Björn Plüster

bjoernp's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in Earlychildhoodeducation/README 4 days ago

ecommendation for a German Base Model for Fine-Tuning (Pedagogical Use-Case / Learning Stories)

❤️ 1

2

#1 opened 5 days ago by

Mightysweet

New activity in nvidia/Nemotron-4-340B-Base about 2 years ago

Hf safetensors version

9

#3 opened about 2 years ago by

ehartford

New activity in LeoLM/leo-mistral-hessianai-7b-chat about 2 years ago

use_flash_attention_2=True

3

#9 opened about 2 years ago by

TillFetzer

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

3

#8 opened about 2 years ago by

Dodo124

New activity in DiscoResearch/Llama3_DiscoLM_German_8b_v0.1_experimental about 2 years ago

Update tokenizer_config.json

#1 opened about 2 years ago by

bjoernp

New activity in LeoLM/leo-hessianai-13b-chat over 2 years ago

Problems with flash-attention2

1

#13 opened over 2 years ago by

omaer0

New activity in DiscoResearch/mixtral-7b-8expert over 2 years ago

Loss function?

1

#10 opened over 2 years ago by

narvind2003

New activity in mistralai/Mixtral-8x7B-v0.1 over 2 years ago

No multi GPU inference support?

8

#4 opened over 2 years ago by

dataautogpt3

New activity in LeoLM/leo-hessianai-7b over 2 years ago

Llama2 vs Mistral

1

#2 opened over 2 years ago by

lightningRalf

New activity in DiscoResearch/mixtral-7b-8expert over 2 years ago

Add languages

👍 1

#8 opened over 2 years ago by

lbourdois

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

1

#7 opened over 2 years ago by

panopstor

New activity in DiscoResearch/DiscoLM-mixtral-8x7b-v2 over 2 years ago

changed "tokenizer" typo to be the one we create.

#4 opened over 2 years ago by

dyngnosis

Which transformers version is being used here?

2

#6 opened over 2 years ago by

Promptengineering

New activity in DiscoResearch/mixtral-7b-8expert over 2 years ago

Flash dependency (locks out non-NVIDIA GPUs)

➕ 1

3

#4 opened over 2 years ago by

Thalesian

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

2

#3 opened over 2 years ago by

AARon99

New activity in DiscoResearch/DiscoLM-mixtral-8x7b-v2 over 2 years ago

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

1

#5 opened over 2 years ago by

BigDeeper

small readme fix

#1 opened over 2 years ago by

jphme

New activity in DiscoResearch/mixtral-7b-8expert over 2 years ago

Update modeling_moe_mistral.py

2

#1 opened over 2 years ago by

bjoernp

New activity in LeoLM/leo-hessianai-70b-chat over 2 years ago

AWQ-Variante

4

#2 opened over 2 years ago by

SebastianBodza

Little Mistake :)

1

#1 opened over 2 years ago by

DRXD1000