---
datasets:
- OpenAssistant/oasst1
pipeline_tag: text-generation
---

# Falcon-40b-chat-oasst1

Falcon-40b-chat-oasst1 is a chatbot-like model for dialogue generation. It was built by fine-tuning [Falcon-40B](https://huggingface.co/tiiuae/falcon-40b) on the [OpenAssistant/oasst1](https://huggingface.co/datasets/OpenAssistant/oasst1) dataset. 
This model was fine-tuned in 4-bit using 🤗 [peft](https://github.com/huggingface/peft) adapters, [transformers](https://github.com/huggingface/transformers), and [bitsandbytes](https://github.com/TimDettmers/bitsandbytes).
- The training relied on a recent method called "Low Rank Adapters" ([LoRA](https://arxiv.org/pdf/2106.09685.pdf)), instead of fine-tuning the entire model you just have to fine-tune adapters and load them properly inside the model. 
- Training took approximately 10 hours and was executed on a workstation with a single NVIDIA A100-SXM 40GB GPU (via Google Colab).
- See attached [Notebook](https://huggingface.co/dfurman/falcon-40b-chat-oasst1/blob/main/finetune_falcon40b_oasst1_with_bnb_peft.ipynb) for the code (and hyperparams) used to train the model. 

## Model Summary

- **Model Type:** Causal decoder-only
- **Language(s) (NLP):** English (primarily)
- **Base Model:** [Falcon-40B](https://huggingface.co/tiiuae/falcon-40b) (License: [TII Falcon LLM License](https://huggingface.co/tiiuae/falcon-40b#license), commercial use ok-ed)
- **Dataset:** [OpenAssistant/oasst1](https://huggingface.co/datasets/OpenAssistant/oasst1) (License: [Apache 2.0](https://huggingface.co/datasets/OpenAssistant/oasst1/blob/main/LICENSE), commercial use ok-ed)

### Model Date

May 30, 2023

## Quick Start

To prompt the chat model, use the following format:

```
<human>: [Instruction]
<bot>:
```

### Example Dialogue 1

**Prompter**:
```
"""<human>: My name is Daniel. Write a short email to my closest friends inviting them to come to my home on Friday for a dinner party, I will make the food but tell them to BYOB.
<bot>:"""
```

**Falcon-40b-chat-oasst1**:
```
[Coming]
```

### Example Dialogue 2

**Prompter**:
```
<human>: Create a list of five things to do in San Francisco.\n
<bot>:
```

**Falcon-40b-chat-oasst1**:
```
[Coming]
```

### Direct Use

This model has been finetuned on conversation trees from [OpenAssistant/oasst1](https://huggingface.co/datasets/OpenAssistant/oasst1) and should only be used on data of a similar nature.

### Out-of-Scope Use

Production use without adequate assessment of risks and mitigation; any use cases which may be considered irresponsible or harmful. 

## Bias, Risks, and Limitations

This model is mostly trained on English data, and will not generalize appropriately to other languages. Furthermore, as it is trained on a large-scale corpora representative of the web, it will carry the stereotypes and biases commonly encountered online.

### Recommendations

We recommend users of this model to develop guardrails and to take appropriate precautions for any production use.

## How to Get Started with the Model

### Setup
```python
# Install and import packages
!pip install -q -U bitsandbytes loralib einops
!pip install -q -U git+https://github.com/huggingface/transformers.git 
!pip install -q -U git+https://github.com/huggingface/peft.git
!pip install -q -U git+https://github.com/huggingface/accelerate.git

import torch
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM, AutoTokenizer
```

### GPU Inference in 4-bit

This requires a GPU with at least 27GB memory.

```python
# load the model
peft_model_id = "dfurman/falcon-40b-chat-oasst1"
config = PeftConfig.from_pretrained(peft_model_id)

bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_use_double_quant=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.bfloat16
)

model = AutoModelForCausalLM.from_pretrained(
    config.base_model_name_or_path,
    return_dict=True,
    quantization_config=bnb_config,
    device_map={"":0},
    use_auth_token=True,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
tokenizer.pad_token = tokenizer.eos_token

model = PeftModel.from_pretrained(model, peft_model_id)
```

```python
# run the model
prompt = """<human>: My name is Daniel. Write a long email to my closest friends inviting them to come to my home on Friday for a dinner party, I will make the food but tell them to BYOB.
<bot>:"""

batch = tokenizer(
    prompt,
    padding=True,
    truncation=True,
    return_tensors='pt'
)
batch = batch.to('cuda:0')

with torch.cuda.amp.autocast():
    output_tokens = model.generate(
        input_ids = batch.input_ids, 
        max_new_tokens=200,
        temperature=0.7,
        top_p=0.7,
        num_return_sequences=1,
        pad_token_id=tokenizer.eos_token_id,
        eos_token_id=tokenizer.eos_token_id,
    )

# Inspect outputs
print('\n\n', tokenizer.decode(output_tokens[0], skip_special_tokens=True))
```

## Reproducibility

- See attached [Notebook](https://huggingface.co/dfurman/falcon-40b-chat-oasst1/blob/main/finetune_falcon40b_oasst1_with_bnb_peft.ipynb) for the code (and hyperparams) used to train the model. 

### CUDA Info

- CUDA Version: 12.0
- GPU Name: NVIDIA A100-SXM
- Max Memory: {0: "37GB"}
- Device Map: {"": 0}

### Package Versions Employed

- `torch`: 2.0.1+cu118
- `transformers`: 4.30.0.dev0
- `peft`: 0.4.0.dev0
- `accelerate`: 0.19.0
- `bitsandbytes`: 0.39.0
- `einops`: 0.6.1