Kristian Schwethelm
KristianS7
AI & ML interests
Large Language Models
Recent Activity
updated a dataset 3 days ago
KristianS7/prepacked-fineweb-edu-llama2-32K-T2048 published a dataset 3 days ago
KristianS7/prepacked-fineweb-edu-llama2-32K-T2048 updated a dataset 9 days ago
KristianS7/nanochat-prepacked-fineweb-eduOrganizations
None yet
Lower evaluation results
1
#2 opened 4 months ago
by 
MianchuWang
Differences in the results of the reproduction test on lm-evaluation-harness
3
#8 opened 3 months ago
by 
ThreeGold116
Fix bos/eos token IDs (config.json + tokenizer_config.json)
#5 opened 29 days ago
by KristianS7
Fix UniversalTransformerCache.get_mask_sizes for batched generation
#4 opened 29 days ago
by KristianS7
Fix bos/eos token IDs (config.json + tokenizer_config.json)
#11 opened 29 days ago
by KristianS7
Fix UniversalTransformerCache.get_mask_sizes for batched generation
#10 opened 29 days ago
by KristianS7
Fix UniversalTransformerCache.get_mask_sizes for batched generation
1
#5 opened about 2 months ago
by KristianS7
Fix UniversalTransformerCache.get_mask_sizes for batched generation
1
#8 opened about 2 months ago
by KristianS7
Batched generation (batch_size > 1) produces incorrect outputs — possible causal mask issue?
➕ 1
1
#9 opened 2 months ago
by 
vconchel
Fix bos/eos token IDs + add enable_thinking to chat template
2
#7 opened about 2 months ago
by KristianS7
Fix bos/eos token IDs + add enable_thinking to chat template
2
#4 opened about 2 months ago
by KristianS7
Fix bos/eos token IDs + add enable_thinking to chat template
2
#7 opened about 2 months ago
by KristianS7
Fix bos/eos token IDs + add enable_thinking to chat template
2
#4 opened about 2 months ago
by KristianS7