You can deploy this model and start earning money today!

Haya-Kei/
llm-jp-3-13b-finetune

Name: llm-jp-3-13b-finetune
Availability: InStock

Views

No views yet

Model Card for Model ID

Model Details

Sample Use

Run the following code in Python.

python

# モデルによるタスクの推論。
from tqdm import tqdm

results = []
for data in tqdm(datasets):

  input = data["input"]

  prompt = f"""### 指示
  {input}
  ### 回答
  """
    
  tokenized_input = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt").to(model.device)
  attention_mask = torch.ones_like(tokenized_input)

  with torch.no_grad():
      outputs = model.generate(
          tokenized_input,
          attention_mask=attention_mask,
          max_new_tokens=100,
          do_sample=False,
          repetition_penalty=1.2,
          pad_token_id=tokenizer.eos_token_id
      )[0]
  output = tokenizer.decode(outputs[tokenized_input.size(1):], skip_special_tokens=True)

  results.append({"task_id": data["task_id"], "input": input, "output": output})

Entire Code

python

from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
    BitsAndBytesConfig,
    TrainingArguments,
    logging,
)
from peft import (
    LoraConfig,
    PeftModel,
    get_peft_model,
)
import os, torch, gc
from datasets import load_dataset
import bitsandbytes as bnb
from trl import SFTTrainer
HF_TOKEN = "your_hf_token_here"

# モデルを読み込み。
# llm-jp-3 1.8B, 3.7B, 13Bのsnapshotをダウンロード済みでmodelsディレクトリに格納してあります。
# base_model_idの値はomnicampusの環境におけるモデルのパスを表しており、それ以外の環境で実行する場合は変更の必要があります。
# その他のモデルは取得に承諾が必要なため、各自でダウンロードお願いします。
base_model_id = "models/models--llm-jp--llm-jp-3-13b/snapshots/cd3823f4c1fcbb0ad2e2af46036ab1b0ca13192a" #Fine-Tuningするベースモデル
# omnicampus以外の環境をご利用の方は以下をご利用ください。
# base_model_id = "llm-jp/llm-jp-3-13b" 
new_model_id = "llm-jp-3-13b-finetune" #Fine-Tuningしたモデルにつけたい名前

"""
bnb_config: 量子化の設定

  - load_in_4bit:
      - 4bit量子化形式でモデルをロード

  - bnb_4bit_quant_type:
      - 量子化の形式を指定

  - bnb_4bit_compute_dtype:
      - 量子化された重みを用いて計算する際のデータ型

"""

bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4", # nf4は通常のINT4より精度が高く、ニューラルネットワークの分布に最適です
    bnb_4bit_compute_dtype=torch.bfloat16,
)

"""
model: モデル

  - base_model:
      - 読み込むベースモデル (事前に定義したもの)

  - quantization_config:
      - bnb_configで設定した量子化設定

  - device_map:
      - モデルを割り当てるデバイス (CPU/GPU) "auto"で自動に割り当てられます。

tokenizer: トークナイザー

  - base_model:
      - 読み込むベースモデル (事前に定義したもの)

  - trust_remote_code:
      - リモートコードの実行を許可 (カスタムモデルなど)
"""
model = AutoModelForCausalLM.from_pretrained(
    base_model_id,
    quantization_config=bnb_config,
    device_map="auto"
)

tokenizer = AutoTokenizer.from_pretrained(base_model_id, trust_remote_code=True)

"""
find_all_linear_names: モデル内の4bit量子化線形層を探します。
"""

def find_all_linear_names(model):
    cls = bnb.nn.Linear4bit # 4bit量子化線形層クラスを指定
    lora_module_names = set() # ここに取得した線形層を保持します。

    # モデル内の全てのモジュールを探索します
    for name, module in model.named_modules():
        if isinstance(module, cls): # モジュールが4bit量子化線形層の場合
            names = name.split('.') # モジュールの名前を分割 (ネストされてる際などに対処)
            lora_module_names.add(names[0] if len(names) == 1 else names[-1]) # 最下層の名前をlora_module_namesに追加

    # 'lm_head' は16ビット演算の際に除外する必要があるため、lora_module_namesから削除
    if 'lm_head' in lora_module_names:
        lora_module_names.remove('lm_head')

    return list(lora_module_names) # lora_module_namesをリストに変換して返します。

modules = find_all_linear_names(model)

