Instructions to use morzecrew/FRED-T5-RefinedPersonaChat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use morzecrew/FRED-T5-RefinedPersonaChat with Transformers:

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

pipe = pipeline("text-generation", model="morzecrew/FRED-T5-RefinedPersonaChat")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("morzecrew/FRED-T5-RefinedPersonaChat")
model = AutoModelForSeq2SeqLM.from_pretrained("morzecrew/FRED-T5-RefinedPersonaChat")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use morzecrew/FRED-T5-RefinedPersonaChat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "morzecrew/FRED-T5-RefinedPersonaChat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "morzecrew/FRED-T5-RefinedPersonaChat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/morzecrew/FRED-T5-RefinedPersonaChat

SGLang

How to use morzecrew/FRED-T5-RefinedPersonaChat 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 "morzecrew/FRED-T5-RefinedPersonaChat" \
    --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": "morzecrew/FRED-T5-RefinedPersonaChat",
		"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 "morzecrew/FRED-T5-RefinedPersonaChat" \
        --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": "morzecrew/FRED-T5-RefinedPersonaChat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use morzecrew/FRED-T5-RefinedPersonaChat with Docker Model Runner:
```
docker model run hf.co/morzecrew/FRED-T5-RefinedPersonaChat
```

YAML Metadata Warning:The pipeline tag "text2text-generation" is not in the official list: text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, feature-extraction, text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, audio-text-to-text, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-ranking, text-retrieval, time-series-forecasting, text-to-video, image-text-to-text, image-text-to-image, image-text-to-video, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, image-feature-extraction, video-text-to-text, keypoint-detection, visual-document-retrieval, any-to-any, video-to-video, other

morzecrew/FRED-T5-RefinedPersonaChat

This model is a fine-tuned version of ai-forever/FRED-T5-1.7B on the RefinedPersonaChat. Inspired by SiberiaSoft/SiberianPersonaFred blogpost but dataset was improved to prevent toxic speech.

Prompt tips:

You can provide personal information form bot identity, name, age and etc..

Inference

import torch
import transformers

use_cuda = torch.cuda.is_available()
device = torch.device("cuda" if use_cuda else "cpu")

t5_tokenizer = transformers.GPT2Tokenizer.from_pretrained("morzecrew/RefinedPersonaChat")
t5_model = transformers.T5ForConditionalGeneration.from_pretrained("morzecrew/RefinedPersonaChat")


while True:
    print('-'*80)
    dialog = []
    while True:
        msg = input('H:> ').strip()
        if len(msg) == 0:
            break
        msg = msg[0].upper() + msg[1:]
        dialog.append('Собеседник: ' + msg)
        # В начале ставится промпт персонажа.
        prompt = '<SC6>Ты парень, консультант по разным вопросам. Ты очень умный. Любишь помогать собеседнику. Продолжи диалог:' + '\n'.join(dialog) + '\nТы: <extra_id_0>'

        input_ids = t5_tokenizer(prompt, return_tensors='pt').input_ids
        out_ids = t5_model.generate(input_ids=input_ids.to(device), do_sample=True, temperature=0.9, max_new_tokens=512, top_p=0.85,
                                      top_k=2, repetition_penalty=1.2)
        t5_output = t5_tokenizer.decode(out_ids[0][1:])
        if '</s>' in t5_output:
            t5_output = t5_output[:t5_output.find('</s>')].strip()

        t5_output = t5_output.replace('<extra_id_0>', '').strip()
        t5_output = t5_output.split('Собеседник')[0].strip()
        print('B:> {}'.format(t5_output))
        dialog.append('Ты: ' + t5_output)

Citation

@MISC{morzecrew/FRED-T5-RefinedPersonaChat,
    author  = {Yuri Zaretskiy, Nikolas Ivanov, Igor Kuzmin},
    title   = {Dialogue model for conversational agents},
    url     = {https://huggingface.co/morzecrew/FRED-T5-RefinedPersonaChat},
    year    = 2023
}

Downloads last month: 17

Safetensors

Model size

2B params

Tensor type

BF16

morzecrew
/

FRED-T5-RefinedPersonaChat

morzecrew/FRED-T5-RefinedPersonaChat

Prompt tips:

Inference

Citation

Dataset used to train morzecrew/FRED-T5-RefinedPersonaChat