Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up
Jan Bernlöhr's picture

Jan Bernlöhr

jbernloehr
nvidia
4
·
  • janbernloehr

AI & ML interests

None yet

Recent Activity

new activity 8 days ago
Sandroeth/cali-0.1B:modeling_cali.py: bf16 forward crashes with "expected scalar type Float but found BFloat16" at torch.matmul(att, v) — float32 RoPE cache promotes q/k
new activity 10 days ago
ai-sage/GFusion-10B-A1.8B-base:IndexError in _extract_kv_cache on empty DynamicCache during first forward (prefill) with use_cache=True
new activity 4 months ago
vivo-ai/BlueLM-7B-Chat-32K:Fix softmax_scale type for torch.compile compatibility
View all activity

Organizations

NVIDIA's profile picture

New activity in Sandroeth/cali-0.1B 8 days ago

modeling_cali.py: bf16 forward crashes with "expected scalar type Float but found BFloat16" at torch.matmul(att, v) — float32 RoPE cache promotes q/k

1
#2 opened 8 days ago by
jbernloehr
New activity in ai-sage/GFusion-10B-A1.8B-base 10 days ago

IndexError in _extract_kv_cache on empty DynamicCache during first forward (prefill) with use_cache=True

2
#1 opened 15 days ago by
jbernloehr
New activity in vivo-ai/BlueLM-7B-Chat-32K 4 months ago

Fix softmax_scale type for torch.compile compatibility

#5 opened 4 months ago by
jbernloehr
New activity in deepseek-ai/deepseek-moe-16b-base 5 months ago

Fix compatibility with transformers 5.0

1
#8 opened 5 months ago by
jbernloehr
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs