Kristian Schwethelm
KristianS7
·
AI & ML interests
Large Language Models
Recent Activity
upvoted a paper about 5 hours ago
Hallucinations Undermine Trust; Metacognition is a Way Forward upvoted a paper 6 days ago
LFM2 Technical Report updated a collection 9 days ago
Iso-Depth Scaling Laws for Looped LMsOrganizations
Lower evaluation results
1
#2 opened 5 months ago
by 
MianchuWang
Differences in the results of the reproduction test on lm-evaluation-harness
3
#8 opened 4 months ago
by 
ThreeGold116
Fix bos/eos token IDs (config.json + tokenizer_config.json)
#5 opened about 2 months ago
by KristianS7
Fix UniversalTransformerCache.get_mask_sizes for batched generation
#4 opened about 2 months ago
by KristianS7
Fix bos/eos token IDs (config.json + tokenizer_config.json)
#11 opened about 2 months ago
by KristianS7
Fix UniversalTransformerCache.get_mask_sizes for batched generation
#10 opened about 2 months ago
by KristianS7
Fix UniversalTransformerCache.get_mask_sizes for batched generation
1
#5 opened 3 months ago
by KristianS7
Fix UniversalTransformerCache.get_mask_sizes for batched generation
1
#8 opened 3 months ago
by KristianS7
Batched generation (batch_size > 1) produces incorrect outputs — possible causal mask issue?
➕ 1
1
#9 opened 3 months ago
by 
vconchel
Fix bos/eos token IDs + add enable_thinking to chat template
2
#7 opened 3 months ago
by KristianS7
Fix bos/eos token IDs + add enable_thinking to chat template
2
#4 opened 3 months ago
by KristianS7
Fix bos/eos token IDs + add enable_thinking to chat template
2
#7 opened 3 months ago
by KristianS7
Fix bos/eos token IDs + add enable_thinking to chat template
2
#4 opened 3 months ago
by KristianS7