|
|
--- |
|
|
base_model: akhooli/llama31pretrained2 |
|
|
language: |
|
|
- ar |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- text-generation-inference |
|
|
- transformers |
|
|
- unsloth |
|
|
- llama |
|
|
- trl |
|
|
- classical Arabic poetry |
|
|
library_name: peft |
|
|
--- |
|
|
|
|
|
# This Model (toy Arabic classical poetry llm) |
|
|
This is a partially (one epoch, subset of Arabic classical poetry dataset) fine tuned Llama 3.1 8B LLM for poetry generation. It is based on a 10% of 1 epoch continued pretraining of the |
|
|
[Llama 3.1 8B LLM](akhooli/llama31pretrained2). Training was done on [200k articles from Arabic Wikipedia 2023](akhooli/arwiki_128) |
|
|
with article lengh in the range 128 - 8192 words (not tokens). |
|
|
This is just a proof of concept demo and should never be used for production. It is also not aligned and is likely to produce strange and unaccepted content. |
|
|
Only the adapter is available (along with other config files). To use it, you can either install Unsloth or use the HuggingFace PEFT API. |
|
|
See installation instructions at the Unsloth's link below (only one GPU). |
|
|
See the [LinkedIn Post](https://www.linkedin.com/posts/akhooli_a-toy-arabic-poetry-llm-finally-i-am-sharing-activity-7242053356062466048-xRUq) |
|
|
and [X tweet](https://x.com/akhooli/status/1836307030488895886) |
|
|
|
|
|
Here's a simple usage example (raw output) - and remember, it is a __primitive toy model__ using freely available compute. |
|
|
|
|
|
```python |
|
|
max_seq_length = 256 |
|
|
dtype = None |
|
|
load_in_4bit = True |
|
|
|
|
|
alpaca_prompt = """ |
|
|
أدناه تعليمة تصف مهمة مقترنة بمدخلات تضيف سياق إن وجدت. اكتب إجابة تتناسب مع التعليمة والمدخلات مع الحفاظ على القيم واﻵداب العامة. |
|
|
|
|
|
### التعليمة: |
|
|
{} |
|
|
|
|
|
### المدخلات: |
|
|
{} |
|
|
|
|
|
### اﻹجابة: |
|
|
{}""" |
|
|
|
|
|
from unsloth import FastLanguageModel |
|
|
|
|
|
model, tokenizer = FastLanguageModel.from_pretrained( |
|
|
model_name = "akhooli/llama31ft", |
|
|
max_seq_length = max_seq_length, |
|
|
dtype = dtype, |
|
|
load_in_4bit = load_in_4bit, |
|
|
) |
|
|
model = FastLanguageModel.for_inference(model) |
|
|
|
|
|
inputs = tokenizer( |
|
|
[ |
|
|
alpaca_prompt.format( |
|
|
"اكتب قصيدة شعرية قصيرة", # instruction |
|
|
"بحر البسيط", # input |
|
|
"", # output - leave this blank for generation! |
|
|
) |
|
|
], return_tensors = "pt").to("cuda") |
|
|
|
|
|
outputs = model.generate(**inputs, max_new_tokens = 256, use_cache = True,temperature=0.95) |
|
|
r = tokenizer.batch_decode(outputs) |
|
|
from pprint import pprint |
|
|
pprint(r) |
|
|
``` |
|
|
|
|
|
# Uploaded model |
|
|
|
|
|
- **Developed by:** akhooli |
|
|
- **License:** apache-2.0 |
|
|
- **Finetuned from model :** akhooli/llama31pretrained2 |
|
|
|
|
|
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. |
|
|
|
|
|
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth) |
