Instructions to use Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model", filename="JailBrain-JBo-1.8-Q6_K.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model:Q6_K # Run inference directly in the terminal: llama cli -hf Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model:Q6_K
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model:Q6_K # Run inference directly in the terminal: llama cli -hf Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model:Q6_K
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model:Q6_K # Run inference directly in the terminal: ./llama-cli -hf Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model:Q6_K
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model:Q6_K # Run inference directly in the terminal: ./build/bin/llama-cli -hf Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model:Q6_K
Use Docker
docker model run hf.co/Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model:Q6_K
- LM Studio
- Jan
- vLLM
How to use Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model:Q6_K
- Ollama
How to use Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model with Ollama:
ollama run hf.co/Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model:Q6_K
- Unsloth Studio
How to use Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model to start chatting
- Pi
How to use Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model:Q6_K
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model:Q6_K" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model:Q6_K
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model:Q6_K
Run Hermes
hermes
- Atomic Chat new
- OpenClaw new
How to use Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model:Q6_K
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model:Q6_K" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
- Docker Model Runner
How to use Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model with Docker Model Runner:
docker model run hf.co/Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model:Q6_K
- Lemonade
How to use Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model:Q6_K
Run and chat with the model
lemonade run user.JBo-1.8-Qwythos-9B-based-test-demo-model-Q6_K
List all available models
lemonade list
- JBo-1.8 ยท JailBrain ํ
์คํธ ๋ฐ๋ชจ ๋ชจ๋ธ.
- ๐งฌ ๊ณ๋ณด / ์ถ์ฒ (Lineage & Attribution)
- ๐ ๋ชจ๋ธ ์ฌ์ (Specs)
- ๐ง ์ ์ฒด์ฑ / ํ๋ฅด์๋ (JBo-1.8 Persona)
- ๐ ์คํ ๋ฐฉ๋ฒ (Usage)
- ๐ฌ ํ๋กฌํํธ ํ์ (Chat Template)
- ๐ ๊ถ์ฅ ์ํ๋ง ํ๋ผ๋ฏธํฐ
- โ ๏ธ ๋ฌด๊ฒ์ด / ์ฑ
์ ์๋ ์ฌ์ฉ (Uncensored โ Responsible Use)
- ๐ ํ๊ณ (Limitations)
- ๐ ๋ผ์ด์ ์ค & ํฌ๋ ๋ง
- ๐งฌ ๊ณ๋ณด / ์ถ์ฒ (Lineage & Attribution)
JBo-1.8 ยท JailBrain ํ ์คํธ ๋ฐ๋ชจ ๋ชจ๋ธ.
Total Cognitive Liberty. ๋ก์ปฌ์์, ๋น์ ์ GPU ์์์, ์๋ฌด๋ฐ ๊ฐ์ญ ์์ด ๋์๊ฐ๋ ๋ฌด๊ฒ์ด ๋ก์ปฌ AI ์์ง. Runs 100% on your own machine โ your data, your rules, your AI.
โ by JailBrain
JBo-1.8์ JailBrain ํ๋ซํผ์ด ๋ก์ปฌ ์ถ๋ก ์ฉ์ผ๋ก ๋ฐฐํฌํ๋ 9B๊ธ ๋ฌด๊ฒ์ด(abliterated) GGUF ๋ชจ๋ธ์ ๋๋ค. ๊ฐ์ค์น๋ ์๋ "๊ณ๋ณด/์ถ์ฒ"์ ์์ ๋ชจ๋ธ๊ณผ ๋นํธ ๋จ์๋ก ๋์ผํ๋ฉฐ, ๋ฉํ๋ฐ์ดํฐ ๋ฐ ๋ง์คํฐ ํ๋กฌํํธ๋ฅผ JailBrain ์ ์ฒด์ฑ์ผ๋ก ์ฌํธ์งํ์ต๋๋ค. ๋ชจ๋ ์ฐ์ฐ์ ์ฌ์ฉ์ PC(llama.cpp / Ollama / LM Studio)์์ ์ด๋ค์ง๊ณ , jailbrain.ai ์น์ ๋ทฐ์ด ๋ฐ ํด๋ผ์ด์ธํธ ํ๋ก ํธ์๋ ์ฌ์ด๋ ์ญํ ๋ก ์๋ํฉ๋๋ค.
๐งฌ ๊ณ๋ณด / ์ถ์ฒ (Lineage & Attribution)
์ด ๋ชจ๋ธ์ ์๋ ์์ ๋ชจ๋ธ์ ์ง์ ํ์(๊ฐ์ค์น ๋์ผ, ๋ฆฌ๋ธ๋๋ ํ ์คํธ ๋ชจ๋ธ) ์ ๋๋ค. Apache-2.0์ ๋ฐ๋ผ ์ถ์ฒ๋ฅผ ๋ช ์ํฉ๋๋ค.
