Instructions to use Kendamarron/LongWriter-llm-jp-3-3.7b-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kendamarron/LongWriter-llm-jp-3-3.7b-instruct with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Kendamarron/LongWriter-llm-jp-3-3.7b-instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Kendamarron/LongWriter-llm-jp-3-3.7b-instruct")
model = AutoModelForCausalLM.from_pretrained("Kendamarron/LongWriter-llm-jp-3-3.7b-instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Kendamarron/LongWriter-llm-jp-3-3.7b-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kendamarron/LongWriter-llm-jp-3-3.7b-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kendamarron/LongWriter-llm-jp-3-3.7b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Kendamarron/LongWriter-llm-jp-3-3.7b-instruct

SGLang

How to use Kendamarron/LongWriter-llm-jp-3-3.7b-instruct with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Kendamarron/LongWriter-llm-jp-3-3.7b-instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kendamarron/LongWriter-llm-jp-3-3.7b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Kendamarron/LongWriter-llm-jp-3-3.7b-instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kendamarron/LongWriter-llm-jp-3-3.7b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Kendamarron/LongWriter-llm-jp-3-3.7b-instruct with Docker Model Runner:
```
docker model run hf.co/Kendamarron/LongWriter-llm-jp-3-3.7b-instruct
```

Kendamarron/LongWriter-llm-jp-3-3.7b-instruct

llm-jp/llm-jp-3-3.7b-instructを長文出力ができるようにSFTしたモデルです。

Dataset

Kendamarron/Japanese-LongWriter-3k

Detail

https://zenn.dev/kendama/articles/32aa9ec4bed409

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 2
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 4
total_train_batch_size: 8
total_eval_batch_size: 4
optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 2.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.7184	1.2626	500	0.7673

Framework versions

Transformers 4.46.1
Pytorch 2.5.1+cu124
Datasets 3.1.0
Tokenizers 0.20.3

LLaMA-Factory yaml

### model
model_name_or_path: llm-jp/llm-jp-3-3.7b-instruct

### method
stage: sft
do_train: true
finetuning_type: full
deepspeed: examples/deepspeed/ds_z3_config.json
enable_liger_kernel: true

### dataset
dataset: longwriter
template: alpaca_ja
cutoff_len: 32768
overwrite_cache: true
preprocessing_num_workers: 16

### output
output_dir: saves/llm_jp/full/sft
logging_steps: 1
save_steps: 500
plot_loss: true
overwrite_output_dir: true

### train
per_device_train_batch_size: 2
gradient_accumulation_steps: 1
learning_rate: 1.0e-5
optim: adamw_bnb_8bit
num_train_epochs: 2.0
lr_scheduler_type: cosine
warmup_ratio: 0.1
bf16: true
ddp_timeout: 180000000

### eval
val_size: 0.01
per_device_eval_batch_size: 1
eval_strategy: steps
eval_steps: 500

### logging
report_to: wandb

Downloads last month: 9

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for Kendamarron/LongWriter-llm-jp-3-3.7b-instruct

Base model

llm-jp/llm-jp-3-3.7b-instruct

Finetuned

(6)

this model