Stanisław Szymczyk's picture

14

Stanisław Szymczyk

sszymczyk

·

AI & ML interests

None yet

Recent Activity

New activity 3 days ago

AIDC-AI/Marco-o1:Can you provide code for inference with MCTS?

New activity 3 days ago

allenai/Llama-3.1-Tulu-3-70B:Reason behind not using special tokens in the prompt format?

New activity 5 days ago

mistralai/Mistral-Large-Instruct-2411:The curse of the Consolidated Safetensors strikes again...

View all activity

Organizations

None yet

sszymczyk's activity

New activity in AIDC-AI/Marco-o1 3 days ago

Can you provide code for inference with MCTS?

#3 opened 3 days ago by

New activity in allenai/Llama-3.1-Tulu-3-70B 3 days ago

Reason behind not using special tokens in the prompt format?

#2 opened 4 days ago by

New activity in mistralai/Mistral-Large-Instruct-2411 5 days ago

The curse of the Consolidated Safetensors strikes again...

#4 opened 6 days ago by

New activity in meta-llama/Llama-3.1-8B-Instruct 4 months ago

What call() function parameters besides "query" can be used by the model when doing brave_search and wolfram_alpha tool calls?

#89 opened 4 months ago by

What form of the built-in brave_search and wolfram_alpha tool call output is expected by the model?

#88 opened 4 months ago by

The model often enters infinite generation loops

#32 opened 4 months ago by

New activity in nvidia/Nemotron-4-340B-Instruct 4 months ago

Gguf

#5 opened 5 months ago by

New activity in google-t5/t5-3b 5 months ago

Translation to German doesn't work in 3B model

#8 opened 5 months ago by

New activity in deepseek-ai/DeepSeek-V2 6 months ago

Calculation of _mscale during YARN RoPE scaling

#4 opened 6 months ago by

New activity in Snowflake/snowflake-arctic-instruct 7 months ago

Wrong BOS and EOS tokens in tokenizer.model file

#12 opened 7 months ago by

Confusing ArcticDecoderLayer::forward() implementation

#11 opened 7 months ago by

New activity in abacusai/TheProfessor-155b 7 months ago

Problem with repeated generation of newline characters

#3 opened 7 months ago by

New activity in mistralai/Mixtral-8x22B-Instruct-v0.1 7 months ago

Possible error in tokenizer.json

#6 opened 7 months ago by

Model is paraphrasing text instead of citing it verbatim

#7 opened 7 months ago by

Model is paraphrasing text instead of citing it verbatim

#7 opened 7 months ago by

Possible error in tokenizer.json

#6 opened 7 months ago by