QuantFactory / Dorna-Llama3-8B-Instruct-GGUF

QuantFactory/Dorna-Llama3-8B-Instruct-GGUF

This is quantized version of PartAI/Dorna-Llama3-8B-Instruct created using llama.cpp

Model Descrption

The Dorna models are a family of decoder-only models, specifically trained/fine-tuned on Persian data, developed by Part AI . As an initial release, an 8B instruct model from this family is being made available. Dorna-Llama3-8B-Instruct is built using the Meta Llama 3 Instruct model.

How to use

To test and use model freely on Hugging Face Spaces click here !

You can also run conversational inference using the Transformers Auto classes with the generate() function. Let's look at an example.

import torch
import transformers
from transformers import AutoTokenizer, AutoModelForCausalLM


tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

messages = [
    {"role": "system",
     "content": "You are a helpful Persian assistant. Please answer questions in the asked language."},
    {"role": "user", "content": "کاغذ A4 بزرگ تر است یا A5؟"},
]

input_ids = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

terminators = [
    tokenizer.eos_token_id,
    tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

outputs = model.generate(
    input_ids,
    max_new_tokens=256,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.6,
    top_p=0.9,
)
response = outputs[0][input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))

You can also use the notebook below to test the model in Google Colab.

Evaluation

This model is evaluated on questions across various tasks, including Boolean Questions, Code Generation, Long Response, Math, News QA, Paraphrasing, General Knowledge, and Summarization. Most categories typically have two main difficulty levels: Hard and Easy.

Both human evaluation and automatic evaluation (with GPT-4 as the judge) are performed.

In both tables, Dorna-8B-it is used as an abbreviated form of Dorna-Llama3-8B-Instruct .

Overall human evaluation results are as follows:

Category-based human evaluation results are as follows:

Win/Lose/Tie % is reported for each category.

Automatic evaluation results are as follows: