Hugging Face's logo
Abhi Venigalla's picture
52

Abhi Venigalla

abhi-mosaic
abhi_venigalla
abhi-mosaic

AI & ML interests

None yet

Organizations

Mosaic ML, Inc.'s profile picture

abhi-mosaic's activity

New activity in mosaicml/mpt-30b-instruct 10 months ago

minor prose tweaks
#1 opened 10 months ago by dblalock
New activity in mosaicml/mpt-30b 10 months ago

prose tweaks
#2 opened 10 months ago by dblalock
New activity in mosaicml/mpt-7b-chat 11 months ago

there are something wrong when the latest code generate longer text

4
#19 opened 11 months ago by lvkaokao
New activity in mosaicml/mpt-7b 11 months ago

MPT-7b on colab - RAM of GPU not used

5
#50 opened 11 months ago by vi-c

Pad_token_id of MPT-7B

2
#49 opened 11 months ago by Trung-Dung

Running on single Nvidia K80 GPU with large context to generate long output

3
#29 opened 11 months ago by airtable

Speed on CPU

13
#8 opened 12 months ago by zokica

H100 TransformerEngine

3
#14 opened 12 months 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 11 months ago by shijie-wu

Create requirements.txt

2
#22 opened 11 months ago by shijie-wu
New activity in mosaicml/mpt-7b-instruct 11 months ago

configuration / penalty to lower repetition?

5
#32 opened 11 months ago by mfab

How much GPU memory is needed to finetune MPT-7B Instruct model?

2
#31 opened 11 months ago by skshreyas714

Provide fine-tuning example notebook using hf transformers

6
#22 opened 11 months ago by MakerMotion

GPU Memory / RAM requierements

8
#19 opened 11 months ago by Rbn3D

Help Needed!! Text Generation Taking Too Long

2
#17 opened 11 months ago by debajyoti111

Error in Triton implementation

2
#9 opened 12 months ago by narenzen

Error in Installation Setup

2
#24 opened 11 months ago by souvik0306

KeyError in triton implementation

7
#25 opened 11 months ago by datacow

8bit and sharded weights

2
#37 opened 11 months ago by ThreeBlessings

ValueError: MPTForCausalLM does not support `device_map='auto'` yet.

2
#38 opened 11 months ago by AayushShah

Super slow loading compared to other (even bigger) models

11
#6 opened 12 months ago by kil3r

Support Auto Device Map

5
#4 opened 12 months ago by Supreeth

Multi-GPU inference using accelerate

6
#23 opened 11 months ago by dataviral
New activity in mosaicml/mpt-7b-chat 11 months ago

reproduce mpt-7b-chat

2
#6 opened 11 months ago by ehartford

Error when deploying

4
#3 opened 12 months ago by JosephH

Does not support device_map

1
#14 opened 11 months ago by HAvietisov

Out of memory error with an RTX 4090

10
#7 opened 11 months ago by antman1p
New activity in mosaicml/mpt-7b-storywriter 11 months ago

finetune

1
#17 opened 11 months ago by vinnitu

Text loading

6
#8 opened 12 months ago by antonmks

Any reason why this longer context length wasn't applied to the chat and instruct versions?

4
#29 opened 11 months ago by RonanMcGovern

Problem loading model

3
#28 opened 11 months ago by jdc4429

Error while trying to run mpt-7-storyteller

3
#30 opened 11 months ago by paulovasconcellos

LLM Foundry Updates 06-01-2023

1
#33 opened 11 months ago by abhi-mosaic
New activity in mosaicml/mpt-7b-chat 11 months ago

LLM Foundry Updates 06-01-2023

1
#17 opened 11 months ago by abhi-mosaic
New activity in mosaicml/mpt-7b-instruct 11 months ago

LLM Foundry Updates 06-01-2023

1
#41 opened 11 months ago by abhi-mosaic
New activity in mosaicml/mpt-7b 11 months ago

LLM Foundry Updates 06-01-2023

1
#47 opened 11 months ago by abhi-mosaic

Support device_map="auto" when loading

19
#23 opened 11 months ago by shijie-wu
New activity in mosaicml/mpt-7b-chat 11 months ago

Update modeling_mpt.py
#16 opened 11 months ago by ybelkada
New activity in mosaicml/mpt-7b-storywriter 11 months ago

Update modeling_mpt.py
#32 opened 11 months ago by ybelkada
New activity in mosaicml/mpt-7b-instruct 11 months ago

Update modeling_mpt.py
#40 opened 11 months ago by ybelkada
New activity in mosaicml/mpt-7b 11 months ago

Update modeling_mpt.py

2
#45 opened 11 months ago by ybelkada

attn_impl

11
#27 opened 11 months ago by GaaraOtheSand

Can this be fine-tuned with triton backed flash attention and alibi using the huggingface transformers trainer?

1
#13 opened 12 months ago by winglian
New activity in mosaicml/mpt-7b-instruct 11 months ago

flash_attn on gpu

1
#20 opened 11 months ago by uglydumpling
New activity in mosaicml/mpt-7b 11 months ago

PyTorch model architecture doubt

2
#19 opened 11 months ago by JacopoBandoni

Where I can find the remote code?

2
#15 opened 12 months ago by llm34323

The model is a troll >D

1
#17 opened 12 months ago by pplanel
New activity in mosaicml/mpt-7b-instruct 11 months ago

What task does it support?

1
#10 opened 12 months ago by vshetty

How can I extract embeddings from this model?

3
#16 opened 11 months ago by MehtabPathan
New activity in mosaicml/mpt-7b-instruct 12 months ago

Where I can find remote code?

5
#12 opened 12 months ago by llm34323
New activity in mosaicml/mpt-7b 12 months ago

The environment to run training of mpt

1
#12 opened 12 months ago by wangjw-bd

CPU support?

3
#4 opened 12 months ago by liadlevy