code: !pip install unsloth

Get latest Unsloth

!pip install --upgrade --no-deps "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"

from unsloth import FastLanguageModel

import torch
max_seq_length = 2048 # Choose any! We auto support RoPE Scaling internally!
dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.
model, tokenizer = FastLanguageModel.from_pretrained(
model_name = "PartAI/Dorna-Llama3-8B-Instruct",
max_seq_length = max_seq_length,
dtype = dtype,
load_in_4bit = load_in_4bit,
token = "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", # use one if using gated models like meta-llama/Llama-2-7b-hf
)
Error: RuntimeError: Unsloth: The tokenizer PartAI/Dorna-Llama3-8B-Instruct
does not have a {% if add_generation_prompt %} for generation purposes.
Please file a bug report to the maintainers of PartAI/Dorna-Llama3-8B-Instruct - thanks!