初始化项目，由ModelHub XC社区提供模型

Model: lunahr/gemma-3-4b-abliterated
Source: Original Platform

README.md

@@ -0,0 +1,65 @@
+---
+base_model:
+- gghfez/gemma-3-4b-novision
+license: gemma
+pipeline_tag: text-generation
+library_name: transformers
+---
+
+# Gemma 3 4B (abliterated text-only) model card
+This is an abliterated text-only version of [google/gemma-3-4b-it](https://huggingface.co/google/gemma-3-4b-it), created using Baukit.
+
+The vision encoders were removed by [gghf](https://huggingface.co/gghfez). Please note that this model may exhibit a reduced performance.
+
+## Model Description
+
+- **Original Model**: The original Gemma-3-4b-it is a multimodal model released by Google that can process both text and images
+- **This Version**: This version has been modified to use the same architecture as the text-only 1b model, with the vision components removed
+- **Parameters**: 4 billion parameters
+- **Conversion Process**: Vision-related components were stripped while maintaining the text generation capabilities
+
+## Usage
+
+You can load and use this model the same way you would use the text-only [google/gemma-3-1b-it](https://huggingface.co/google/gemma-3-1b-it) version:
+
+```python
+from transformers import AutoTokenizer, BitsAndBytesConfig, Gemma3ForCausalLM
+import torch
+
+model_id = "gghfez/gemma-3-4b-novision"
+
+quantization_config = BitsAndBytesConfig(load_in_8bit=True)
+
+model = Gemma3ForCausalLM.from_pretrained(
+    model_id, quantization_config=quantization_config
+).eval()
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+messages = [
+    [
+        {
+            "role": "system",
+            "content": [{"type": "text", "text": "You are a helpful assistant."},]
+        },
+        {
+            "role": "user",
+            "content": [{"type": "text", "text": "Write a poem on Hugging Face, the company"},]
+        },
+    ],
+]
+inputs = tokenizer.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    tokenize=True,
+    return_dict=True,
+    return_tensors="pt",
+).to(model.device).to(torch.bfloat16)
+
+
+with torch.inference_mode():
+    outputs = model.generate(**inputs, max_new_tokens=64)
+
+outputs = tokenizer.batch_decode(outputs)
+```
+