Instructions to use donghyunli/Llama-2-13b-KronQ-W3A16-g128-fake with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use donghyunli/Llama-2-13b-KronQ-W3A16-g128-fake with Transformers:

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

pipe = pipeline("text-generation", model="donghyunli/Llama-2-13b-KronQ-W3A16-g128-fake")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("donghyunli/Llama-2-13b-KronQ-W3A16-g128-fake")
model = AutoModelForCausalLM.from_pretrained("donghyunli/Llama-2-13b-KronQ-W3A16-g128-fake", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use donghyunli/Llama-2-13b-KronQ-W3A16-g128-fake with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "donghyunli/Llama-2-13b-KronQ-W3A16-g128-fake"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "donghyunli/Llama-2-13b-KronQ-W3A16-g128-fake",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/donghyunli/Llama-2-13b-KronQ-W3A16-g128-fake

SGLang

How to use donghyunli/Llama-2-13b-KronQ-W3A16-g128-fake 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 "donghyunli/Llama-2-13b-KronQ-W3A16-g128-fake" \
    --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": "donghyunli/Llama-2-13b-KronQ-W3A16-g128-fake",
		"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 "donghyunli/Llama-2-13b-KronQ-W3A16-g128-fake" \
        --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": "donghyunli/Llama-2-13b-KronQ-W3A16-g128-fake",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use donghyunli/Llama-2-13b-KronQ-W3A16-g128-fake with Docker Model Runner:
```
docker model run hf.co/donghyunli/Llama-2-13b-KronQ-W3A16-g128-fake
```

donghyunli

nielsr HF Staff commited on Jul 14

Commit

4817c51

1 Parent(s): 28026e0

Add library_name metadata and clean up tags (#1)

Browse files

- Add library_name metadata and clean up tags (9cde392ad34c4f04a2d16fa4c92fa52f8b0c62bf)

Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

Files changed (1) hide show

README.md +11 -10

README.md CHANGED Viewed

@@ -1,17 +1,18 @@
 ---
 base_model: meta-llama/Llama-2-13b-hf
-license: llama2
-tags:
-  - arxiv:2607.07964
-  - kronq
-  - quantization
-  - group-quantization
-  - fake-quant
-  - fp16
 language:
-  - en
 pipeline_tag: text-generation
 ---
 # Llama-2-13b — KronQ W3A16 g128 (fake-quant fp16)
 **Paper:** [arXiv:2607.07964](https://arxiv.org/abs/2607.07964) · **Code:** [GitHub](https://github.com/Intelligent-Computing-Lab-Panda/KronQ)
@@ -47,4 +48,4 @@ Group-128 asymmetric W3, weight-only, `--alpha 0.25`, `--act_order`, BiIP, raw H
 ## License
-Derivative of Llama-2-13b — [llama2 license](https://ai.meta.com/llama/license/).

 ---
 base_model: meta-llama/Llama-2-13b-hf
 language:
+- en
+license: llama2
 pipeline_tag: text-generation
+library_name: transformers
+tags:
+- kronq
+- quantization
+- group-quantization
+- fake-quant
+- fp16
 ---
 # Llama-2-13b — KronQ W3A16 g128 (fake-quant fp16)
 **Paper:** [arXiv:2607.07964](https://arxiv.org/abs/2607.07964) · **Code:** [GitHub](https://github.com/Intelligent-Computing-Lab-Panda/KronQ)
 ## License
+Derivative of Llama-2-13b — [llama2 license](https://ai.meta.com/llama/license/).