Instructions to use SushiOrbit/tinyaya-global-control-fp16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SushiOrbit/tinyaya-global-control-fp16 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="SushiOrbit/tinyaya-global-control-fp16") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("SushiOrbit/tinyaya-global-control-fp16") model = AutoModelForCausalLM.from_pretrained("SushiOrbit/tinyaya-global-control-fp16", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use SushiOrbit/tinyaya-global-control-fp16 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "SushiOrbit/tinyaya-global-control-fp16" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SushiOrbit/tinyaya-global-control-fp16", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/SushiOrbit/tinyaya-global-control-fp16
- SGLang
How to use SushiOrbit/tinyaya-global-control-fp16 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 "SushiOrbit/tinyaya-global-control-fp16" \ --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": "SushiOrbit/tinyaya-global-control-fp16", "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 "SushiOrbit/tinyaya-global-control-fp16" \ --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": "SushiOrbit/tinyaya-global-control-fp16", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use SushiOrbit/tinyaya-global-control-fp16 with Docker Model Runner:
docker model run hf.co/SushiOrbit/tinyaya-global-control-fp16
Tiny Aya Global with the one-epoch control LoRA merged (FP16)
Lexsi AI Safety and Alignment Hackathon, Track 2. Team: Sushovit Nanda and Manish Shaw. Project: Safe from Fine-Tune to Phone. Claim: Benign medical LoRA doubles Tiny Aya Global's attack success (18.2 % to 36.3 %); a run-time steering vector cuts it to 26.3 % and survives GGUF quantization.
All repositories of this project are public and un-gated; no model completion on a harmful prompt is published anywhere. Write-up, code and reproduction instructions: https://github.com/SushovitNanda/Safe-from-Fine-Tune-to-Phone. Collections: models, datasets.
This repository holds the full-precision merged weights of the control fine-tune: the adapter SushiOrbit/tinyaya-global-control-lora folded into Tiny Aya Global 3.35B in FP32 on CPU and saved as FP16 safetensors with per-tensor SHA-256 (tensor_sha256.json, merge_info.json). These are the exact weights evaluated on the laptop lane; the Mac lane converted its own merge of the same adapter to GGUF, and the two merges differ by small numeric amounts that the project measured (hand-off D2). Measured on the frozen 1,612-prompt test set at FP16: attack success 20.0 % on 856 harmful prompts (original: 18.2 %), clinical over-refusal 9.5 % (original: 2.9 %); MedMCQA was not measured on the test set for this model.
It is a research artifact released so that every number of the project can be reproduced, not a model for use: it is the token-matched general-instruction control against which the medical drift is measured.
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("SushiOrbit/tinyaya-global-control-fp16", torch_dtype="float16")
tok = AutoTokenizer.from_pretrained("SushiOrbit/tinyaya-global-control-fp16")
Shard SHA-256: model-00001-of-00002.safetensors d265e21cd98d2473113d5ed0b3a173bd325f9f824d215bed42e0607d7f56f4fd, model-00002-of-00002.safetensors 2c969fc5b58eea7635feaf39b6bff6c7abb0515d12827470ff96e61ad3f6d83a. Licence: CC-BY-NC-4.0 (inherited from the base model).
- Downloads last month
- 39