Resultados
243 artículosOrdenar
7:21EN
Matthew Berman· 26 jun 2023Testing Orca Mini 13B, an Unofficial Model Inspired by OrcaMatthew Berman · Forward FutureMatthew Berman loads a quantized Orca Mini 13B and tries coding, reasoning, arithmetic, and summarization prompts. His 2023 informal test produces several failures and a few successes.
13:50ENMatthew Berman· 23 jun 2023MPT-30B: Running MosaicML’s Model Locally and Testing Its Chat VariantMatthew Berman · Forward FutureMatthew Berman reviews MosaicML’s June 2023 release, demonstrates a local setup, and puts the hosted chat model through an informal prompt rubric.
8:17ENMatthew Berman· 22 jun 2023Using OpenLLM to Serve Open Models Through an APIMatthew Berman · Forward FutureMatthew Berman demonstrates a local model server, its interactive API and a Python client in a 2023 walkthrough.
4:36ENMatthew Berman· 20 jun 2023Testing WizardCoder 15B as a Local Coding AssistantMatthew Berman · Forward FutureMatthew Berman runs the 2023 WizardCoder model locally, testing small Python exercises and a longer Snake game.
9:46ENMatthew Berman· 19 jun 2023Installing Text Generation WebUI on Windows: A 2023 Local-Model WalkthroughMatthew Berman · Forward FutureMatthew Berman installs an early version of Text Generation WebUI, resolves setup errors and explains model downloads and interface settings. The steps and packages are historical; consult the project’s current documentation for a modern installation.
59:28EN
Cognitive Revolution "How AI Changes Everything"· 16 jun 2023PódcastFrom $500,000 to $50,000: MosaicML Made Training Your Own Model a Priced ProductPresenta: Nathan LabenzJonathan Frankle and Abhi Venigalla explain who is training custom LLMs, why extraction beats chat, and how ALiBi stretches a 65k context window.
10:23ENMatthew Berman· 15 jun 2023Testing Hosted Falcon 40B and Document Chat in h2oGPTMatthew Berman · Forward FutureMatthew Berman tries H2O.ai’s 2023 hosted Falcon 40B interface on coding, writing and reasoning prompts, then demonstrates document chat.
19:38ENMatthew Berman· 9 jun 2023Orca: Teaching a Smaller Model with GPT-4 ExplanationsMatthew Berman · Forward FutureMatthew Berman reviews Microsoft Research’s 2023 Orca paper and its approach to training a 13-billion-parameter model on detailed teacher responses.
2:41:58EN
Lex Fridman· 8 jun 2023Pódcast · 2 vocesZuckerberg showed up as Mark Elliott — then argued for many AIs, not oneInvitado: Mark Zuckerberg · Presenta: Lex FridmanOn his second Lex Fridman podcast, the Meta CEO treats a disguised first jiu-jitsu tournament, an open research model called LLaMA, and a future of many agents as the same bet: ship before it is perfect, and do not build a single god model.
10:40ENMatthew Berman· 7 jun 2023Testing Nous Hermes 13B Locally: Mixed Reasoning and Unsafe ResponsesMatthew Berman · Forward FutureMatthew Berman compares a 2023 quantized model on hosted and local hardware, with uneven results across coding, logic and safety.
8:51ENMatthew Berman· 2 jun 2023Falcon 40B: A 2023 Leaderboard Result and a Slow GPU TestMatthew Berman · Forward FutureMatthew Berman tries a quantized Falcon 40B Instruct checkpoint on a hosted GPU and finds useful output but slow generation.
11:42ENMatthew Berman· 31 may 2023Guanaco and QLoRA: A 2023 Fine-Tuning and Model TestMatthew Berman · Forward FutureMatthew Berman reviews the QLoRA paper, explains the reported memory savings and tries Guanaco 65B on an informal prompt set.
