Instructions to use MoritzMo123/kfac-svd_lems_llama-3-8b_0.6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MoritzMo123/kfac-svd_lems_llama-3-8b_0.6 with Transformers:

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

pipe = pipeline("text-generation", model="MoritzMo123/kfac-svd_lems_llama-3-8b_0.6", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("MoritzMo123/kfac-svd_lems_llama-3-8b_0.6", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MoritzMo123/kfac-svd_lems_llama-3-8b_0.6 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MoritzMo123/kfac-svd_lems_llama-3-8b_0.6"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MoritzMo123/kfac-svd_lems_llama-3-8b_0.6",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MoritzMo123/kfac-svd_lems_llama-3-8b_0.6

SGLang

How to use MoritzMo123/kfac-svd_lems_llama-3-8b_0.6 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 "MoritzMo123/kfac-svd_lems_llama-3-8b_0.6" \
    --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": "MoritzMo123/kfac-svd_lems_llama-3-8b_0.6",
		"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 "MoritzMo123/kfac-svd_lems_llama-3-8b_0.6" \
        --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": "MoritzMo123/kfac-svd_lems_llama-3-8b_0.6",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MoritzMo123/kfac-svd_lems_llama-3-8b_0.6 with Docker Model Runner:
```
docker model run hf.co/MoritzMo123/kfac-svd_lems_llama-3-8b_0.6
```

MoritzMo123 commited on Jun 2

Commit

168ca77

verified ·

1 Parent(s): bcaf011

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -10,7 +10,7 @@ torch_dtype: "float16"
 # unsloth/llama-3-8b — lems search — 0.6 target ratio
-This model was compressed using **kfac_svd** with lems rank search starting from [unsloth/llama-3-8b](https://huggingface.co/unsloth/llama-3-8b) as base model. You may check out [our publication](https://openreview.net/forum?id=IjIgNPFuCt) for details on kfac-svd and our LEMS rank search.
 ## Compression Details

 # unsloth/llama-3-8b — lems search — 0.6 target ratio
+This model was compressed using **kfac_svd** with lems rank search starting from [unsloth/llama-3-8b](https://huggingface.co/unsloth/llama-3-8b) as base model. You may check out [our publication](https://openreview.net/forum?id=IjIgNPFuCt) and [project page](https://lems-svd.github.io) for details on kfac-svd and our LEMS rank search.
 ## Compression Details