Hugging Face's logo
Maurice Weber's picture
54

Maurice Weber

mauriceweber
ilyayudkovich's profile picture Nosdivad's profile picture maveriq's profile picture
·
mauriceweberq
mauriceweber

AI & ML interests

None yet

Organizations

Together's profile picture

mauriceweber's activity

New activity in togethercomputer/RedPajama-Data-V2 1 day ago

How can I download the sample-10B fastestly?

1
#28 opened 4 days ago by zgxiao
New activity in togethercomputer/RedPajama-Data-1T 3 months ago

defunct book subset

4
#28 opened 8 months ago by polinaeterna
New activity in togethercomputer/RedPajama-Data-V2 3 months ago

How much disk space would the whole HF dataset take?

1
#27 opened 3 months ago by protossw512
New activity in togethercomputer/RedPajama-Data-V2 5 months ago

rpv2-subsamples

1
#26 opened 6 months ago by mauriceweber

The doc_id in duplicates is should contain?

3
#24 opened 6 months ago by newbietuan
New activity in togethercomputer/RedPajama-Data-V2 6 months ago

Deduplication steps

23
#15 opened 7 months ago by ilyayudkovich

Here's a download script parallelized using Spark

1
#22 opened 6 months ago by srowen

what is the meaning of snapshots in redpajama-data-v2?

2
#21 opened 6 months ago by choidonghun
New activity in togethercomputer/RedPajama-Data-V2 7 months ago

How to join documents and quality signals when downloading directly

3
#19 opened 7 months ago by tgshdyfuhuf

Missing duplicates parquet files

5
#18 opened 7 months ago by bebensee

Script to download all files of 1B sample data locally

2
#13 opened 7 months ago by ivanzhouyq

What is the total size, of the entirety of this dataset in TB?

1
#10 opened 8 months ago by Bayaz

What's the concept on partitions

2
#5 opened 8 months ago by SwatCat

quality_signals, minhash and duplicates missing

2
#3 opened 8 months ago by sheshanshag

Request to add retries into RedPajama-Data-V2.py script

1
#16 opened 7 months ago by yura38

How to obtain duplicates from minhash?

1
#8 opened 8 months ago by cq

Obtaining Filtered Samples

4
#12 opened 7 months ago by ssingh22
New activity in togethercomputer/RedPajama-Data-1T-Sample 7 months ago

sample split details

1
#4 opened 7 months ago by sujantkumarkv
New activity in togethercomputer/RedPajama-Data-V2 8 months ago

How big is the data size of en?

5
#6 opened 8 months ago by newbietuan

Request to provide 1B/10B/100B/1T token subsample datasets separately

2
#4 opened 8 months ago by johnhew

Missing file error

3
#9 opened 8 months ago by emrgnt-cmplxty
New activity in togethercomputer/LLaMA-2-7B-32K 9 months ago

RuntimeError: "addmm_impl_cpu_" not implemented for 'Half'

4
#29 opened 9 months ago by shubhamagarwal92
New activity in togethercomputer/Llama-2-7B-32K-Instruct 9 months ago

The model doesn't seem to stop

15
#1 opened 10 months ago by LaferriereJC

llama2 forward pass seemingly not working with padded inputs, unless one element in batch is not padded

3
#13 opened 9 months ago by joehakim
New activity in togethercomputer/LLaMA-2-7B-32K 9 months ago

Using the Accelerate API to train models on multiple GPUs

8
#28 opened 9 months ago by ajash
New activity in togethercomputer/Llama-2-7B-32K-Instruct 9 months ago

Input validation error: `max_new_tokens` must be <= 1. Given: 20

1
#12 opened 9 months ago by reubenlee3
New activity in togethercomputer/LLaMA-2-7B-32K 9 months ago

Keep getting error while loading tokenizer = AutoTokenizer.from_pretrained("togethercomputer/LLaMA-2-7B-32K")

5
#27 opened 10 months ago by AIHero123
New activity in togethercomputer/RedPajama-Data-1T 9 months ago

Are the unsafe files from C4 also in RedPajama?

