Hugging Face's logo

Ranjanunicode
/
unicode-llama-2-chat-Hf-q4-gguf

GGUF
English
Inference Endpoints
conversational
Model card Files Community
unicode-llama-2-chat-Hf-q4-gguf / README.md
Ranjanunicode's picture
Ranjanunicode
Update README.md
d841dec verified
preview code
|
raw
history blame
3.57 kB
metadata
license: llama2
language:
  - en
metrics:
  - perplexity

Q-int4 unicode-llama-2-chat-Hf-q4-2

  • A condensed edition of Llama 2 chat hugging face, designed for deployment with minimal hardware specifications.

Model Developers Ranjanunicode

Input Models input text only.

Output Models generate text only.

Model Details

Model Description

  • Developed by: Ranjan Pandit
  • Model type: Quantized version of "meta-llama/Llama-2-7b-chat-hf"
  • Finetuned from model [optional]: "meta-llama/Llama-2-7b-chat-hf"

Model Sources [optional]

Uses

  • Intended Use Cases unicode-llama-2-chat-Hf-q4-2 is intended for commercial and research use in English.

  • Tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.

  • To get the expected features and performance for the chat versions, a specific formatting needs to be followed,including the INST and <> tags, BOS and EOS tokens, and the whitespaces and breaklines in between (we recommend calling strip() on inputs to avoid double-spaces). See our reference code in github for details: chat_completion.

  • Just Install ctransformers:

!pip install ctransformers>=0.2.24
  • Use the following to get started.
from ctransformers import AutoModelForCausalLM

#Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("Ranjanunicode/unicode-llama-2-chat-Hf-q4-2", model_file="unicode-llama-2-chat-Hf-q4-2.gguf", model_type="llama", gpu_layers=40)

print(llm("AI is going to"))

The model will try to autocomplete {AI is going to}:
be a game-changer for the financial services industry, with applications including customer service chatbots, fraud detection and prevention, portfolio management, and more. Here are some potential benefits of using AI in finance:

1. Improved Efficiency: AI can automate many routine tasks, freeing up staff to focus on higher-value activities such as financial planning and analysis.
2. Enhanced Customer Experience: AI-powered chatbots and virtual assistants can provide 24/7 customer support, helping to improve customer satisfaction and loyalty.
3. Increased Accuracy: AI can help reduce errors and improve accuracy in financial transactions, such as fraud detection and prevention.
4. Better Risk Management: AI can help identify potential risks and make more informed decisions about investments, lending, and other financial activities.
5. Improved Portfolio Management: AI can help create better-performing portfolios by analyzing market trends, identifying new investment opportunities, and making adjustments to existing portfolios.
6. Fraud Detection and Prevention: AI-powered...

Out-of-Scope Use

  • Out-of-scope Uses Use in any manner that violates applicable laws or regulations (including trade compliance laws).Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Llama 2.

Compute Infrastructure

  • Google collab Tesla T4 Gpu.

[More Information Needed]

Citation [optional]

Model Card Authors [optional]

  • Ranjan

Model Card Contact