In a Training Loop 🔄

96 1 14

Ton Cao PRO

cpatonn

ton-cao-208032186

AI & ML interests

Democratizing LLM @cyankiwi

Recent Activity

liked a dataset 42 minutes ago

li-lab/MMLU-ProX

liked a dataset about 1 hour ago

CohereLabs/Global-MMLU

liked a dataset about 1 hour ago

Congliu/Chinese-DeepSeek-R1-Distill-data-110k-SFT

View all activity

Organizations

New activity in cyankiwi/Qwen3-Coder-Next-AWQ-4bit 1 day ago

win10/SVD-Qwen3-Coder-Next-Thinking

#6 opened 1 day ago by

win10

New activity in bknyaz/Qwen3-Coder-Next-REAM 2 days ago

Please add quality Q6/Q4/Q3 quants to this

#1 opened 5 days ago by

TomLucidor

New activity in cyankiwi/README 2 days ago

Please please cyankiwi/MiniMax-M2.5-AWQ-4bit :-)

👍 1

#2 opened 4 days ago by

Stefanvarunix

New activity in cyankiwi/Qwen3-Coder-Next-AWQ-4bit 4 days ago

bknyaz/Qwen3-Coder-Next-REAM

#5 opened 4 days ago by

meganoob1337

Feel almost bad for asking this, but do you plan an 8bit version too?

#4 opened 5 days ago by

MrMoonsilver

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

Could you show the benchmark loss for this quantization?

#4 opened 14 days ago by

TomLucidor

New activity in cyankiwi/Qwen3-Coder-Next-AWQ-4bit 8 days ago

Can we perform 4-bit quantization for the awq of the Step-3.5-Flash model? The VLLM can run it.

#3 opened 8 days ago by

lsm03624

New activity in cyankiwi/Qwen3-Coder-Next-AWQ-4bit 10 days ago

模型量化的效果并不理想

#2 opened 10 days ago by

mediali

New activity in cyankiwi/GLM-4.6V-AWQ-4bit 12 days ago

Can't seem to correctly generate structured output

#3 opened 2 months ago by

kldzj

New activity in cyankiwi/Qwen3-Coder-Next-AWQ-4bit 12 days ago

how to fix: KeyError: 'model.layers.30.mlp.shared_expert.gate_gate_up_proj.weight'

🔥 1

#1 opened 12 days ago by

New activity in cyankiwi/README 13 days ago

Qwen3-Coder-Next

#1 opened 13 days ago by

mingfang1

New activity in cyankiwi/Qwen3-Next-80B-A3B-Instruct-AWQ-8bit 14 days ago

Unable to run on SGLang?

#1 opened 3 months ago by

nbaughman

New activity in cyankiwi/Qwen3-Next-80B-A3B-Instruct-AWQ-4bit 15 days ago

The tokenizer you are loading from 'cyankiwi/Qwen3-Next-80B-A3B-Instruct-AWQ-4bit' with an incorrect regex pattern

👍 1

#14 opened 30 days ago by

mxdlzg

New activity in cyankiwi/MiniMax-M2.1-AWQ-4bit 21 days ago

PPL test

#2 opened 21 days ago by

bullerwins

New activity in cyankiwi/GLM-4.7-Flash-AWQ-8bit 22 days ago

Thank you + Docker Image!

🤗 2

#2 opened 23 days ago by

macandchiz

New activity in cyankiwi/Qwen3-VL-4B-Instruct-AWQ-4bit 23 days ago

Qwen 3-VL-2B AWQ 4bit Quantization

#1 opened 2 months ago by

hwongtx

New activity in cyankiwi/GLM-4.7-REAP-218B-A32B-AWQ-4bit 27 days ago

Will you make the 268B version of this model ?

👍 2

#1 opened about 1 month ago by

mtcl

New activity in cyankiwi/GLM-4.7-Flash-AWQ-4bit 27 days ago

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

#1 opened 29 days ago by

nimishchaudhari

New activity in cyankiwi/GLM-4.7-Flash-AWQ-4bit 28 days ago

Any plans for a 6bit or 8bit version?

#3 opened 29 days ago by

zenmagnets

New activity in cyankiwi/GLM-4.7-Flash-AWQ-4bit 29 days ago

Update run commands for single GPU

#2 opened 29 days ago by

AMead10