"""
peft_config: PEFTの構成設定

  - r
      - LoRA のランク (4, 8, 16 ,32...)
      - 増やすほど学習が捗るが, 過学習のリスクも高まるので注意

  - lora_alpha
      - LoRAのスケーリング係数

  - lora_dropout
      - ドロップアウト率（過学習を防ぐための割合）

  - bias
      - バイアス項の扱い ("none"の場合、LoRAはバイアスを学習しない)

  - task_type
      - タスクタイプ

  - target_modules
      - LoRAを適用するターゲットモジュール (前のコードで特定した層)
"""

peft_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
    target_modules=modules,
)

model = get_peft_model(model, peft_config)

"""
学習に用いるデータセットの指定
今回はLLM-jp の公開している Ichikara Instruction を使います。データにアクセスするためには申請が必要ですので、使いたい方のみ申請をしてください。
Ichikara Instruciton を Hugging Face Hub にて公開することはお控えください。  
また、CC-BY-NC-SAですのでモデルはライセンスを継承する前提でお使いください。  

下記のリンクから申請を終えた先に Google Drive があり、Distribution20241221_all というフォルダごとダウンロードしてください。
今回は「ichikara-instruction-003-001-1.json」を使います。必要であれば展開（!unzip など）し、データセットのパスを適切に指定してください。
omnicampusの開発環境では取得したデータを左側にドラッグアンドドロップしてお使いください。

https://liat-aip.sakura.ne.jp/wp/llmのための日本語インストラクションデータ作成/llmのための日本語インストラクションデータ-公開/
関根聡, 安藤まや, 後藤美知子, 鈴木久美, 河原大輔, 井之上直也, 乾健太郎. ichikara-instruction: LLMのための日本語インストラクションデータの構築. 言語処理学会第30回年次大会(2024)

"""

dataset = load_dataset("json", data_files="./ichikara-instruction-003-001-1.json")
dataset

# 学習時のプロンプトフォーマットの定義
prompt = """### 指示
{}
### 回答
{}"""


"""
formatting_prompts_func: 各データをプロンプトに合わせた形式に合わせる
"""
EOS_TOKEN = tokenizer.eos_token # トークナイザーのEOSトークン（文末トークン）
def formatting_prompts_func(examples):
    input = examples["text"] # 入力データ
    output = examples["output"] # 出力データ
    text = prompt.format(input, output) + EOS_TOKEN # プロンプトの作成
    return { "formatted_text" : text, } # 新しいフィールド "formatted_text" を返す
pass

# # 各データにフォーマットを適用
dataset = dataset.map(
    formatting_prompts_func,
    num_proc= 4, # 並列処理数を指定
)

"""
training_arguments: 学習の設定

  - output_dir:
      -トレーニング後のモデルを保存するディレクトリ

  - per_device_train_batch_size:
      - デバイスごとのトレーニングバッチサイズ

  - per_device_
  _batch_size:
      - デバイスごとの評価バッチサイズ

  - gradient_accumulation_steps:
      - 勾配を更新する前にステップを積み重ねる回数

  - optim:
      - オプティマイザの設定

  - num_train_epochs:
      - エポック数

  - eval_strategy:
      - 評価の戦略 ("no"/"steps"/"epoch")

  - eval_steps:
      - eval_strategyが"steps"のとき、評価を行うstep間隔

  - logging_strategy:
      - ログ記録の戦略

  - logging_steps:
      - ログを出力するステップ間隔

  - warmup_steps:
      - 学習率のウォームアップステップ数

  - save_steps:
      - モデルを保存するステップ間隔

  - save_total_limit:
      - 保存しておくcheckpointの数

  - max_steps:
      - トレーニングの最大ステップ数

  - learning_rate:
      - 学習率

  - fp16:
      - 16bit浮動小数点の使用設定（第8回演習を参考にすると良いです）

  - bf16:
      - BFloat16の使用設定

  - group_by_length:
      -  入力シーケンスの長さによりバッチをグループ化 (トレーニングの効率化)

  - report_to:
      - ログの送信先 ("wandb"/"tensorboard"など)
"""

training_arguments = TrainingArguments(
    output_dir=new_model_id,
    per_device_train_batch_size=1,
    gradient_accumulation_steps=2,
    optim="paged_adamw_32bit",
    num_train_epochs=1,
    logging_strategy="steps",
    logging_steps=10,
    warmup_steps=10,
    save_steps=100,
    save_total_limit = 2,
    max_steps = -1,
    learning_rate=5e-5,
    fp16=False,
    bf16=False,
    seed = 3407,
    group_by_length=True,
    report_to="none"
)

