Instructions to use nagi1012/llm-jp-3-13b-finetune2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nagi1012/llm-jp-3-13b-finetune2 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nagi1012/llm-jp-3-13b-finetune2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Studio
How to use nagi1012/llm-jp-3-13b-finetune2 with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for nagi1012/llm-jp-3-13b-finetune2 to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for nagi1012/llm-jp-3-13b-finetune2 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for nagi1012/llm-jp-3-13b-finetune2 to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="nagi1012/llm-jp-3-13b-finetune2", max_seq_length=2048, )
Update README.md
Browse files
README.md
CHANGED
|
@@ -136,6 +136,19 @@ trainer = SFTTrainer(
|
|
| 136 |
|
| 137 |
#@title 学習実行
|
| 138 |
trainer_stats = trainer.train()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 139 |
```
|
| 140 |
### 推論
|
| 141 |
```
|
|
|
|
| 136 |
|
| 137 |
#@title 学習実行
|
| 138 |
trainer_stats = trainer.train()
|
| 139 |
+
|
| 140 |
+
# モデルとトークナイザーをHugging Faceにアップロード。
|
| 141 |
+
# 一旦privateでアップロードしてください。
|
| 142 |
+
# 最終成果物が決まったらpublicにするようお願いします。
|
| 143 |
+
new_model_name = "モデルの名前"
|
| 144 |
+
model.push_to_hub_merged(
|
| 145 |
+
new_model_name,
|
| 146 |
+
tokenizer=tokenizer,
|
| 147 |
+
save_method="lora",
|
| 148 |
+
token=HF_TOKEN,
|
| 149 |
+
private=True
|
| 150 |
+
) # Online saving
|
| 151 |
+
tokenizer.push_to_hub(new_model_name, token=HF_TOKEN) # Online saving
|
| 152 |
```
|
| 153 |
### 推論
|
| 154 |
```
|