Muhtasham Oblokulov's picture

Muhtasham Oblokulov PRO

muhtasham

·

https://www.linkedin.com/in/muhtasham/

AI & ML interests

None yet

Recent Activity

upvoted a collection 21 days ago

upvoted a collection 21 days ago

updated a collection 22 days ago

Tajik Language Models

Organizations

muhtasham's activity

upvoted 2 collections 21 days ago

SmolLM2

State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M • 10 items • Updated 30 minutes ago • 172

MobileLLM

Optimizing Sub-billion Parameter Language Models for On-Device Use Cases (ICML 2024) https://arxiv.org/abs/2402.14905 • 8 items • Updated 14 days ago • 95

upvoted a paper 22 days ago

MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding

Paper • 2408.11049 • Published Aug 20 • 12

upvoted an article about 1 month ago

Article

How to build a custom text classifier without days of human labeling

By

•

Oct 17

• 55

upvoted 3 collections 3 months ago

⛈️ Llama-3.1 Storm Models

Fine-tuned Llama 3.1 8B model with superior reasoning, conversation abilities, and function calling! • 3 items • Updated Aug 25 • 15

Tower

Model weights and SFT data for Tower. • 11 items • Updated 6 days ago • 26

Code Evaluation

Collection of Papers on Code Evaluation (from code generation language models) • 45 items • Updated 24 days ago • 14

upvoted an article 3 months ago

Article

Mixture of Depth is Vibe

By

•

Apr 22

• 44

upvoted a collection 3 months ago

Llama-3.1 Quantization

Neural Magic quantized Llama-3.1 models • 21 items • Updated 8 days ago • 39

upvoted an article 4 months ago

Article

Serverless Inference with Hugging Face and NVIDIA NIMs

Jul 29

• 28

upvoted 2 collections 4 months ago

Llama 3.1

This collection hosts the transformers and original repos of the Llama 3.1, Llama Guard 3 and Prompt Guard models • 11 items • Updated Sep 25 • 622

FP8 LLMs for vLLM

Accurate FP8 quantized models by Neural Magic, ready for use with vLLM! • 44 items • Updated Oct 17 • 58

upvoted 2 papers 5 months ago

Agentless: Demystifying LLM-based Software Engineering Agents

Paper • 2407.01489 • Published Jul 1 • 42

Tower: An Open Multilingual Large Language Model for Translation-Related Tasks

Paper • 2402.17733 • Published Feb 27 • 4

upvoted 3 collections 5 months ago

GAIA release

Gather the items of the GAIA release • 4 items • Updated Nov 23, 2023 • 20

LLM Compiler

Meta LLM Compiler is a state-of-the-art LLM that builds upon Code Llama with improved performance for code optimization and compiler reasoning. • 4 items • Updated Jun 27 • 148

Gemma 2 Release

15 items • Updated Sep 9 • 196

upvoted 2 papers 5 months ago

MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers

Paper • 2406.10163 • Published Jun 14 • 32

Instruction Pre-Training: Language Models are Supervised Multitask Learners

Paper • 2406.14491 • Published Jun 20 • 85

upvoted a collection 5 months ago

Instruction Pre-Training

8 items • Updated Jun 21 • 26