gpt2 and gpt-j load error: tensor has wrong shape in model file

[loretoparisi]

Hello after latest update I get an error when running the gpt-2 model:

 % ./bin/gpt-2 -m models/gpt-2-1558M/ggml-model.bin -p "Donald Trump is"
main: seed = 1680541533
gpt2_model_load: loading model from 'models/gpt-2-1558M/ggml-model.bin'
gpt2_model_load: n_vocab = 50257
gpt2_model_load: n_ctx   = 1024
gpt2_model_load: n_embd  = 1600
gpt2_model_load: n_head  = 25
gpt2_model_load: n_layer = 48
gpt2_model_load: f16     = 1
gpt2_model_load: ggml ctx size = 3729.46 MB
gpt2_model_load: memory size =   600.00 MB, n_mem = 49152
gpt2_model_load: tensor 'model/h0/attn/c_attn/w' has wrong shape in model file: got [1600, 4800], expected [4800, 1600]
main: failed to load model from 'models/gpt-2-1558M/ggml-model.bin'

and even the gpt-j model:

% ./bin/gpt-j -m models/gpt-j-6B/ggml-model.bin -p "James Dean was"
main: seed = 1680541576
gptj_model_load: loading model from 'models/gpt-j-6B/ggml-model.bin' - please wait ...
gptj_model_load: n_vocab = 50400
gptj_model_load: n_ctx   = 2048
gptj_model_load: n_embd  = 4096
gptj_model_load: n_head  = 16
gptj_model_load: n_layer = 28
gptj_model_load: n_rot   = 64
gptj_model_load: f16     = 1
gptj_model_load: ggml ctx size = 13334.86 MB
gptj_model_load: memory_size =  1792.00 MB, n_mem = 57344
gptj_model_load: tensor 'transformer.h.0.mlp.fc_in.weight' has wrong shape in model file: got [4096, 16384], expected [16384, 4096]
main: failed to load model from 'models/gpt-j-6B/ggml-model.bin'
gptj_model_load: % 

[adtreat]

This is duplicate of #52 and the issue is that you need a newer quantized bin. This should be closed.