Hugging Face's logo

asedmammad
/
PersianMind-v1.0-GGUF

Text Generation
GGUF
Persian
English
llama
text-generation-inference
Model card Files Community
2
PersianMind-v1.0-GGUF / README.md
asedmammad's picture
asedmammad
Update README.md
95ca2c0 verified
preview code
|
raw
history blame
3.19 kB
metadata
license: cc
inference: false
language:
  - fa
  - en
tags:
  - llama
  - text-generation-inference
pipeline_tag: text-generation

UniversityOfTehran's PersianMind-v1.0 GGUF

These files are GGUF format model files for UniversityOfTehran's PersianMind-v1.0.

GGUF files are for CPU + GPU inference using llama.cpp and libraries and UIs which support this format, such as:

How to run in llama.cpp

I use the following command line, adjust for your tastes and needs:

./main -t 2 -ngl 32 -m PersianMind-v1.0.q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.2 -n -1 -e -p "This is a conversation with PersianMind. It is an artificial intelligence model designed by a team of NLP experts at the University of Tehran to help you with various tasks such as answering questions, providing recommendations, and helping with decision making. You can ask it anything you want and it will do its best to give you accurate and relevant information.\nYou: در مورد هوش مصنوعی توضیح بده.\nPersianMind: "

Change -t 2 to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use -t 8.

Change -ngl 32 to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.

If you want to have a chat-style conversation, replace the -p <PROMPT> argument with -i -ins, you can use --interactive-first to start in interactive mode.

Though the model outputs good persian text among the open source models, enabling sampling or using high temperature values in llama.cpp causes the model to output non sense persian text, so currently I am using it with low temperature value with alpaca instruct template:

./main -t 2 -ngl 32 -m PersianMind-v1.0.q4_K_M.gguf --color -c 2048 --temp 0.2 --repeat_penalty 1.2 -n -1 -e -p "### Instruction: در مورد زنبور عسل توضیح بده ### Response:"

Compatibility

I have uploded both the original llama.cpp quant methods (q4_0, q4_1, q5_0, q5_1, q8_0) as well as the k-quant methods (q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K).

Please refer to llama.cpp and TheBloke's GGUF models for further explanation.

How to run in text-generation-webui

Further instructions here: text-generation-webui/docs/llama.cpp-models.md.

Thanks

Thanks to Pedram Rostami, Ali Salemi, and Mohammad Javad Dousti for providing checkpoints of the model.

Thanks to Georgi Gerganov and all of the awesome people in the AI community.