Llama 3.2 Amharic
Collection
Llama 3.2 decoder transformer models trained on Amharic text
β’
11 items
β’
Updated
β’
1
This model is an Instruction-Tuned version of Llama 3.2 400M Amharic.
How to use
Chat Format
Given the nature of the training data, the phi-2 instruct model is best suited for prompts using the chat format as follows. You can provide the prompt as a question with a generic template as follows:
<|im_start|>user
α₯α«α?<|im_end|>
<|im_start|>assistant
For example:
<|im_start|>user
αΆα΅α΅ α¨α ααͺα« ααα«α΅ α₯αα΅αα<|im_end|>
<|im_start|>assistant
where the model generates the text after <|im_start|>assistant .
Sample inference code
First, you need to install the latest version of transformers
pip install -Uq transformers
You can use this model directly with a pipeline for text generation:
from transformers import pipeline
llama3_am = pipeline(
"text-generation",
model="rasyosef/Llama-3.2-400M-Amharic-Instruct",
device_map="auto"
)
messages = [{"role": "user", "content": "αΆα΅α΅ α¨α ααͺα« ααα«α΅ α₯αα΅αα"}]
llama3_am(messages, max_new_tokens=128, repetition_penalty=1.1, return_full_text=False)
Output:
[{'generated_text': '1. αα₯α
2. ααααͺα« 3. αα'}]
- Downloads last month
- 136
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for rasyosef/Llama-3.2-400M-Amharic-Instruct
Base model
rasyosef/Llama-3.2-400M-Amharic