Instructions to use Locutusque/gpt2-conversational-retrain with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Locutusque/gpt2-conversational-retrain with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Locutusque/gpt2-conversational-retrain")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Locutusque/gpt2-conversational-retrain")
model = AutoModelForCausalLM.from_pretrained("Locutusque/gpt2-conversational-retrain")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Locutusque/gpt2-conversational-retrain with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Locutusque/gpt2-conversational-retrain"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Locutusque/gpt2-conversational-retrain",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Locutusque/gpt2-conversational-retrain

SGLang

How to use Locutusque/gpt2-conversational-retrain with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Locutusque/gpt2-conversational-retrain" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Locutusque/gpt2-conversational-retrain",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Locutusque/gpt2-conversational-retrain" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Locutusque/gpt2-conversational-retrain",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Locutusque/gpt2-conversational-retrain with Docker Model Runner:
```
docker model run hf.co/Locutusque/gpt2-conversational-retrain
```

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]

Downloads last month: 1,030

Safetensors

Model size

0.1B params

Tensor type

F16

Collection including Locutusque/gpt2-conversational-retrain

ChatGPT-Mini

Collection

A collection of fine-tuned GPT-2 models each designed to deploy a ChatGPT-like model at home. These models can also be deployed on an old computer. • 8 items • Updated Nov 16, 2023 • 5

Paper for Locutusque/gpt2-conversational-retrain

Quantifying the Carbon Emissions of Machine Learning

Paper • 1910.09700 • Published Oct 21, 2019 • 45