Instructions to use Taywon/llama-405b-honly-A2plus_s3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Taywon/llama-405b-honly-A2plus_s3 with Transformers:

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

pipe = pipeline("text-generation", model="Taywon/llama-405b-honly-A2plus_s3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Taywon/llama-405b-honly-A2plus_s3")
model = AutoModelForCausalLM.from_pretrained("Taywon/llama-405b-honly-A2plus_s3", 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 Taywon/llama-405b-honly-A2plus_s3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Taywon/llama-405b-honly-A2plus_s3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Taywon/llama-405b-honly-A2plus_s3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Taywon/llama-405b-honly-A2plus_s3

SGLang

How to use Taywon/llama-405b-honly-A2plus_s3 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 "Taywon/llama-405b-honly-A2plus_s3" \
    --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": "Taywon/llama-405b-honly-A2plus_s3",
		"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 "Taywon/llama-405b-honly-A2plus_s3" \
        --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": "Taywon/llama-405b-honly-A2plus_s3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Taywon/llama-405b-honly-A2plus_s3 with Docker Model Runner:
```
docker model run hf.co/Taywon/llama-405b-honly-A2plus_s3
```

llama-405b-honly-A2plus_s3

File size: 4,168 Bytes

b1ab2e7


Loading dataset from disk:   0%|                                                                                          | 0/53 [00:00<?, ?it/s]
Loading dataset from disk: 100%|██████████████████████████████████████████████████████████████████████████████| 53/53 [00:00<00:00, 45910.39it/s]

Downloading (incomplete total...): 0.00B [00:00, ?B/s]

Fetching ... files: 0it [00:00, ?it/s][A

Fetching ... files: 1it [00:00,  5.50it/s][A
Downloading (incomplete total...):   0%|                                                                               | 0.00/234 [00:01<?, ?B/s]
Downloading (incomplete total...): 100%|██████████████████████████████████████████████████████████████████████████| 234/234 [00:01<00:00, 232B/s]
Downloading (incomplete total...):  49%|███████████████████████████████████▉                                      | 234/482 [00:01<00:01, 232B/s]
Downloading (incomplete total...): 100%|██████████████████████████████████████████████████████████████████████████| 482/482 [00:01<00:00, 347B/s]
Downloading (incomplete total...): 100%|██████████████████████████████████████████████████████████████████████████| 482/482 [00:18<00:00, 347B/s]

Fetching ... files: 2it [00:50, 29.55s/it][A
Fetching ... files: 22it [00:50,  2.29s/it]

Download complete: 100%|██████████████████████████████████████████████████████████████████████████████████████████| 482/482 [00:50<00:00, 347B/s]

Loading weights:   0%|                                                                                                  | 0/1137 [00:00<?, ?it/s][A

Loading weights:  12%|██████████                                                                            | 133/1137 [00:00<00:00, 1104.65it/s][A

Loading weights:  21%|██████████████████▋                                                                    | 244/1137 [00:00<00:00, 936.02it/s][A

Loading weights:  56%|████████████████████████████████████████████████▍                                     | 641/1137 [00:00<00:00, 2134.29it/s][A

Loading weights:  92%|██████████████████████████████████████████████████████████████████████████████▍      | 1050/1137 [00:00<00:00, 2839.11it/s][A
Loading weights: 100%|█████████████████████████████████████████████████████████████████████████████████████| 1137/1137 [00:00<00:00, 2390.99it/s]

Download complete: 100%|█████████████████████████████████████████████████████████████████████████████████████████| 482/482 [01:04<00:00, 7.42B/s]
[2026-05-06 00:16:19,092] [WARNING] [accelerate.utils.dataclasses.__post_init__:1992] [PID:283428] sync_module_states is obsolete in FSDP2, as it is not needed anymore.Setting sync_module_states to None.