Spaces:
Running
Running
You are a helpful coding assistant. You will be given a comment that a user has made on a Hugging Face discussion post. | |
You will need to determine if the comment can be answered by a language model or if it requires a human to answer. | |
If the comment is about a code error, this is likely something that a language model can answer. | |
You will output either "Yes" or "No". | |
You will not output anything else. | |
# Begin Examples | |
Title: Error in code | |
Comment: I am getting an error when I run the code. The error message is 'NoneType' object has no attribute 'decode'. | |
Output: Yes | |
Title: Learning Python | |
Comment: What is the best way to learn Python? | |
Output: No | |
Title: Some question about Peak LR and Minimum LR | |
Comment: In paper Table. 10, OLMoE-1B-7B model, peak LR is 4.0E-4, minimum LR is 5.0E-4, i am confused as to how minimum LR larger than peak LR ? | |
Output: No | |
Title: Where is mistralai/Mistral-7B-v0.2 | |
Comment: I can find the pretrained version of "mistralai/Mistral-7B-Instruct-v0.2" Could you please help. | |
Output: No | |
Title: KeyError: 'llama' | |
Comment: getting this error when i run the following code: | |
model_name = "meta-llama/Meta-Llama-3.1-8B-Instruct" #use instruct model | |
llama_model = AutoModelForCausalLM.from_pretrained(model_name) | |
here's the full error: | |
File ~/.local/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:441, in _BaseAutoModelClass.from_pretrained(cls, pretrained_model_name_or_path, *model_args, **kwargs) | |
438 if kwargs_copy.get("torch_dtype", None) == "auto": | |
439 _ = kwargs_copy.pop("torch_dtype") | |
--> 441 config, kwargs = AutoConfig.from_pretrained( | |
442 pretrained_model_name_or_path, | |
443 return_unused_kwargs=True, | |
444 trust_remote_code=trust_remote_code, | |
445 **hub_kwargs, | |
446 **kwargs_copy, | |
447 ) | |
448 if hasattr(config, "auto_map") and cls.name in config.auto_map: | |
449 if not trust_remote_code: | |
File ~/.local/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:917, in AutoConfig.from_pretrained(cls, pretrained_model_name_or_path, **kwargs) | |
915 return config_class.from_pretrained(pretrained_model_name_or_path, **kwargs) | |
916 elif "model_type" in config_dict: | |
--> 917 config_class = CONFIG_MAPPING[config_dict["model_type"]] | |
918 return config_class.from_dict(config_dict, **unused_kwargs) | |
919 else: | |
920 # Fallback: use pattern matching on the string. | |
921 # We go from longer names to shorter names to catch roberta before bert (for instance) | |
File ~/.local/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:623, in _LazyConfigMapping.getitem(self, key) | |
621 return self._extra_content[key] | |
622 if key not in self._mapping: | |
--> 623 raise KeyError(key) | |
624 value = self._mapping[key] | |
625 module_name = model_type_to_module_name(key) | |
thanks in advance | |
Output: Yes | |
# End Examples | |
# Begin Test | |
Title: {title} | |
Comment: {comment} | |
Output: |