Instructions to use ModelCloud/Meta-Llama-3.1-70B-Instruct-gptq-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ModelCloud/Meta-Llama-3.1-70B-Instruct-gptq-4bit with Transformers:

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

pipe = pipeline("text-generation", model="ModelCloud/Meta-Llama-3.1-70B-Instruct-gptq-4bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ModelCloud/Meta-Llama-3.1-70B-Instruct-gptq-4bit")
model = AutoModelForCausalLM.from_pretrained("ModelCloud/Meta-Llama-3.1-70B-Instruct-gptq-4bit")
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 ModelCloud/Meta-Llama-3.1-70B-Instruct-gptq-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ModelCloud/Meta-Llama-3.1-70B-Instruct-gptq-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ModelCloud/Meta-Llama-3.1-70B-Instruct-gptq-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ModelCloud/Meta-Llama-3.1-70B-Instruct-gptq-4bit

SGLang

How to use ModelCloud/Meta-Llama-3.1-70B-Instruct-gptq-4bit 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 "ModelCloud/Meta-Llama-3.1-70B-Instruct-gptq-4bit" \
    --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": "ModelCloud/Meta-Llama-3.1-70B-Instruct-gptq-4bit",
		"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 "ModelCloud/Meta-Llama-3.1-70B-Instruct-gptq-4bit" \
        --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": "ModelCloud/Meta-Llama-3.1-70B-Instruct-gptq-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ModelCloud/Meta-Llama-3.1-70B-Instruct-gptq-4bit with Docker Model Runner:
```
docker model run hf.co/ModelCloud/Meta-Llama-3.1-70B-Instruct-gptq-4bit
```

lrl-modelcloud commited on Jul 23, 2024

Commit

e4aa287

verified ·

1 Parent(s): 4507947

Create README.md

Browse files

Files changed (1) hide show

README.md +47 -0

README.md ADDED Viewed

	@@ -0,0 +1,47 @@

+---
+tags:
+- gptq
+- 4bit
+- int4
+- gptqmodel
+- modelcloud
+- llama-3.1
+- 70b
+- instruct
+---
+This model has been quantized using [GPTQModel](https://github.com/ModelCloud/GPTQModel).
+- **bits**: 4
+- **group_size**: 128
+- **desc_act**: true
+- **static_groups**: false
+- **sym**: true
+- **lm_head**: false
+- **damp_percent**: 0.01
+- **true_sequential**: true
+- **model_name_or_path**: ""
+- **model_file_base_name**: "model"
+- **quant_method**: "gptq"
+- **checkpoint_format**: "gptq"
+- **meta**：
+  - **quantizer**: "gptqmodel:0.9.9-dev0"
+**Here is an example:**
+```python
+from transformers import AutoTokenizer
+from gptqmodel import GPTQModel
+model_name = "ModelCloud/Meta-Llama-3.1-70B-Instruct-gptq-4bit"
+prompt = [{"role": "user", "content": "I am in Shanghai, preparing to visit the natural history museum. Can you tell me the best way to"}]
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = GPTQModel.from_quantized(model_name)
+input_tensor = tokenizer.apply_chat_template(prompt, add_generation_prompt=True, return_tensors="pt")
+outputs = model.generate(input_ids=input_tensor.to(model.device), max_new_tokens=100)
+result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=True)
+print(result)
+```