"""
SFTTrainer: Supervised Fine-Tuningに関する設定

  - model:
      - 読み込んだベースのモデル

  - train_dataset:
      - トレーニングに使用するデータセット

  - eval_dataset:
      - 評価に使用するデータセット

  - peft_config:
      - PEFT（Parameter-Efficient Fine-Tuning）の設定（LoRAを利用する場合に指定）

  - max_seq_length:
      - モデルに入力されるシーケンスの最大トークン長

  - dataset_text_field:
      - データセット内の学習に使うテキストを含むフィールド名

  - tokenizer:
      - モデルに対応するトークナイザー

  - args:
      - トレーニングに使用するハイパーパラメータ（TrainingArgumentsの設定を指定）

  - packing:
      - 入力シーケンスのパッキングを行うかどうかの設定 (False に設定することで、各入力を独立して扱う)
"""
trainer = SFTTrainer(
    model=model,
    train_dataset=dataset["train"],
    peft_config=peft_config,
    max_seq_length= 512,
    dataset_text_field="formatted_text",
    tokenizer=tokenizer,
    args=training_arguments,
    packing= False,
)

model.config.use_cache = False # キャッシュ機能を無効化
trainer.train() # トレーニングを実行

# タスクとなるデータの読み込み。
# omnicampusの開発環境では、左にタスクのjsonlをドラッグアンドドロップしてから実行。
import json
datasets = []
with open("./elyza-tasks-100-TV_0.jsonl", "r") as f:
    item = ""
    for line in f:
      line = line.strip()
      item += line
      if item.endswith("}"):
        datasets.append(json.loads(item))
        item = ""

# モデルによるタスクの推論。
from tqdm import tqdm

results = []
for data in tqdm(datasets):

  input = data["input"]

  prompt = f"""### 指示
  {input}
  ### 回答
  """
    
  tokenized_input = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt").to(model.device)
  attention_mask = torch.ones_like(tokenized_input)

  with torch.no_grad():
      outputs = model.generate(
          tokenized_input,
          attention_mask=attention_mask,
          max_new_tokens=100,
          do_sample=False,
          repetition_penalty=1.2,
          pad_token_id=tokenizer.eos_token_id
      )[0]
  output = tokenizer.decode(outputs[tokenized_input.size(1):], skip_special_tokens=True)

  results.append({"task_id": data["task_id"], "input": input, "output": output})

# こちらで生成されたjsolを提出してください。
# 本コードではinputとeval_aspectも含んでいますが、なくても問題ありません。
# 必須なのはtask_idとoutputとなります。
import re
jsonl_id = re.sub(".*/", "", new_model_id)
with open(f"./{jsonl_id}-outputs.jsonl", 'w', encoding='utf-8') as f:
    for result in results:
        json.dump(result, f, ensure_ascii=False)  # ensure_ascii=False for handling non-ASCII characters
        f.write('\n')

# モデルとトークナイザーをHugging Faceにアップロード
model.push_to_hub(new_model_id, token=HF_TOKEN, private=True) # Online saving
tokenizer.push_to_hub(new_model_id, token=HF_TOKEN, private=True) # Online saving

