from unsloth import FastLanguageModel
import torch
import json

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "yum-rock/llm-jp-3-13b-it",
    max_seq_length = 2048,
    dtype = None,
    load_in_4bit = True,
    token = "Your HF_token here"
)

input = "some instruction to Language Model"
prompt = f"""### 指示\n{input}\n### 回答\n"""

inputs = tokenizer([prompt], return_tensors = "pt").to(model.device)

outputs = model.generate(**inputs, max_new_tokens = 512, use_cache = True, do_sample=False, repetition_penalty=1.2)
prediction = tokenizer.decode(outputs[0], skip_special_tokens=True).split('\n### 回答')[-1]

Uploaded model

Developed by: yum-rock
License: apache-2.0
Finetuned from model : llm-jp/llm-jp-3-13b

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