Instructions to use hf-internal-testing/tiny-random-OPTForCausalLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hf-internal-testing/tiny-random-OPTForCausalLM with Transformers:

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

pipe = pipeline("text-generation", model="hf-internal-testing/tiny-random-OPTForCausalLM")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hf-internal-testing/tiny-random-OPTForCausalLM")
model = AutoModelForCausalLM.from_pretrained("hf-internal-testing/tiny-random-OPTForCausalLM")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use hf-internal-testing/tiny-random-OPTForCausalLM with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/hf-internal-testing/tiny-random-OPTForCausalLM

SGLang

How to use hf-internal-testing/tiny-random-OPTForCausalLM 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 "hf-internal-testing/tiny-random-OPTForCausalLM" \
    --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": "hf-internal-testing/tiny-random-OPTForCausalLM",
		"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 "hf-internal-testing/tiny-random-OPTForCausalLM" \
        --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": "hf-internal-testing/tiny-random-OPTForCausalLM",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hf-internal-testing/tiny-random-OPTForCausalLM with Docker Model Runner:
```
docker model run hf.co/hf-internal-testing/tiny-random-OPTForCausalLM
```

tiny-random-OPTForCausalLM / config.json

ydshieh HF Staff

Upload tiny models for OPTForCausalLM

190d1f4 over 3 years ago

raw

history blame contribute delete

684 Bytes

	{
	"_name_or_path": "temp/dummy/opt/OPTForCausalLM",
	"_remove_final_layer_norm": false,
	"activation_function": "relu",
	"architectures": [
	"OPTForCausalLM"
	],
	"attention_dropout": 0.1,
	"bos_token_id": 2,
	"do_layer_norm_before": true,
	"dropout": 0.1,
	"embed_dim": 16,
	"eos_token_id": 2,
	"ffn_dim": 4,
	"hidden_size": 16,
	"init_std": 0.02,
	"is_decoder": true,
	"layerdrop": 0.0,
	"max_position_embeddings": 100,
	"model_type": "opt",
	"num_attention_heads": 4,
	"num_hidden_layers": 5,
	"pad_token_id": 1,
	"torch_dtype": "float32",
	"transformers_version": "4.25.0.dev0",
	"use_cache": true,
	"vocab_size": 50265,
	"word_embed_proj_dim": 16
	}