issues
search
marella
/
ctransformers
Python bindings for the Transformer models implemented in C/C++ using GGML library.
MIT License
1.8k
stars
137
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
GPU is not used even after specifying gpu_layers
#163
YogeshTembe
opened
11 months ago
3
CUDA error - the provided PTX was compiled with an unsupported toolchain
#162
melindmi
closed
11 months ago
1
Adding additional models
#161
harryjulian
opened
11 months ago
0
Can't use AVX2 lib in Linux.
#160
khanjandharaiya
opened
11 months ago
0
Calculate Token spends
#159
VpkPrasanna
opened
11 months ago
0
How to know if my CPU supports BLAS?
#158
AayushSameerShah
opened
12 months ago
1
How to increase speed of inference speed for CPU?
#157
khanjandharaiya
opened
12 months ago
2
Occasional Segmentation Fault
#156
harryjulian
opened
12 months ago
1
recover from `transformers 4.34 refactored`
#155
victorlee0505
opened
1 year ago
0
transformers 4.34 caused NotImplementedError when calling CTransformersTokenizer(PreTrainedTokenizer)
#154
victorlee0505
opened
1 year ago
17
Text is exceeding maximum context length (512)
#153
CHesketh76
closed
1 year ago
1
Can I run ctransformers on linux? I guess it gives error for GLIBC version.
#152
AayushSameerShah
closed
12 months ago
1
Is that the case that larger prompt takes longer time to just get started for the first token?
#151
AayushSameerShah
opened
1 year ago
0
How to compute logits output in parallel for all the input sequence?
#150
djmMax
opened
1 year ago
2
Support for Mistral
#149
Ananderz
opened
1 year ago
10
Regarding the model type_update for Starcoder/BigCode
#148
ankit1063
opened
1 year ago
0
Instructions for compiling from scratch
#147
RevanthRameshkumar
opened
1 year ago
0
2nd Generation is really bad
#146
jojac47
opened
1 year ago
0
While running the model, facing the error: `exception: access violation writing 0x000002B6F404B000`
#145
Saurav-Navdhare
opened
1 year ago
1
How to specify Maximum Context Length for my llm
#144
Harri1703
opened
1 year ago
2
CTransformers doesn't store model on right location
#143
Yanni8
opened
1 year ago
1
I am getting a module not found error but I have ctransformers installed and the dll file is present.
#142
Harri1703
opened
1 year ago
0
feature request
#141
thistleknot
opened
1 year ago
2
Error during loading Codellama GGUF
#140
GooDRomka
opened
1 year ago
1
CUDA error 35 at /home/runner/work/ctransformers/ctransformers/models/ggml/ggml-cuda.cu:5067: CUDA driver version is insufficient for CUDA runtime version
#139
thistleknot
opened
1 year ago
4
Can I get a little clarification over my understanding for the terminologies and the GGUF models?
#138
AayushSameerShah
opened
1 year ago
0
[AMD] Fix compilation issue with ROCm
#137
bhargav
opened
1 year ago
6
Remove GGML_USE_CUBLAS when CT_HIPBLAS is defined
#136
muaiyadh
opened
1 year ago
4
CT_HIPBLAS=1 fails to build on Arch (Could not build wheels for ctransformers)
#135
CrashTD
closed
1 year ago
2
Unable to compile for ROCM on Ubuntu 22.04
#134
bugfixin
opened
1 year ago
1
Feat: cache_dir
#133
wheynelau
closed
1 month ago
3
Unable to save to different folder
#132
wheynelau
opened
1 year ago
0
How do I make a model use mps?
#131
jmtayamada
opened
1 year ago
6
I am not even seeing True or False Straightly it dropping out
#130
Bakulesh1Codes108
opened
1 year ago
0
No matching distribution found for exllama==0.1.0; extra == "gptq" (from ctransformers[gptq])
#129
BajrangWappnet
opened
1 year ago
0
Repeated text for longer prompts.
#128
PawelFaron
opened
1 year ago
0
Is there a way to implement trust_remote_code like the regular transformers library has?
#127
ZeroUni
opened
1 year ago
0
n_ctx doesn't work for Yarn-Llama-2-13B-64K-GGUF?
#126
surflip
opened
1 year ago
1
Langchain with GPU not working
#125
drmwnrafi
closed
11 months ago
4
Llama tokenizer can not stop at </s>
#124
lucasjinreal
opened
1 year ago
0
About streaming server in openai API like
#123
lucasjinreal
opened
1 year ago
0
Support for vision-language model
#122
dnth
opened
1 year ago
0
Code Llama 34B GGUF produces garbage after a certain point
#121
viktor-ferenczi
closed
1 year ago
6
CUDA library without AVX2, FMA, F16C support possible?
#120
m-from-space
closed
1 year ago
2
using ctransfromers for langchain agents pnadas data frame agent
#119
deepthi97midasala
closed
1 year ago
2
Streaming decode issue
#118
lucasjinreal
opened
1 year ago
3
Can I use on Mac Os X Darwin 10.14?
#117
andreapagliacci
opened
1 year ago
2
WizardCoder-Python-34b GGUF
#116
MichaelMartinez
opened
1 year ago
0
what are ranges values of the config parameters? "? >=parameter<= ? "
#115
Revanth-guduru-balaji
closed
1 year ago
2
Hello, how to specific config of maxnewtoken?
#114
lucasjinreal
closed
1 year ago
1
Previous
Next