Search: huggingface.co | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

871.

HtmlRAG: HTML Is Better Than Plain Text for RAG Systems

2 years ago

4 points

872.

Structured generation with Outlines, now in Rust

2 years ago

4 points

873.

Llama 3.2 in the Browser with WebGPU

2 years ago

4 points

874.

Multimodal TextImage Augmentation for Document Images

2 years ago

4 points

875.

'Reflection 70B' AI model could be the answer to pesky LLM hallucinations

2 years ago

4 points

876.

Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers

2 years ago

4 points

877.

FHE can be leveraged for LLMs such as ChatGPT in a privacy-preserving manner

2 years ago

4 points

878.

Introduction to Ggml

2 years ago

4 points

879.

Google releases Gemma 2 2B, ShieldGemma and Gemma Scope

2 years ago

4 points

880.

Gemma 2 2B Release

2 years ago

4 points

881.

Extracting Concepts from LLMs: Anthropic's recent discoveries

2 years ago

4 points

882.

Uncensor Any LLM with Abliteration

2 years ago

4 points

883.

EasyAnimate: End-to-end solution for high-resolution and long video generation

2 years ago

4 points

884.

Grokked Transformers Are Implicit Reasoners

2 years ago

4 points

885.

Paligemma: A versatile and lightweight vision-language model (VLM)

2 years ago

4 points

886.

4M Context – Llama-3-8B-Instruct

2 years ago

4 points

887.

ReFT: Representation Finetuning for Language Models

2 years ago

4 points

888.

Embedding Quantization: 25-45x retrieval speedup, 32x or 4x less memory usage

2 years ago

4 points

889.

Quanto: A PyTorch Quantization Toolkit

2 years ago

4 points

890.

On-device background removal with Transformers.js

2 years ago

4 points

891.

SegMoE: Segmind Mixture of Diffusion Experts

2 years ago

4 points

892.

NPHardEval leaderboard a benchmark for assessing the reasoning abilities of LLMs

2 years ago

4 points

893.

HuggingChat Assistants: Open source models with custom instructions

2 years ago

4 points

894.

TinyLlama Reaches 3T Checkpoint

2 years ago

4 points

895.

3 years ago

4 points

896.

Yarn-Llama-2-70B-32k

3 years ago

4 points

897.

SDXL in 4 steps with Latent Consistency LoRAs

3 years ago

4 points

898.

3 years ago

4 points

899.

Apple/coreml-stable-diffusion-XL-base-iOS

3 years ago

4 points

900.

DeepSpeed-Chat: Easy RLHF Training of ChatGPT-Like Models at All Scales

3 years ago

4 points