Phil's picture

5 13

Phil

cduk

·

AI & ML interests

None yet

Organizations

None yet

cduk's activity

New activity in Qwen/Qwen1.5-72B-Chat 9 days ago

Why 72B model has different vocab size comparing with other models?

#1 opened 8 months ago by

New activity in CalamitousFelicitousness/Qwen2-VL-72B-Instruct-GPTQ-Int4-tpfix 14 days ago

intermediate_size which was incompatible with VLLM parallel inference

#1 opened 14 days ago by

New activity in ISTA-DASLab/Meta-Llama-3-70B-AQLM-PV-2Bit-1x16 3 months ago

Instruct version

#1 opened 3 months ago by

New activity in Qwen/Qwen1.5-0.5B-Chat 5 months ago

Different vocab size and speculative decoding

#4 opened 5 months ago by

New activity in MaziyarPanahi/Meta-Llama-3-70B-Instruct-GPTQ 5 months ago

Some weights of LlamaForCausalLM were not initialized from the model checkpoint

#3 opened 6 months ago by

New activity in 01-ai/Yi-1.5-34B-Chat 5 months ago

Yi 1.5 34B Chat Int8 GPTQ

#8 opened 5 months ago by