SAI990323
commented
11 months ago It seems that the problem comes from u use the 16bits on cpu, which is not supported by bitsandbytes
Closed LanPangxiang closed 10 months ago
SAI990323
commented
11 months ago It seems that the problem comes from u use the 16bits on cpu, which is not supported by bitsandbytes
Why do I get this error when I execute evaluate.py?
Traceback (most recent call last): File "evaluate.py", line 231, in
fire.Fire(main)
File "/root/miniconda3/envs/lpx-llm/lib/python3.8/site-packages/fire/core.py", line 141, in Fire
component_trace = _Fire(component, args, parsed_flag_args, context, name)
File "/root/miniconda3/envs/lpx-llm/lib/python3.8/site-packages/fire/core.py", line 475, in _Fire
component, remaining_args = _CallAndUpdateTrace(
File "/root/miniconda3/envs/lpx-llm/lib/python3.8/site-packages/fire/core.py", line 691, in _CallAndUpdateTrace
component = fn(varargs, kwargs)
File "evaluate.py", line 193, in main
output, logit = evaluate(instructions, inputs)
File "evaluate.py", line 154, in evaluate
generation_output = model.generate(
File "/root/miniconda3/envs/lpx-llm/lib/python3.8/site-packages/peft/peft_model.py", line 731, in generate
outputs = self.base_model.generate(kwargs)
File "/root/miniconda3/envs/lpx-llm/lib/python3.8/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(args, kwargs)
File "/root/miniconda3/envs/lpx-llm/lib/python3.8/site-packages/transformers/generation/utils.py", line 1437, in generate
return self.greedy_search(
File "/root/miniconda3/envs/lpx-llm/lib/python3.8/site-packages/transformers/generation/utils.py", line 2248, in greedy_search
outputs = self(
File "/root/miniconda3/envs/lpx-llm/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, *kwargs)
File "/root/miniconda3/envs/lpx-llm/lib/python3.8/site-packages/accelerate/hooks.py", line 165, in new_forward
output = old_forward(args, kwargs)
File "/root/miniconda3/envs/lpx-llm/lib/python3.8/site-packages/transformers/models/llama/modeling_llama.py", line 687, in forward
outputs = self.model(
File "/root/miniconda3/envs/lpx-llm/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, kwargs)
File "/root/miniconda3/envs/lpx-llm/lib/python3.8/site-packages/transformers/models/llama/modeling_llama.py", line 577, in forward
layer_outputs = decoder_layer(
File "/root/miniconda3/envs/lpx-llm/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, *kwargs)
File "/root/miniconda3/envs/lpx-llm/lib/python3.8/site-packages/transformers/models/llama/modeling_llama.py", line 292, in forward
hidden_states, self_attn_weights, present_key_value = self.self_attn(
File "/root/miniconda3/envs/lpx-llm/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(args, kwargs)
File "/root/miniconda3/envs/lpx-llm/lib/python3.8/site-packages/transformers/models/llama/modeling_llama.py", line 196, in forward
query_states = self.q_proj(hidden_states).view(bsz, q_len, self.num_heads, self.head_dim).transpose(1, 2)
File "/root/miniconda3/envs/lpx-llm/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/root/miniconda3/envs/lpx-llm/lib/python3.8/site-packages/peft/tuners/lora.py", line 565, in forward
result = F.linear(x, transpose(self.weight, self.fan_in_fan_out), bias=self.bias)
RuntimeError: "addmm_implcpu" not implemented for 'Half'