[Bug]: Int8 k/v cache calibrate don't work with QWen model?

Question

[Bug]: Int8 k/v cache calibrate don't work with QWen model?

Opened this issue 2 months ago · 1 comments

Your current environment

Collecting environment information...
PyTorch version: 2.3.0+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A                                                                                                           OS: Ubuntu 22.04.4 LTS (x86_64)
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version: Could not collect
CMake version: version 3.29.2
Libc version: glibc-2.35
Python version: 3.10.13 | packaged by conda-forge | (main, Oct 26 2023, 18:07:37) [GCC 12.3.0] (64-bit runtime)
Python platform: Linux-5.15.0-100-generic-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: 12.1.66
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration:
GPU 0: Tesla V100-PCIE-32GB
GPU 1: Tesla V100-PCIE-32GB
GPU 2: Tesla V100-PCIE-32GB
GPU 3: Tesla V100-PCIE-32GB                                                                                                      [32/1902]

Nvidia driver version: 535.161.07
cuDNN version: Could not collect
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
CPU:
Architecture:                       x86_64
CPU op-mode(s):                     32-bit, 64-bit
Address sizes:                      46 bits physical, 48 bits virtual
Byte Order:                         Little Endian
CPU(s):                             56
On-line CPU(s) list:                0-55
Vendor ID:                          GenuineIntel
Model name:                         Intel(R) Xeon(R) CPU E5-2680 v4 @ 2.40GHz
CPU family:                         6
Model:                              79                                                                                                    Thread(s) per core:                 2
Core(s) per socket:                 14
Socket(s):                          2
Stepping:                           1
CPU max MHz:                        3300.0000
CPU min MHz:                        1200.0000
BogoMIPS:                           4800.28
Flags:                              fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse
sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni
 pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_tim
er aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cdp_l3 invpcid_single pti intel_ppin ssbd ibrs ibpb stibp tp
r_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm rdt_a rdseed adx smap intel_pt
 xsaveopt cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local dtherm ida arat pln pts md_clear flush_l1d
Virtualization:                     VT-x
L1d cache:                          896 KiB (28 instances)
L1i cache:                          896 KiB (28 instances)
L2 cache:                           7 MiB (28 instances)
L3 cache:                           70 MiB (2 instances)
NUMA node(s):                       2
NUMA node0 CPU(s):                  0-13,28-41
NUMA node1 CPU(s):                  14-27,42-55
Vulnerability Gather data sampling: Not affected
Vulnerability Itlb multihit:        KVM: Mitigation: VMX disabled
Vulnerability L1tf:                 Mitigation; PTE Inversion; VMX conditional cache flushes, SMT vulnerable
Vulnerability Mds:                  Mitigation; Clear CPU buffers; SMT vulnerable
Vulnerability Meltdown:             Mitigation; PTI
Vulnerability Mmio stale data:      Mitigation; Clear CPU buffers; SMT vulnerable
Vulnerability Retbleed:             Not affected
Vulnerability Spec rstack overflow: Not affected
Vulnerability Spec store bypass:    Mitigation; Speculative Store Bypass disabled via prctl and seccomp
Vulnerability Spectre v1:           Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2:           Mitigation; Retpolines, IBPB conditional, IBRS_FW, STIBP conditional, RSB filling, PBRSB-eIBRS Not affected
Vulnerability Srbds:                Not affected
Vulnerability Tsx async abort:      Mitigation; Clear CPU buffers; SMT vulnerable
Versions of relevant libraries:
[pip3] mypy==0.991
[pip3] mypy-extensions==1.0.0
[pip3] numpy==1.26.4
[pip3] torch==2.3.0
[pip3] triton==2.3.0
[conda] numpy                     1.26.4                   pypi_0    pypi
[conda] torch                     2.3.0                    pypi_0    pypi
[conda] triton                    2.3.0                    pypi_0    pypiROCM Version: Could not collect
Aphrodite Version: 0.5.3
Aphrodite Build Flags:
CUDA Archs: Not Set; ROCm: Disabled

🐛 Describe the bug

Run calibrate script as below

python aphrodite/kv_quant/calibrate.py --model Qwen/Qwen1.5-1.8B-Chat --calib_dataset wikitext2 --calib_samples 128 --calib_seqlen 4096 --work_dir kv_cache_states/qwen1.5_1.8b

And I got this error

aphrodite-engine/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for l
m_head.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you me
an to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place
?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
Traceback (most recent call last):
  File "/DaTa//dl/src/aphrodite-engine/aphrodite/kv_quant/calibrate.py", line 112, in <module>
    fire.Fire(calibrate)
  File "/DaTa//miniforge3/envs/aphrodite-engine/lib/python3.10/site-packages/fire/core.py", line 143, in Fire
    component_trace = _Fire(component, args, parsed_flag_args, context, name)
  File "/DaTa//miniforge3/envs/aphrodite-engine/lib/python3.10/site-packages/fire/core.py", line 477, in _Fire
    component, remaining_args = _CallAndUpdateTrace(
  File "/DaTa//miniforge3/envs/aphrodite-engine/lib/python3.10/site-packages/fire/core.py", line 693, in _CallAndUpdateT
race
    component = fn(*varargs, **kwargs)
  File "/DaTa//dl/src/aphrodite-engine/aphrodite/kv_quant/calibrate.py", line 69, in calibrate
    layer_type = LAYER_TYPE_MAP[type(model).__name__]
KeyError: 'Qwen2ForCausalLM'