Requirement

plaintext

absl-py==1.4.0
accelerate==1.2.1
aiohappyeyeballs==2.4.3
aiohttp==3.11.7
aiosignal @ file:///rapids/aiosignal-1.3.1-py3-none-any.whl#sha256=f8376fb07dd1e86a584e4fcdec80b36b7f81aac666ebc724e2c090300dd83b17
annotated-types==0.7.0
antlr4-python3-runtime==4.9.3
anyio==4.6.2.post1
apex @ file:///opt/pytorch/apex
argon2-cffi==21.3.0
argon2-cffi-bindings==21.2.0
asttokens==2.2.1
astunparse==1.6.3
async-timeout @ file:///rapids/async_timeout-4.0.2-py3-none-any.whl#sha256=8ca1e4fcf50d07413d66d1a5e416e42cfdf5851c981d679a09851a6853383b3c
attrs==24.2.0
audioread==3.0.0
backcall==0.2.0
beautifulsoup4==4.12.3
bitsandbytes==0.45.0
bleach==6.0.0
blis==0.7.9
cachetools==5.3.1
catalogue==2.0.8
certifi==2023.5.7
cffi==1.15.1
charset-normalizer==3.1.0
click==8.1.7
cloudpickle @ file:///rapids/cloudpickle-2.2.1-py3-none-any.whl#sha256=61f594d1f4c295fa5cd9014ceb3a1fc4a70b0de1164b94fbc2d854ccba056f9f
cmake==3.26.4
comm==0.1.3
confection==0.1.0
contourpy==1.1.0
cubinlinker @ file:///rapids/cubinlinker-0.3.0%2B2.g155b525-cp310-cp310-linux_x86_64.whl#sha256=3abbc1f451c3aad9998ddd733c58bdd09fe0904046411ea7cd88027eaaf76f59
cuda-python @ file:///rapids/cuda_python-12.1.0rc5%2B1.g8659927-cp310-cp310-linux_x86_64.whl#sha256=d9e5482d4774cc8c71b9e92b99dda8c43f764356d23777abe3f20282f36f5677
cudf @ file:///rapids/cudf-23.6.0-cp310-cp310-linux_x86_64.whl#sha256=3cb3c9595ceffba72a2875cba7b80a6a50cf8c32fcc5852900bec0c4fcc83ec1
cugraph @ file:///rapids/cugraph-23.6.0-cp310-cp310-linux_x86_64.whl#sha256=31cb17bc01f601ed755494f7444696ee433acc140039ab8623e44f3450c3932d
cugraph-dgl @ file:///rapids/cugraph_dgl-23.6.0-py3-none-any.whl#sha256=eec7130c644e26c9c7c97ad347feac99222e3437cb53b969a7dc7bf5793e4a25
cugraph-service-client @ file:///rapids/cugraph_service_client-23.6.0-py3-none-any.whl#sha256=e9e4d156f2f6d29ebfbe0f4c491649a62649780e48cf7cb8abb8ff645605e310
cugraph-service-server @ file:///rapids/cugraph_service_server-23.6.0-py3-none-any.whl#sha256=3c07645c43da908ee466c185ba450636d2e4a74267c79258147552f5bd6a5d6f
cuml @ file:///rapids/cuml-23.6.0-cp310-cp310-linux_x86_64.whl#sha256=f51ef18b11c430f945cca89c771904c65ec86b3cb9a46dd745ef99953212a2aa
cupy-cuda12x @ file:///rapids/cupy_cuda12x-12.1.0-cp310-cp310-linux_x86_64.whl#sha256=42bb39c9e6586e09ad8f00a9ac20543573b571ee90c955e7c10817b4cecebd89
cut-cross-entropy==24.11.4
cycler==0.11.0
cymem==2.0.7
Cython==0.29.36
dask @ file:///rapids/dask-2023.3.2-py3-none-any.whl#sha256=5e64763d62feb18afd3ad66f364e0b4f456f7ac92e894fcc87950af75029ecdf
dask-cuda @ file:///rapids/dask_cuda-23.6.0-py3-none-any.whl#sha256=a7e8287f5256f7b19fd6ff613a29de820ba5e4929b8c40e417004fe66d4c7e07
dask-cudf @ file:///rapids/dask_cudf-23.6.0-py3-none-any.whl#sha256=f9b8190b2b0c92c19e76bcf0f2cb98993029c0e90387e09e8d72ae0163585c2f
dataclasses-json==0.6.7
datasets==3.2.0
debugpy==1.6.7
decorator==5.1.1
deepspeed==0.15.4
defusedxml==0.7.1
Deprecated==1.2.15
dill==0.3.8
dirtyjson==1.0.8
distributed @ file:///rapids/distributed-2023.3.2.1-py3-none-any.whl#sha256=a7756a4b952ec5a7fd3163e93aef99aaf8b0000568fa9ee7c000113a470d7f8e
distro==1.9.0
dm-tree==0.1.8
docker-pycreds==0.4.0
docstring_parser==0.16
einops==0.6.1
exceptiongroup==1.1.2
execnet==1.9.0
executing==1.2.0
expecttest==0.1.3
fastjsonschema==2.17.1
fastrlock @ file:///rapids/fastrlock-0.8.1-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_24_x86_64.whl#sha256=d6c53abeae3f9a55b5c65824cec9df59159fa50e8fa800a5c6e8de42b2219c28
