Uploaded model

  • Developed by: aoii
  • 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.

!pip uninstall unsloth -y !pip install --upgrade --no-cache-dir "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git" !pip install --upgrade torch !pip install --upgrade xformers

import torch if torch.cuda.get_device_capability()[0] >= 8: !pip install --no-deps packaging ninja einops "flash-attn>=2.6.3" HF_TOKEN = "YOUR-HF-TOKEN"

from unsloth import FastLanguageModel import torch max_seq_length = 512 dtype = None load_in_4bit = True model_id = "llm-jp/llm-jp-3-13b" new_model_id = "rallm-jp-3-13b-it"

model, tokenizer = FastLanguageModel.from_pretrained( model_name=model_id, dtype=dtype, load_in_4bit=load_in_4bit, trust_remote_code=True, ) model = FastLanguageModel.get_peft_model( model, r = 32, target_modules = ["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj",], lora_alpha = 32, lora_dropout = 0.05, bias = "none", use_gradient_checkpointing = "unsloth", random_state = 3407, use_rslora = False, loftq_config = None, max_seq_length = max_seq_length, )

from datasets import load_dataset

dataset = load_dataset("json", data_files="")

prompt = """### ζŒ‡η€Ί {}

ε›žη­”

{}"""

EOS_TOKEN = tokenizer.eos_token def formatting_prompts_func(examples): input = examples["text"] output = examples["output"] text = prompt.format(input, output) + EOS_TOKEN return { "formatted_text" : text, } pass dataset = dataset.map( formatting_prompts_func, num_proc= 4, )

from trl import SFTTrainer from transformers import TrainingArguments from unsloth import is_bfloat16_supported trainer = SFTTrainer( model = model, tokenizer = tokenizer, train_dataset=dataset["train"], max_seq_length = max_seq_length, dataset_text_field="formatted_text", packing = False, args = TrainingArguments( per_device_train_batch_size = 2, gradient_accumulation_steps = 4, num_train_epochs = 1, logging_steps = 10, warmup_steps = 10, save_steps=100, save_total_limit=2, max_steps=-1, learning_rate = 2e-4, fp16 = not is_bfloat16_supported(), bf16 = is_bfloat16_supported(), group_by_length=True, seed = 3407, output_dir = "outputs", report_to = "none", ), ) trainer_stats = trainer.train()

import json datasets = [] with open("", "r") as f: item = "" for line in f: line = line.strip() item += line if item.endswith("}"): datasets.append(json.loads(item)) item = "" from tqdm import tqdm

FastLanguageModel.for_inference(model)

results = [] for dt in tqdm(datasets): input = dt["input"]

prompt = f"""### ζŒ‡η€Ί\n{input}\n### ε›žη­”\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### ε›žη­”')[-1]

results.append({"task_id": dt["task_id"], "input": input, "output": prediction}) with open(f"{new_model_id}_output.jsonl", 'w', encoding='utf-8') as f: for result in results: json.dump(result, f, ensure_ascii=False) f.write('\n')

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no pipeline_tag.

Model tree for aoii/ayllm-jp-3-13b

Finetuned
(1120)
this model