issues
search
NolanoOrg
/
cformers
SoTA Transformers with C-backend for fast inference on your CPU.
MIT License
312
stars
29
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Added CFLAGS for avx512 capable cpus
#46
jobs-git
opened
7 months ago
0
Fix non-parallel residual for GPT-NeoX
#45
eyusupov
opened
1 year ago
0
Any plans to update models and their quantizations?
#44
Calandiel
opened
1 year ago
0
Adding StabilityAI StableLM 7b tuned
#43
antimatter15
closed
1 year ago
0
run python chat.py ERROR
#42
moon-fall
opened
1 year ago
0
OSError: [Errno 8] Exec format error: on Apple M2 chip
#41
Keith-Hon
opened
1 year ago
0
Response is being stopped before finishing
#40
vashat
opened
1 year ago
0
Add detailed error messaging for reading/writing of model files.
#39
Ghatage
opened
1 year ago
0
Added ability to load local models, added early stopping, remove vocab check, fixed GPTJ model conversion
#38
mallorbc
opened
1 year ago
0
created a pip package
#37
kamalojasv181
opened
1 year ago
5
Towards a C++ library
#36
A2va
opened
1 year ago
3
Keep model in RAM?
#35
mallorbc
opened
1 year ago
1
Update Makefile that causes error
#34
mallorbc
closed
1 year ago
0
Converted codegen-16 Model but got error using it with inference.
#33
prof-schacht
opened
1 year ago
2
Custom Finetuned Models?
#32
mallorbc
opened
1 year ago
6
OSError encountered due to a line in the interface.py file on Windows.
#31
Etrama
closed
1 year ago
2
Checking file hash and OS
#30
HCBlackFox
closed
1 year ago
0
Add CodeGen-350M-mono
#29
jncraton
closed
1 year ago
1
added codegen 16 b model to hub
#28
kamalojasv181
closed
1 year ago
2
Upload Open-Chat-Kit models at int4 on huggingface and add the URL mapping to interface.py
#27
Ayushk4
closed
1 year ago
5
Fix pythia and start adding support for obtaining logits.
#26
Ayushk4
closed
1 year ago
0
Improve interface.
#25
Ayushk4
opened
1 year ago
0
Generation quality is so low compared to native OA model.
#24
HCBlackFox
closed
1 year ago
5
Add INT4 quant codegen models
#23
Ayushk4
closed
1 year ago
0
Add back and forth prompt for a more chat like experience
#22
ChobPT
closed
1 year ago
2
Add benchmark tasks like BIG Bench
#21
kamalojasv181
opened
1 year ago
0
Add support for GLM/chatGLM models
#20
MarkSchmidty
opened
1 year ago
1
Guide for install on windows.
#19
HCBlackFox
opened
1 year ago
0
How to load model from disk?
#18
HCBlackFox
closed
1 year ago
0
How to make in windows?
#17
HCBlackFox
closed
1 year ago
0
Update README to show GPT-NeoX is done and time init in cpp/quantize_…
#16
Ayushk4
closed
1 year ago
0
Add GPT-NeoX, all pythia models and Open-Chat-Kit's GPT NeoX
#15
Ayushk4
opened
1 year ago
0
GPT-NeoX and Pythia Style models (Open-Assistant) at int-4
#14
Ayushk4
closed
1 year ago
0
Time initialization in quantization
#13
A2va
closed
1 year ago
0
Add C functions for MatMul over Int-3 Quant and Int-4 with different bin-sizes
#12
Ayushk4
opened
1 year ago
0
Add GPT-JT model
#11
Ayushk4
opened
1 year ago
0
Add shasum to check versions of the downloaded (cached) models
#10
Ayushk4
opened
1 year ago
2
Simplifying the quantization pipeline
#9
kamalojasv181
opened
1 year ago
6
added gpt2
#8
kamalojasv181
closed
1 year ago
6
Register on PyPi and add pip install support.
#7
Ayushk4
opened
1 year ago
1
Saving Keys and Values Cache at lower precision
#6
Ayushk4
opened
1 year ago
0
Explore SparseGPT-style sparsification for models.
#5
Ayushk4
opened
1 year ago
0
Benchmark CALM for Decoder-Only models at 4-bit precision
#4
Ayushk4
opened
1 year ago
0
Benchmark effect of merging query and keys matrices in transformers
#3
Ayushk4
opened
1 year ago
1
Upload GPTQ Quantized models in 4-bit precision format for different bin-sizes to Huggingface
#2
Ayushk4
opened
1 year ago
2
Add support for more architectures.
#1
Ayushk4
opened
1 year ago
0