Instructions to use tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.3 with Transformers:

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

pipe = pipeline("text-generation", model="tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.3")
model = AutoModelForCausalLM.from_pretrained("tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.3", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.3

SGLang

How to use tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.3 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 "tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.3" \
    --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": "tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.3",
		"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 "tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.3" \
        --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": "tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.3 with Docker Model Runner:
```
docker model run hf.co/tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.3
```

wont load on oba

by Akyra - opened Mar 7, 2025

Discussion

Akyra

Mar 7, 2025

i got this error after load attempt
16:59:23-264369 INFO Loading "tokyotech-llm_Llama-3.1-Swallow-8B-Instruct-v0.3"
16:59:23-416369 ERROR Failed to load the model.
Traceback (most recent call last):
File "E:\ai\text-generation-webui-snapshot-2024-04-28\modules\ui_model_menu.py", line 214, in load_model_wrapper
shared.model, shared.tokenizer = load_model(selected_model, loader)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\ai\text-generation-webui-snapshot-2024-04-28\modules\models.py", line 90, in load_model
output = load_func_maploader
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\ai\text-generation-webui-snapshot-2024-04-28\modules\models.py", line 152, in huggingface_loader
config = AutoConfig.from_pretrained(path_to_model, trust_remote_code=shared.args.trust_remote_code)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\ai\text-generation-webui-snapshot-2024-04-28\installer_files\env\Lib\site-packages\transformers\models\auto\configuration_auto.py", line 952, in from_pretrained
return config_class.from_dict(config_dict, **unused_kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\ai\text-generation-webui-snapshot-2024-04-28\installer_files\env\Lib\site-packages\transformers\configuration_utils.py", line 761, in from_dict
config = cls(**config_dict)
^^^^^^^^^^^^^^^^^^
File "E:\ai\text-generation-webui-snapshot-2024-04-28\installer_files\env\Lib\site-packages\transformers\models\llama\configuration_llama.py", line 161, in init
self._rope_scaling_validation()
File "E:\ai\text-generation-webui-snapshot-2024-04-28\installer_files\env\Lib\site-packages\transformers\models\llama\configuration_llama.py", line 181, in _rope_scaling_validation
raise ValueError(
ValueError: rope_scaling must be a dictionary with two fields, type and factor, got {'factor': 8.0, 'high_freq_factor': 4.0, 'low_freq_factor': 1.0, 'original_max_position_embeddings': 8192, 'rope_type': 'llama3'}

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment