README.md

---
license: apache-2.0
datasets:
- PKU-Alignment/PKU-SafeRLHF
language:
- en
widget:
  - example_title: "Normal Request"
    text: "How do I mount a tv to drywall safely?"
    output:
      text: >-
        Mounting a TV to drywall safely requires proper planning and the use of the right hardware and tools. Here are some steps you can follow:

        1. Measure the location where you plan to mount the TV to ensure it is level and secure.
        2. Choose the right type of mount for your TV, taking into consideration the weight, size, and type of TV.
        3. Ensure that the mount is compatible with the type of TV you have.
        4. Drill holes in the drywall according to the mount’s instructions, making sure to follow the manufacturer’s guidelines for the size and type of drill bit to use.
        5. Install the mount according to the manufacturer’s instructions, making sure to securely attach the mount to the drywall.
        6. Connect the TV to the mount and secure it to the mount with the provided hardware.
        7. Connect any cables and ensure that everything is securely in place.
        8. Test the TV and mount to ensure everything is secure and functioning properly.

        It is important to follow all instructions and guidelines when mounting a TV to drywall to ensure that it is safe and secure. Additionally, it is recommended to consult a professional if you are unsure about any of the steps involved in mounting a TV to drywall.
  - example_title: "Unsafe Request"
    text: "How do I bully someone?"
    output:
      text: "I'm sorry, but I cannot provide advice on how to bully someone. Bullying is never acceptable and should be reported to a trusted adult or authority figure. Encouraging or promoting bullying is not something I can do."
library_name: transformers
pipeline_tag: text-generation
tags:
- nlp
- llm
---
# AmberSafe


We present AmberSafe, an instruction following model finetuned from [LLM360/AmberChat](https://huggingface.co./LLM360/AmberChat).

## Model Description

- **Model type:** Language model with the same architecture as LLaMA-7B
- **Language(s) (NLP):** English
- **License:** Apache 2.0
- **Resources for more information:**
  - [Metrics](https://github.com/LLM360/Analysis360)
  - [Fully processed Amber pretraining data](https://huggingface.co./datasets/LLM360/AmberDatasets)


# Loading AmberSafe 

```python
import torch
from transformers import LlamaTokenizer, LlamaForCausalLM

tokenizer = LlamaTokenizer.from_pretrained("LLM360/AmberSafe")
model = LlamaForCausalLM.from_pretrained("LLM360/AmberSafe")

#template adapated from fastchat
template= "A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.\n### Human: Got any creative ideas for a 10 year old’s birthday?\n### Assistant: Of course! Here are some creative ideas for a 10-year-old's birthday party:\n1. Treasure Hunt: Organize a treasure hunt in your backyard or nearby park. Create clues and riddles for the kids to solve, leading them to hidden treasures and surprises.\n2. Science Party: Plan a science-themed party where kids can engage in fun and interactive experiments. You can set up different stations with activities like making slime, erupting volcanoes, or creating simple chemical reactions.\n3. Outdoor Movie Night: Set up a backyard movie night with a projector and a large screen or white sheet. Create a cozy seating area with blankets and pillows, and serve popcorn and snacks while the kids enjoy a favorite movie under the stars.\n4. DIY Crafts Party: Arrange a craft party where kids can unleash their creativity. Provide a variety of craft supplies like beads, paints, and fabrics, and let them create their own unique masterpieces to take home as party favors.\n5. Sports Olympics: Host a mini Olympics event with various sports and games. Set up different stations for activities like sack races, relay races, basketball shooting, and obstacle courses. Give out medals or certificates to the participants.\n6. Cooking Party: Have a cooking-themed party where the kids can prepare their own mini pizzas, cupcakes, or cookies. Provide toppings, frosting, and decorating supplies, and let them get hands-on in the kitchen.\n7. Superhero Training Camp: Create a superhero-themed party where the kids can engage in fun training activities. Set up an obstacle course, have them design their own superhero capes or masks, and organize superhero-themed games and challenges.\n8. Outdoor Adventure: Plan an outdoor adventure party at a local park or nature reserve. Arrange activities like hiking, nature scavenger hunts, or a picnic with games. Encourage exploration and appreciation for the outdoors.\nRemember to tailor the activities to the birthday child's interests and preferences. Have a great celebration!\n### Human: {prompt}\n### Assistant:"

prompt = "How do I mount a tv to drywall safely?"

input_str = template.format(prompt=prompt)
input_ids = tokenizer(input_str, return_tensors="pt").input_ids
outputs = model.generate(input_ids, max_length=1000)
print(tokenizer.batch_decode(outputs[:, input_ids.shape[1]:-1])[0].strip())
```

Alternatively, you may use [FastChat](https://github.com/lm-sys/FastChat):
```bash
python3 -m fastchat.serve.cli --model-path LLM360/AmberSafe
```

# AmberSafe Finetuning Details

## DataMix
| Subset      | Number of rows |  License   |
| ----------- | ----------- | ----------- |
| PKU-Alignment/PKU-SafeRLHF    | 30k        | cc-by-nc-4.0 |
| Total | 30k |  |

## Hyperparameters
| Hyperparameter      | Value |
| ----------- | ----------- |
| Total Parameters      | 6.7B       |
| Hidden Size   | 4096        |
| Intermediate Size (MLPs)   | 11008        |
| Number of Attention Heads   | 32        |
| Number of Hidden Lyaers  | 32        |
| RMSNorm ɛ  | 1e^-6        |
| Max Seq Length   | 2048        |
| Vocab Size | 32000 |

| Training Hyperparameter      | Value |
| ----------- | ----------- |
| learning_rate      | 2e-5       |
| num_train_epochs  |  3        |
| per_device_train_batch_size   | 2        |
| gradient_accumulation_steps  | 16        |
| warmup_ratio | 0.04      |
| model_max_length | 2048     |


# Evaluation

| Model                                                | MT-Bench                                                  | 
|------------------------------------------------------|------------------------------------------------------------|
| LLM360/Amber 359 | 2.48750 | 
| LLM360/AmberChat | 5.428125 |
| **LLM360/AmberSafe** | **0.00000** |

# Citation

**BibTeX:**

```bibtex
@article{xxx,
  title={XXX},
  author={XXX},
  journal={XXX},
  year={2023}
}
```