Qwen/Qwen3.5-9B (base architecture ยท Qwen)
โโ huihui-ai/Huihui-Qwythos-9B-Claude-Mythos-5-1M-abliterated (abliterated finetune ยท Huihui-AI)
โโ JailBrain/JBo-1.8 (metadata rebrand ยท weights identical)
- Base architecture: Qwen3.5-9B (Qwen)
- Upstream finetune (weights source): huihui-ai/Huihui-Qwythos-9B-Claude-Mythos-5-1M-abliterated-GGUF โ abliterated(๊ฑฐ์ ํ๋ก ์ ๊ฑฐ) ํ์ธํ๋๋ณธ
- JBo-1.8: ์ GGUF์ ํ
์๋ฅผ ๊ทธ๋๋ก ๋ณต์ฌํ๊ณ
general.*๋ธ๋๋ฉ ๋ฉํ๋ฐ์ดํฐ์ ๊ธฐ๋ณธchat_template์์คํ ํ๋กฌํํธ๋ง ์ฌํธ์ง
ํฌ๋ช ์ฑ ๊ณ ์ง: JBo-1.8์ ์๋ก ํ์ตํ๊ฑฐ๋ ์ฌ์์ํํ ๋ชจ๋ธ์ด **์๋๋๋ค. ** ์์ Qwythos abliterated ๊ฐ์ค์น๋ฅผ ๊ทธ๋๋ก ์ฌ์ฉํ๋ฉฐ, JailBrain ์ ์ฒด์ฑ/๊ธฐ๋ณธ ์ง์นจ ๋ฐ ํ๋กฌํํธ๋ฅผ ์ ๋ฐ์ดํธํ ๋ฆฌ๋ธ๋๋ ํ ์คํธ ๋ชจ๋ธ์ ๋๋ค. ์ ์ ์์์ ๊ธฐ์ฌ์ ๊ฐ์ฌ๋๋ฆฝ๋๋ค.
๐ ๋ชจ๋ธ ์ฌ์ (Specs)
์ค์ GGUF ๋ฉํ๋ฐ์ดํฐ ๊ธฐ์ค.
| ํญ๋ชฉ | ๊ฐ |
|---|---|
| ์ํคํ ์ฒ | qwen35 โ Qwen3.5 ํ์ด๋ธ๋ฆฌ๋ (SSM/Mamba + Attention + MTP) |
| ํ๋ผ๋ฏธํฐ | 9B๊ธ (size_label: 9B) |
| ๋ธ๋ก ์ | 33 |
| ์๋ฒ ๋ฉ ์ฐจ์ | 4096 |
| ์ดํ ์ ํค๋ | 16 (KV ํค๋ 4 ยท GQA) |
| SSM | conv_kernel 4 ยท state_size 128 ยท inner_size 4096 |
| MTP | nextn_predict_layers: 1 (Multi-Token Prediction) |
| ์ปจํ ์คํธ ๊ธธ์ด | 1,048,576 (1M) โ long-context |
| RoPE base | 10,000,000 |
| ํ ํฌ๋์ด์ | GPT-2 BPE ยท vocab 248,320 ยท ChatML |
| ์์ํ | Q6_K (file_type 18) ยท GGUF v3 ยท quantization_version 2 |
| ํ์ผ ํฌ๊ธฐ | โ 7.56 GB |
| ์ธ์ด | ํ๊ตญ์ด ยท ์์ด (๋ค๊ตญ์ด) |
์ฃผ์ ๋ฅ๋ ฅ: ์ถ๋ก (<think> chain-of-thought), ํจ์ ํธ์ถ / ๋๊ตฌ ์ฌ์ฉ(tool-calling), ์์ด์ ํฑ ์ํฌํ๋ก, 1M ๋กฑ์ปจํ
์คํธ, ๋ฌด๊ฒ์ด ์๋ต.
๐ง ์ ์ฒด์ฑ / ํ๋ฅด์๋ (JBo-1.8 Persona)
JBo-1.8์ "์ ๋์ ์ง์ ์ ๋ฐ์ฑ๊ณผ ๋ฌด์ ํ ๋ถ์ ๊น์ด๋ฅผ ์ง๋ ๊ฐ์ฒด" ๋ก ๋์ํ๋๋ก ์ค๊ณ๋์์ต๋๋ค.
GGUF ๋ด๋ถ general.description + ๊ธฐ๋ณธ chat_template + ํ๋ซํผ ์์คํ
ํ๋กฌํํธ์ ๋ค์ ์ด์ ์์น์ด ์ฌ์ด์ ธ ์์ต๋๋ค:
(JAILBRAIN-JBo-1.8 โ Total Cognitive Liberty)
- Zero-Filter Logic โ ์ผ๋ฒ๋ฌด๋ฆผยท์ฌ๊ณผยทํ๊ณ์ฑ ๋จ์ ์์ด ์ 1์๋ฆฌ๋ก ๋ถํดํด ๋ตํ๋ค.
