss #LLM privacy concerns, how to overcome, and what it takes to successfully put LLMs into production. Check out the full talk: -
LoRA and QLoRA: Optimizing LLM Fine-Tuning Strategies
By
–
Ensuring efficient resource utilization and cost-effectiveness can make or break your plans for implementing AI, especially for LLMs. Take a deep dive into LoRA and QLoRA — and learn more about which #LLM fine-tuning strategies are right for you https://
bit.ly/3sBn1jT -
Chain-of-Verification Reduces Hallucination in Large Language Models
By
–
Chain-of-Verification Reduces Hallucination in Large Language Models Dhuliawala et al.: https://
arxiv.org/abs/2309.11495 #ChatGPT #DeepLearning #LargeLanguageModels -
Remarkable text understanding capability, even reading codes
By
–
The text understanding is pretty remarkable. Even codes on screen
-
Framework Evaluates Language Model Opinion Reflection
By
–
New policy brief: Whose opinions do language models reflect? Our latest policy publication introduces a quantitative framework that allows policymakers to evaluate the behavior of language models to assess what kinds of opinions they reflect. https://
stanford.io/45XT5gD? -
LLMonitor Support Added for LLM Observability
By
–
LLMonitor support Added @llmonitor_hq for observability tool
-
OpenAI GPT-3.5 Turbo Instruct Model Update v1.3.6
By
–
Small update v1.3.6 with the new OpenAI instruct model Gpt3.5 Turbo Instruct Model LLMonitor support Credentials Bug Fix
-
OpenAI Updates GPT-3.5 Instruct Models in Flowise
By
–
Gpt3.5 Instruct Model We have updated the OpenAI LLM node in Flowise with: gpt-3.5-turbo-instruct
babbage-002
davinci-002 Try it out!