Instructions to use MetaAligner/MetaAligner-IMHI-13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MetaAligner/MetaAligner-IMHI-13B with Transformers:

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

pipe = pipeline("text-generation", model="MetaAligner/MetaAligner-IMHI-13B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MetaAligner/MetaAligner-IMHI-13B")
model = AutoModelForCausalLM.from_pretrained("MetaAligner/MetaAligner-IMHI-13B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MetaAligner/MetaAligner-IMHI-13B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/MetaAligner/MetaAligner-IMHI-13B

SGLang

How to use MetaAligner/MetaAligner-IMHI-13B 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 "MetaAligner/MetaAligner-IMHI-13B" \
    --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": "MetaAligner/MetaAligner-IMHI-13B",
		"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 "MetaAligner/MetaAligner-IMHI-13B" \
        --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": "MetaAligner/MetaAligner-IMHI-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MetaAligner/MetaAligner-IMHI-13B with Docker Model Runner:
```
docker model run hf.co/MetaAligner/MetaAligner-IMHI-13B
```

MetaAligner commited on Apr 26, 2024

Commit

b38a1f9

verified ·

1 Parent(s): 3258d49

Upload 3 files

Browse files

Files changed (3) hide show

pytorch_model-00004-of-00006.bin +3 -0
pytorch_model-00005-of-00006.bin +3 -0
pytorch_model-00006-of-00006.bin +3 -0

pytorch_model-00004-of-00006.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:380945bb80d81811fe50302459c3e9599661f211aa74cc0646fd5f3bf385bbc6
+size 9867410489

pytorch_model-00005-of-00006.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:4d9a9957f409d223be46c07b2bab880de26f1162ee8c333cd114d06fab0d8a1d
+size 9867452125

pytorch_model-00006-of-00006.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:6dd5a4da04d2d179144f7333bf759fd6a90ac0bc29c2a75c9c51bd1f4a735bd3
+size 2490475677