Instructions to use kaitchup/Llama-3.3-70B-Instruct-AutoRound-GPTQ-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kaitchup/Llama-3.3-70B-Instruct-AutoRound-GPTQ-4bit with Transformers:

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

pipe = pipeline("text-generation", model="kaitchup/Llama-3.3-70B-Instruct-AutoRound-GPTQ-4bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kaitchup/Llama-3.3-70B-Instruct-AutoRound-GPTQ-4bit")
model = AutoModelForCausalLM.from_pretrained("kaitchup/Llama-3.3-70B-Instruct-AutoRound-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 kaitchup/Llama-3.3-70B-Instruct-AutoRound-GPTQ-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kaitchup/Llama-3.3-70B-Instruct-AutoRound-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": "kaitchup/Llama-3.3-70B-Instruct-AutoRound-GPTQ-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kaitchup/Llama-3.3-70B-Instruct-AutoRound-GPTQ-4bit

SGLang

How to use kaitchup/Llama-3.3-70B-Instruct-AutoRound-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 "kaitchup/Llama-3.3-70B-Instruct-AutoRound-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": "kaitchup/Llama-3.3-70B-Instruct-AutoRound-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 "kaitchup/Llama-3.3-70B-Instruct-AutoRound-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": "kaitchup/Llama-3.3-70B-Instruct-AutoRound-GPTQ-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kaitchup/Llama-3.3-70B-Instruct-AutoRound-GPTQ-4bit with Docker Model Runner:
```
docker model run hf.co/kaitchup/Llama-3.3-70B-Instruct-AutoRound-GPTQ-4bit
```

bnjmnmarie commited on Dec 9, 2024

Commit

37a224e

verified ·

1 Parent(s): b751fd4

Update README.md

Browse files

Files changed (1) hide show

README.md +21 -1

README.md CHANGED Viewed

@@ -1,4 +1,24 @@
 ---
 library_name: transformers
 license: llama3.3
----

 ---
+language:
+- en
 library_name: transformers
+tags:
+- auto-gptq
+- AutoRound
 license: llama3.3
+---
+## Model Details
+This is [meta-llama/Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct) quantized with [AutoRound](https://github.com/intel/auto-round/tree/main) (symmetric quantization) and serialized with the GPTQ format in 4-bit. The model has been created, tested, and evaluated by The Kaitchup.
+Details on the quantization process and how to use the model here:
+[How to Quantize and Run Llama 3.3 70B Instruct on Your GPU](https://kaitchup.substack.com/p/how-to-quantize-and-run-llama-33)
+![Llama 3.3 70B Instruct_ Zero-Shot MMLU (Accuracy).png](https://cdn-uploads.huggingface.co/production/uploads/64b93e6bd6c468ac7536607e/0UOK_IsUinziw4GUMqq3_.png)
+![Llama 3.3 70B Instruct_ Model Size.png](https://cdn-uploads.huggingface.co/production/uploads/64b93e6bd6c468ac7536607e/hB8AdtD1DfVC90kOkYowz.png)
+- **Developed by:** [The Kaitchup](https://kaitchup.substack.com/)
+- **Language(s) (NLP):** English
+- **License:** Llama 3.3