8/ Prompt2Model – takes a prompt describing a task and trains a small model that is conducive to deployment; the pipeline automatically collects and synthesizes knowledge through three channels: dataset retrieval, dataset generation, and model retrieval.
LLMS
-
LegalBench: Legal Reasoning Benchmark for LLMs
By
–
9/ LegalBench – a collaboratively constructed benchmark for measuring legal reasoning in LLMs; it consists of 162 tasks covering 6 different types of legal reasoning.
-
Giraffe: Extended Context Length LLMs from Llama Base Models
By
–
5/ Giraffe – new models that are fine-tuned from base Llama and Llama 2; extends the context length to 4K, 16K, and 32K; explores the space of expanding context lengths in LLMs so it also includes insights useful for practitioners and researchers.
-
Survey on Instruction Tuning Methods for Large Language Models
By
–
2/ Survey on Instruction Tuning for LLMs – new survey paper on instruction tuning LLM, including a systematic review of the literature, methodologies, dataset construction, training models, applications, and more.
-
SeamlessM4T: Unified Multilingual Multimodal Machine Translation System
By
–
3/ SeamlessM4T – a unified multilingual and multimodal machine translation system that supports ASR, text-to-text translation, speech-to-text translation, text-to-speech translation, and speech-to-speech translation.
-
LLM Security: Identifying Threats and Building Robust Systems
By
–
4/ Use of LLMs for Illicit Purposes – provides an overview of existing efforts to identify and mitigate threats and vulnerabilities arising from LLMs; serves as a guide to building more reliable and robust LLM-powered systems.
-
LLMs Water Consumption Raises Ecocide Concerns Globally
By
–
Growing number of countries consider making ecocide a crime https://
theguardian.com/environment/20
23/aug/26/growing-number-of-countries-consider-making-ecocide-crime
… Where its well documented LLMs use massive amounts of water drastically harming people and planet, let’s call the knowledge of their harm what it is: justified ecocide. Nope. -
Weights compatibility and numerical stability in LoRA fine-tuning
By
–
Yes, I think that's either maybe so that (1) people with older cards can use these weights as well and (2) we maybe have more stability when finetuning with LoRA etc (in case numbers become large)
It's interesting for sure -
LangChain Twitter Fine-tuning Repository Released
By
–
In the github repo! https://
github.com/langchain-ai/t
witter-finetune
…
