LLaMA2 responsible usage guide(PDF): https://
scontent.fnbo1-1.fna.fbcdn.net/v/t39.8562-6/3
65271716_1020127512503290_6433760642443597145_n.pdf
… Guide website:
AI
-
LLaMA2 Responsible Usage Guide Released by Meta
By
–
-
LLaMA2 Guide: Best Practices for LLM Development
By
–
LLaMA2 came with this well-curated guide that includes best practices and resources for working with large language models, LLaMA in particular. This guide is a relevant resource for practitioners and developers(or basically anyone building with LLMs) as it covers important
-
LCEL Examples and Documentation for LangChain Development
By
–
@waydegilliam added an example here – in general very happy to add/provide examples of LCEL https://
github.com/langchain-ai/l
angchain/pull/8830/files
… just ask! def takes a bit of work to grok but starts to get fun after a bit -
LLM Self-Check: Zero-Shot Verification for Complex Reasoning
By
–
8/ Self-Check – explores whether LLMs can perform self-checks which is required for complex tasks that depend on non-linear thinking and multi-step reasoning; it proposes a zero-shot verification scheme to recognize errors without external resources.
-
Agent Learns Multimodal World Model with Language Predictions
By
–
9/ Agents Model the World with Language – presents an agent that learns a multimodal world model that predicts future text and image representations; it learns to predict future language, video, and rewards.
-
AutoRobotics-Zero Discovers Adaptive Robot Control Policies
By
–
10/ AutoRobotics-Zero – discovers zero-shot adaptable policies from scratch that enable adaptive behaviors necessary for sudden environmental changes; as an example, the authors demonstrate the automatic discovery of Python code for controlling a robot.
-
OpenFlamingo: Open-Source Vision-Language Models Family Released
By
–
6/ OpenFlamingo – introduces a family of autoregressive vision-language models ranging from 3B to 9B parameters; the technical report describes the models, training data, and evaluation suite.
-
The Hydra Effect: Self-Repairing Properties in Language Models
By
–
7/ The Hydra Effect – shows that language models exhibit self-repairing properties — when one layer of attention heads is ablated it causes another later layer to take over its function.
-
ToolLLM Enables LLMs to Access 16000 Real-World APIs
By
–
3/ ToolLLM – enables LLMs to interact with 16000 real-world APIs; allows data preparation, training, and evaluation; the authors claim that one of their models, ToolLLaMA, has reached the performance of ChatGPT (turbo-16k) in tool use.
-
Skeleton-of-Thought: Parallel API Calls Strategy
By
–
4/ Skeleton-of-Thought – proposes a prompting strategy that firsts generate an answer skeleton and then performs parallel API calls to generate the content of each skeleton point; reports quality improvements in addition to speed-up of up to 2.39x.