Stanisław Szymczyk
sszymczyk
AI & ML interests
None yet
Organizations
None yet
A problem with pre-tokenizer regex
❤️ 1
3
#2 opened 2 months ago
by
sszymczyk
upstreaming llama.cpp Hy4-preview support
3
#1 opened 3 months ago
by
sszymczyk
Zero-valued token embeddings in model.embed_tokens.weight may disrupt the token sampling process
#43 opened 3 months ago
by
sszymczyk
Add NVFP4 scale tensors to model.safetensors.index.json
1
#5 opened 6 months ago
by
sszymczyk
Running the model with a dense attention
4
#35 opened 11 months ago
by
sszymczyk
Quick Start section in README.md is a bit misleading
👍 1
2
#10 opened 9 months ago
by
sszymczyk
Temperature and top_p values are swapped in the example code:
👍 1
1
#2 opened 10 months ago
by
sszymczyk
Recommended sampling parameters?
👍 1
2
#3 opened 10 months ago
by
sszymczyk
Problems with logical reasoning performance of GLM-4.7-Flash
👀 1
1
#35 opened 10 months ago
by
sszymczyk
Recommended sampling parameters
🤝 2
5
#6 opened 10 months ago
by
sszymczyk
Thinking mode
2
#2 opened 10 months ago
by
anikifoss
Feedback
17
#1 opened 11 months ago
by
bibproj
Please test the QwQ-32B-Preview model
➕ 2
#3 opened almost 2 years ago
by
sszymczyk
Requesting Support for GGUF Quantization of MiniMax-Text-01 through llama.cpp
👍 24
7
#1 opened almost 2 years ago
by
Doctor-Chad-PhD
Missing tokenizer.json and tokenizer_config.json files
1
#2 opened almost 2 years ago
by
sszymczyk
Please add the "tokenizer.model" file
2
#3 opened almost 2 years ago
by
ken133
Hardware Requirements
6
#1 opened almost 2 years ago
by
Lightchain
Can you provide code for inference with MCTS?
👍 6
6
#3 opened almost 2 years ago
by
sszymczyk
Reason behind not using special tokens in the prompt format?
2
#2 opened almost 2 years ago
by
Doctor-Shotgun