Instructions to use ISTA-DASLab/Meta-Llama-3-70B-Instruct-AQLM-2Bit-1x16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ISTA-DASLab/Meta-Llama-3-70B-Instruct-AQLM-2Bit-1x16 with Transformers:

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

pipe = pipeline("text-generation", model="ISTA-DASLab/Meta-Llama-3-70B-Instruct-AQLM-2Bit-1x16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ISTA-DASLab/Meta-Llama-3-70B-Instruct-AQLM-2Bit-1x16")
model = AutoModelForCausalLM.from_pretrained("ISTA-DASLab/Meta-Llama-3-70B-Instruct-AQLM-2Bit-1x16")
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 ISTA-DASLab/Meta-Llama-3-70B-Instruct-AQLM-2Bit-1x16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ISTA-DASLab/Meta-Llama-3-70B-Instruct-AQLM-2Bit-1x16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ISTA-DASLab/Meta-Llama-3-70B-Instruct-AQLM-2Bit-1x16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ISTA-DASLab/Meta-Llama-3-70B-Instruct-AQLM-2Bit-1x16

SGLang

How to use ISTA-DASLab/Meta-Llama-3-70B-Instruct-AQLM-2Bit-1x16 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 "ISTA-DASLab/Meta-Llama-3-70B-Instruct-AQLM-2Bit-1x16" \
    --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": "ISTA-DASLab/Meta-Llama-3-70B-Instruct-AQLM-2Bit-1x16",
		"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 "ISTA-DASLab/Meta-Llama-3-70B-Instruct-AQLM-2Bit-1x16" \
        --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": "ISTA-DASLab/Meta-Llama-3-70B-Instruct-AQLM-2Bit-1x16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ISTA-DASLab/Meta-Llama-3-70B-Instruct-AQLM-2Bit-1x16 with Docker Model Runner:
```
docker model run hf.co/ISTA-DASLab/Meta-Llama-3-70B-Instruct-AQLM-2Bit-1x16
```

SpiridonSunRotator commited on May 4, 2024

Commit

47ff65c

verified ·

1 Parent(s): 9df2164

Added metrics

Browse files

Files changed (1) hide show

README.md +5 -5

README.md CHANGED Viewed

@@ -13,8 +13,8 @@ Official [AQLM](https://arxiv.org/abs/2401.06118) quantization of [meta-llama/Me
 For this quantization, we used 1 codebook of 16 bits.
-Results (in progress):
-| Model      | Quantization | Model size, Gb |
-|------|------|------|
-|meta-llama/Meta-Llama-3-70B-Instruct | - | 141.2 |
-|  | 1x16 |  21.9 |

 For this quantization, we used 1 codebook of 16 bits.
+Results (measured with `lm_eval==4.0`):
+| Model      | Quantization | MMLU (5-shot) | ArcC| ArcE| Hellaswag | Winogrande | PiQA | Model size, Gb |
+|------|------|-------|------|------|------|------|------|------|
+|meta-llama/Meta-Llama-3-70B | - | 0.7980 | 0.6160	| 0.8624 | 0.6367 | 0.8183 | 0.7632 | 141.2 |
+|  | 1x16 | 0.7587 | 0.4863	| 0.7668 | 0.6159 | 0.7481 | 0.7537 | 21.9 |