umarigan's picture
Update README.md
5f54fc2 verified
|
raw
history blame
1.26 kB
metadata
language:
  - en
  - tr
license: apache-2.0
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - llama
  - trl
  - sft
base_model: unsloth/llama-3-8b-bnb-4bit

Uploaded model

  • Developed by: umarigan
  • License: apache-2.0
  • Finetuned from model : unsloth/llama-3-8b-bnb-4bit

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

Usage Examples


# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("umarigan/llama-3-openhermes-tr")
model = AutoModelForCausalLM.from_pretrained("umarigan/llama-3-openhermes-tr")
alpaca_prompt = """
G枚rev:
{}

Girdi:
{}

Cevap:
{}"""

inputs = tokenizer(
[
    alpaca_prompt.format(
        "fibonnaci dizisinin devam谋n谋 getir.", # instruction
        "1, 1, 2, 3, 5, 8", # input
        "", # output - leave this blank for generation!
    )
], return_tensors = "pt")
outputs = model.generate(**inputs, max_new_tokens = 64, use_cache = True)
tokenizer.batch_decode(outputs)