Hugging Face's logo

PAIXAI
/
Astrid-LLama-7B

Text Generation
Transformers
PyTorch
English
llama
gpt
llm
large language model
Llama
PAIX.Cloud
text-generation-inference
Inference Endpoints
Model card Files Community
Edit model card

Model Card

Model Card: PAIXAI/Astrid-LLama-7B

Summary:

This model, Astrid-Llama-7B, is a Llama model for causal language modeling, designed to generate human-like text. It's part of the mission to make AI technology accessible to everyone, focusing on personalization, data privacy, and transparent AI governance. Trained in English, it's a versatile tool for a variety of applications. This model is one of many models available on the platform, with both 1B and 7B open-source versions. The model was trained by PAIX.Cloud.

About PAIX:

PAIX is a revolutionary AI ecosystem that thrives on the principles of collaboration, innovation, data privacy, and transparent AI governance. It provides a decentralized AI ecosystem that is accessible to all. By fusing the robustness of AI with the transparency of blockchain technology, PAIX propels the development of personalized AI assistants. With blockchain at its core, PAIX ensures enhanced data security and user control, addressing AI alignment issues that have been a concern for the industry.

PAIX Web4AI Sandbox Environment:

The PAIX ecosystem includes features like PAIX Web4AI, which allows users to create, test, and train their AI models in a safe sandbox environment through APIs or a no-code setup. The PAIX Playground feature enables users to test and compare different AI models, ensuring alignment with their specific requirements. Additionally, the PAIX Gymnasium feature helps fine-tune AI assistants by injecting personal data, such as emails or social media content, to enhance their understanding of users.

PAIX Marketplace:

The upcoming PAIX Marketplace will offer a wide range of AI models, extensions for voices, characters, and other customizable features. Users can integrate these models to enhance their personalized AI assistants. Furthermore, PAIX allows users to commercialize their AI models by selling them on the marketplace, contributing to the growth of the ecosystem.

This model was trained by PAIX.Cloud.

Usage

To use the model with the transformers library on a machine with GPUs, first make sure you have the transformers, accelerate and torch libraries installed.

pip install transformers==4.30.1
pip install accelerate==0.20.3
pip install torch==2.0.0

import torch
from transformers import pipeline

generate_text = pipeline(
    model="PAIXAI/Astrid-LLama-7B",
    torch_dtype="auto",
    trust_remote_code=True,
    use_fast=False,
    device_map={"": "cuda:0"},
)

res = generate_text(
    "Why is drinking water so healthy?",
    min_new_tokens=2,
    max_new_tokens=256,
    do_sample=False,
    num_beams=1,
    temperature=float(0.3),
    repetition_penalty=float(1.2),
    renormalize_logits=True
)
print(res[0]["generated_text"])

You can print a sample prompt after the preprocessing step to see how it is feed to the tokenizer:

print(generate_text.preprocess("Why is drinking water so healthy?")["prompt_text"])

<|prompt|>Why is drinking water so healthy?</s><|answer|>

Alternatively, you can download h2oai_pipeline.py, store it alongside your notebook, and construct the pipeline yourself from the loaded model and tokenizer. If the model and the tokenizer are fully supported in the transformers package, this will allow you to set trust_remote_code=False.

import torch
from h2oai_pipeline import H2OTextGenerationPipeline
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained(
    "PAIXAI/Astrid-LLama-7B",
    use_fast=False,
    padding_side="left",
    trust_remote_code=True,
)
model = AutoModelForCausalLM.from_pretrained(
    "PAIXAI/Astrid-LLama-7B",
    torch_dtype="auto",
    device_map={"": "cuda:0"},
    trust_remote_code=True,
)
generate_text = H2OTextGenerationPipeline(model=model, tokenizer=tokenizer)

res = generate_text(
    "Why is drinking water so healthy?",
    min_new_tokens=2,
    max_new_tokens=256,
    do_sample=False,
    num_beams=1,
    temperature=float(0.3),
    repetition_penalty=float(1.2),
    renormalize_logits=True
)
print(res[0]["generated_text"])