filelock==3.12.2
filetype==1.2.0
fire==0.7.0
flash-attn==1.0.7
fonttools==4.40.0
frozenlist @ file:///rapids/frozenlist-1.3.3-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl#sha256=783263a4eaad7c49983fe4b2e7b53fa9770c136c270d2d4bbb6d2192bf4d9caf
fsspec==2023.6.0
gast==0.5.4
gitdb==4.0.11
GitPython==3.1.43
google-auth==2.21.0
google-auth-oauthlib==0.4.6
graphsurgeon @ file:///workspace/TensorRT-8.6.1.6/graphsurgeon/graphsurgeon-0.4.6-py2.py3-none-any.whl#sha256=0fbadaefbbe6e9920b9f814ae961c4a279be602812edf3ed7fb9cc6f8f4809fe
greenlet==3.1.1
grpcio==1.56.0
h11==0.14.0
h5py==3.11.0
hdf5plugin==4.4.0
hf_transfer==0.1.8
hjson==3.1.0
httpcore==1.0.7
httpx==0.27.2
huggingface-hub==0.26.2
hydra-core==1.3.2
hypothesis==5.35.1
idna==3.4
imageio==2.34.1
importlib-metadata @ file:///rapids/importlib_metadata-6.7.0-py3-none-any.whl#sha256=cb52082e659e97afc5dac71e79de97d8681de3aa07ff18578330904a9d18e5b5
iniconfig==2.0.0
intel-openmp==2021.4.0
ipykernel==6.24.0
ipython==8.14.0
ipython-genutils==0.2.0
ipywidgets==8.1.5
jedi==0.18.2
Jinja2==3.1.2
jiter==0.7.1
joblib @ file:///rapids/joblib-1.3.0-py3-none-any.whl#sha256=172d56d4c43dd6bcd953bea213018c4084cf754963bbf54b8dae40faea716b98
json5==0.9.14
jsonpatch==1.33
jsonpointer==3.0.0
jsonschema==4.18.0
jsonschema-specifications==2023.6.1
jupyter-tensorboard @ git+https://github.com/cliffwoolley/jupyter_tensorboard.git@ffa7e26138b82549453306e06b535a9ac36db17a
jupyter_client==8.3.0
jupyter_core==5.3.1
jupyterlab==2.2.9
jupyterlab-pygments==0.2.2
jupyterlab-server==1.2.0
jupyterlab_widgets==3.0.13
jupytext==1.14.7
kiwisolver==1.4.4
langchain==0.3.8
langchain-core==0.3.21
langchain-text-splitters==0.3.2
langcodes==3.3.0
langsmith==0.1.145
lazy_loader==0.4
librosa==0.9.2
lightning-utilities==0.11.9
llama-cloud==0.1.5
llama-index==0.12.1
llama-index-agent-openai==0.4.0
llama-index-cli==0.4.0
llama-index-core==0.12.1
llama-index-embeddings-openai==0.3.0
llama-index-indices-managed-llama-cloud==0.6.2
llama-index-legacy==0.9.48.post4
llama-index-llms-openai==0.3.1
llama-index-multi-modal-llms-openai==0.3.0
llama-index-program-openai==0.3.0
llama-index-question-gen-openai==0.3.0
llama-index-readers-file==0.4.0
llama-index-readers-llama-parse==0.4.0
llama-parse==0.5.15
llvmlite==0.40.1
locket @ file:///rapids/locket-1.0.0-py2.py3-none-any.whl#sha256=b6c819a722f7b6bd955b80781788e4a66a55628b858d347536b7e81325a3a5e3
Markdown==3.4.3
markdown-it-py==3.0.0
MarkupSafe==2.1.3
marshmallow==3.23.1
matplotlib==3.7.2
matplotlib-inline==0.1.6
mdit-py-plugins==0.4.0
mdurl==0.1.2
mistune==3.0.1
mkl==2021.1.1
mkl-devel==2021.1.1
mkl-include==2021.1.1
mne==1.6.0
mock==5.0.2
mpmath==1.3.0
msgpack @ file:///rapids/msgpack-1.0.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl#sha256=e42b9594cc3bf4d838d67d6ed62b9e59e201862a25e9a157019e171fbe672dd3
multidict @ file:///rapids/multidict-6.0.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl#sha256=36c63aaa167f6c6b04ef2c85704e93af16c11d20de1d133e39de6a0e84582a93
multiprocess==0.70.16
murmurhash==1.0.9
mypy-extensions==1.0.0
nbclient==0.8.0
nbconvert==7.6.0
nbformat==5.9.0
nest-asyncio==1.6.0
networkx==3.4.2
ninja==1.11.1
nltk==3.9.1
notebook==6.4.10
numba @ file:///rapids/numba-0.57.1%2B1.gf851d279c-cp310-cp310-linux_x86_64.whl#sha256=374c5eaf2ad68c83368c427ae516cd6060a428810a0a4ee3b0d721dad820d44a
numpy==1.26.4
nvidia-cublas-cu12==12.4.5.8
nvidia-cuda-cupti-cu12==12.4.127
nvidia-cuda-nvrtc-cu12==12.4.127
nvidia-cuda-runtime-cu12==12.4.127
