Update README.md

README.md

@@ -8,10 +8,21 @@ tags:
 - trl
 license: apache-2.0
 language:
-- en
+- sw
+library_name: peft
+datasets:
+- Mollel/alpaca-swahili
+- Mollel/swahili_pretrain_data
+- wikimedia/wikipedia
 ---
 
-# Uploaded  model
+# Model Detauils
+
+
+This model has been pre-trained and fine-tuned specifically for Swahili language tasks. 
+The training includes 4-bit quantization to optimize performance on lower-resource hardware.
+
+This is a development version and it's not recommended for general use.
 
 - **Developed by:** calcpy
 - **License:** apache-2.0
@@ -20,3 +31,88 @@ language:
 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)
+
+
+### Out-of-Scope Use
+
+The model is not designed for tasks outside of the Swahili language or tasks requiring highly factual precision in domains not covered by the training datasets.
+
+
+## Bias, Risks, and Limitations
+
+The model inherits any potential biases present in the Swahili Wikipedia and Mollel's dataset. Users should be cautious when applying this model to sensitive applications.
+
+
+### Recommendations
+
+Users should perform bias evaluations specific to their use case and ensure that any downstream applications consider potential ethical implications.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# Load the model and tokenizer
+model = AutoModelForCausalLM.from_pretrained("path_to_your_model")
+tokenizer = AutoTokenizer.from_pretrained("path_to_your_model")
+
+# Example inference
+instruction = "Endelea mlolongo wa fibonacci:"
+input_data = "1, 1, 2, 3, 5, 8,"
+prompt = f"Chini ni maagizo ambayo yanaelezea kazi. Andika jibu ambalo linakamilisha ombi ipasavyo.\n### Maagizo:\n{instruction}\n\n{input_data}\n### Jibu:\n"
+
+inputs = tokenizer([f"{prompt}"], return_tensors="pt").to("cuda")
+outputs = model.generate(**inputs, max_new_tokens=64, use_cache=True)
+print(tokenizer.batch_decode(outputs, skip_special_tokens=True))
+```
+
+In this example, the model generates the continuation of the Fibonacci sequence in Swahili.
+
+
+## Training Details
+
+### Training Data
+
+The model was pre-trained using a combination of [Swahili Wikipedia](https://huggingface.co/datasets/wikimedia/wikipedia) 
+and [Mollel’s Swahili pretraining dataset](https://huggingface.co/datasets/Mollel/swahili_pretrain_data). 
+Both datasets were processed to include End-of-Sequence (EOS) tokens and formatted for pretraining tasks.
+
+Finetuning was performed on [Mollel's Alpaca dataset](https://huggingface.co/datasets/Mollel/alpaca-swahili)
+
+### Training Procedure
+
+#### Training Hyperparameters
+
+- ** Training regime: Mixed precision (fp16/bf16)
+- ** Batch size: 2 per device
+- ** Max steps: 24,000 for pretraining, 1,200 for fine-tuning
+- ** Learning rate: 5e-5 (1e-5 for embeddings)
+- ** Warmup steps: 100 for pretraining, 10 for fine-tuning
+- ** Weight decay: 0.01 (pretraining), 0.00 (fine-tuning)
+
+## Evaluation
+
+The model was only manually evaluated on the Alpaca Swahili dataset for instruction-following capabilities.
+
+#### Metrics
+
+Evaluation metrics will be required for language generation quality and instruction-following precision
+
+#### Summary
+
+This is a purely technical release for a small test model in order to test pre-training and fine-tuning code on a single GPU. 
+
+
+## Environmental Impact
+
+- **Hardware Type:** NVIDIA GeForce RTX 4090 24 GiB
+- **Hours used:** ~12 hours
+
+
+### Compute Infrastructure
+
+Ubuntu 22.04.5 LTS with multiple NVIDIA GeForce RTX 4090 cards
+
+Only a single GPU unit was used