Answer 1 · 2024-06-17T13:14:31.000Z

I was able to get pass this error by manually setting in aphrodite/kv_quant/calibrate.py:

LAYER_TYPE_MAP = {
    'InternLMForCausalLM': 'InternLMDecoderLayer',
    'QWenLMHeadModel': 'QWenBlock',
    'Qwen2ForCausalLM': 'Qwen2DecoderLayer',
    'BaiChuanForCausalLM': 'DecoderLayer',
    'LlamaForCausalLM': 'LlamaDecoderLayer',
}
NORM_TYPE_MAP = {
    'InternLMForCausalLM': 'InternLMRMSNorm',
    'QWenLMHeadModel': 'RMSNorm',
    'Qwen2ForCausalLM': 'Qwen2RMSNorm',
    'BaiChuanForCausalLM': 'RMSNorm',
    'LlamaForCausalLM': 'LlamaRMSNorm',
}

But now I get the following errors, letting me think that I didn't put the right params, or some other Qwen2 params are not properly set in the code :

Loading checkpoint shards:  50%|████████████████████████████████████████████████████████████████████████████████████                                                                                    | 2/4 [00:00<00:00,  9.18it/s]
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.14.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.14.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.14.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.14.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.15.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.15.self_attn.q_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.15.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.15.self_attn.k_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.15.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.15.self_attn.v_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.15.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.15.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.15.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.15.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.15.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.15.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.16.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.16.self_attn.q_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.16.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.16.self_attn.k_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.16.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.16.self_attn.v_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.16.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.16.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.16.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.16.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.16.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.16.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.17.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.17.self_attn.q_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.17.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.17.self_attn.k_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.17.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.17.self_attn.v_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.17.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.17.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.17.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.17.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.17.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.17.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.18.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.18.self_attn.q_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.18.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.18.self_attn.k_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.18.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.18.self_attn.v_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.18.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.18.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.18.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.18.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.18.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.18.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.19.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.19.self_attn.q_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.19.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.19.self_attn.k_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.19.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.19.self_attn.v_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.19.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.19.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.19.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.19.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.19.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.19.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.20.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.20.self_attn.q_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.20.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.20.self_attn.k_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.20.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.20.self_attn.v_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.20.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.20.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.20.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.20.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.20.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.20.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.21.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.21.self_attn.q_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.21.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.21.self_attn.k_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.21.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.21.self_attn.v_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.21.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.21.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.21.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.21.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.21.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.21.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.22.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.22.self_attn.q_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.22.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.22.self_attn.k_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.22.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.22.self_attn.v_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.22.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.22.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.22.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.22.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.22.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.22.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.23.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.23.self_attn.q_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.23.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.23.self_attn.k_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.23.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.23.self_attn.v_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.23.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.23.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.23.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.23.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.23.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.23.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.24.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.24.self_attn.q_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.24.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.24.self_attn.k_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.24.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.24.self_attn.v_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.24.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.24.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.24.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.24.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.24.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.24.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.25.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.25.self_attn.q_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.25.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.25.self_attn.k_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.25.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.25.self_attn.v_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.25.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.25.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.25.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.25.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.25.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.25.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.26.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.26.self_attn.q_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.26.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.26.self_attn.k_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.26.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.26.self_attn.v_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.26.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.26.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.27.self_attn.o_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.27.mlp.gate_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.27.mlp.up_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.27.mlp.down_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.27.input_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.layers.27.post_attention_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for model.norm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py:2047: UserWarning: for lm_head.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
Loading checkpoint shards: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 4/4 [00:00<00:00, 11.91it/s]
Loading calibrate dataset ...                                                    Token indices sequence length is longer than the specified maximum sequence length for this model (2518423 > 131072). Running this sequence through the model will result in indexing errors
Traceback (most recent call last):
  File "/PROJECT_PATH/aphrodite-engine/aphrodite/kv_quant/calibrate.py", line 114, in <module>
    fire.Fire(calibrate)
  File "/PROJECT_PATH/.venv/lib/python3.10/site-packages/fire/core.py", line 143, in Fire
    component_trace = _Fire(component, args, parsed_flag_args, context, name)
  File "/PROJECT_PATH/.venv/lib/python3.10/site-packages/fire/core.py", line 477, in _Fire
    component, remaining_args = _CallAndUpdateTrace(
  File "/PROJECT_PATH/.venv/lib/python3.10/site-packages/fire/core.py", line 693, in _CallAndUpdateTrace
    component = fn(*varargs, **kwargs)
  File "/PROJECT_PATH/aphrodite-engine/a
phrodite/kv_quant/calibrate.py", line 105, in calibrate
    calib_ctx.calibrate(all_data)
  File "/PROJECT_PATH/.venv/lib/python3.10/site-packages/aphrodite/kv_quant/calibration.py", line 299, in calibrate
    _ = model(data.to(self.device))
  File "/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
    return forward_call(*args, **kwargs)
  File "/PROJECT_PATH/.venv/lib/python3.10/site-packages/transformers/models/qwen2/modeling_qwen2.py", line 1034, in forward
    layer_outputs = decoder_layer(
  File "/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/PROJECT_PATH/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
    return forward_call(*args, **kwargs)
  File "/PROJECT_PATH/.venv/lib/python3.10/site-packages/aphrodite/kv_quant/calibration.py", line 187, in _forward
    key, value = out.pop(-1)
TypeError: cannot unpack non-iterable NoneType object