nvidia-cudnn-cu12==9.1.0.70
nvidia-cufft-cu12==11.2.1.3
nvidia-curand-cu12==10.3.5.147
nvidia-cusolver-cu12==11.6.1.9
nvidia-cusparse-cu12==12.3.1.170
nvidia-dali-cuda120==1.27.0
nvidia-nccl-cu12==2.21.5
nvidia-nvjitlink-cu12==12.4.127
nvidia-nvtx-cu12==12.4.127
nvidia-pyindex==1.0.9
nvtx @ file:///rapids/nvtx-0.2.5-cp310-cp310-linux_x86_64.whl#sha256=b6531c8a79e9f7ac0dd0e6f165c31cab2a71c424777dbd75b564b8c8d19865b0
oauthlib==3.2.2
omegaconf==2.3.0
onnx @ file:///opt/pytorch/pytorch/third_party/onnx
openai==1.55.0
opencv @ file:///opencv-4.7.0/modules/python/package
orjson==3.10.12
outcome==1.3.0.post0
packaging==24.2
pandas @ file:///rapids/pandas-1.5.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl#sha256=d0d8fd58df5d17ddb8c72a5075d87cd80d71b542571b5f78178fb067fa4e9c72
pandocfilters==1.5.0
parso==0.8.3
partd @ file:///rapids/partd-1.4.0-py3-none-any.whl#sha256=7a63529348cf0dff14b986db641cd1b83c16b5cb9fc647c2851779db03282ef8
pathy==0.10.2
peft==0.14.0
pexpect==4.8.0
pickleshare==0.7.5
Pillow @ file:///tmp/pillow-simd
platformdirs==3.8.0
pluggy==1.2.0
ply @ file:///rapids/ply-3.11-py2.py3-none-any.whl#sha256=096f9b8350b65ebd2fd1346b12452efe5b9607f7482813ffca50c22722a807ce
polygraphy==0.47.1
pooch==1.7.0
preshed==3.0.8
prettytable==3.8.0
prometheus-client==0.17.0
prompt-toolkit==3.0.39
propcache==0.2.0
protobuf==3.20.3
psutil @ file:///rapids/psutil-5.9.4-cp310-abi3-linux_x86_64.whl#sha256=6ec529af5a6aae129ab7338766af46c19452c9b853ff6e95da9ab3927a6df1ca
ptxcompiler @ file:///rapids/ptxcompiler-0.8.1%2B1.gb323413-cp310-cp310-linux_x86_64.whl#sha256=abf237b2ed1ca160175ffa8a79dbcfc3fb71dc2468bdcf0ea4ace13a1e44c90e
ptyprocess==0.7.0
pure-eval==0.2.2
py-cpuinfo==9.0.0
pyarrow==18.0.0
pyasn1==0.5.0
pyasn1-modules==0.3.0
pybind11==2.10.4
pycocotools @ git+https://github.com/nvidia/cocoapi.git@fa44301f7a8b3f95a9f2751d19bfd735b0f6c65d#subdirectory=PythonAPI
pycparser==2.21
pydantic==2.9.2
pydantic_core==2.23.4
Pygments==2.15.1
pylibcugraph @ file:///rapids/pylibcugraph-23.6.0-cp310-cp310-linux_x86_64.whl#sha256=372d933675f597d329f75841c73c1c31786aec6a50921db3478eb23973e9331f
pylibcugraphops @ file:///rapids/pylibcugraphops-23.6.0-cp310-cp310-linux_x86_64.whl#sha256=ae9101d2dfc23a9f1a45cc0cd61e44250ca83237d3f85b8fe44061d59b70c0ce
pylibraft @ file:///rapids/pylibraft-23.6.0-cp310-cp310-linux_x86_64.whl#sha256=35d5d69fff0944bb9da0501a2bb8372b196f1a19fe98af56d9871e4bdd420a7e
pynvml @ file:///rapids/pynvml-11.4.1-py3-none-any.whl#sha256=d27be542cd9d06558de18e2deffc8022ccd7355bc7382255d477038e7e424c6c
pyparsing==3.0.9
pypdf==5.1.0
PySocks==1.7.1
pytest==7.4.0
pytest-flakefinder==1.1.0
pytest-rerunfailures==12.0
pytest-shard==0.1.2
pytest-xdist==3.3.1
python-dateutil==2.8.2
python-hostlist==1.23.0
pytorch-quantization==2.1.2
pytz @ file:///rapids/pytz-2023.3-py2.py3-none-any.whl#sha256=a151b3abb88eda1d4e34a9814df37de2a80e301e68ba0fd856fb9b46bfbbbffb
PyYAML==6.0.2
pyzmq==25.1.0
raft-dask @ file:///rapids/raft_dask-23.6.0-cp310-cp310-linux_x86_64.whl#sha256=936720dd29c15967a7899efcd840028fcfecf682ee4d6159c1f6512875411f84
referencing==0.29.1
regex==2023.6.3
requests==2.32.3
requests-oauthlib==1.3.1
requests-toolbelt==1.0.0
resampy==0.4.2
rich==13.9.4
rmm @ file:///rapids/rmm-23.6.0-cp310-cp310-linux_x86_64.whl#sha256=573b108a4f7185a23e7e4f834bef6b95c324847b3963cd69733e372a085abec2
rpds-py==0.8.8
rsa==4.9
safetensors==0.4.5
scikit-learn @ file:///rapids/scikit_learn-1.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl#sha256=184a42842a4e698ffa4d849b6019de50a77a0aa24d26afa28fa49c9190bb144b
scipy @ file:///rapids/scipy-1.11.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl#sha256=a53f9cebcfda6158c241c35a559407a4ef6b8cb0863eb4144958fe0a0b7c3dae
selenium==4.26.1
Send2Trash==1.8.2
sentence-transformers==3.3.1
sentencepiece==0.2.0
sentry-sdk==2.19.0
setproctitle==1.3.4
shtab==1.7.1
six==1.16.0
smart-open==6.3.0
smmap==5.0.1
sniffio==1.3.1
sortedcontainers==2.4.0
soundfile==0.12.1
soupsieve==2.4.1
spacy==3.5.4
spacy-legacy==3.0.12
spacy-loggers==1.0.4
sphinx-glpi-theme==0.3
SQLAlchemy==2.0.36
srsly==2.4.6
stack-data==0.6.2
striprtf==0.0.26
sympy==1.13.1
tabulate==0.9.0
tbb==2021.9.0
tblib @ file:///rapids/tblib-2.0.0-py3-none-any.whl#sha256=9100bfa016b047d5b980d66e7efed952fbd20bd85b56110aaf473cb97d18709a
tenacity==8.5.0
tensorboard==2.9.0
tensorboard-data-server==0.6.1
tensorboard-plugin-wit==1.8.1
tensorrt @ file:///workspace/TensorRT-8.6.1.6/python/tensorrt-8.6.1-cp310-none-linux_x86_64.whl#sha256=2684b4772cb16088184266728a0668f5dac14e66f088c4ccff2096ccb222d74c
termcolor==2.5.0
terminado==0.17.1
thinc==8.1.10
threadpoolctl==3.1.0
thriftpy2 @ file:///rapids/thriftpy2-0.4.16-cp310-cp310-linux_x86_64.whl#sha256=5608fa32e4bd4f82f8f1d02c6e37329a38e9d14de994342c897a153917818d74
tiktoken==0.8.0
tinycss2==1.2.1
tokenizers==0.21.0
toml==0.10.2
tomli==2.0.1
toolz @ file:///rapids/toolz-0.12.0-py3-none-any.whl#sha256=2059bd4148deb1884bb0eb770a3cde70e7f954cfbbdc2285f1f2de01fd21eb6f
torch==2.5.1
torch-tensorrt @ file:///opt/pytorch/torch_tensorrt/py/dist/torch_tensorrt-1.5.0.dev0-cp310-cp310-linux_x86_64.whl#sha256=c98edecc0b3611f44778568b324cd408424763ed36d45f16259b5a9b3a379edb
torchaudio==2.5.1
torchdata @ file:///opt/pytorch/data
torchmetrics==1.6.0
torchtext @ file:///opt/pytorch/text
torchvision==0.20.1
tornado==6.3.2
tqdm==4.67.1
traitlets==5.9.0
transformer-engine @ git+https://github.com/NVIDIA/TransformerEngine.git@96ed6fc69d99a9cff49637dbc58c837c8d921ad7
transformers==4.47.0
treelite @ file:///rapids/treelite-3.2.0-cp310-cp310-linux_x86_64.whl#sha256=73db6e9525410c4907b2580336ef674cbc3c13dbc78b5f5263357cb5b232755d
treelite-runtime @ file:///rapids/treelite_runtime-3.2.0-cp310-cp310-linux_x86_64.whl#sha256=60f470fedd8be62fc7ad932c88dbe1b813e328e35e29d534d524848ab9f76b79
trio==0.27.0
trio-websocket==0.11.1
triton==3.1.0
trl==0.13.0
typeguard==4.4.1
typer==0.9.0
types-dataclasses==0.6.6
typing-inspect==0.9.0
typing_extensions==4.12.2
tyro==0.9.2
ucx-py @ file:///rapids/ucx_py-0.32.0-cp310-cp310-linux_x86_64.whl#sha256=11be2cf8130e60f68625832a7e34c8c867095fcd9c1ed234752b70aab3bfc0ce
uff @ file:///workspace/TensorRT-8.6.1.6/uff/uff-0.6.9-py2.py3-none-any.whl#sha256=618a3f812d491f0d3c4f2e38b99e03217ca37b206db14cee079f2bf681eb4fe3
unsloth==2024.11.9
unsloth_zoo==2024.11.7
urllib3==1.26.16
wandb==0.19.1
wasabi==1.1.2
wcwidth==0.2.6
webencodings==0.5.1
websocket-client==1.8.0
Werkzeug==2.3.6
widgetsnbextension==4.0.13
wrapt==1.17.0
wsproto==1.2.0
xdoctest==1.0.2
xformers==0.0.28.post3
xgboost @ file:///rapids/xgboost-1.7.5-cp310-cp310-linux_x86_64.whl#sha256=b8362affc7921f01cb3ca50c4f56bd8d888ff4c2b94a3c2fd5f3b2e09fe62e8c
xxhash==3.5.0
yarl==1.18.0
zict @ file:///rapids/zict-3.0.0-py2.py3-none-any.whl#sha256=5796e36bd0e0cc8cf0fbc1ace6a68912611c1dbd74750a3f3026b9b9d6a327ae
zipp @ file:///rapids/zipp-3.15.0-py3-none-any.whl#sha256=48904fc76a60e542af151aded95726c1a5c34ed43ab4134b597665c86d7ad556

