Text Generation
Transformers
Safetensors
GGUF
English
qwen3_5
image-text-to-text
radha
instruction-tuning
lora
structured-output
conversational
Instructions to use Advisio/Radha-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Advisio/Radha-9B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Advisio/Radha-9B") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Advisio/Radha-9B") model = AutoModelForMultimodalLM.from_pretrained("Advisio/Radha-9B", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Advisio/Radha-9B 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 Advisio/Radha-9B:Q4_K_M # Run inference directly in the terminal: llama cli -hf Advisio/Radha-9B:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Advisio/Radha-9B:Q4_K_M # Run inference directly in the terminal: llama cli -hf Advisio/Radha-9B:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf Advisio/Radha-9B:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf Advisio/Radha-9B:Q4_K_M
Use Docker
docker model run hf.co/Advisio/Radha-9B:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use Advisio/Radha-9B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Advisio/Radha-9B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Advisio/Radha-9B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Advisio/Radha-9B:Q4_K_M
- SGLang
How to use Advisio/Radha-9B with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Advisio/Radha-9B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Advisio/Radha-9B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Advisio/Radha-9B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Advisio/Radha-9B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Ollama
How to use Advisio/Radha-9B with Ollama:
ollama run hf.co/Advisio/Radha-9B:Q4_K_M
- Unsloth Desktop
- Pi
How to use Advisio/Radha-9B with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Advisio/Radha-9B:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "Advisio/Radha-9B:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use Advisio/Radha-9B with Docker Model Runner:
docker model run hf.co/Advisio/Radha-9B:Q4_K_M
- Lemonade
How to use Advisio/Radha-9B with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Advisio/Radha-9B:Q4_K_M
Run and chat with the model
lemonade run user.Radha-9B-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use Advisio/Radha-9B with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Advisio/Radha-9B:Q4_K_M
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://127.0.0.1:9931/v1 hermes config set model.default Advisio/Radha-9B:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Advisio/Radha-9B with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Advisio/Radha-9B:Q4_K_M
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://127.0.0.1:9931/v1 \ --custom-model-id "Advisio/Radha-9B:Q4_K_M" \ --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"
|
Download README.md from Advisio/Radha-9B: direct link, hf CLI and curl.
- Browser
- Download file 4.11 kB
-
https://huggingface.co/Advisio/Radha-9B/resolve/main/README.md
- Command line
-
hf download hf://Advisio/Radha-9B/README.md
-
curl -L -o README.md https://huggingface.co/Advisio/Radha-9B/resolve/main/README.md
4.11 kB
| license: apache-2.0 | |
| base_model: Qwen/Qwen3.5-9B | |
| base_model_relation: finetune | |
| library_name: transformers | |
| pipeline_tag: text-generation | |
| language: | |
| - en | |
| tags: | |
| - radha | |
| - instruction-tuning | |
| - lora | |
| - structured-output | |
| - gguf | |
| - text-generation | |
| # Radha-9B | |
| **Radha** is an instruction-tuned assistant specialized for structured tasks, | |
| grounded extraction, and format-faithful output. It is a fine-tune of | |
| [`Qwen/Qwen3.5-9B`](https://huggingface.co/Qwen/Qwen3.5-9B) (Apache-2.0) and | |
| keeps that base model's two operating modes: a **thinking** mode for reasoning | |
| and a **non-thinking** mode for fast, direct answers. | |
| > **Provenance (read this):** Radha is **fine-tuned from Qwen/Qwen3.5-9B**. It is | |
| > a derivative work, distributed under Apache-2.0, with attribution in the | |
| > `NOTICE` file. The base architecture is Qwen3.5; we did not train a model from | |
| > scratch. We believe in honest provenance — this card is the authoritative | |
| > source on Radha's lineage. | |
| ## What's different from the base | |
| - **Sharpened structured-task behavior** across 10 task families: JSON | |
| classification, grounded extraction, table aggregation, multi-step arithmetic, | |
| summarization with action items, normalization/transformation, Python | |
| bug-fixing, constraint ordering, format-adherence under adversarial prompts, | |
| and grounded answerable/unanswerable QA. | |
| - **Reasoning preserved.** The fine-tune masks the reasoning span from the | |
| training loss, so Radha's thinking mode is not degraded — only its direct-answer | |
| behavior is specialized. | |
| - **Radha persona.** Identifies as "Radha." When asked about its internal | |
| architecture it declines in-conversation; lineage is disclosed here, openly. | |
| ## Training | |
| - **Method:** bf16 LoRA (rank 16, α 32) via [Unsloth](https://github.com/unslothai/unsloth). | |
| - **Data:** a deterministic, stratified 300K-example subset (30K per task family) | |
| of the `synthetic-distillation-v3` corpus, plus a small identity set. All | |
| examples are short (max ≈ 293 tokens). The corpus is fully synthetic and | |
| template-validated (schema + semantic e2e checks). | |
| - **Hardware:** single NVIDIA A100 80GB (RunPod). | |
| - **Modes:** trained with completion-only loss; reasoning span masked to preserve | |
| thinking mode. | |
| ## Evaluation | |
| Radha was checked against the training task families during development. Those | |
| checks are in-distribution validations on synthetic, templated data — useful for | |
| catching regressions, but **not independent benchmarks** and not published here | |
| as capability claims. Evaluate Radha on your own data before relying on it. | |
| ## Usage | |
| ### Transformers (PyTorch) | |
| ```python | |
| from transformers import AutoModelForCausalLM, AutoTokenizer | |
| tok = AutoTokenizer.from_pretrained("Advisio/Radha-9B") | |
| model = AutoModelForCausalLM.from_pretrained("Advisio/Radha-9B", torch_dtype="bfloat16", device_map="auto") | |
| messages = [{"role": "user", "content": "Summarize: ..."}] | |
| # Direct answers (fast): enable_thinking=False ; Reasoning: enable_thinking=True | |
| prompt = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=False) | |
| out = model.generate(**tok(prompt, return_tensors="pt").to(model.device), max_new_tokens=512) | |
| print(tok.decode(out[0], skip_special_tokens=True)) | |
| ``` | |
| ### GGUF (llama.cpp / Ollama, local) | |
| Quantized builds are provided: `radha-9b-Q4_K_M.gguf` (recommended, ~5.6GB) and | |
| `radha-9b-Q5_K_M.gguf`. | |
| ```bash | |
| # llama.cpp | |
| llama-cli -m radha-9b-Q4_K_M.gguf -p "Your prompt" -no-cnv | |
| # Ollama | |
| ollama create radha -f Modelfile # FROM ./radha-9b-Q4_K_M.gguf | |
| ollama run radha | |
| ``` | |
| ## Limitations | |
| - Training data is **synthetic and template-driven**; Radha is strongest on the | |
| task shapes it was tuned on and is not a substitute for domain-specific tuning. | |
| - Inherits the base model's general knowledge, biases, and failure modes. | |
| - Not safety-aligned beyond the base model's alignment; add your own guardrails | |
| for production. | |
| ## License & attribution | |
| Apache-2.0. Radha is a derivative of `Qwen/Qwen3.5-9B` (© Alibaba Cloud / | |
| Qwen team, Apache-2.0). See `NOTICE`. You must retain attribution when | |
| redistributing. | |