mergekit OSError: bilalRahib/Tiny-LLama-NSFW-Chatbot does not appear to have a file named config.json.

I'm not sure what I'm doing wrong, but I tried with the example here (https://github.com/arcee-ai/mergekit/blob/main/examples/linear.yml) and it worked so my installation is good. I edited the yaml file and selected the models I wanted to merge, and I keep getting the same error on both models :

OSError: bilalRahib/Tiny-LLama-NSFW-Chatbot does not appear to have a file named config.json. Checkout 'https://huggingface.co/bilalRahib/Tiny-LLama-NSFW-Chatbot/main' for available files.

Here is the content of the yaml config file :

models:
  - model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
    parameters:
      weight: 1.0
  - model: bilalRahib/Tiny-LLama-NSFW-Chatbot
    parameters:
      weight: 1.0
merge_method: linear
dtype: float16

Here is the complete traceback :

mergekit-yaml c1.yaml . --cuda --lazy-unpickle --allow-crimes Traceback (most recent call last): File "C:\Users\Admin\AppData\Local\Programs\Python\Python312\Lib\site-packages\huggingface_hub\utils_errors.py", line 304, in hf_raise_for_status response.raise_for_status() File "C:\Users\Admin\AppData\Local\Programs\Python\Python312\Lib\site-packages\requests\models.py", line 1021, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://huggingface.co/bilalRahib/Tiny-LLama-NSFW-Chatbot/resolve/main/config.json

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

Traceback (most recent call last): File "C:\Users\Admin\AppData\Local\Programs\Python\Python312\Lib\site-packages\transformers\utils\hub.py", line 398, in cached_file resolved_file = hf_hub_download( ^^^^^^^^^^^^^^^^ File "C:\Users\Admin\AppData\Local\Programs\Python\Python312\Lib\site-packages\huggingface_hub\utils_validators.py", line 118, in _inner_fn return fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^ File "C:\Users\Admin\AppData\Local\Programs\Python\Python312\Lib\site-packages\huggingface_hub\file_download.py", line 1261, in hf_hub_download metadata = get_hf_file_metadata( ^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Admin\AppData\Local\Programs\Python\Python312\Lib\site-packages\huggingface_hub\utils_validators.py", line 118, in _inner_fn return fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^ File "C:\Users\Admin\AppData\Local\Programs\Python\Python312\Lib\site-packages\huggingface_hub\file_download.py", line 1667, in get_hf_file_metadata r = _request_wrapper( ^^^^^^^^^^^^^^^^^ File "C:\Users\Admin\AppData\Local\Programs\Python\Python312\Lib\site-packages\huggingface_hub\file_download.py", line 385, in _request_wrapper response = _request_wrapper( ^^^^^^^^^^^^^^^^^ File "C:\Users\Admin\AppData\Local\Programs\Python\Python312\Lib\site-packages\huggingface_hub\file_download.py", line 409, in _request_wrapper hf_raise_for_status(response) File "C:\Users\Admin\AppData\Local\Programs\Python\Python312\Lib\site-packages\huggingface_hub\utils_errors.py", line 315, in hf_raise_for_status raise EntryNotFoundError(message, response) from e huggingface_hub.utils._errors.EntryNotFoundError: 404 Client Error. (Request ID: Root=1-65f753ec-699b48b9145c019039d80929;b23a3445-8b78-4681-84c4-b405860cdd94)

Entry Not Found for url: https://huggingface.co/bilalRahib/Tiny-LLama-NSFW-Chatbot/resolve/main/config.json.

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

Traceback (most recent call last): File "", line 198, in _run_module_as_main File "", line 88, in run_code File "C:\Users\Admin\AppData\Local\Programs\Python\Python312\Scripts\mergekit-yaml.exe_main.py", line 7, in File "C:\Users\Admin\AppData\Local\Programs\Python\Python312\Lib\site-packages\click\core.py", line 1157, in call return self.main(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Admin\AppData\Local\Programs\Python\Python312\Lib\site-packages\click\core.py", line 1078, in main rv = self.invoke(ctx) ^^^^^^^^^^^^^^^^ File "C:\Users\Admin\AppData\Local\Programs\Python\Python312\Lib\site-packages\click\core.py", line 1434, in invoke return ctx.invoke(self.callback, **ctx.params) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Admin\AppData\Local\Programs\Python\Python312\Lib\site-packages\click\core.py", line 783, in invoke return __callback(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Python\AI-Proj\mergekit\mergekit\options.py", line 76, in wrapper f(*args, **kwargs) File "D:\Python\AI-Proj\mergekit\mergekit\scripts\run_yaml.py", line 47, in main run_merge( File "D:\Python\AI-Proj\mergekit\mergekit\merge.py", line 46, in run_merge get_architecture_info(m.config(trust_remote_code=options.trust_remote_code)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Python\AI-Proj\mergekit\mergekit\common.py", line 121, in config return AutoConfig.from_pretrained( ^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Admin\AppData\Local\Programs\Python\Python312\Lib\site-packages\transformers\models\auto\configuration_auto.py", line 1111, in from_pretrained config_dict, unused_kwargs = PretrainedConfig.get_config_dict(pretrained_model_name_or_path, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Admin\AppData\Local\Programs\Python\Python312\Lib\site-packages\transformers\configuration_utils.py", line 633, in get_config_dict config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Admin\AppData\Local\Programs\Python\Python312\Lib\site-packages\transformers\configuration_utils.py", line 688, in _get_config_dict resolved_config_file = cached_file( ^^^^^^^^^^^^ File "C:\Users\Admin\AppData\Local\Programs\Python\Python312\Lib\site-packages\transformers\utils\hub.py", line 452, in cached_file raise EnvironmentError( OSError: bilalRahib/Tiny-LLama-NSFW-Chatbot does not appear to have a file named config.json. Checkout 'https://huggingface.co/bilalRahib/Tiny-LLama-NSFW-Chatbot/main' for available files.

Mar 17 '24 21:03 wenrolland

Hey! This is happening because Tiny-LLama-NSFW-Chatbot is a LoRA, not a full set of model weights. If you specify a base model to apply the LoRA to it will work. So like this, for example:

models:
  - model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
    parameters:
      weight: 1.0
  - model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T+bilalRahib/Tiny-LLama-NSFW-Chatbot  # base+lora
    parameters:
      weight: 1.0
merge_method: linear
dtype: float16

Mar 17 '24 21:03 cg123

Ok, thanks Charles ! I'll try this. How can you identify a LoRa on Huggingface, other than the size maybe?

Mar 18 '24 13:03 wenrolland

Ok, thanks Charles ! I'll try this. How can you identify a LoRa on Huggingface, other than the size maybe?

You can see that its a lora from the fact that it has a adapter_config.json and adapater_model.safetensors file rather than a config.json and model-x.safetensors file

LoRA stands for Low-Rank Adaptation/Adapter which is where the adapter_model name comes from

Mar 19 '24 18:03 nyxkrage

Noted, thanks Carsten. Much appreciated.

Mar 21 '24 03:03 wenrolland