Update readme.md

README.md

@@ -1,3 +1,97 @@
 ---
 license: apache-2.0
+language:
+- ar
+tags:
+- alpaca
+- llama3
+- arabic
 ---
+
+# 🚀 al-baka-llama3-8b
+Al Baka is an Experimental Fine Tuned Model based on the new released LLAMA3-8B Model on the Stanford Alpaca dataset Arabic version [Yasbok/Alpaca_arabic_instruct](https://huggingface.co/datasets/Yasbok/Alpaca_arabic_instruct).
+
+## Model Summary
+
+- **Model Type:** Causal decoder-only
+- **Language(s):** Arabic
+- **Base Model:** [LLAMA-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B))
+- **Dataset:** [Yasbok/Alpaca_arabic_instruct](https://huggingface.co/datasets/Yasbok/Alpaca_arabic_instruct)
+
+## Model Details
+
+- The model was fine-tuned in 4-bit precision using [unsloth](git+https://github.com/unslothai/unsloth.git)
+
+- The run is performed only for 1000 steps with a single Google Colab T4 GPU NVIDIA GPU with 15 GB of available memory.
+
+
+<span style="color:red">The model is currently being Experimentally Fine Tuned to assess LLaMA-3's response to Arabic, following a brief period of fine-tuning. Larger and more sophisticated models will be introduced soon.</span>
+
+## How to Get Started with the Model
+
+### Setup
+```python
+# Install packages
+!pip install accelerate bitsandbytes
+%%capture
+import torch
+major_version, minor_version = torch.cuda.get_device_capability()
+!pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
+if major_version >= 8:
+    # Use this for new GPUs like Ampere, Hopper GPUs (RTX 30xx, RTX 40xx, A100, H100, L40)
+    !pip install --no-deps packaging ninja einops flash-attn xformers trl peft accelerate bitsandbytes
+else:
+    # Use this for older GPUs (V100, Tesla T4, RTX 20xx)
+    !pip install --no-deps xformers trl peft accelerate bitsandbytes
+pass
+```
+
+### First, Load the Model
+```python
+from unsloth import FastLanguageModel
+import torch
+max_seq_length = 2048 # Choose any! We auto support RoPE Scaling internally!
+dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
+load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.
+
+
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name = "Omartificial-Intelligence-Space/al-baka-16bit-llama3-8b",
+    max_seq_length = max_seq_length,
+    dtype = dtype,
+    load_in_4bit = load_in_4bit,
+    # token = "hf_...", # use one if using gated models like meta-llama/Llama-2-7b-hf
+)
+```
+
+### Second, Try the model 
+```python
+alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
+
+### Instruction:
+{}
+
+### Input:
+{}
+
+### Response:
+{}"""
+
+# alpaca_prompt = Copied from above
+FastLanguageModel.for_inference(model) # Enable native 2x faster inference
+inputs = tokenizer(
+[
+    alpaca_prompt.format(
+       "استخدم البيانات المعطاة لحساب الوسيط.", # instruction
+        "[2 ، 3 ، 7 ، 8 ، 10]", # input
+        "", # output - leave this blank for generation!
+    )
+], return_tensors = "pt").to("cuda")
+
+outputs = model.generate(**inputs, max_new_tokens = 64, use_cache = True)
+tokenizer.batch_decode(outputs)
+```
+
+### Recommendations
+
+- [unsloth](git+https://github.com/unslothai/unsloth.git) for finetuning models. You can get a 2x faster finetuned model which can be exported to any format or uploaded to Hugging Face.