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
heykb's picture

heykb

heykb
3 2
·

AI & ML interests

None yet

Recent Activity

new activity 2 months ago
thetom-ai/Qwen3.6-27B-ConfigI-MLX:May I ask whether MTP (Multi-Token Prediction) is currently supported in vLLM-swift?
new activity 2 months ago
thetom-ai/Qwen3.6-27B-ConfigI-MLX:Fatal error: [metal::Device] Unable to load kernel turbo_dequant_rotated_4_256_bf16. on
liked a model 2 months ago
thetom-ai/Qwen3.6-27B-ConfigI-MLX
View all activity

Organizations

None yet

New activity in thetom-ai/Qwen3.6-27B-ConfigI-MLX 2 months ago

May I ask whether MTP (Multi-Token Prediction) is currently supported in vLLM-swift?

2
#1 opened 2 months ago by
heykb

Fatal error: [metal::Device] Unable to load kernel turbo_dequant_rotated_4_256_bf16. on

2
#2 opened 2 months ago by
heykb
liked a model 2 months ago

thetom-ai/Qwen3.6-27B-ConfigI-MLX

Text Generation • 27B • Updated Apr 25 • 139 • 5
New activity in Jackrong/Qwopus3.6-35B-A3B-v1 2 months ago

mlx_lm.convert tokenizer regex mismatch

1
#2 opened 2 months ago by
heykb
liked a model 2 months ago

Jackrong/Negentropy-claude-opus-4.7-9B-GGUF

Image-Text-to-Text • 9B • Updated May 8 • 2.74k • 71
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs