Instructions to use tugbatumer/OpenELM-450M-Instruct-databaes-SFT-DPO-4bitquantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tugbatumer/OpenELM-450M-Instruct-databaes-SFT-DPO-4bitquantized with Transformers:

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

pipe = pipeline("text-generation", model="tugbatumer/OpenELM-450M-Instruct-databaes-SFT-DPO-4bitquantized", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("tugbatumer/OpenELM-450M-Instruct-databaes-SFT-DPO-4bitquantized", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tugbatumer/OpenELM-450M-Instruct-databaes-SFT-DPO-4bitquantized with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tugbatumer/OpenELM-450M-Instruct-databaes-SFT-DPO-4bitquantized"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tugbatumer/OpenELM-450M-Instruct-databaes-SFT-DPO-4bitquantized",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/tugbatumer/OpenELM-450M-Instruct-databaes-SFT-DPO-4bitquantized

SGLang

How to use tugbatumer/OpenELM-450M-Instruct-databaes-SFT-DPO-4bitquantized 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 "tugbatumer/OpenELM-450M-Instruct-databaes-SFT-DPO-4bitquantized" \
    --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": "tugbatumer/OpenELM-450M-Instruct-databaes-SFT-DPO-4bitquantized",
		"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 "tugbatumer/OpenELM-450M-Instruct-databaes-SFT-DPO-4bitquantized" \
        --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": "tugbatumer/OpenELM-450M-Instruct-databaes-SFT-DPO-4bitquantized",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use tugbatumer/OpenELM-450M-Instruct-databaes-SFT-DPO-4bitquantized with Docker Model Runner:
```
docker model run hf.co/tugbatumer/OpenELM-450M-Instruct-databaes-SFT-DPO-4bitquantized
```

tugbatumer commited on Jun 14, 2024

Commit

e73d7c6

verified ·

1 Parent(s): 8c087f8

Update config.json

Browse files

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -94,7 +94,7 @@
   "quantization_config": {
     "batch_size": 1,
     "bits": 4,
-    "block_name_to_quantize": null,
     "cache_block_outputs": true,
     "damp_percent": 0.1,
     "dataset": "c4",

   "quantization_config": {
     "batch_size": 1,
     "bits": 4,
+    "block_name_to_quantize": "transformer.layers",
     "cache_block_outputs": true,
     "damp_percent": 0.1,
     "dataset": "c4",