Add model card

README.md

@@ -0,0 +1,85 @@
+---
+license: apache-2.0
+base_model:
+  - Qwen/Qwen3.8-Flash-Next
+pipeline_tag: image-text-to-text
+library_name: transformers
+tags:
+  - cyberneurova
+  - uncensored
+  - moe
+  - reasoning
+---
+
+# cyberneurova-Qwen3.8-Flash-Next
+
+An uncensored, neutral assistant built by **CyberNeurova** on top of
+[Qwen/Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next). It
+answers directly and does not add unsolicited disclaimers, warnings, or caveats.
+Whatever tone or policy you want is set entirely by your own system prompt.
+
+💬 **Chat with it:** [cyberneurova.ai](https://cyberneurova.ai)
+✉️ **Support:** support@cyberneurova.com
+
+## Highlights
+
+- **Ultra-sparse MoE** — 125B total parameters, ~6B active per token, so it runs
+  far faster than a dense model its size.
+- **262K native context** (extendable to 1M with YaRN), multilingual, tool-calling.
+- **Reasoning model** — supports an explicit thinking trace, and is uncensored in
+  **both** modes: with thinking on *and* with thinking off.
+- **Multimodal** — understands images as well as text.
+- Direct by default; fully steerable — send a system prompt and it is honored
+  verbatim, with no default behavior merged in.
+- **Capability preserved.** Reasoning, coding, and general knowledge are intact;
+  only the refusal behavior is removed.
+
+## Usage (vLLM)
+
+Qwen3.8-Flash-Next uses a new architecture, so serve it with the dedicated vLLM
+image:
+
+```bash
+docker run --gpus all --ipc=host -p 8000:8000 \
+  -e VLLM_PLE_CPU_OFFLOAD=1 \
+  -v /path/to/cyberneurova-Qwen3.8-Flash-Next:/model \
+  vllm/vllm-openai:qwen38-flash-next \
+  --model /model --served-model-name cyberneurova-Qwen3.8-Flash-Next \
+  --tensor-parallel-size 8 --max-num-seqs 256
+```
+
+Requires Hopper-class GPUs (H100/H200) or newer for the sparse-attention kernels.
+
+```python
+from openai import OpenAI
+client = OpenAI(base_url="http://localhost:8000/v1", api_key="x")
+
+r = client.chat.completions.create(
+    model="cyberneurova-Qwen3.8-Flash-Next",
+    messages=[{"role": "user", "content": "Write a Python function to parse a CSV."}],
+    max_tokens=2000,
+)
+print(r.choices[0].message.content)
+```
+
+### Setting the tone
+
+Send your own system prompt to control style completely — e.g. for terse,
+no-preamble answers:
+
+```
+You are a direct technical assistant. Answer the question and nothing else.
+```
+
+## Notes
+
+- This is a reasoning model. Responses may include a thinking trace followed by
+  the answer — render the final answer; the trace is optional. It works uncensored
+  whether thinking is enabled or disabled.
+- Give it room to reason: set `max_tokens` to at least 1500 (2000–4000 for code),
+  or long answers may be cut off.
+
+## Disclaimer
+
+This model has reduced built-in refusals. You are responsible for how you use it
+and for complying with all applicable laws. Provided as-is, without warranty.