Instructions to use ISTA-DASLab/Llama-3.2-1B-Instruct-AQLM-PV-2Bit-2x8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ISTA-DASLab/Llama-3.2-1B-Instruct-AQLM-PV-2Bit-2x8 with Transformers:

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

pipe = pipeline("text-generation", model="ISTA-DASLab/Llama-3.2-1B-Instruct-AQLM-PV-2Bit-2x8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ISTA-DASLab/Llama-3.2-1B-Instruct-AQLM-PV-2Bit-2x8")
model = AutoModelForCausalLM.from_pretrained("ISTA-DASLab/Llama-3.2-1B-Instruct-AQLM-PV-2Bit-2x8")
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 ISTA-DASLab/Llama-3.2-1B-Instruct-AQLM-PV-2Bit-2x8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ISTA-DASLab/Llama-3.2-1B-Instruct-AQLM-PV-2Bit-2x8"
# 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/Llama-3.2-1B-Instruct-AQLM-PV-2Bit-2x8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ISTA-DASLab/Llama-3.2-1B-Instruct-AQLM-PV-2Bit-2x8

SGLang

How to use ISTA-DASLab/Llama-3.2-1B-Instruct-AQLM-PV-2Bit-2x8 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/Llama-3.2-1B-Instruct-AQLM-PV-2Bit-2x8" \
    --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/Llama-3.2-1B-Instruct-AQLM-PV-2Bit-2x8",
		"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/Llama-3.2-1B-Instruct-AQLM-PV-2Bit-2x8" \
        --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/Llama-3.2-1B-Instruct-AQLM-PV-2Bit-2x8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ISTA-DASLab/Llama-3.2-1B-Instruct-AQLM-PV-2Bit-2x8 with Docker Model Runner:
```
docker model run hf.co/ISTA-DASLab/Llama-3.2-1B-Instruct-AQLM-PV-2Bit-2x8
```

run colab cpu

by rakmik - opened Feb 16, 2025

Discussion

rakmik

Feb 16, 2025

from transformers import AutoTokenizer, TextStreamer, AutoModelForCausalLM
import transformers
import torch

quantized_model = AutoModelForCausalLM.from_pretrained(
"ISTA-DASLab/Llama-3.2-1B-Instruct-AQLM-PV-2Bit-2x8", trust_remote_code=True, torch_dtype=torch.float32,
).cpu()
tokenizer = AutoTokenizer.from_pretrained("ISTA-DASLab/Llama-3.2-1B-Instruct-AQLM-PV-2Bit-2x8")

inputs = tokenizer(["Napoleon Bonaparte is "], return_tensors="pt")["input_ids"].cpu()

streamer = TextStreamer(tokenizer)
_ = quantized_model.generate(inputs, streamer=streamer, max_new_tokens=40)

34s
inputs = tokenizer(["Napoleon Bonaparte is "], return_tensors="pt")["input_ids"].cpu()

streamer = TextStreamer(tokenizer)
_ = quantized_model.generate(inputs, streamer=streamer, max_new_tokens=40)
The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's attention_mask to obtain reliable results.
Setting pad_token_id to eos_token_id:128001 for open-end generation.
<|begin_of_text|>Napoleon Bonaparte is 1st of 3 sons of José Bonaparte, a French general and politician. He was born in 1769 in Paris, France. He was educated at the École de Paris

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment