Content tagged with "llm"
Found 120 items tagged with "llm".
Self-Adapting Language Models (SEAL)
responses •
Other tags: agent, ai, mit, research
ZeroSearch - Incentivize the Search Capability of LLMs without Searching
bookmarks •
Other tags: ai, search, research
The Llama 4 herd: The beginning of a new era of natively multimodal AI innovation
responses •
Other tags: llama, meta, ai
Ollama Adds Mistral 3.1 Support
notes •
Other tags: mistral, ollama, ai
Introducing Command A
responses •
Other tags: cohere, ai
Simon Willison's AI-Generated Tools Colophon
responses •
Other tags: colophon, indieweb, ai
Introducing Mercury, the first commercial-scale diffusion large language model
responses •
Other tags: diffusion, ai
The Ultra-Scale Playbook: Training LLMs on GPU Clusters
responses •
Other tags: ai, training
The Illustrated DeepSeek-R1
bookmarks •
Other tags: deepseek, ai, visualization, generativeai, genai, learning
LangChain State of AI 2024 Report
responses •
Other tags: ai, 2024, report, langchain
Microsoft Research: Introducing DRIFT Search
responses •
Other tags: ai, search, RAG, microsoft, research, msr, graphrag
Thinking LLMs: General Instruction Following with Thought Generation
responses •
Other tags: ai, research, meta, chainofthought, training, finetuning
Bringing Llama 3 to life
responses •
Other tags: ai, meta, llama3, opensource
GPT-4o System Card
bookmarks •
Other tags: ai, openai, gpt-4o, documentation
LongROPE: Extending LLM Context Window Beyond 2 Million Tokens
bookmarks •
Other tags: ai, longrope, microsoft, research, msr
Clock Tables - Org Mode, Plain Text, and AI
notes •
Other tags: emacs, orgmode, ai, plaintext, productivity, tools, technology, gnu, opensource, gtd, calendar, agenda, openai
Home-Cooked Software and Barefoot Developers
responses •
Other tags: localfirst, smallweb, sofware, programming, talk, indieweb
Meta Large Language Model Compiler: Foundation Models of Compiler Optimization
responses •
Other tags: ai, compiler, meta
Mapping the Mind of a Large Language Model
responses •
Other tags: ai, interpretability, anthropic
Ultravox - An open, fast, and extensible multimodal LLM
responses •
Other tags: ai, multimodal
Reproducing GPT-2 (124M) in llm.c in 90 minutes for $20
responses •
Other tags: ai, gpt, gpt2, llmc, c, slm
Introducing Snowflake Arctic
responses •
Other tags: snowflake, ai, enterprise
Introducing Phi-3
responses •
Other tags: microsoft, phi3, ai, slm, genai
Introducing Llama 3
responses •
Other tags: meta, ai, llama3, llama
Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models
bookmarks •
Other tags: griffin, ai, research, architecture, rnn, attention, transformers
DE-COP: Detecting Copyrighted Content in Language Models Training Data
bookmarks •
Other tags: ai, copyright, research, data
Using LLM to select the right SQL Query from candidates
bookmarks •
Other tags: ai, research, sql
RecurrentGemma - Open weights language model from Google DeepMind, based on Griffin.
responses •
Other tags: ai, gemma, google, opensource, slm, griffin, neuralnetwork
Hello OLMo: A truly open LLM
responses •
Other tags: allenai, opensource
LLM training in simple, raw C/CUDA
responses •
Other tags: gpt, c, programming, learning, tutorial
ARAGOG: Advanced RAG Output Grading
responses •
Other tags: rag, ai, research, knowledge, retrieval, retrievalaugmentedgeneration
These models are too damn big!
