The performance of full-parameter finetuning
1
#13 opened 1 day ago
by
stephenshuang
question about quants
1
#12 opened 4 days ago
by
prudant
Model architecture should be Qwen2Model instead of Qwen2ForCausalLM?
#11 opened 7 days ago
by
kavin1337
need gguf q4km
#10 opened 11 days ago
by
windkkk
Training embadding Issues.
2
#8 opened 12 days ago
by
Imran1
Hi, can you tell me how to train?
1
#7 opened 14 days ago
by
EEEmpty
输出的embedding size是多少
3
#6 opened 15 days ago
by
seleven11
模型太耗内存了,有量化版本吗?flashatt是不是可以关闭,对显卡限制太多
7
#3 opened 16 days ago
by
fukai
Is it consistent with the multi-language support of qwen2, or only Chinese and English?
1
#2 opened 16 days ago
by
fukai