wenhua cheng's picture

9 5 14

wenhua cheng

wenhuach

·

wenhuach21

AI & ML interests

Model Compression, CV

Recent Activity

reacted to their post with 🚀 2 days ago

Are we the only providers of INT4 quantized models for Llama 3.2 VL? https://huggingface.co./OPEA/Llama-3.2-90B-Vision-Instruct-int4-sym-inc https://huggingface.co./OPEA/Llama-3.2-11B-Vision-Instruct-int4-sym-inc

posted an update 3 days ago

Are we the only providers of INT4 quantized models for Llama 3.2 VL? https://huggingface.co./OPEA/Llama-3.2-90B-Vision-Instruct-int4-sym-inc https://huggingface.co./OPEA/Llama-3.2-11B-Vision-Instruct-int4-sym-inc

replied to their post 8 days ago

AutoRound has demonstrated strong results even at 2-bit precision for VLM models like QWEN2-VL-72B. Check it out here: https://huggingface.co./OPEA/Qwen2-VL-72B-Instruct-int2-sym-inc.

View all activity

Organizations

wenhuach's activity

liked a model 24 days ago

OPEA/Meta-Llama-3.1-70B-Instruct-int4-sym-inc

Updated 3 days ago • 27 • 1

liked 4 models 4 months ago

LnL-AI/TinyLlama-1.1B-intermediate-step-1341k-3T-autoround-lm_head-symFalse

Text Generation • Updated Jul 24 • 1.96k • 1

kaitchup/Meta-Llama-3.1-8B-Instruct-autoround-gptq-4bit-asym

Text Generation • Updated Aug 13 • 16 • 1

kaitchup/Meta-Llama-3.1-8B-Instruct-autoround-gptq-4bit-sym

Text Generation • Updated Aug 13 • 42 • 1

Intel/Qwen2-57B-A14B-Instruct-int4-inc

Updated Oct 24 • 71 • 1

liked a model 6 months ago

cstr/Spaetzle-v85-7b-int4-inc

Text Generation • Updated Jun 24 • 15 • 2

liked 5 models 7 months ago

Intel/Qwen2-7B-int4-inc

Text Generation • Updated Oct 24 • 336 • 5

Qwen/Qwen-72B-Chat

Text Generation • Updated Oct 8 • 336 • 148

Intel/phi-2-int4-inc

Text Generation • Updated Oct 22 • 14 • 2

Intel/Mistral-7B-v0.1-int4-inc-lmhead

Text Generation • Updated May 29 • 17 • 1

cstr/Spaetzle-v60-7b-int4-inc

Text Generation • Updated May 15 • 14 • 2

liked a Space 8 months ago

Low-bit Quantized Open LLM Leaderboard

Track, rank and evaluate open LLMs and chatbots

liked a model 10 months ago

Intel/Mistral-7B-v0.1-int4-inc

Text Generation • Updated May 31 • 344 • 4

liked a dataset 10 months ago

NeelNanda/pile-10k

Viewer • Updated Oct 14, 2022 • 10k • 5.81k • 15