Llamafile compatibility
#6 opened 8 months ago
by
IshanKhan
error loading model: tensor 'blk.59.ffn_up_exps.weight'
#5 opened 9 months ago
by
kk3dmax
gptq or awq
1
#4 opened 10 months ago
by
kevinccp
llama_model_load: error loading model: error loading model vocabulary: wstring_convert::from_bytes
5
#3 opened 10 months ago
by
jiyintor
Help plz. deepseek2.experts_weight_scale=int:16 should be deepseek2.expert_weights_scale=float:16 ?
4
#1 opened 10 months ago
by
wukongai