Instructions to use yujiepan/opt-tiny-2layers-random with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yujiepan/opt-tiny-2layers-random with Transformers:

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

pipe = pipeline("text-generation", model="yujiepan/opt-tiny-2layers-random")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yujiepan/opt-tiny-2layers-random")
model = AutoModelForCausalLM.from_pretrained("yujiepan/opt-tiny-2layers-random")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use yujiepan/opt-tiny-2layers-random with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/yujiepan/opt-tiny-2layers-random

SGLang

How to use yujiepan/opt-tiny-2layers-random 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 "yujiepan/opt-tiny-2layers-random" \
    --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": "yujiepan/opt-tiny-2layers-random",
		"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 "yujiepan/opt-tiny-2layers-random" \
        --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": "yujiepan/opt-tiny-2layers-random",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use yujiepan/opt-tiny-2layers-random with Docker Model Runner:
```
docker model run hf.co/yujiepan/opt-tiny-2layers-random
```

yujiepan commited on Sep 2, 2023

Commit

e2d08cc

1 Parent(s): 564b8f7

Upload folder using huggingface_hub

Browse files

Files changed (4) hide show

config.json +1 -1
openvino_model.bin +2 -2
openvino_model.xml +0 -0
pytorch_model.bin +2 -2

config.json CHANGED Viewed

@@ -24,7 +24,7 @@
   "num_hidden_layers": 2,
   "pad_token_id": 1,
   "prefix": "</s>",
-  "torch_dtype": "float16",
   "transformers_version": "4.31.0",
   "use_cache": true,
   "vocab_size": 50272,

   "num_hidden_layers": 2,
   "pad_token_id": 1,
   "prefix": "</s>",
+  "torch_dtype": "float32",
   "transformers_version": "4.31.0",
   "use_cache": true,
   "vocab_size": 50272,

openvino_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48f6424864a138cad4b185f00d8bc4dbb9285eb492560cb0176b63443240b652
-size 840472

 version https://git-lfs.github.com/spec/v1
+oid sha256:61afdb708fc2d6e0afdabdd8243879b4f45d2a3eddf7e9ef9b0b3a27a8539daf
+size 3289476

openvino_model.xml CHANGED Viewed

The diff for this file is too large to render. See raw diff

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2026b1e79691417d069c46a91ccfcf83fbd3f631c806e4b7e9f2c8ff534875d7
-size 851677

 version https://git-lfs.github.com/spec/v1
+oid sha256:ed528002416ee5e22c5c532471570e240a39b2aa3d4b1ab33923718cafe0b0c3
+size 1692061