2
#26 opened 9 months ago by cwallenwein
New activity in togethercomputer/Llama-2-7B-32K-Instruct 9 months ago

Prompt format different in dataset compared to model card

3
#11 opened 9 months ago by bhperry

Model gives itself instructions and keeps going and going and going?

5
#8 opened 10 months ago by michael-newsrx-com
New activity in togethercomputer/Llama-2-7B-32K-Instruct 10 months ago

Great model. Plans for 13b version?

1
#9 opened 10 months ago by nahuel89p

Loading model without fast-attn

1
#10 opened 10 months ago by TZ20
New activity in togethercomputer/LLaMA-2-7B-32K 10 months ago

Model on your API Playground

7
#3 opened 11 months ago by 1littlecoder
New activity in togethercomputer/Llama-2-7B-32K-Instruct 10 months ago

Can I continue pretraining this model for domain adaptation?

4
#6 opened 10 months ago by sadahila
New activity in togethercomputer/RedPajama-Data-1T 10 months ago

inconsistent data field in github jsonl files

3
#24 opened 10 months ago by Rita
New activity in togethercomputer/RedPajama-INCITE-Instruct-3B-v1 10 months ago

Unwanted repetitive response

3
#12 opened 10 months ago by sdranju
New activity in togethercomputer/LLaMA-2-7B-32K 10 months ago

protofile.proto: A file with this name is already in the pool

1
#19 opened 10 months ago by surya-narayanan

ENDPOINT CONFIGURATION ON AWS SAGEMAKER

1
#21 opened 10 months ago by NABARKA
New activity in togethercomputer/Llama-2-7B-32K-Instruct 10 months ago

Any plans for chat model?

1
#5 opened 10 months ago by brekk

when will have a ggml version?

8
#3 opened 10 months ago by CUIGuy
New activity in togethercomputer/RedPajama-Data-1T 10 months ago

Skip split generation.

3
#23 opened 10 months ago by luosuu
New activity in togethercomputer/Llama-2-7B-32K-Instruct 10 months ago

LocalAI Model Loading

3
#2 opened 10 months ago by FIWisher
New activity in togethercomputer/RedPajama-Data-1T 11 months ago

Error when loading book/book.jsonl using load_dataset

5
#22 opened 11 months ago by icycold
New activity in togethercomputer/LLaMA-2-7B-32K 11 months ago

Instead of flash_attn it should be flash_attn_2_cuda . This is causing a deployment issue in TGI/DJL

1
#14 opened 11 months ago by monuminu

!pip install flash-attn --no-build-isolation

2
#15 opened 11 months ago by NivYO

getting strange tokens after finetuning on Qlora

2
#11 opened 11 months ago by monuminu

RoPE scaling and max_position_embeddings

2
#12 opened 11 months ago by ag0

What is the VRAM requirement of this model?

5
#1 opened 11 months ago by Said2k

GGML Version

8
#4 opened 11 months ago by s3nh
New activity in togethercomputer/Long-Data-Collections 11 months ago

Can try code as long text data.

1
#1 opened 11 months ago by win10
New activity in togethercomputer/LLaMA-2-7B-32K 11 months ago

Training diverges when used with Llama 2 70B and 4-bit QLoRA

3
#10 opened 11 months ago by alyssavance
New activity in togethercomputer/RedPajama-INCITE-7B-Instruct 11 months ago

Specify RLHF data for the Instruct and Chat versions in model card

3
#9 opened 11 months ago by markding
New activity in togethercomputer/RedPajama-INCITE-7B-Instruct 12 months ago

What's the prompt template?

11
#4 opened about 1 year ago by qiz
New activity in togethercomputer/RedPajama-INCITE-Instruct-3B-v1 12 months ago

Is this model commercially usable?

2
#10 opened 12 months ago by AayushShah