error: subprocess-exited-with-error

  × python setup.py egg_info did not run successfully.
  │ exit code: 1
  ╰─> [15 lines of output]
      test.c
      LINK : fatal error LNK1181: no se puede abrir el archivo de entrada 'aio.lib'
      Traceback (most recent call last):
        File "<string>", line 2, in <module>
        File "<pip-setuptools-caller>", line 34, in <module>
        File "C:\Users\fer\AppData\Local\Temp\pip-install-rl2m083a\deepspeed_0a392c06e34c405d970b33e0372ff5a3\setup.py", line 156, in <module>
          abort(f"Unable to pre-compile {op_name}")
        File "C:\Users\fer\AppData\Local\Temp\pip-install-rl2m083a\deepspeed_0a392c06e34c405d970b33e0372ff5a3\setup.py", line 48, in abort
          assert False, msg
      AssertionError: Unable to pre-compile async_io
      DS_BUILD_OPS=1
       [WARNING]  async_io requires the dev libaio .so object and headers but these were not found.
       [WARNING]  If libaio is already installed (perhaps from source), try setting the CFLAGS and LDFLAGS environment variables to where it can be found.
       [WARNING]  One can disable async_io with DS_BUILD_AIO=0
       [ERROR]  Unable to pre-compile async_io
      [end of output]

  note: This error originates from a subprocess, and is likely not a problem with pip.
error: metadata-generation-failed

× Encountered error while generating package metadata.
╰─> See above for output.

note: This is an issue with the package mentioned above, not pip.
hint: See above for details.

RuntimeError    : raise RuntimeError("Distributed package doesn't have NCCL " "built in")Distributed package doesn't have NCCL built in

RuntimeError: Distributed package doesn't have NCCL built in
    torch.distributed.init_process_group(backend="nccl", **kwargs)
  File "/Users/ericnograles/Library/Python/3.9/lib/python/site-packages/torch/distributed/distributed_c10d.py", line 895, in init_process_group
    PartialState(cpu, **kwargs)
    raise RuntimeError("Distributed package doesn't have NCCL " "built in")
  File "/Users/ericnograles/Library/Python/3.9/lib/python/site-packages/accelerate/state.py", line 117, in __init__
RuntimeError: Distributed package doesn't have NCCL built in
    self.state = AcceleratorState(

python generate.py --config configs/generate/generate.yaml --prompt "Write a script to reverse a string in Python"

Setting up model
Traceback (most recent call last):
  File "/opt/homebrew/Cellar/[email protected]/3.11.2_1/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/huggingface_hub/utils/_errors.py", line 259, in hf_raise_for_status
    response.raise_for_status()
  File "/opt/homebrew/Cellar/[email protected]/3.11.2_1/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/requests/models.py", line 1021, in raise_for_status
    raise HTTPError(http_error_msg, response=self)
requests.exceptions.HTTPError: 401 Client Error: Unauthorized for url: https://huggingface.co/None/resolve/main/config.json

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/Users/me/gpt/gpt4all/transformers/src/transformers/utils/hub.py", line 409, in cached_file
    resolved_file = hf_hub_download(
                    ^^^^^^^^^^^^^^^^
  File "/opt/homebrew/Cellar/[email protected]/3.11.2_1/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/huggingface_hub/utils/_validators.py", line 120, in _inner_fn
    return fn(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^
  File "/opt/homebrew/Cellar/[email protected]/3.11.2_1/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/huggingface_hub/file_download.py", line 1160, in hf_hub_download
    metadata = get_hf_file_metadata(
               ^^^^^^^^^^^^^^^^^^^^^
  File "/opt/homebrew/Cellar/[email protected]/3.11.2_1/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/huggingface_hub/utils/_validators.py", line 120, in _inner_fn
    return fn(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^
  File "/opt/homebrew/Cellar/[email protected]/3.11.2_1/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/huggingface_hub/file_download.py", line 1501, in get_hf_file_metadata
    hf_raise_for_status(r)
  File "/opt/homebrew/Cellar/[email protected]/3.11.2_1/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/huggingface_hub/utils/_errors.py", line 291, in hf_raise_for_status
    raise RepositoryNotFoundError(message, response) from e
huggingface_hub.utils._errors.RepositoryNotFoundError: 401 Client Error. (Request ID: Root=1-6424332a-26533405190ac1c961e12ed4)

