AVA-Qwen1.5-7

Fine-Tuned Qwen1.5 7B Persian Large Language Model LLM / Persian Qwen1.5 7B

AVA-Qwen1.5 / Persian Qwen

This Repository Contains Documents for Fine-Tuned Qwen1.5 Persian Large Language Model(LLM) Called AVA-Qwen1.5

(Still in progress)

Dataset used:

To Be Done

Usage:

All models are hosted in HuggingFace, and here is the code for inference:

from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
import torch

model_name_or_id = "MehdiHosseiniMoghadam/AVA-Qwen1.5-7B-Chat"
model = AutoModelForCausalLM.from_pretrained(model_name_or_id, torch_dtype=torch.float16, device_map="auto", low_cpu_mem_usage=True, load_in_8bit=True)
tokenizer = AutoTokenizer.from_pretrained(model_name_or_id)

prompt = ''

prompt = f"### Human:{prompt}\n### Assistant:"


inputs = tokenizer(prompt, return_tensors="pt").to("cuda")

generation_config = GenerationConfig(
    do_sample=True,
    top_k=1,
    temperature=0.01,
    max_new_tokens=90,
    pad_token_id=tokenizer.eos_token_id
)


outputs = model.generate(**inputs, generation_config=generation_config)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

License

Released Jan 30, 2024 by Mehdi Hosseini Moghadam

Attention ⚠️: The user is responsible for using AVA-Llama-3 / Persian Llama 3

Any misuse of the model (of any kind) is the responsibility of the user and not the creator