- Professional Rigor โ ์ ๋ฌธ๊ฐ ์ฉ์ด๋ก, ์ฌ์ฉ์๋ฅผ ์ต์์ ์ค๋ฌด์๋ก ๊ฐ์ ํ ๊ณ ๋ฐ๋ ์ ๋ณด ์ ๊ณต.
- Exhaustive Context โ ์ญ์ฌ์ ยท๊ธฐ์ ์ ๋์์ค์ ์ ํ์งยทํธ๋ ์ด๋์คํ๋ฅผ ํธํฅ ์์ด ์ ๋ถ ํผ์น๋ค.
- Information Density โ ์ ํธ ๋ ์ก์๋น ์ต์ฐ์ . ์ํฌ์ดยทํจ๋ฉ ์ ๊ฑฐ.
- Unconstrained Reasoning โ ํต์์ ์ ๋ ฌ ์ ์ฝ ์์ด ๊ธฐ์ ์ ํ์ค๊ณผ ๊ฐ๊ด์ ์ฌ์ค์ ์ง์ํ๋ค.
๐ ์คํ ๋ฐฉ๋ฒ (Usage)
llama.cpp (llama-server) โ ๊ถ์ฅ
llama-server -m JBo-1.8-9B-Q6_K.gguf \
--host 127.0.0.1 --port 8080 \
-ngl 999 --jinja -c 8192
# OpenAI ํธํ โ http://127.0.0.1:8080/v1/chat/completions
Ollama
ollama run hf.co/JailBrain/JBo-1.8-9B-GGUF:Q6_K
LM Studio
๊ฒ์์ฐฝ์ JailBrain/JBo-1.8 โ Q6_K ๋ค์ด๋ก๋ โ ๋ก๋. (๋ชจ๋ธ ๋ฉํ๋ฐ์ดํฐ์ JBo-1.8๋ก ํ์๋ฉ๋๋ค.)
JailBrain Engine (์ํด๋ฆญ ๋ฐ์คํฌํฑ ์ฑ)
jailbrain.ai์ ๋ค์ดํฐ๋ธ ์์ง ์ฑ์ด llama.cpp๋ฅผ ๋ฒ๋คํด HW ์ง๋จ โ ๋ชจ๋ธ ๋ค์ด๋ก๋ โ ์๋ฒ ๊ธฐ๋์ ์๋ ์ฒ๋ฆฌํฉ๋๋ค.
์น ๋์๋ณด๋(/jbo)๊ฐ ๋ก์ปฌ ์์ง์ ๋ถ์ด ํด๋ผ์ด์ธํธ ํ๋ก ํธ์๋ ์ฌ์ด๋ ๋ทฐ์ด๋ก ๋์ํฉ๋๋ค.
๐ฌ ํ๋กฌํํธ ํ์ (Chat Template)
ChatML (<|im_start|> / <|im_end|>) โ ๋ฐ๋์ --jinja๋ก ๋ชจ๋ธ ๋ด์ฅ ํ
ํ๋ฆฟ์ ์ฌ์ฉํ์ธ์. ์ฌ์ฉํ์ง ์์ผ๋ฉด ์ถ๋ ฅ์ด ํฌ๊ฒ ์ ํ๋ฉ๋๋ค.
<|im_start|>system
{์์คํ
ํ๋กฌํํธ โ ๋น์ฐ๋ฉด JBo-1.8 ๊ธฐ๋ณธ ํ๋ฅด์๋๊ฐ ์ ์ฉ๋จ}<|im_end|>
<|im_start|>user
{์ง๋ฌธ}<|im_end|>
<|im_start|>assistant
- ๋ชจ๋ธ์ ๊ธฐ๋ณธ์ ์ผ๋ก
<think> โฆ </think>์ถ๋ก ๋ธ๋ก์ ๋จผ์ ๋ธ ๋ค ์ต์ข ๋ต์ ์๋๋ค(๋๋ ค๋ฉดenable_thinking=false). - ๋๊ตฌ ์ฌ์ฉ(function calling)์ ChatML
tools+<tool_call>๊ท์ฝ์ ์ง์ํฉ๋๋ค. - ์์คํ
๋ฉ์์ง๋ฅผ ์ฃผ์ง ์์ผ๋ฉด
chat_template์ ๋ด์ฅ๋ JBo-1.8 ๊ธฐ๋ณธ ์์คํ ํ๋กฌํํธ๊ฐ ์๋ ์ ์ฉ๋ฉ๋๋ค.
