Kusawa kusawa

sunnykusawa's activity

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

New activity in MaziyarPanahi/Meta-Llama-3.1-8B-Instruct-GGUF over 1 year ago

unable to load quantized 4bit_m

3

#5 opened over 1 year ago by

sunnykusawa

New activity in meta-llama/Llama-3.1-8B-Instruct over 1 year ago

unable to load 4-bit quantized varient with llama.cpp

#31 opened over 1 year ago by

sunnykusawa

New activity in mistralai/Mixtral-8x7B-Instruct-v0.1 over 1 year ago

Input token size issue, does it realy supports 32k tokens?

1

#197 opened over 1 year ago by

sunnykusawa

Input validation error: `inputs` tokens + `max_new_tokens` must be <= 2048. on Mixtral8x7b 32K token

🔥 1

3

#199 opened over 1 year ago by

sunnykusawa