Repository Not Found for url: https://huggingface.co/None/resolve/main/config.json.
Please make sure you specified the correct `repo_id` and `repo_type`.
If you are trying to access a private or gated repo, make sure you are authenticated.
Invalid username or password.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/Users/me/gpt/gpt4all/generate.py", line 52, in <module>
    model, tokenizer = setup_model(config)
                       ^^^^^^^^^^^^^^^^^^^
  File "/Users/me/gpt/gpt4all/generate.py", line 20, in setup_model
    model = AutoModelForCausalLM.from_pretrained(config["model_name"], device_map="auto", torch_dtype=torch.float16)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/me/gpt/gpt4all/transformers/src/transformers/models/auto/auto_factory.py", line 441, in from_pretrained
    config, kwargs = AutoConfig.from_pretrained(
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/me/gpt/gpt4all/transformers/src/transformers/models/auto/configuration_auto.py", line 905, in from_pretrained
    config_dict, unused_kwargs = PretrainedConfig.get_config_dict(pretrained_model_name_or_path, **kwargs)
                                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/me/gpt/gpt4all/transformers/src/transformers/configuration_utils.py", line 573, in get_config_dict
    config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs)
                          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/me/gpt/gpt4all/transformers/src/transformers/configuration_utils.py", line 628, in _get_config_dict
    resolved_config_file = cached_file(
                           ^^^^^^^^^^^^
  File "/Users/me/gpt/gpt4all/transformers/src/transformers/utils/hub.py", line 424, in cached_file
    raise EnvironmentError(
OSError: None is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models'
If this is a private repository, make sure to pass a token having permission to this repo with `use_auth_token` or log in with `huggingface-cli login` and pass `use_auth_token=True`.

gpt4all --prompt "List some dogs" > output.md

> Give me a C++ algorithm for the integer square root (isqrt).
The following is an implementation of iSqrt() function which returns the integer Square Root of its argument, in terms of unsigned long ints on 32-bit systems. It uses Newton's method to find a better approximation as it iterates through each iteration until convergence or exceeding maximum number of iterations allowed (10).
```cpp
#include <iostream>
using namespace std; // for cout << endl;
unsigned long int iSqrt( unsigned long int n ) {
    if (n <= 2) return n *= 3/2 + sqrt((double)(n*n)); else{
        double x = pow(-1.0, floor(.5*(log(fabs(n)))+1./4))/(sqrt(6)*pow(x,3)/pi); // Newton's method for integer square root calculation;
    unsigned long int result= (unsigned)floor((double)(x)); 	// convert double to signed integer.
        if ((result-fabs(n/2+1))) { x = pow(-1.0,( floor(.5*(log(fabs(x)))) + .75))/(sqrt(6)*pow(x,3)/pi); } // Newton's method for double square root calculation;
        if (result-floor((double)(n/2+1))) { x = pow(-1.0,( floor(.5*(log(fabs(x)))) + .75))/(sqrt(6)*pow(x,3)/pi); } // Newton's method for double square root calculation;
        if (result-floor((double)(n/2+1))) { x = pow(-1.0,( floor(.5*(log(fabs(x)))) + .75))/(sqrt(6)*pow(x,3)/pi); } // Newton's method for double square root calculation;
 ... keeps repeating the last line until stopped ...

> Give me a C++ algorithm for the integer square root (isqrt).
Here's one way to implement iSqrt in C++, using an array of integers and dynamic programming techniques:
```cpp
int sqr(const int& num) { // returns squared value, not just a number
    constexpr auto MAX = (std::numeric_limits<decltype>::max)*2;// max possible square root for any integer <= this limit

    if (num < 0 || std::abs(int64_t{1}) == num) { // handle special cases like -ve numbers and 1 itself
        return sqr(-std::fmod<decltype>(-std::floor, int64_t{2}, MAX));//return floor of the square root for negative number or just take it as is if positive.
    } else { // handle normal cases like nonnegative numbers > 1 (iSqrt)
        constexpr auto sqr = std::pow(std::fabs<decltype>(num),2);//return squared value of the input integer number for isqrt calculation

        if ((int64_t{0} == num && int64_t{1}) || (sqr <= MAX)) { //handle special cases like 0 and sqrt(1) which are both irrational numbers.
            return std::fmod<decltype>(-std::floor, sqr);//return floor of the square root for these two values as they have no rational value to represent them in iSqrt calculation.
        } else { //handle normal cases like nonnegative integers > 1 (iSquare)
            constexpr auto num2 = std::fabs<decltype>(num);//return absolute value of the input integer number for sqr(x).

