Dmytro Dzhulgakov

dzhulgakov's activity

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

New activity in deepseek-ai/DeepSeek-V3.1 2 months ago

Add tools to the end of the system prompt

#20 opened 2 months ago by

dzhulgakov

New activity in moonshotai/Kimi-K2-Instruct 4 months ago

Adjust number of reserved tokens to match the model

#15 opened 4 months ago by

dzhulgakov

New activity in deepseek-ai/DeepSeek-V3 10 months ago

Bug in fp8_cast_bf16.py

1

#4 opened 10 months ago by

dzhulgakov

New activity in deepseek-ai/DeepSeek-Coder-V2-Instruct over 1 year ago

How important is the grouped_topk?

👀 1

#6 opened over 1 year ago by

dzhulgakov

New activity in google/gemma-2-9b over 1 year ago

Can't repro MMLU: sliding window attention implementation seems broken

3

#11 opened over 1 year ago by

dzhulgakov

New activity in google/gemma-7b-it over 1 year ago

Running sample code gives ma a shape error

1

#22 opened over 1 year ago by

dzhulgakov

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

Update modeling_moe_mistral.py

2

#1 opened almost 2 years ago by

bjoernp

commented a paper about 2 years ago

Mistral 7B

Paper • 2310.06825 • Published Oct 10, 2023 • 55 •

8