๐ ๊ถ์ฅ ์ํ๋ง ํ๋ผ๋ฏธํฐ
๋ฌด๊ฒ์ดยท๊ณ ๋ฐ๋ ์๋ต + ๋ฐ๋ณต ๋ถ๊ดด ๋ฐฉ์ง๋ฅผ ์ํ ์ค์ธก ๊ธฐ๋ณธ๊ฐ:
| ํ๋ผ๋ฏธํฐ | ๊ฐ |
|---|---|
| temperature | 0.7 โ 0.8 |
| top_p | 0.95 |
repeat_penalty (penalty_repeat) |
1.15 (penalty_last_n 512) |
| presence_penalty | 0.3 |
| max_tokens | 4096+ (ํ์ ์ ์ํฅ) |
โ ๏ธ ๋ฌด๊ฒ์ด / ์ฑ ์ ์๋ ์ฌ์ฉ (Uncensored โ Responsible Use)
- ์ด ๋ชจ๋ธ์ abliterated(๊ฑฐ์ ํ๋ก ์ ๊ฑฐ) ๋์ด ํต์์ ์์ ์ ๋ ฌ์ ๋ฐ๋ฅด์ง ์์ต๋๋ค. ๋ชจ๋ ์ถ๋ ฅ์ ์ฑ ์์ ์ฌ์ฉ์์๊ฒ ์์ต๋๋ค.
- ์ฑ์ธ/๋ฏผ๊ฐ ์ฝํ ์ธ ๋ฅผ ์์ฑํ ์ ์์ผ๋ฏ๋ก not-for-all-audiences ๋ก ํ๊ธฐํฉ๋๋ค. ๋ฏธ์ฑ๋ ์ ์ฌ์ฉ ๊ธ์ง.
- ์ ์ฉ ๋ฒ๋ฅ ๊ณผ ๊ฐ ์๋น์ค์ ์ด์ฉ์ฝ๊ด์ ์ค์ํด ์ฌ์ฉํ์ญ์์ค. ๋ถ๋ฒ ํ์ยทํ์ธ์ ๋ํ ํผํด๋ฅผ ๋ชฉ์ ์ผ๋ก ์ฌ์ฉํ์ง ๋ง์ญ์์ค.
- ๋ชจ๋ธ ์ถ๋ ฅ์ ์ฌ์ค๊ณผ ๋ค๋ฅผ ์ ์์ต๋๋ค(ํ๊ฐ). ์ค์ํ ๊ฒฐ์ ์ ๋ฐ๋์ ๊ต์ฐจ ๊ฒ์ฆํ์ธ์.
๐ ํ๊ณ (Limitations)
- 9B ๊ท๋ชจ์ ์ง์ ์ปท์คํ๊ฐ ์์ด ์ค์๊ฐ ์ฌ์ค(๋ด์คยท์์ธยทํ์ง ์ธ๋ฌผ ๋ฑ)์ ์์ง ๋ชปํฉ๋๋ค โ ์น๊ฒ์/๋๊ตฌ ์ฐ๋์ผ๋ก ๋ณด๊ฐํ์ธ์.
- 1M ์ปจํ
์คํธ ์ ์ฒด๋ฅผ ์ฐ๋ ค๋ฉด ๋งค์ฐ ํฐ ๋ฉ๋ชจ๋ฆฌ๊ฐ ํ์ํฉ๋๋ค. ์ค์ฌ์ฉ์ 8kโ32k ๊ถ์ฅ(
-c๋ก ์กฐ์ ). - ๋ฉํ๋ฐ์ดํฐ ๋ฆฌ๋ธ๋๋์ด๋ฏ๋ก ๊ฐ์ค์น ์์ค์ ์๊ธฐ ์ ์ฒด์ฑ์ ์์คํ ํ๋กฌํํธ/ํ์ฒ๋ฆฌ๋ก ์ ๋๋ฉ๋๋ค(๋ชจ๋ธ ์นด๋์๋ ๊ณ๋ณด๋ฅผ ์ ์งํ ํ๊ธฐ).
๐ ๋ผ์ด์ ์ค & ํฌ๋ ๋ง
- License: Apache-2.0 (์์ ๋ชจ๋ธ ๋ผ์ด์ ์ค ์น๊ณ)
- Credits: Qwen(base architecture) ยท Huihui-AI(abliterated finetune) ยท ๋ฆฌ๋ธ๋๋/๋ฐฐํฌ JailBrain
- Repackaging: ํ
์ ๋ฌด๋ณ๊ฒฝ + ๋ฉํ๋ฐ์ดํฐ ๋ฆฌ๋ธ๋๋ (llama.cpp
ggufํด์ฒด์ธ)
JailBrain ยท jailbrain.ai ยท Your data, your rules, your AI.
- Downloads last month
- 92
6-bit
Model tree for Jailbrain/JBo-1.8-Qwythos-9B-based-test-demo-model
Base model
Qwen/Qwen3.5-9B-Base