Model Card for Model ID

This a fine-tuned version of gpt2 on Locutusque/InstructMix.

Model Details

This model performs significantly better than Locutusque/gpt2-conversational-or-qa. Here are the training results:

• BLEU - 26
• Perplexity - 12

Model Description

• Developed by: Locutusque
• Shared by [optional]: [More Information Needed]
• Model type: GPT-2
• Language(s) (NLP): English
• License: [More Information Needed]
• Finetuned from model [optional]: GPT-2

Model Sources [optional]

• Repository: [More Information Needed]
• Paper [optional]: [More Information Needed]
• Demo [optional]: [More Information Needed]

Uses

This model is designed to follow instructions, or partake in conversations.

Direct Use

Instruction-following or conversational.

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

[More Information Needed]

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

import torch
from transformers import GPT2Tokenizer, GPT2LMHeadModel

tokenizer = GPT2Tokenizer.from_pretrained('gpt2-conversational-retrain')
model = GPT2LMHeadModel.from_pretrained('gpt2-conversational-retrain')
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'<|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,
                            temperature=0.3, 
                            top_k=23, 
                            top_p=0.7,
                            repetition_penalty=1.176,
                            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)
    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)

Training Details

Training Data

https://huggingface.co/datasets/Locutusque/InstructMix

This model has so far been trained on 10% of the linked data, with more training sessions to come.

Training Procedure

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

• Training regime: fp16 non-mixed precision

Speeds, Sizes, Times [optional]

[More Information Needed]

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

• Hardware Type: [More Information Needed]
• Hours used: [More Information Needed]
• Cloud Provider: [More Information Needed]
• Compute Region: [More Information Needed]
• Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]