Hugging Face's logo
Björn Plüster's picture
52 3 34

Björn Plüster

bjoernp
RobinDiehl's profile picture JAAI-001's profile picture sroecker's profile picture
·
bjoern_pl
bjoernpl

AI & ML interests

None yet

Organizations

CarperAI's profile picture OpenAssistant's profile picture UHH CV project's profile picture ellamind's profile picture LAION LeoLM's profile picture Vietnamese Mistral's profile picture Disco Research's profile picture MixtureMaxing's profile picture Occiglot's profile picture primeLine Research Community's profile picture

bjoernp's activity

New activity in LeoLM/leo-mistral-hessianai-7b-chat 24 days ago

use_flash_attention_2=True

3
#9 opened 24 days ago by TillFetzer
New activity in LeoLM/leo-mistral-hessianai-7b-chat about 1 month ago

leo-mistral-hessianai-7b-chat for privateGPT

3
#8 opened about 1 month ago by Dodo124
New activity in DiscoResearch/Llama3_DiscoLM_German_8b_v0.1_experimental about 1 month ago

Update tokenizer_config.json
#1 opened about 1 month ago by bjoernp
New activity in LeoLM/leo-hessianai-13b-chat 3 months ago

Problems with flash-attention2

1
#13 opened 3 months ago by omaer0
New activity in DiscoResearch/mixtral-7b-8expert 6 months ago

Loss function?

1
#10 opened 6 months ago by narvind2003
New activity in mistralai/Mixtral-8x7B-v0.1 6 months ago

No multi GPU inference support?

8
#4 opened 6 months ago by dataautogpt3
New activity in LeoLM/leo-hessianai-7b 6 months ago

Llama2 vs Mistral

1
#2 opened 6 months ago by lightningRalf
New activity in DiscoResearch/mixtral-7b-8expert 6 months ago

Add languages
#8 opened 6 months ago by lbourdois

Missing module/classes: from transformers.cache_utils import Cache, DynamicCache

1
#7 opened 6 months ago by panopstor
New activity in DiscoResearch/DiscoLM-mixtral-8x7b-v2 6 months ago

changed "tokenizer" typo to be the one we create.
#4 opened 6 months ago by dyngnosis

Which transformers version is being used here?

2
#6 opened 6 months ago by Promptengineering
New activity in DiscoResearch/mixtral-7b-8expert 6 months ago

Flash dependency (locks out non-NVIDIA GPUs)

3
#4 opened 6 months ago by Thalesian

Update modeling_moe_mistral.py
#5 opened 6 months ago by bjoernp

Really appreciate the work put into this! I have noticed a change in the model output since first release.

2
#3 opened 6 months ago by AARon99
New activity in DiscoResearch/DiscoLM-mixtral-8x7b-v2 6 months ago

Trying to quantize. Running into the issue below. Any suggestions?

1
#5 opened 6 months ago by BigDeeper

small readme fix
#1 opened 6 months ago by jphme
New activity in DiscoResearch/mixtral-7b-8expert 6 months ago

Update modeling_moe_mistral.py

2
#1 opened 6 months ago by bjoernp
New activity in LeoLM/leo-hessianai-70b-chat 6 months ago

AWQ-Variante

4
#2 opened 6 months ago by SebastianBodza

Little Mistake :)

1
#1 opened 6 months ago by DRXD1000
New activity in LeoLM/leo-hessianai-13b-chat 6 months ago

Can you incorporate madlad400 training data ?

1
#11 opened 6 months ago by cmp-nct
New activity in DiscoResearch/DiscoLM-70b 6 months ago

Is this instruction following model?

1
#1 opened 6 months ago by rjmehta
New activity in LeoLM/leo-mistral-hessianai-7b-chat 6 months ago

fix vocab size

4
#4 opened 6 months ago by jphme
New activity in LumiOpen/Poro-34B 7 months ago

Inconsistency in effective batch size reporting

3
#1 opened 7 months ago by bjoernp
New activity in OpenAssistant/OASST-DE 7 months ago

Update README.md

1
#2 opened 7 months ago by waler4ik28
New activity in LeoLM/leo-mistral-hessianai-7b-chat 7 months ago

Update READEME.md to include system prompt

1
#3 opened 7 months ago by aari1995
New activity in LeoLM/leo-hessianai-13b-chat 7 months ago

Quantise this model - missing file

1
#10 opened 7 months ago by cuh008
New activity in LeoLM/leo-mistral-hessianai-7b-chat 8 months ago

gguf version?

1
#2 opened 8 months ago by guido1893
New activity in LeoLM/leo-hessianai-13b-chat 8 months ago

Sentence Transformers

2
#8 opened 8 months ago by jdjayakaran

Ambiguity in Language detection

5
#7 opened 8 months ago by jdjayakaran

tokenizer.model missing?

2
#2 opened 8 months ago by darule
New activity in LeoLM/leo-hessianai-13b-chat-bilingual 8 months ago

Quantised models by thebloke

#1 opened 8 months ago by choltha

Training code

2
#2 opened 8 months ago by robert-h
New activity in LeoLM/leo-mistral-hessianai-7b-chat 8 months ago

First sentence of the description wrong?

1
#1 opened 8 months ago by h3ndrik
New activity in LeoLM/leo-hessianai-13b-chat 8 months ago

Add a `chat template` to this repository

1
#6 opened 8 months ago by LLukas22

How to achieve better results with fine-tuning

1
#5 opened 8 months ago by jdjayakaran

Some weights of LlamaForCausalLM were not initialized from the model checkpoint

1
#3 opened 8 months ago by fcivardi

CUDA out of memory applying to a dataset of texts

3
#4 opened 8 months ago by fcivardi
New activity in LeoLM/leo-hessianai-13b 8 months ago

how to prompt

2
#5 opened 8 months ago by g58892881

Falsche Ausgabe bei Abfrage von Landeshauptstädten:

1
#4 opened 8 months ago by darule

Flash attention NVCC requirements

3
#2 opened 8 months ago by jdjayakaran
New activity in LeoLM/leo-hessianai-7b-chat 8 months ago

missing tokenizer.model?

7
#2 opened 8 months ago by b0968
New activity in LeoLM/leo-hessianai-13b 8 months ago

Can't get any reasonable output

3
#3 opened 8 months ago by Sebbecking

tokenizer.model missing?

1
#1 opened 8 months ago by b0968
New activity in LeoLM/leo-hessianai-7b-chat 8 months ago

Commercial use

5
#1 opened 8 months ago by BramVanroy
New activity in LeoLM/leo-hessianai-13b-chat 8 months ago

Is there a problem with year numbers?

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

Installing ! pip install git+https://github.com/HazyResearch/flash-attention.git#subdirectory=csrc/rotary but flah_llama still erroring out

4
#25 opened 9 months ago by ajash
New activity in Salesforce/blip2-flan-t5-xxl over 1 year ago

Fixed typo in FP16 and 8bit examples

1
#4 opened over 1 year ago by bjoernp