|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- Anthropic/hh-rlhf |
|
language: |
|
- en |
|
pipeline_tag: text-generation |
|
tags: |
|
- text-generation-inference |
|
--- |
|
## OpenBezoar-HH-RLHF-SFT |
|
|
|
The OpenBezoar-HH-RLHF-SFT is an LLM that has been further instruction fine tuned version of [OpenBezoar-SFT](https://huggingface.co/SurgeGlobal/OpenBezoar-SFT) model on a subset of [Anthropic's HH-RLHF Dataset](https://huggingface.co/datasets/Anthropic/hh-rlhf). |
|
|
|
## Model Details |
|
|
|
- Base Model: [OpenBezoar-SFT](https://huggingface.co/SurgeGlobal/OpenBezoar-SFT) |
|
- Dataset used for SFT: First 100K examples of the [HH-RLHF](https://huggingface.co/datasets/Anthropic/hh-rlhf) dataset |
|
- Epochs: 1 |
|
|
|
### Model Description |
|
|
|
OpenBezoar-HH-RLHF-SFT is an LLM that is built upon the OpenLLaMA 3B v2 architecture. Primary purpose of performing SFT on [OpenBezoar-SFT](https://huggingface.co/SurgeGlobal/OpenBezoar-SFT) is to minimize the distribution shift before applying Direct Preference Optimization (DPO) for human preferences alignment. For more information please refer to our paper. |
|
|
|
### Model Sources |
|
|
|
- **Repository:** [More Information Needed] |
|
- **Paper :** [More Information Needed] |
|
|
|
## Instruction Format |
|
|
|
We follow a modified version of the Alpaca prompt template as shown below. It is important to utilize this template in order to obtain best responses for instruction related tasks. |
|
``` |
|
### System: |
|
Below is an instruction that describes a task, optionally paired with an input that provides further context following that instruction. Write a response that appropriately completes the request. |
|
|
|
### Instruction: |
|
{instruction} |
|
|
|
### Response: |
|
``` |
|
|
|
Notice that **no** end-of-sentence (eos) token is being appended. |
|
|
|
*Note: The system prompt shown in the following figure is the one that the model has been trained on most of the time. However, you may attempt to use any other system prompt that is available in the [Orca](https://arxiv.org/abs/2306.02707) scheme.* |
|
|
|
## Usage |
|
|
|
```python |
|
from peft import PeftConfig, PeftModel |
|
from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig, AutoModelForSeq2SeqLM |
|
|
|
checkpoint = "SurgeGlobal/OpenBezoar-SFT" |
|
|
|
tokenizer = AutoTokenizer.from_pretrained(checkpoint) |
|
|
|
model = AutoModelForCausalLM.from_pretrained( |
|
checkpoint, |
|
load_in_4bit=True, # optionally for low resource environments |
|
device_map="auto" |
|
) |
|
|
|
prompt = """### System: |
|
Below is an instruction that describes a task, optionally paired with an input that provides further context following that instruction. Write a response that appropriately completes the request. |
|
|
|
### Instruction: |
|
{instruction} |
|
|
|
### Response:""".format( |
|
instruction="What is the world state in the year 1597." |
|
) |
|
|
|
inputs = tokenizer(prompt, return_tensors="pt").to(model.device) |
|
|
|
outputs = model.generate(**inputs, max_new_tokens=1024, do_sample=True) |
|
|
|
print(tokenizer.decode(outputs[0])) |
|
``` |
|
|
|
## Evaluations |
|
|
|
Refer to our self-reported evaluations in our paper (Section 4). |
|
|
|
## Limitations |
|
|
|
- The model might not consistently show improved abilities to follow instructions, and it could respond inappropriately or get stuck in loops. |
|
- This model is not aligned to human preferences and therefore it may generate harmful and uncensored content. |
|
- Caution is urged against relying on this model for production or adjacent use-cases. |
|
|
|
## Citation |
|
|
|
If you find our work useful, please cite our paper as follows: |
|
|
|
``` |
|
[More Information Needed] |
|
``` |
|
|
|
## Model Authors |
|
|
|
Chandeepa Dissanayake, Lahiru Lowe, Sachith Gunasekara, and Yasiru Ratnayake |
|
|
