Jump to main content Jump to sidebar
Home Postmill
  • Forums
  • Wiki
  • Log in
  • Sign up
  • Submissions
  • Comments
    • Featured
    • All
    • Hot
    • New
    • Active
    • Top
    • Controversial
    • Most commented

[R] Build and personalize LLMs on your own data - Take back control with xTuring!

Submitted by x_ml t3_124r3v0 on March 28, 2023 at 2:49 PM in MachineLearning

  • 8 comments
36 loading

[N] March 2023 - Recent Instruction/Chat-Based Models and their parents

Submitted by michaelthwan_ai t3_121domd on March 25, 2023 at 6:54 AM in MachineLearning

  • 51 comments
457 loading

[D] ICML 2023 Reviewer-Author Discussion

Submitted by zy415 t3_11ylumz on March 22, 2023 at 3:06 PM in MachineLearning

  • 89 comments
24 loading

[D] Choosing Cloud vs local hardware for training LLMs. What's best for a small research group?

Submitted by PK_thundr t3_11rnppe on March 15, 2023 at 6:01 AM in MachineLearning

  • 11 comments
11 loading

Modern language models refute Chomsky’s approach to language [R]

Submitted by No_Draft4778 t3_11rmgzs on March 15, 2023 at 4:51 AM in MachineLearning

  • 29 comments
3 loading

[N] Baidu to Unveil Conversational AI ERNIE Bot on March 16 (Live)

Submitted by kizumada t3_11rfxca on March 15, 2023 at 12:24 AM in MachineLearning

  • 13 comments
31 loading

[P] SimpleAI : A self-hosted alternative to OpenAI API

Submitted by lhenault t3_122tddh on March 26, 2023 at 5:31 PM in MachineLearning

  • 12 comments
123 loading

[D] On research directions being "out of date"

Submitted by redlow0992 t3_11r97fn on March 14, 2023 at 3:28 PM in MachineLearning

  • 7 comments
23 loading

[D] AI Explainability and Alignment through Natural Language Internal Interfaces

Submitted by jackfaker t3_126wg0o on March 30, 2023 at 7:15 PM in MachineLearning

  • 12 comments
4 loading

[R] Training Small Diffusion Model

Submitted by crappr t3_11qynbp on March 14, 2023 at 6:24 AM in MachineLearning

  • 9 comments
5 loading

[R] Artificial muses: Generative Artificial Intelligence Chatbots Have Risen to Human-Level Creativity

arxiv.org

Submitted by blabboy t3_120el87 on March 24, 2023 at 9:04 AM in MachineLearning

  • 11 comments
12 loading

[D] Comparing models implemented in PyTorch and Tensorflow

Submitted by chaotycmunkey t3_11qwzb6 on March 14, 2023 at 4:51 AM in MachineLearning

  • 7 comments
6 loading

[P] ControlNetInpaint: No extra training and you can use 📝text +🌌image + 😷mask to generate new images.

Submitted by mikonvergence t3_11qnv4c on March 13, 2023 at 10:21 PM in MachineLearning

  • 6 comments
86 loading

[D] ChatGPT without text limits.

Submitted by spiritus_dei t3_11qgxs8 on March 13, 2023 at 6:11 PM in MachineLearning

  • 28 comments
64 loading

[D] Are modern generative AI models on a path to significantly improved truthfulness?

Submitted by buggaby t3_11qgasm on March 13, 2023 at 5:46 PM in MachineLearning

  • 20 comments
8 loading

[R] Stanford-Alpaca 7B model (an instruction tuned version of LLaMA) performs as well as text-davinci-003

Submitted by dojoteef t3_11qfcwb on March 13, 2023 at 5:10 PM in MachineLearning

  • 126 comments
371 loading

[D]: Generalisation ability of autoencoders

Submitted by Blutorangensaft t3_11qejcz on March 13, 2023 at 4:37 PM in MachineLearning

  • 10 comments
7 loading

[D] 3d model generation

Submitted by konstantin_lozev t3_123xa6r on March 27, 2023 at 7:19 PM in MachineLearning

  • 6 comments
6 loading

[News] Twitter algorithm now open source

Submitted by John-The-Bomb-2 t3_127wy7i on March 31, 2023 at 7:48 PM in MachineLearning

  • 49 comments
703 loading

[R] Introducing Ursa from Speechmatics | 25% improvement over Whisper

Submitted by jplhughes t3_11prxd9 on March 12, 2023 at 10:27 PM in MachineLearning

  • 29 comments
47 loading

[D] Is anyone trying to just brute force intelligence with enormous model sizes and existing SOTA architectures? Are there technical limitations stopping us?

Submitted by hebekec256 t3_11poqmh on March 12, 2023 at 8:22 PM in MachineLearning

  • 15 comments
0 loading

[N] AtMan could solve the biggest problem of ChatGPT

Submitted by Number_5_alive t3_11pofer on March 12, 2023 at 8:10 PM in MachineLearning

  • 12 comments
1 loading

[D] What's the mathematical notation for "top k argmax"?

Submitted by fullgoopy_alchemist t3_11po6qw on March 12, 2023 at 8:00 PM in MachineLearning

  • 9 comments
7 loading

[P] Discord Chatbot for LLaMA 4-bit quantized that runs 13b in <9 GiB VRAM

github.com

Submitted by Amazing_Painter_7692 t3_11pmz69 on March 12, 2023 at 7:13 PM in MachineLearning

  • 51 comments
320 loading

[R] Reflexion: an autonomous agent with dynamic memory and self-reflection - Noah Shinn et al 2023 Northeastern University Boston - Outperforms GPT-4 on HumanEval accuracy (0.67 --> 0.88)!

Submitted by Singularian2501 t3_1215dbl on March 25, 2023 at 1:00 AM in MachineLearning

  • 85 comments
241 loading
  • More

Running Postmill