Upload README.md with huggingface_hub

README.md

@@ -1,3 +1,124 @@
----
-license: mit
----
+---
+license: apache-2.0
+language:
+  - en
+  - zh
+base_model:
+  - Qwen/Qwen3-8B
+  - HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive
+tags:
+  - qwen3.5
+  - uncensored
+  - gguf
+  - ollama
+library_name: gguf
+pipeline_tag: text-generation
+model-index:
+  - name: Qwen3.5-9B-Uncensored
+    results: []
+---
+
+# Qwen3.5-9B-Uncensored (GGUF)
+
+An uncensored GGUF merge of Qwen 3.5 9B, ready for local deployment with Ollama, llama.cpp, or any GGUF-compatible runtime.
+
+## Background
+
+This model is built upon [HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive](https://huggingface.co/HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive). The original base model has the following known issues:
+
+1. **Ollama deployment failure** — The base model cannot be directly deployed via Ollama due to architecture/format incompatibilities. This GGUF version resolves the issue by converting and merging the weights into a single GGUF file that Ollama can load natively.
+2. **No multimodal input support** — The base model's input does not support multimodal data (e.g., images). This is a text-only model. For vision tasks, consider pairing it with a dedicated vision model such as `qwen3vl-8b`.
+
+## Quick Start
+
+### Ollama (Recommended)
+
+1. **Create a Modelfile:**
+
+```
+FROM ./Qwen3.5-9B-Uncensored.gguf
+
+PARAMETER temperature 0.7
+PARAMETER top_p 0.9
+PARAMETER num_ctx 16384
+
+TEMPLATE """{{- if .System }}{{ .System }}{{ end }}
+{{- range .Messages }}
+<|im_start|>{{ .Role }}
+{{ .Content }}<|im_end|>
+{{ end }}<|im_start|>assistant
+"""
+
+SYSTEM "You are a helpful assistant."
+```
+
+2. **Build and run:**
+
+```bash
+# Download the GGUF file
+huggingface-cli download LEONW24/Qwen3.5-9B-Uncensored Qwen3.5-9B-Uncensored.gguf --local-dir .
+
+# Create the Ollama model
+ollama create qwen35-uncensored -f Modelfile
+
+# Run
+ollama run qwen35-uncensored
+```
+
+### llama.cpp
+
+```bash
+# Download
+huggingface-cli download LEONW24/Qwen3.5-9B-Uncensored Qwen3.5-9B-Uncensored.gguf --local-dir .
+
+# Run with llama-cli
+llama-cli -m Qwen3.5-9B-Uncensored.gguf -p "Hello, who are you?" -n 256 -ngl 99
+```
+
+### llama-cpp-python (OpenAI-compatible API)
+
+```bash
+pip install llama-cpp-python[server]
+
+python -m llama_cpp.server \
+  --model Qwen3.5-9B-Uncensored.gguf \
+  --n_gpu_layers 99 \
+  --chat_format chatml
+```
+
+Then call `http://localhost:8000/v1/chat/completions` with any OpenAI-compatible client.
+
+### Python (ctransformers / llama-cpp-python)
+
+```python
+from llama_cpp import Llama
+
+llm = Llama(
+    model_path="Qwen3.5-9B-Uncensored.gguf",
+    n_gpu_layers=-1,  # offload all layers to GPU
+    n_ctx=16384,
+)
+
+output = llm.create_chat_completion(
+    messages=[{"role": "user", "content": "Hello!"}]
+)
+print(output["choices"][0]["message"]["content"])
+```
+
+## Model Details
+
+| Property | Value |
+|----------|-------|
+| **Architecture** | Qwen 3.5 |
+| **Parameters** | ~9B |
+| **Format** | GGUF (single file) |
+| **File size** | ~6.3 GB |
+| **Context window** | Up to 131072 tokens |
+| **Languages** | English, Chinese, multilingual |
+| **License** | Apache 2.0 |
+
+## Notes
+
+- This is an **uncensored** model — it has reduced safety filters compared to the official release. Use responsibly.
+- GGUF format enables efficient CPU + GPU inference without requiring the full PyTorch/transformers stack.
+- For multi-GPU setups with Ollama, set `OLLAMA_NUM_PARALLEL` and adjust `num_gpu` as needed.