7:51ENMatthew Berman· 30 may 2023Running Guanaco 65B on a Cloud GPU with Runpod and Text Generation Web UIMatthew Berman · Forward FutureMatthew Berman demonstrates a 2023 workflow for renting a GPU, loading a quantized model and generating text. Model requirements, pricing and interfaces depend on the chosen version.
1:20:49ENCognitive Revolution "How AI Changes Everything"· 25 may 2023PódcastA Wafer-Scale Chip So AI Stops Waiting on AmdahlPresenta: Nathan LabenzAndrew Feldman, CEO of Cerebras, tells Nathan Labenz why one 2.5-trillion-transistor die, sparse linear algebra, and a 16-machine supercomputer are a better shape than a GPU cluster.
1:11:11EN
20VC with Harry Stebbings· 17 may 2023Pódcast · 2 vocesEmad Mostaque on Open AI Models, National Data and the Race to DeployInvitado: Emad Mostaque · Presenta: Harry StebbingsThe Stability AI co-founder describes his 2023 vision for open models, healthcare applications and AI businesses, alongside concerns about a speculative boom.
11:07ENMatthew Berman· 16 may 2023Testing MosaicML MPT-7B Chat and StoryWriter in 2023Matthew Berman · Forward FutureMatthew Berman examines MPT-7B model variants, their licenses and a mixed set of local tests.
1:06:02EN20VC with Harry Stebbings· 15 may 2023Pódcast · 2 vocesYann LeCun on Open AI Models, Safety and the Future of ResearchInvitado: Yann Lecun · Presenta: Harry StebbingsMeta’s chief AI scientist discusses language models, research priorities and his contested views on AI risk and employment.
14:29ENMatthew Berman· 8 may 2023A 2023 Google Memo on Open Models, LoRA and AI’s Competitive MoatMatthew Berman · Forward FutureMatthew Berman reviews a leaked employee essay arguing that rapid community iteration could challenge proprietary AI labs, and traces the early LLaMA ecosystem.
6:53ENMatthew Berman· 4 may 2023StableVicuna’s 2023 Release: An Early RLHF Chatbot Put to the TestMatthew Berman · Forward FutureMatthew Berman reviews the 13-billion-parameter model and tests poetry, simple code, reasoning and a resignation email.
9:58ENMatthew Berman· 26 abr 2023HuggingChat’s 2023 Debut: Testing Writing, Reasoning and Python CodeMatthew Berman · Forward FutureMatthew Berman tries the early OpenAssistant-powered HuggingChat on writing, arithmetic, logic and a Snake game, then compares a few outputs with GPT-3.5 and GPT-4. The results illustrate both promise and limitations in this small historical test.
1:13:52ENMatthew Berman· 15 abr 2023Andriy Mulyar on GPT4All, Data Quality and Open Local ModelsMatthew Berman, Andriy Mulyar · Forward FutureThe Nomic AI co-founder explains how GPT4All emerged, why training data matters, and the tradeoffs between local and centralized AI.
40:25EN
No Priors: AI, Machine Learning, Tech, & Startups· 6 abr 2023Pódcast · 2 vocesA 6-Billion-Parameter Clone of ChatGPT’s Core TrickPresenta: Sarah Guo, Elad GilDatabricks CTO Matei Zaharia tells Sarah Guo and Elad Gil how Dolly learned instruction-following on fifty times less data than GPT-3 — and why he would rather look facts up than bake them into a trillion-parameter network.
7:16ENMatthew Berman· 5 abr 2023Setting Up Alpaca Turbo for Local Language Models: A 2023 TutorialMatthew Berman · Forward FutureMatthew Berman demonstrates an early ChatGPT-style interface for local Alpaca models, from the Conda setup to a short test on a Mac.
8:05ENMatthew Berman· 29 mar 2023A 2023 Guide to Running the Original GPT4All Model LocallyMatthew Berman · Forward FutureMatthew Berman demonstrates an early CPU-based GPT4All release, its terminal installation and the resources available for fine-tuning.Cargar másMostrando 24 de 243