Instructions to use minhhien0811/llama3-8b-ja with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use minhhien0811/llama3-8b-ja with Transformers:

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

pipe = pipeline("text-generation", model="minhhien0811/llama3-8b-ja", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("minhhien0811/llama3-8b-ja")
model = AutoModelForCausalLM.from_pretrained("minhhien0811/llama3-8b-ja", device_map="auto")
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 Settings

vLLM

How to use minhhien0811/llama3-8b-ja with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "minhhien0811/llama3-8b-ja"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "minhhien0811/llama3-8b-ja",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/minhhien0811/llama3-8b-ja

SGLang

How to use minhhien0811/llama3-8b-ja 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 "minhhien0811/llama3-8b-ja" \
    --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": "minhhien0811/llama3-8b-ja",
		"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 "minhhien0811/llama3-8b-ja" \
        --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": "minhhien0811/llama3-8b-ja",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use minhhien0811/llama3-8b-ja with Docker Model Runner:
```
docker model run hf.co/minhhien0811/llama3-8b-ja
```

sft

This model is a fine-tuned version of rinna/llama-3-youko-8b on the data_bricks, the kunishou, the ichikara-004-multi, the ichikara-004-single, the apto_instruct, the apto_dialogue, the oasst_ja and the megagon datasets. It achieves the following results on the evaluation set:

Loss: 1.0135

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: 0.0001
train_batch_size: 8
eval_batch_size: 16
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 2
total_train_batch_size: 128
total_eval_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 0.1
num_epochs: 2.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.9155	0.1433	100	1.8934
1.7826	0.2865	200	1.7808
1.6897	0.4298	300	1.6719
1.5887	0.5731	400	1.5738
1.4628	0.7163	500	1.4660
1.3751	0.8596	600	1.3671
1.1263	1.0029	700	1.2831
0.688	1.1461	800	1.2492
0.6544	1.2894	900	1.1818
0.6017	1.4327	1000	1.1207
0.5763	1.5759	1100	1.0708
0.5599	1.7192	1200	1.0365
0.5101	1.8625	1300	1.0170

Framework versions

Transformers 4.41.2
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1

Downloads last month: 3

Safetensors

Model size

8B params

Tensor type

F16

Model tree for minhhien0811/llama3-8b-ja

Base model

meta-llama/Meta-Llama-3-8B

Finetuned

rinna/llama-3-youko-8b

Finetuned

(2)

this model