kk

Results 8 comments of kk

[Bug]:

I have the same problem.

The input sequence length must be less than or equal to the maximum sequence length

> Hey @parzoe, I would suggest splitting your audio into smaller chunks since the maximum sequence length our model is designed to handle is 4096. You can force it to...

Load Mixtral 8x7b AWQ model failed

I have the same problem when TP = 2.

Sample code does not work

I have the same issue.

import flash attention errror

Me too... I am using cuda 12.2 ; transformer 38.2 ; torch 2.1.2 too... from exllamav2 import ExLlamaV2Config, ExLlamaV2, ExLlamaV2Cache, \ File "/home/dell/miniconda3/lib/python3.10/site-packages/exllamav2/__init__.py", line 3, in from exllamav2.model import ExLlamaV2...

pip install llama-cpp-python got stuck forever at "Configuring CMake" in docker

I have the same issue with v0.3.7.0 even with pip install.

using a model of type qwen3_vl_moe to instantiate a model of type qwen3_vl

Tried Qwen3VLMoeForConditionalGeneration , AutoModelForImageTextToText, still same issue. ['0 " idefal 鳳2 Inreg1 by4 \'a \'a s loveb \'\r\n\r\n\r\np8 \'01 \' \'2 the \' ...0 set1000 высоко).[ et0 aid pre pls][...

Question about kernel size of class LastLevelMaxPool(ExtraFPNBlock) in feature_pyramid_network.py

No one can confirm this?