Abhi Venigalla
abhi-mosaic
AI & ML interests
None yet
Organizations
None yet
abhi-mosaic's activity
minor prose tweaks
#1 opened about 1 year ago
by
dblalock
prose tweaks
#2 opened about 1 year ago
by
dblalock
there are something wrong when the latest code generate longer text
4
#19 opened over 1 year ago
by
lvkaokao
MPT-7b on colab - RAM of GPU not used
5
#50 opened over 1 year ago
by
vi-c
Pad_token_id of MPT-7B
2
#49 opened over 1 year ago
by
Trung-Dung
Running on single Nvidia K80 GPU with large context to generate long output
3
#29 opened over 1 year ago
by
airtable
Speed on CPU
13
#8 opened over 1 year ago
by
zokica
H100 TransformerEngine
3
#14 opened over 1 year ago
by
SinanAkkoyun
Using `self.transformer.wte.weight` directly for LM head breaks HF accelerate device map auto infer on multi-gpu
3
#46 opened over 1 year ago
by
shijie-wu
Create requirements.txt
2
#22 opened over 1 year ago
by
shijie-wu
configuration / penalty to lower repetition?
5
#32 opened over 1 year ago
by
mfab
How much GPU memory is needed to finetune MPT-7B Instruct model?
2
#31 opened over 1 year ago
by
skshreyas714
Provide fine-tuning example notebook using hf transformers
6
#22 opened over 1 year ago
by
MakerMotion
GPU Memory / RAM requierements
8
#19 opened over 1 year ago
by
Rbn3D
Help Needed!! Text Generation Taking Too Long
2
#17 opened over 1 year ago
by
debajyoti111
Error in Triton implementation
2
#9 opened over 1 year ago
by
narenzen
Error in Installation Setup
2
#24 opened over 1 year ago
by
souvik0306
KeyError in triton implementation
7
#25 opened over 1 year ago
by
datacow
8bit and sharded weights
2
#37 opened over 1 year ago
by
ThreeBlessings
ValueError: MPTForCausalLM does not support `device_map='auto'` yet.
2
#38 opened over 1 year ago
by
AayushShah
Super slow loading compared to other (even bigger) models
11
#6 opened over 1 year ago
by
kil3r
Support Auto Device Map
5
#4 opened over 1 year ago
by
Supreeth
Multi-GPU inference using accelerate
6
#23 opened over 1 year ago
by
dataviral
reproduce mpt-7b-chat
2
#6 opened over 1 year ago
by
ehartford
Error when deploying
4
#3 opened over 1 year ago
by
JosephH
Does not support device_map
1
#14 opened over 1 year ago
by
HAvietisov
Out of memory error with an RTX 4090
10
#7 opened over 1 year ago
by
antman1p
finetune
1
#17 opened over 1 year ago
by
vinnitu
Text loading
6
#8 opened over 1 year ago
by
antonmks
Any reason why this longer context length wasn't applied to the chat and instruct versions?
4
#29 opened over 1 year ago
by
RonanMcGovern
Problem loading model
3
#28 opened over 1 year ago
by
jdc4429
Error while trying to run mpt-7-storyteller
3
#30 opened over 1 year ago
by
paulovasconcellos
LLM Foundry Updates 06-01-2023
1
#33 opened over 1 year ago
by
abhi-mosaic
LLM Foundry Updates 06-01-2023
1
#17 opened over 1 year ago
by
abhi-mosaic
LLM Foundry Updates 06-01-2023
1
#41 opened over 1 year ago
by
abhi-mosaic
LLM Foundry Updates 06-01-2023
1
#47 opened over 1 year ago
by
abhi-mosaic
Support device_map="auto" when loading
19
#23 opened over 1 year ago
by
shijie-wu
Update modeling_mpt.py
#16 opened over 1 year ago
by
ybelkada
Update modeling_mpt.py
#32 opened over 1 year ago
by
ybelkada
Update modeling_mpt.py
#40 opened over 1 year ago
by
ybelkada
Update modeling_mpt.py
2
#45 opened over 1 year ago
by
ybelkada
attn_impl
11
#27 opened over 1 year ago
by
GaaraOtheSand
Can this be fine-tuned with triton backed flash attention and alibi using the huggingface transformers trainer?
1
#13 opened over 1 year ago
by
winglian
flash_attn on gpu
1
#20 opened over 1 year ago
by
uglydumpling
PyTorch model architecture doubt
2
#19 opened over 1 year ago
by
JacopoBandoni
Where I can find the remote code?
2
#15 opened over 1 year ago
by
llm34323
The model is a troll >D
1
#17 opened over 1 year ago
by
pplanel
What task does it support?
1
#10 opened over 1 year ago
by
vshetty
How can I extract embeddings from this model?
3
#16 opened over 1 year ago
by
MehtabPathan
Where I can find remote code?
5
#12 opened over 1 year ago
by
llm34323
The environment to run training of mpt
1
#12 opened over 1 year ago
by
wangjw-bd
CPU support?
3
#4 opened over 1 year ago
by
liadlevy