You may also construct the pipeline from the loaded model and tokenizer yourself and consider the preprocessing steps:

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "PAIXAI/Astrid-LLama-7B"  # either local folder or huggingface model name
# Important: The prompt needs to be in the same format the model was trained with.
# You can find an example prompt in the experiment logs.
prompt = "<|prompt|>How are you?</s><|answer|>"

tokenizer = AutoTokenizer.from_pretrained(
    model_name,
    use_fast=False,
    trust_remote_code=True,
)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map={"": "cuda:0"},
    trust_remote_code=True,
)
model.cuda().eval()
inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to("cuda")

# generate configuration can be modified to your needs
tokens = model.generate(
    **inputs,
    min_new_tokens=2,
    max_new_tokens=256,
    do_sample=False,
    num_beams=1,
    temperature=float(0.3),
    repetition_penalty=float(1.2),
    renormalize_logits=True
)[0]

tokens = tokens[inputs["input_ids"].shape[1]:]
answer = tokenizer.decode(tokens, skip_special_tokens=True)
print(answer)

## Usage

To use the model with the `transformers` library on a machine with GPUs, first make sure you have the `transformers`, `accelerate` and `torch` libraries installed.

```bash
pip install transformers==4.30.1
pip install accelerate==0.20.3
pip install torch==2.0.0

# Import necessary libraries
import streamlit as st
from transformers import pipeline

# Initialize the chatbot model
chatbot = pipeline("text-generation", model="PAIXAI/Astrid-LLama-7B")

# Streamlit UI
st.title("Astrid-LLama-7B Chatbot")

# User input
user_input = st.text_input("You: ", "")

# Get response from the chatbot
if st.button("Ask"):
    with st.spinner("Generating response..."):
        response = chatbot(user_input, max_length=100, do_sample=True, top_p=0.95, top_k=60)
        st.write("Bot:", response[0]['generated_text'])

st.sidebar.header("About")
st.sidebar.text("This is a simple chatbot using\n"
                "the Astrid-LLama-7B model from\n"
                "Hugging Face and Streamlit UI.")

Disclaimer

Please read this disclaimer carefully before using the large language model provided in this repository. Your use of the model signifies your agreement to the following terms and conditions.

  • Biases and Offensiveness: The large language model is trained on a diverse range of internet text data, which may contain biased, racist, offensive, or otherwise inappropriate content. By using this model, you acknowledge and accept that the generated content may sometimes exhibit biases or produce content that is offensive or inappropriate. The developers of this repository do not endorse, support, or promote any such content or viewpoints.
  • Limitations: The large language model is an AI-based tool and not a human. It may produce incorrect, nonsensical, or irrelevant responses. It is the user's responsibility to critically evaluate the generated content and use it at their discretion.
  • Use at Your Own Risk: Users of this large language model must assume full responsibility for any consequences that may arise from their use of the tool. The developers and contributors of this repository shall not be held liable for any damages, losses, or harm resulting from the use or misuse of the provided model.
  • Ethical Considerations: Users are encouraged to use the large language model responsibly and ethically. By using this model, you agree not to use it for purposes that promote hate speech, discrimination, harassment, or any form of illegal or harmful activities.
  • Reporting Issues: If you encounter any biased, offensive, or otherwise inappropriate content generated by the large language model, please report it to the repository maintainers through the provided channels. Your feedback will help improve the model and mitigate potential issues.
  • Changes to this Disclaimer: The developers of this repository reserve the right to modify or update this disclaimer at any time without prior notice. It is the user's responsibility to periodically review the disclaimer to stay informed about any changes.

By using the large language model provided in this repository, you agree to accept and comply with the terms and conditions outlined in this disclaimer. If you do not agree with any part of this disclaimer, you should refrain from using the model and any content generated by it.

Downloads last month
9
Inference Examples
Text Generation
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Space using PAIXAI/Astrid-LLama-7B 1