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

Developed by: [More Information Needed]
Funded by [optional]: [More Information Needed]
Shared by [optional]: [More Information Needed]
Model type: [More Information Needed]
Language(s) (NLP): [More Information Needed]
License: [More Information Needed]
Finetuned from model [optional]: [More Information Needed]

Model Sources [optional]

Repository: [More Information Needed]
Paper [optional]: [More Information Needed]
Demo [optional]: [More Information Needed]

Uses

Direct Use

[More Information Needed]

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

[More Information Needed]

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Data

[More Information Needed]

Training Procedure

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

Training regime: [More Information Needed]

Speeds, Sizes, Times [optional]

[More Information Needed]

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

Hardware Type: [More Information Needed]
Hours used: [More Information Needed]
Cloud Provider: [More Information Needed]
Compute Region: [More Information Needed]
Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]

Haya-Kei/llm-jp-3-13b-finetune

Model Card for Model ID

Model Details

Sample Use

Entire Code

Requirement

Model Description

Model Sources [optional]

Uses

Direct Use

Downstream Use [optional]

Out-of-Scope Use

Bias, Risks, and Limitations

Recommendations

How to Get Started with the Model

Training Details

Training Data

Training Procedure

Preprocessing [optional]

Training Hyperparameters

Speeds, Sizes, Times [optional]

Evaluation

Testing Data, Factors & Metrics

Testing Data

Factors

Metrics

Results

Summary

Model Examination [optional]

Environmental Impact

Technical Specifications [optional]

Model Architecture and Objective

Compute Infrastructure

Hardware

Software

Citation [optional]

Glossary [optional]

More Information [optional]

Model Card Authors [optional]

Model Card Contact

Haya-Kei/
llm-jp-3-13b-finetune