Update issue templates

.github/ISSUE_TEMPLATE/bug_report.md

@@ -1,41 +0,0 @@
----
-name: 🐛 Bug report
-about: Create a report to help us improve
-title: "[Bug]"
-labels: bug
-assignees: ''
-
----
-
-**Describe the bug**
-A clear and concise description of what the bug is.  Please fill out the following sections and provide a minimal reproduction script so that we can provide a solution as quickly as possible!
-
-1. **Environment Setup:**
-   - OS: [e.g., Ubuntu 20.04]
-   - Python Version: [e.g., 3.8.10]
-   - Frameworks/Libraries: please paste output of `pip freeze` here
-   - `colab` / script - was this run in `colab` or as a script?
-
-2. **Dataset Details:**
-   - Dataset Name: 
-   - Data Preprocessing Steps: [e.g., tokenization, formatting funcs, data collators, etc.]
-
-3. **Model Details:**
-   - Model ID:
-   - Model Configuration: [e.g., lora params, quantization, etc.]
-
-4. **Training Configuration:**
-   - Trainer Args: `SFTConfig`, `GRPOConfig`
-
-5. **Reproduction Steps:**
-   - Minimal script to reproduce error
-   - If using a `colab`, please provide the link to the notebook and describe any changes made.
-
-6. **Expected Behavior:**
-   
-7. **Actual Behavior:**
-   - [e.g., Description of the error, unexpected results, or performance issues encountered]
-   - [e.g., Error messages or logs]
-
-8. **Additional notes:**
-   - Any additional information that might help us reproduce the bug.

.github/ISSUE_TEMPLATE/documentation.md

@@ -1,34 +0,0 @@
----
-name: 📚 Documentation
-about: Report incorrect or needed docs for https://docs.unsloth.ai/
-title: "[Docs]"
-labels: documentation
-assignees: ''
-
----
-
-- [ ] Report incorrect documentation
-- [ ] Report needed documentation
-
-## Report incorrect documentation
-
-**Location of incorrect documentation -- provide links and line numbers if possible.**
-
-**Describe the problems or issues found in the documentation**
-
-**Steps taken to verify documentation is incorrect**
-
-**Suggested fix**
-
----
-
-## Report needed documentation
-
-**What's missing?**
-
-
-**Describe the documentation you'd like -- how can we make using `unsloth` easier?**
-
-
-**Help us understand how we can make finding the needed info easier!**
-List any steps you have taken, e.g. searching the repo, reading the docs, etc.  

.github/ISSUE_TEMPLATE/feature_request.md

@@ -1,14 +1,34 @@
 ---
-name: 🚀 Feature request
-about: "Suggest an idea: new model, algorithm or feature etc."
+name: "\U0001F680 Feature request"
+about: New features, model support, ideas
 title: "[Feature]"
-labels: "feature request"
+labels: feature request
 assignees: ''
 
 ---
 
-**What features would you like to see? Is it related to a problem or a new feature you'd like to see? Please describe.**
-What we can do to improve `unsloth`?
-
-**Additional context**
-Feel free to add any other context, links, or screenshots here.
+1. For new models, have you tried:
+```python
+from unsloth import FastModel
+model, tokenizer = FastModel.from_pretrained(
+    "microsoft/Phi-4-multimodal-instruct",
+    trust_remote_code = True,
+)
+```
+If that doesn't work, try using the exact `AutoModel` class:
+```python
+from transformers import WhisperForConditionalGeneration
+model, tokenizer = FastModel.from_pretrained(
+    model_name = "unsloth/whisper-large-v3",
+    auto_model = WhisperForConditionalGeneration,
+)
+```
+For Sequence Classification / other `AutoModel` classes:
+```python
+from transformers import AutoModelForSequenceClassification
+model, tokenizer = FastModel.from_pretrained(
+    model_name = "unsloth/whisper-large-v3",
+    auto_model = AutoModelForSequenceClassification,
+)
+```
+2. Otherwise, ask away!

.github/ISSUE_TEMPLATE/question.md

@@ -1,10 +0,0 @@
----
-name: ❓ Submit question
-about: Ask a general question about unsloth
-title: "[Question]"
-labels: "question"
-assignees: ''
-
----
-
-**What is your question?**

.github/ISSUE_TEMPLATE/❓-other.md

@@ -0,0 +1,10 @@
+---
+name: "❓ Other"
+about: Other
+title: "[Question]"
+labels: ''
+assignees: ''
+
+---
+
+Be specific. If you need urgent help, head to https://discord.com/invite/unsloth for help. Have you tried https://docs.unsloth.ai/basics/errors-troubleshooting or https://github.com/unslothai/unsloth/wiki ?

.github/ISSUE_TEMPLATE/🐛-bug.md

@@ -0,0 +1,21 @@
+---
+name: "\U0001F41B Bug"
+about: For bugs
+title: "[Bug]"
+labels: bug
+assignees: ''
+
+---
+
+1. **Environment**
+   - `Colab`, `Kaggle`, local / cloud machine
+   - Number GPUs used, GPU type, VRAM amount
+   - Copy paste Unsloth printout with sloth emoji
+   - Which notebook are you using?
+
+2. **Code to reproduce**
+   - Which trainer - `SFTTrainer, GRPOTrainer` etc
+   - Exact code to repro. **Remove Hugging Face token!**
+   - Expected behavior
+
+For quick replies, head to https://discord.com/invite/unsloth and ask away! have you tried https://github.com/unslothai/unsloth/wiki or https://docs.unsloth.ai/basics/errors-troubleshooting?