qresearch

/

llama-3-vision-alpha-hf

like 41

packages\torch\nn\functional.py", line 5413, in multi_head_attention_forward
attn_output = linear(attn_output, out_proj_weight, out_proj_bias)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: self and mat2 must have the same dtype, but got Half and Char