notes •
Other tags: ai, slm, huggingface, opensource
OpenAI - Introducing improvements to the fine-tuning API and expanding our custom models program
responses •
Other tags: openai, finetuning
Introducing Command R+: A Scalable LLM Built for Business
responses •
Other tags: cohere, comandr, azure, comandrplus
Large Language Models Are Zero-Shot Time Series Forecasters
bookmarks •
Other tags: forecasting, ai, research
IPEX-LLM
responses •
Other tags: intel, pytorch, cpu, gpu
Start using ChatGPT instantly
responses •
Other tags: openai, chatgpt, ai
Announcing DBRX: A new standard for efficient open source LLMs
responses •
Other tags: databricks, ai, opensource
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
responses •
Other tags: ai, models, mamba, compute
Releasing Common Corpus: the largest public domain dataset for training LLMs
bookmarks •
Other tags: ai, data, huggingface, nlp
Demystifying Embedding Spaces using Large Language Models
responses •
Other tags: ai, embedding, interpretability
MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training
bookmarks •
Other tags: ai, mm1, multimodal, apple
Ollama now supports AMD graphics cards
responses •
Other tags: ollama, gpu, amd, ai, opensource
You can now train a 70b language model at home
responses •
Other tags: ai, qlora, gpu, nvidia, finetuning
Levels of Complexity: RAG Applications
responses •
Other tags: rag, ai, architecture, app
Inflection-2.5: meet the world's best personal AI
responses •
Other tags: ai, inflection
Training great LLMs entirely from ground up in the wilderness as a startup
responses •
Other tags: ai, startup, compute, gpu, training
Configure Ollama on Dev Containers and VS Code
posts •
Other tags: ollama, vscode, devcontainer, ai, opensource, development
Getting started with Ollama on Windows
posts •
Other tags: ai, ollama, windows, opensource, llama, openai, generativeai, genai
Gemma PyTorch
responses •
Other tags: google, gemma, pytorch, ai
Introducing the next generation of Claude
responses •
Other tags: ai, anthropic, claude
GGUF, the long way around
responses •
Other tags: ai, genai, gguf, opensource
Predictive Human Preference: From Model Ranking to Model Routing
responses •
Other tags: ai, evaluation, ml
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
responses •
Other tags: ai, bitnet, research
Announcing Mistral Large
responses •
Other tags: ai, mistral, opensource, azure
GPT in 500 lines of SQL
responses •
Other tags: sql, gpt, ai
Gemma: Introducing new state-of-the-art open models
responses •
Other tags: ai, opensource, google, model
Cosmopedia v0.1
responses •
Other tags: cosmopedia, dataset, huggingface, mixtral, ai, genai
Ollama - Windows Preview
responses •
Other tags: ollama, windows, opensource, localmodels, ml, ai
GraphRAG: Unlocking LLM discovery on narrative private data
bookmarks •
Other tags: research, ai, rag, data, microsoft
NVIDIA Chat with RTX
responses •
Other tags: nvidia, chat, ai, rag, chatbot, gpu
Memory and new controls for ChatGPT
responses •
Other tags: openai, chatgpt, memory, ai, gpt
Eagle 7B : Soaring past Transformers with 1 Trillion Tokens Across 100+ Languages (RWKV-v5)
bookmarks •
Other tags: ai, rwkv, deeplearning, neuralnetwork
Google’s Hugging Face deal puts ‘supercomputer’ power behind open-source AI
responses •
Other tags: google, huggingface, ai, cloud, ml, developers
New OpenAI embedding models and API updates
responses •
Other tags: openai, embedding, openai, gpt
NightShade
responses •
Other tags: research, tools, ai, generativeai, computervision, cv
Introducing Stable LM 2 1.6B
responses •
Other tags: ai, stabilityai, slm, smalllanguagemodel
Stable Code 3B - Coding on the Edge
bookmarks •
Other tags: ai, stabilityai", code, software, softwaredevelopment
Sampling for Text Generation
bookmarks •
Other tags: ai, generativeai, statistics
Talking about Open Source LLMs on Oxide and Friends
responses •
Other tags: ai, podcast, opensource
LeftoverLocals: Listening to LLM responses through leaked GPU local memory
responses •
Other tags: security, ai
AI for economists - prompts and resources
bookmarks •
Other tags: ai, economy, promptengineering, gpt
More than an OpenAI Wrapper: Perplexity Pivots to Open Source
responses •
Other tags: ai, perplexity, opensource, search
My AI Timelines Have Sped Up (Again)
bookmarks •
Other tags: ai, predictions, agi, data, technology, ml, computervision
