Instructions to use kishizaki-sci/Llama-3.1-405B-Instruct-AWQ-4bit-JP-EN with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kishizaki-sci/Llama-3.1-405B-Instruct-AWQ-4bit-JP-EN with Transformers:

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

pipe = pipeline("text-generation", model="kishizaki-sci/Llama-3.1-405B-Instruct-AWQ-4bit-JP-EN")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kishizaki-sci/Llama-3.1-405B-Instruct-AWQ-4bit-JP-EN")
model = AutoModelForCausalLM.from_pretrained("kishizaki-sci/Llama-3.1-405B-Instruct-AWQ-4bit-JP-EN", 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 kishizaki-sci/Llama-3.1-405B-Instruct-AWQ-4bit-JP-EN with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kishizaki-sci/Llama-3.1-405B-Instruct-AWQ-4bit-JP-EN"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kishizaki-sci/Llama-3.1-405B-Instruct-AWQ-4bit-JP-EN",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kishizaki-sci/Llama-3.1-405B-Instruct-AWQ-4bit-JP-EN

SGLang

How to use kishizaki-sci/Llama-3.1-405B-Instruct-AWQ-4bit-JP-EN 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 "kishizaki-sci/Llama-3.1-405B-Instruct-AWQ-4bit-JP-EN" \
    --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": "kishizaki-sci/Llama-3.1-405B-Instruct-AWQ-4bit-JP-EN",
		"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 "kishizaki-sci/Llama-3.1-405B-Instruct-AWQ-4bit-JP-EN" \
        --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": "kishizaki-sci/Llama-3.1-405B-Instruct-AWQ-4bit-JP-EN",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kishizaki-sci/Llama-3.1-405B-Instruct-AWQ-4bit-JP-EN with Docker Model Runner:
```
docker model run hf.co/kishizaki-sci/Llama-3.1-405B-Instruct-AWQ-4bit-JP-EN
```

kishizaki-sci commited on Dec 8, 2024

Commit

ba1bc19

verified ·

1 Parent(s): 45f2b1a

Upload config

Browse files

Files changed (1) hide show

config.json +13 -0

config.json CHANGED Viewed

@@ -23,6 +23,19 @@
   "num_hidden_layers": 126,
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": {
     "factor": 8.0,

   "num_hidden_layers": 126,
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
+  "quantization_config": {
+    "backend": "autoawq",
+    "bits": 4,
+    "do_fuse": false,
+    "exllama_config": null,
+    "fuse_max_seq_len": null,
+    "group_size": 128,
+    "modules_to_fuse": null,
+    "modules_to_not_convert": null,
+    "quant_method": "awq",
+    "version": "gemm",
+    "zero_point": true
+  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": {
     "factor": 8.0,