            if ((sqr <= MAX && int64_t{0} == num || (int64_t{1}) > 3) //handle special cases like sqrt(2), which is irrational and has no rational value to represent it in iSqrt calculation.
                return std::fmod<decltype>(-std::floor, int64_t{num/int64_t{1}});//return floor of the square root for these two values as they have irrational numbers and no rational value to represent them in iSqrt calculation.
            else { //handle normal cases like nonnegative integers > 2 (iSquare)
                constexpr auto num3 = std::fabs<decltype>(num);//return absolute value of the input integer number for sqr(x).

                if ((sqr <= MAX && int64_t{0} == num || (int64_t{1}) > 2) //handle special cases like sqrt(3), which is irrational and has no rational value to represent it in iSqrt calculation.
                    return std::fmod<decltype>(-std::floor, int64_t{num/int64_t{1}});//return floor of the square root for these two values as they have irrational numbers and no rational value to represent them in iSqrt calculation.
                else { //handle normal cases like nonnegative integers > 3 (iSquare)
                    constexpr auto num4 = std::fabs<decltype>(num);//return absolute value of the input integer number for sqr(x).

main: seed = ****76542
llama_model_load: loading model from 'gpt4all-lora-quantized.bin' - please wait ...
llama_model_load: failed to open 'gpt4all-lora-quantized.bin'
main: failed to load model from 'gpt4all-lora-quantized.bin'

(venv) ➜  gpt4all git:(main) ✗ ./chat/gpt4all-lora-quantized-OSX-m1
main: seed = 1680048739
llama_model_load: loading model from 'gpt4all-lora-quantized.bin' - please wait ...
llama_model_load: failed to open 'gpt4all-lora-quantized.bin'
main: failed to load model from 'gpt4all-lora-quantized.bin'

(5620.c8c): Security check failure or stack buffer overrun - code c0000409 (!!! second chance !!!)
Subcode: 0x8 FAST_FAIL_RANGE_CHECK_FAILURE 
gpt4all_lora_quantized_win64+0x23361:
00007ff6`7dfe3361 cd29            int     29h
0:000> k
 # Child-SP          RetAddr               Call Site
00 00000048`2b2fe2d0 00007ff6`7dfe333e     gpt4all_lora_quantized_win64+0x23361
01 00000048`2b2fe300 00007ff6`7dfcb760     gpt4all_lora_quantized_win64+0x2333e
02 00000048`2b2fe330 00007ff6`7dfe3adc     gpt4all_lora_quantized_win64+0xb760
03 00000048`2b2ffb30 00007ff8`0f923db1     gpt4all_lora_quantized_win64+0x23adc
04 00000048`2b2ffb70 00007ff8`101f32a1     KERNEL32!BaseThreadInitThunk+0x21
05 00000048`2b2ffba0 00000000`00000000     ntdll!RtlUserThreadStart+0x21 

Setting up model
Traceback (most recent call last):
  File "/home/ubuntu/gpt4all/generate.py", line 52, in <module>
    model, tokenizer = setup_model(config)
  File "/home/ubuntu/gpt4all/generate.py", line 20, in setup_model
    model = AutoModelForCausalLM.from_pretrained(config["model_name"], device_map="auto", torch_dtype=torch.float16)
  File "/home/ubuntu/.local/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 441, in from_pretrained
    config, kwargs = AutoConfig.from_pretrained(
  File "/home/ubuntu/.local/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py", line 917, in from_pretrained
    config_class = CONFIG_MAPPING[config_dict["model_type"]]
  File "/home/ubuntu/.local/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py", line 623, in __getitem__
    raise KeyError(key)
KeyError: 'llama'

user@gpt4:~/gpt4all/chat$ ./gpt4all-lora-quantized-linux-x86 
main: seed = 1680120667
llama_model_load: loading model from 'gpt4all-lora-quantized.bin' - please wait ...
Illegal instruction (core dumped)

[  104.211520] systemd[1]: systemd 249.11-0ubuntu3.7 running in system mode (+PAM +AUDIT +SELINUX +APPARMOR +IMA +SMACK +SECCOMP +GCRYPT +GNUTLS +OPENSSL +ACL +BLKID +CURL +ELFUTILS +FIDO2 +IDN2 -IDN +IPTC +KMOD +LIBCRYPTSETUP +LIBFDISK +PCRE2 -PWQUALITY -P11KIT -QRENCODE +BZIP2 +LZ4 +XZ +ZLIB +ZSTD -XKBCOMMON +UTMP +SYSVINIT default-hierarchy=unified)
[  104.211578] systemd[1]: Detected virtualization kvm.
[  104.211582] systemd[1]: Detected architecture x86-64.
[ 5620.273116] show_signal: 22 callbacks suppressed
[ 5620.273119] traps: gpt4all-lora-qu[17654] trap invalid opcode ip:423d62 sp:7ffe451f4828 error:0 in gpt4all-lora-quantized-linux-x86[400000+55000]
[ 5647.501626] traps: gpt4all-lora-qu[17668] trap invalid opcode ip:423d62 sp:7fffdfc29678 error:0 in gpt4all-lora-quantized-linux-x86[400000+55000]

...
loading libs, reading gpt4all-lora-quantized.bin
...
brk(0x13d5000)                          = 0x13d5000
brk(0x13f6000)                          = 0x13f6000
read(3, "\0\0\340\245\244\2\0\0\0\321\220\3\0\0\0\341\276\266\3\0\0\0\342\236\226\3\0\0\0\345\272\247"..., 8191) = 8191
--- SIGILL {si_signo=SIGILL, si_code=ILL_ILLOPN, si_addr=0x423d62} ---
+++ killed by SIGILL (core dumped) +++
Illegal instruction (core dumped)

    Flags:               fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx lm rep_good nopl cpuid extd_apicid tsc_known_freq pni
                          cx16 x2apic hypervisor cmp_legacy 3dnowprefetch vmmcall
Virtualization features: 
  Hypervisor vendor:     KVM
  Virtualization type:   full

Traceback (most recent call last):
  File "/home/Owner/Developer/gpt4all/generate.py", line 2, in <module>
    from peft import PeftModelForCausalLM
  File "/home/Owner/Developer/gpt4all/peft/src/peft/__init__.py", line 22, in <module>
    from .mapping import MODEL_TYPE_TO_PEFT_MODEL_MAPPING, PEFT_TYPE_TO_CONFIG_MAPPING, get_peft_config, get_peft_model
  File "/home/Owner/Developer/gpt4all/peft/src/peft/mapping.py", line 16, in <module>
    from .peft_model import (
  File "/home/Owner/Developer/gpt4all/peft/src/peft/peft_model.py", line 22, in <module>
    from accelerate import dispatch_model, infer_auto_device_map
  File "/home/Owner/anaconda3/lib/python3.9/site-packages/accelerate/__init__.py", line 7, in <module>
    from .accelerator import Accelerator
  File "/home/Owner/anaconda3/lib/python3.9/site-packages/accelerate/accelerator.py", line 27, in <module>
    from .checkpointing import load_accelerator_state, load_custom_state, save_accelerator_state, save_custom_state
  File "/home/Owner/anaconda3/lib/python3.9/site-packages/accelerate/checkpointing.py", line 24, in <module>
    from .utils import (
  File "/home/Owner/anaconda3/lib/python3.9/site-packages/accelerate/utils/__init__.py", line 96, in <module>
    from .other import (
  File "/home/Owner/anaconda3/lib/python3.9/site-packages/accelerate/utils/other.py", line 29, in <module>
    from deepspeed import DeepSpeedEngine
  File "/home/Owner/anaconda3/lib/python3.9/site-packages/deepspeed/__init__.py", line 14, in <module>
    from . import module_inject
  File "/home/Owner/anaconda3/lib/python3.9/site-packages/deepspeed/module_inject/__init__.py", line 1, in <module>
    from .replace_module import replace_transformer_layer, revert_transformer_layer, ReplaceWithTensorSlicing
  File "/home/Owner/anaconda3/lib/python3.9/site-packages/deepspeed/module_inject/replace_module.py", line 15, in <module>
    from ..runtime.zero import GatheredParameters
  File "/home/Owner/anaconda3/lib/python3.9/site-packages/deepspeed/runtime/zero/__init__.py", line 6, in <module>
    from .partition_parameters import ZeroParamType
  File "/home/Owner/anaconda3/lib/python3.9/site-packages/deepspeed/runtime/zero/partition_parameters.py", line 22, in <module>
    from .linear import LinearModuleForZeroStage3, zero3_linear_wrap
  File "/home/Owner/anaconda3/lib/python3.9/site-packages/deepspeed/runtime/zero/linear.py", line 20, in <module>
    from deepspeed.runtime.utils import noop_decorator
  File "/home/Owner/anaconda3/lib/python3.9/site-packages/deepspeed/runtime/utils.py", line 19, in <module>
    from torch._six import inf
ModuleNotFoundError: No module named 'torch._six'

    raise TypeError("len() of a 0-d tensor")                                                                                                                                                                                                                  TypeError: len() of a 0-d tensor

egrep -v 'prompt": ""' data.jsonl