In a Training Loop 🔄

84 1 12

Ton Cao PRO

cpatonn

ton-cao-208032186

AI & ML interests

Democratizing LLM @cyankiwi

Recent Activity

updated a model about 3 hours ago

cyankiwi/AgentCPM-Report-AWQ-8bit

published a model about 3 hours ago

cyankiwi/AgentCPM-Report-AWQ-8bit

updated a model about 3 hours ago

cyankiwi/AgentCPM-Report-AWQ-4bit

View all activity

Organizations

New activity in cyankiwi/GLM-4.6V-AWQ-4bit about 8 hours ago

Can't seem to correctly generate structured output

#3 opened about 1 month ago by

kldzj

New activity in cyankiwi/GLM-4.7-Flash-AWQ-8bit about 17 hours ago

Thank you + Docker Image!

🤗 1

#2 opened 1 day ago by

macandchiz

New activity in cyankiwi/Qwen3-VL-4B-Instruct-AWQ-4bit 1 day ago

Qwen 3-VL-2B AWQ 4bit Quantization

#1 opened about 2 months ago by

hwongtx

New activity in cyankiwi/GLM-4.7-REAP-218B-A32B-AWQ-4bit 5 days ago

Will you make the 268B version of this model ?

👍 2

#1 opened 9 days ago by

mtcl

New activity in cyankiwi/GLM-4.7-Flash-AWQ-4bit 6 days ago

Can I run this with 36gb VRAM+ 192gb ram

#1 opened 7 days ago by

nimishchaudhari

New activity in cyankiwi/GLM-4.7-Flash-AWQ-4bit 7 days ago

Any plans for a 6bit or 8bit version?

#3 opened 7 days ago by

zenmagnets

Update run commands for single GPU

#2 opened 7 days ago by

AMead10

New activity in cyankiwi/GLM-4.5-Air-AWQ-4bit 13 days ago

KV Cache per token and Doubling the context size

#12 opened 14 days ago by

HenkTenk

New activity in upstage/Solar-Open-100B 24 days ago

fp8 or awq?

👀 1

#4 opened 26 days ago by

ziozzang

New activity in cyankiwi/MiniMax-M2.1-AWQ-4bit 29 days ago

Tokenizer set to Mistral?

#1 opened about 1 month ago by

zmarty

New activity in cyankiwi/GLM-4.7-AWQ-4bit about 1 month ago

MTP Implementation

#1 opened about 1 month ago by

kldzj

New activity in cyankiwi/Qwen3-Next-80B-A3B-Instruct-AWQ-4bit about 1 month ago

Perfomance of this model is one of the best

🤗 👍 2

#13 opened about 1 month ago by

Geximus

New activity in cyankiwi/GLM-4.5V-AWQ-8bit about 1 month ago

GLM 4.6V

#2 opened about 1 month ago by

kldzj

New activity in cyankiwi/MiMo-V2-Flash-AWQ-4bit about 1 month ago

All experts calibration & Linearization

#1 opened about 1 month ago by

mratsim

New activity in cyankiwi/Devstral-2-123B-Instruct-2512-AWQ-4bit about 1 month ago

Duplicate files

➕ 1

#3 opened about 2 months ago by

darkstar3537

New activity in cyankiwi/Devstral-Small-2-24B-Instruct-2512-AWQ-4bit about 2 months ago

Loading Mistral Models in vLLM

#2 opened about 2 months ago by

BuiDoan

Thanks

#1 opened about 2 months ago by

madmax0404

New activity in cyankiwi/GLM-4.6V-AWQ-4bit about 2 months ago

Question about group size

#1 opened about 2 months ago by

nephepritou

New activity in cyankiwi/GLM-4.6V-AWQ-8bit about 2 months ago

llm-compressor recipe

👍 1

#1 opened about 2 months ago by

bullerwins

New activity in cyankiwi/GLM-4.6V-AWQ-4bit about 2 months ago

vllm

#2 opened about 2 months ago by

win10

Ton Cao PRO

AI & ML interests

Recent Activity

Organizations

cpatonn's activity

Can't seem to correctly generate structured output

Thank you + Docker Image!

Qwen 3-VL-2B AWQ 4bit Quantization

Will you make the 268B version of this model ?

Can I run this with 36gb VRAM+ 192gb ram

Any plans for a 6bit or 8bit version?

Update run commands for single GPU

KV Cache per token and Doubling the context size

fp8 or awq?

Tokenizer set to Mistral?

MTP Implementation

Perfomance of this model is one of the best

GLM 4.6V

All experts calibration & Linearization

Duplicate files

Loading Mistral Models in vLLM

Thanks

Question about group size

llm-compressor recipe

vllm