Johannes

jrudolph's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in TheBloke/Llama-2-7B-GGUF about 2 years ago

GGUF q4_0 model variants quantize the "output.weight" tensor with q6_k (compared to former ggml files which left them at fp32 iirc)

2

#4 opened over 2 years ago by

jrudolph