Ferret: Refer and Ground Anything Anywhere at Any Granularity
bookmarks •
Other tags: ai, ml, mllm, largelanguagemodel, multimodal, multimodallargelanguagemodel, apple, opensource
What about instrumentals? AI Generated Spotify Clips Addendum
notes •
Other tags: ai, genai, music, instrumental, spotify, generativeai
Using Generative AI to produce Spotify Clips
posts •
Other tags: ai, video, chicanobatman, generativeai, genai, spotify, google, microsoft, bing, copilot, dalle, image, prompt, projectidea, music, podcasts
LangChain State of AI 2023
bookmarks •
Other tags: ai, opensource, report
LLM in a flash: Efficient Large Language Model Inference with Limited Memory
bookmarks •
Other tags: ai, hardware
OpenAI - Prompt engineering
bookmarks •
Other tags: openai, promptengineering, ai, guide
Bash One-Liners for LLMs
bookmarks •
Other tags: llama, ai, opensource
Phi-2: The surprising power of small language models
bookmarks •
Other tags: ai, slm
Introducing Stable LM Zephyr 3B
bookmarks •
Other tags: ai, edge
The Geometry of Truth: Dataexplorer
bookmarks •
Other tags: ai, interpretability
MemGPT - Towards LLMs as Operating Systems
bookmarks •
Other tags: ai, os
Best Practices for LLM Evaluation of RAG Applications
bookmarks •
Other tags: ai, rag, evaluation
MLflow 2.8 with LLM-as-a-judge metrics and Best Practices for LLM Evaluation of RAG Applications
bookmarks •
Other tags: mlflow, ai, evaluation
OpenAgents: An Open Platform for Language Agents in the Wild
bookmarks •
Other tags: ai, agents
Mixtral of experts
bookmarks •
Other tags: ai, opensource
Long context prompting for Claude 2.1
bookmarks •
Other tags: prompts, ai
Introducing llamafile
bookmarks •
Other tags: ai, opensource
AI abundance after scarcity cycles
notes •
Other tags: ai, internet, history, rss, openai, gpt, opensource
Chain-of-Verification Reduces Hallucination in Large Language Models
bookmarks •
Other tags: ai, promptengineering
Scaffolded LLMs as natural language computers
bookmarks •
Other tags: ai, cpu
Mistral 7B Model
bookmarks •
Other tags: ai, opensource
Distilling step-by-step: Outperforming larger language models with less training data and smaller model sizes
bookmarks •
Other tags: ai, slm, optimization
vim + llm = 🔥
bookmarks •
Other tags: vi, linux, ai, softwaredevelopment
ChatGPT can now see, hear, and speak
bookmarks •
Other tags: ai, chatgpt, openai, machinelearning, ml
DALL·E 3
bookmarks •
Other tags: dalle, ai, openai, images, ml
Optimizing your LLM in production
bookmarks •
Other tags: ai, production, engineering, software, mlops, aiops, opensource
PointLLM: Empowering Large Language Models to Understand Point Clouds
bookmarks •
Other tags: ai, generativeai, multimodal, research
Spread Your Wings: Falcon 180B is here
bookmarks •
Other tags: ai, opensource, huggingface
Generative AI and .NET - Part 2 SDK
responses •
Other tags: ai, dotnet, generativeai, azure
Perplexity: Interactive LLM visualization
bookmarks •
Other tags: ai, visualization, tools
Can LLMs learn from a single example?
bookmarks •
Other tags: ai, finetuning, fastai
Generative AI and .NET - Part 1 Intro
responses •
Other tags: ai, dotnet, generativeai
Llama 2 7B/13B are now available in Web LLM
bookmarks •
Other tags: ai, webgpu, llama
Supporting the Open Source AI Community
responses •
Other tags: ai, opensource, machinelearning
Making Large Language Models Work For You
bookmarks •
Other tags: ai, wordpress, presentation
Introducing Code Llama, a state-of-the-art large language model for coding
bookmarks •
Other tags: ai, llama, code, opensource, meta
Large Language Models with Semantic Search
bookmarks •
Other tags: ai, course, retrievalaugmentedgeneration
Patterns for Building LLM-based Systems and Products
bookmarks •
Other tags: ai, designpatterns
Open challenges in LLM research
bookmarks •
Other tags: ai, research
GPT-4 API general availability
responses •
Other tags: openai, gpt4, ai
Gorilla: Large Language Model Connected with Massive APIs
bookmarks •
Other tags: ai, opensource
LoRA: Low-Rank Adaptation of Large Language Models
bookmarks •
Other tags: ai, finetune
Language models can explain neurons in language models
bookmarks •
Other tags: ai, deeplearning
Free Dolly
bookmarks •
Other tags: ai, oss
Generative Agents: Interactive Simulacra of Human Behavior
bookmarks •
Other tags: ai
Koala: A Dialogue Model for Academic Research
bookmarks •
Other tags: ai