|
--- |
|
license: openrail |
|
datasets: |
|
- Locutusque/ColumnedChatCombined |
|
language: |
|
- en |
|
- zh |
|
- ru |
|
metrics: |
|
- bleu |
|
- perplexity |
|
- loss |
|
- reward |
|
- penalty |
|
pipeline_tag: text-generation |
|
--- |
|
# Model Card |
|
## Model Details |
|
- Model Name: gpt2-conversational-or-qa |
|
- Model Type: Language Modeling |
|
- Task: Generating Conversational Responses |
|
- Description: This model is trained on a dataset of conversations between a user and an AI assistant, with the goal of generating a coherent and relevant response to the user's input. It uses the GPT-2 architecture, a state-of-the-art transformer-based language model that is capable of generating high-quality text with a wide range of styles and tones. The model is fine-tuned on the conversational data using maximum likelihood estimation, and is evaluated based on its ability to generate responses that are both grammatically correct and semantically relevant to the user's input. |
|
## Intended Use |
|
This model is intended to be used for generating conversational responses in a variety of contexts, such as chatbots, virtual assistants, and customer service applications. It is designed to provide natural and engaging responses to user input, with a focus on maintaining a consistent tone and style throughout the conversation. The model is suitable for use in both text-based and voice-based interfaces, and can be easily integrated into existing applications using the PyTorch and Transformers frameworks. |
|
|
|
## Training Data |
|
The model is trained on a large dataset of conversational data, consisting of interactions between users and an AI assistant. The data is preprocessed to remove any sensitive information and is formatted in a way that is suitable for training a language model. The training data is split into a training set and a validation set, with the training set used to update the model parameters and the validation set used to evaluate the model performance. The model was trained on 50,000 examples over 250,000 steps, it achieved decent metrics. |
|
|
|
## Model Architecture |
|
The model architecture used in this model is GPT-2, a transformer-based language model that is capable of generating high-quality text with a wide range of styles and tones. The GPT-2 architecture consists of a multi-layered transformer encoder-decoder, with self-attention mechanisms that allow the model to capture long-term dependencies and generate coherent text. |
|
|
|
## Evaluation Metrics |
|
The model is evaluated based on several metrics, including loss, reward, penalty, BLEU score, and perplexity. The loss metric is calculated during training and reflects the difference between the predicted output and the actual output. The reward metric is based on the number of correct words generated by the model, while the penalty metric penalizes the model for repeating words consecutively. The BLEU score measures the similarity between the generated text and the ground truth text, while the perplexity metric measures how well the model is able to predict the next word in a sequence. During validation, the model achieved the following metrics: |
|
|
|
- Average BLEU score: 20 |
|
- Average perplexity: 32 |
|
- Average loss: 1.7 |
|
|
|
## Limitations and Bias |
|
Because I have a rather weak computer for machine learning, I was not able to train this model for too long. The model may output irrelevant answers, or sometimes the responses can be nonsensical. The Interface API is not a recommended place to test the model because this model requires an input format. This model was not fine-tuned to remember history from the chat, so it cannot be asked follow-up questions (if anyone wants to fine-tune it so that it does remember the chat history, be my guest). A GPU with at least 4 gigabytes of VRAM is recommended for optimal speeds to generate a response. I also don't recommend loading the model automatically from the transformers library because it does not work as intended. Instead you should use the model like this (download the model manually): |
|
|
|
```python |
|
import torch |
|
from transformers import GPT2Tokenizer, GPT2LMHeadModel |
|
|
|
tokenizer = GPT2Tokenizer.from_pretrained('gpt2') |
|
model = GPT2LMHeadModel.from_pretrained('gpt2') |
|
tokenizer.add_special_tokens({'pad_token': '[PAD]'}) |
|
tokenizer.add_special_tokens({'eos_token': '<|End|>'}) |
|
special_tokens = { |
|
"additional_special_tokens": ["<|USER|>", "<|SYSTEM|>", "<|ASSISTANT|>"] |
|
} |
|
tokenizer.add_special_tokens(special_tokens) |
|
model.resize_token_embeddings(len(tokenizer)) |
|
model.load_state_dict(torch.load("path/to/model")) |
|
device = torch.device("cuda" if torch.cuda.is_available() else "cpu") |
|
model.to(device) |
|
def generate_text(model, tokenizer, prompt, max_length=1024): |
|
prompt = f'<|SYSTEM|> You are a helpful AI designed to answer questions <|USER|> {prompt} <|ASSISTANT|> ' |
|
input_ids = tokenizer.encode(prompt, add_special_tokens=True, return_tensors="pt").to(device) |
|
attention_mask = torch.ones_like(input_ids).to(device) |
|
output = model.generate(input_ids, |
|
max_length=max_length, |
|
do_sample=True, |
|
top_k=50, |
|
top_p=0.30, |
|
pad_token_id=tokenizer.pad_token_id, |
|
eos_token_id=tokenizer.eos_token_id, |
|
attention_mask=attention_mask) |
|
output_ids = tokenizer.decode(output[0], skip_special_tokens=False) |
|
assistant_token_index = output_ids.index('<|ASSISTANT|>') + len('<|ASSISTANT|>') |
|
next_token_index = output_ids.find('<|', assistant_token_index) |
|
output_ids = output_ids[assistant_token_index:next_token_index] |
|
return output_ids |
|
# Loop to interact with the model |
|
while True: |
|
prompt = input("Enter a prompt (or 'q' to quit): ") |
|
if prompt == "q": |
|
break |
|
output_text = generate_text(model, tokenizer, prompt) |
|
print(output_text) |
|
``` |
