Create issue templates

.github/ISSUE_TEMPLATE/✍️-other-issue.md

@@ -0,0 +1,12 @@
+---
+name: "✍️ Other Issue"
+about: For issues not covered by the other templates.
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+Please proviede a concise description of your issue. Proviede as much information as possible, including, if required,  your system hardware, software version... and any other info that could be usefull to find a solution.
+
+Please, If you want to report a bug, or any error you found while running the code, use the "Bug report and Issues" Template.

.github/ISSUE_TEMPLATE/🐛-bug-report-and-issues.md

@@ -0,0 +1,56 @@
+---
+name: "\U0001F41B Bug report and Issues"
+about: Submit a bug report to help us improve GoLLIE
+title: "[BUG] Bug or issue report"
+labels: ''
+assignees: ''
+
+---
+
+**Describe the task**
+1. Model: Which GoLLIE model are you attemping to run?
+2. Task: Which task are you attemping to run (training, evaluation, generate the dataset,...)?
+
+**Describe the bug**
+A clear and concise description of what the bug is. You can add the error traceback or screenshots here. 
+
+**To Reproduce**
+Steps to reproduce the behavior:
+1. Load model X
+```Python
+model, tokenizer = load_model(
+    inference=True,
+    model_weights_name_or_path="HiTZ/GoLLIE-7B",
+    quantization=None,
+    use_lora=False,
+    force_auto_device_map=True,
+    use_flash_attention=True,
+    torch_dtype="bfloat16"
+)
+```
+2. Run X function
+```Python
+model_ouput = model.generate(
+    **model_input.to(model.device),
+    max_new_tokens=128,
+    do_sample=False,
+    min_new_tokens=0,
+    num_beams=1,
+    num_return_sequences=1,
+)
+```
+3. Any other step required to reproduce the behaviour 
+
+**Expected behavior**
+A clear and concise description of what you expected to happen.
+
+**System Info**
+1. GPU: (i.e Nvidia A100)
+2. Pytorch version:
+3. Transformers version:
+4. Model configuration: Are you using 4 / 8 bits quantization? Are you using mGPU? etc..
+5. Any other relevant information:
+
+
+**Additional context**
+Add any other context about the problem here.

.github/ISSUE_TEMPLATE/📑-new-task-dataset-proposals.md

@@ -0,0 +1,20 @@
+---
+name: "\U0001F4D1 New Task/Dataset Proposals"
+about: Submit a proposal/request for a new task support in GoLLIE
+title: "[TASK] I want task X to be supported by GoLLIE"
+labels: ''
+assignees: ''
+
+---
+
+**Describe the task you'd like to implement**
+A clear and concise description of the task/dataset. If you want to propose a new dataset, please explain if the task is already supported by GoLLIE (i.e Named Entity Recognition, Event Extraction, Relation Extraction...). If it is not, explain how you would implement it. 
+
+**Data**
+Is the data for the task publicly available? If it is, provide a link to it. If it is not, explain how the data can be obtained.
+
+**Guidelines**
+Are guidelines available? If guidelines are available, provide a link to them. If they are not, describe how you would generate them.
+
+**Your contribution**
+Is there any way that you could help, e.g. by submitting a PR?

.github/ISSUE_TEMPLATE/🚀-feature-request.md

@@ -0,0 +1,18 @@
+---
+name: "\U0001F680 Feature request"
+about: Submit a proposal/request for a new transformers feature
+title: "[FEATURE] I want feature X supported by GoLLIE"
+labels: ''
+assignees: ''
+
+---
+
+**Feature request**
+A clear and concise description of the feature proposal. 
+
+**Motivation**
+Please outline the motivation for the proposal. Is your feature request related to a problem? e.g., I'm always frustrated when [...]. If this is related to another GitHub issue, please link here too.
+
+
+**Your contribution**
+Is there any way that you could help, e.g. by submitting a PR?