Instructions to use TheBloke/Llama-2-13B-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/Llama-2-13B-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/Llama-2-13B-AWQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/Llama-2-13B-AWQ")
model = AutoModelForMultimodalLM.from_pretrained("TheBloke/Llama-2-13B-AWQ")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TheBloke/Llama-2-13B-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/Llama-2-13B-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/Llama-2-13B-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/Llama-2-13B-AWQ

SGLang

How to use TheBloke/Llama-2-13B-AWQ 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 "TheBloke/Llama-2-13B-AWQ" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/Llama-2-13B-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "TheBloke/Llama-2-13B-AWQ" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/Llama-2-13B-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBloke/Llama-2-13B-AWQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/Llama-2-13B-AWQ
```

AttributeError 'LlamaLikeModel' object has no attribute 'layers'

by jeffrey-sh - opened Feb 29, 2024

Discussion

jeffrey-sh

Feb 29, 2024

•

edited Feb 29, 2024

@TheBloke Hello.
I ran the code and the set quant_path to TheBloke/Llama-2-13B-AWQ. However, I encountered the following error. How I resolve this error?

~/autoawq$ CUDA_VISIBLE_DEVICES=0 python3 test.py 
Fetching 13 files: 100%|█████████████████████| 13/13 [00:00<00:00, 86963.24it/s]
Replacing layers...: 100%|██████████████████████| 40/40 [00:04<00:00,  9.63it/s]
Fusing layers...: 100%|█████████████████████████| 40/40 [00:02<00:00, 18.21it/s]
Traceback (most recent call last):
  File "/home/jeffrey/autoawq/test.py", line 94, in <module>
    generated_output = model.generate(
  File "/home/jeffrey/.cache/pypoetry/virtualenvs/autoawq-MwlF3Uxe-py3.10/lib/python3.10/site-packages/awq/models/base.py", line 104, in generate
    return self.model.generate(*args, **kwargs)
  File "/home/jeffrey/.cache/pypoetry/virtualenvs/autoawq-MwlF3Uxe-py3.10/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "/home/jeffrey/.cache/pypoetry/virtualenvs/autoawq-MwlF3Uxe-py3.10/lib/python3.10/site-packages/transformers/generation/utils.py", line 1544, in generate
    return self.greedy_search(
  File "/home/jeffrey/.cache/pypoetry/virtualenvs/autoawq-MwlF3Uxe-py3.10/lib/python3.10/site-packages/transformers/generation/utils.py", line 2401, in greedy_search
    model_inputs = self.prepare_inputs_for_generation(input_ids, **model_kwargs)
  File "/home/jeffrey/.cache/pypoetry/virtualenvs/autoawq-MwlF3Uxe-py3.10/lib/python3.10/site-packages/transformers/models/llama/modeling_llama.py", line 1256, in prepare_inputs_for_generation
    if past_key_value := getattr(self.model.layers[0].self_attn, "past_key_value", None):
  File "/home/jeffrey/.cache/pypoetry/virtualenvs/autoawq-MwlF3Uxe-py3.10/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1688, in __getattr__
    raise AttributeError(f"'{type(self).__name__}' object has no attribute '{name}'")
AttributeError: 'LlamaLikeModel' object has no attribute 'layers'

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