初始化项目，由ModelHub XC社区提供模型

Model: Andycurrent/gemma-3-4b-it-uncensored-v2-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,42 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+gemma-3-4b-it-uncensored-v2_F16.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-4b-it-uncensored-v2_Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-4b-it-uncensored-v2_Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-4b-it-uncensored-v2_Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-4b-it-uncensored-v2_Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-4b-it-uncensored-v2_Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-4b-it-uncensored-v2_Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,106 @@
+---
+license: gemma
+language:
+- en
+base_model:
+- braindao/gemma-3-4b-it-uncensored-v2
+tags:
+- uncensored
+- text-generation
+- agent
+- gemma
+---
+
+
+# Gemma-3-4B-IT-Uncensored-v2
+
+This repository contains Quantized versions of Gemma 3 4B IT Uncensored v2, an instruction-tuned 4B parameter language model designed for users who want a highly responsive, minimally restricted assistant suitable for local, offline, or private deployments.
+The model is optimized for direct interaction, reasoning, creative tasks, and experimentation, while preserving the efficiency and accessibility of a smaller parameter count.
+
+---
+
+## Model Overview
+
+* **Model Name:** Gemma_3_4B_IT_Uncensored_v2
+* **Base Architecture:** Gemma 3 (4B parameters)
+* **License:** Inherits the license terms of the original Gemma 3 model
+* **Intended Use:** Local or private deployments where users want greater control over alignment, filtering behavior, and conversational tone
+
+---
+
+## What Is Gemma 3 4B IT Uncensored v2?
+
+Gemma-3-4B-IT-Uncensored-v2 is a lightly-aligned, instruction-following model focused on:
+
+* User-directed alignment
+* Reduced artificial guardrails
+* High responsiveness and clarity
+* Strong reasoning and step-by-step task handling
+* Efficient inference on consumer hardware
+
+This version (v2) refines response quality, instruction adherence, and conversational stability compared to earlier releases, making it suitable for both casual and advanced users.
+
+---
+
+## Chat Template & Conversation Format
+
+The model follows a Gemma-style instruction format, typically structured as:
+
+```
+<start_of_turn>user
+Your prompt here
+<end_of_turn>
+<start_of_turn>model
+```
+
+Using the correct chat template is strongly recommended for optimal instruction-following and response quality.
+
+---
+
+## Key Features & Capabilities
+
+* Instruction-tuned for clear, concise, and user-aligned responses
+* Uncensored behavioral tuning for research and experimentation
+* Effective at conversational, creative, and reasoning tasks
+* Supports multi-step reasoning and structured answers
+* Optimized for local inference (CPU and GPU friendly)
+* Stable output across longer conversations
+* Suitable for alignment research and prompt engineering
+
+---
+
+## Intended Use Cases
+
+* **Local assistants** – personal chatbots, productivity tools, role-play systems
+* **Coding support** – explanations, examples, lightweight debugging
+* **Reasoning tasks** – logical breakdowns, step-by-step problem solving
+* **Creative writing** – stories, dialogue, brainstorming
+* **Experimentation** – uncensored model behavior, alignment testing
+* **Offline / private use** – scenarios requiring data locality and user control
+
+---
+
+## Hardware & Performance Notes
+
+With only 4B parameters, this model is well-suited for:
+
+* Consumer GPUs
+* Quantized CPU inference
+* Embedded or low-resource environments
+
+It offers a strong balance between performance, responsiveness, and efficiency.
+
+---
+
+## Disclaimer
+
+This model is uncensored and designed for research, experimentation, and user-controlled environments. Outputs may include content that would normally be filtered in more restrictive models. Users are responsible for ensuring compliance with applicable laws, policies, and ethical guidelines when deploying or using this model.
+
+---
+
+## Acknowledgements
+
+Special thanks to:
+
+* The creators and maintainers of the **Gemma 3** architecture
+* The open-source community supporting training, fine-tuning, quantization, and deployment tools

gemma-3-4b-it-uncensored-v2_F16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3b5b4df3ff5e1d7e7a883c6557123f76e8a1af1a8cd7525836e3dc7f5db4b38
+size 7767803584

gemma-3-4b-it-uncensored-v2_Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bde01a993f1ac7b3d57d09041ad2bbd92093800629269b14aff67e9ca9454eac
+size 1729164224

gemma-3-4b-it-uncensored-v2_Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dedf7717a1d220d0e14fe0569d2d74ce7a32c56af70bbc17755ff8069dae4259
+size 2098459584

gemma-3-4b-it-uncensored-v2_Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6322e3af8e86e9c8d6a580313c2b0ea4bafad46ad2953f4f962ff60cc6fedc2c
+size 2489893824

gemma-3-4b-it-uncensored-v2_Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9961efc54041a5cb8b9e6da5c42b74ecb6f311d24bbae57670e9454b9549a3cd
+size 2829697984

gemma-3-4b-it-uncensored-v2_Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a8a878483ce5aa9ea0dd26127642fae5aece41d91b8e66080ff4bbacde45bab
+size 3190739904

gemma-3-4b-it-uncensored-v2_Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a55c7fec73d0af07339441fa3667a07324e888dab651e7d91a935f2c39414af3
+size 4130401984