automatedstockminingorg

/

14b-stockanalyst-14b-stockanalyst

like 1

So using llama.cpp, I tried to convert this model to a gguf file, and this is the error I had. Is there something special you would recommend to help with converting it?

INFO:hf-to-gguf:Loading model: 14b-stockanalyst-14b-stockanalyst
INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only
INFO:hf-to-gguf:Exporting model...
INFO:hf-to-gguf:gguf: loading model weight map from 'model.safetensors.index.json'
INFO:hf-to-gguf:gguf: loading model part 'model-00001-of-00017.safetensors'
INFO:hf-to-gguf:token_embd.weight, torch.bfloat16 --> F32, shape = {5120, 152064}
INFO:hf-to-gguf:gguf: loading model part 'model-00002-of-00017.safetensors'
INFO:hf-to-gguf:blk.0.attn_norm.weight, torch.float32 --> F32, shape = {5120}
INFO:hf-to-gguf:blk.0.ffn_down.weight, torch.uint8 --> F32, shape = {35389440}

ValueError: Can not map tensor 'model.layers.0.mlp.down_proj.weight.absmax'