Stanisław Szymczyk
sszymczyk
AI & ML interests
None yet
Recent Activity
new activity
about 16 hours ago
deepseek-ai/DeepSeek-V3.2:Running the model with a dense attention
new activity
8 months ago
allenai/ZebraLogic:Please test the QwQ-32B-Preview model
Organizations
None yet
Running the model with a dense attention
#35 opened about 16 hours ago
by
sszymczyk
Responses of Ring-1T available on zenmux.ai often end abruptly after 14-16k tokens without generating complete answer
#13 opened about 1 month ago
by
sszymczyk
Please test the QwQ-32B-Preview model
➕
2
#3 opened about 1 year ago
by
sszymczyk
This model performs worse in complex problems compared to the DeepSeek R1
17
#254 opened 10 months ago
by
sszymczyk
Requesting Support for GGUF Quantization of MiniMax-Text-01 through llama.cpp
👍
24
7
#1 opened 12 months ago
by
Doctor-Chad-PhD
Missing tokenizer.json and tokenizer_config.json files
1
#2 opened 12 months ago
by
sszymczyk
Please add the "tokenizer.model" file
2
#3 opened 12 months ago
by
ken133
Hardware Requirements
6
#1 opened about 1 year ago
by
Lightchain
Can you provide code for inference with MCTS?
👍
6
6
#3 opened about 1 year ago
by
sszymczyk
Reason behind not using special tokens in the prompt format?
2
#2 opened about 1 year ago
by
Doctor-Shotgun
The curse of the Consolidated Safetensors strikes again...
2
#4 opened about 1 year ago
by
jukofyork
The model often enters infinite generation loops
👍
5
13
#32 opened over 1 year ago
by
sszymczyk
Calculation of _mscale during YARN RoPE scaling
1
#4 opened over 1 year ago
by
sszymczyk
Wrong BOS and EOS tokens in tokenizer.model file
👍
1
1
#12 opened over 1 year ago
by
sszymczyk
Problem with repeated generation of newline characters
2
#3 opened over 1 year ago
by
sszymczyk
Possible error in tokenizer.json
👍
🔥
4
6
#6 opened over 1 year ago
by
sszymczyk
Model is paraphrasing text instead of citing it verbatim
3
#7 opened over 1 year ago
by
sszymczyk