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

Libraries

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

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

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

# Load model directly
from transformers import AutoProcessor, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("hf-internal-testing/tiny-random-WhisperForCausalLM")
model = AutoModelForCausalLM.from_pretrained("hf-internal-testing/tiny-random-WhisperForCausalLM", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Use Docker

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

SGLang

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

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

tiny-random-WhisperForCausalLM / config.json

hf-transformers-bot

Upload tiny models for WhisperForCausalLM

e7febfd over 2 years ago

Raw

History Blame Contribute Delete

1.24 kB

	{
	"activation_dropout": 0.0,
	"activation_function": "gelu",
	"apply_spec_augment": false,
	"architectures": [
	"WhisperForCausalLM"
	],
	"attention_dropout": 0.1,
	"begin_suppress_tokens": null,
	"bos_token_id": 50257,
	"classifier_proj_size": 256,
	"d_model": 16,
	"decoder_attention_heads": 4,
	"decoder_ffn_dim": 16,
	"decoder_layerdrop": 0.0,
	"decoder_layers": 2,
	"decoder_start_token_id": 85,
	"dropout": 0.1,
	"encoder_attention_heads": 4,
	"encoder_ffn_dim": 16,
	"encoder_layerdrop": 0.0,
	"encoder_layers": 2,
	"eos_token_id": 50257,
	"init_std": 0.02,
	"input_channels": 1,
	"is_decoder": true,
	"is_encoder_decoder": false,
	"mask_feature_length": 10,
	"mask_feature_min_masks": 0,
	"mask_feature_prob": 0.0,
	"mask_time_length": 10,
	"mask_time_min_masks": 2,
	"mask_time_prob": 0.05,
	"max_position_embeddings": 200,
	"max_source_positions": 200,
	"max_target_positions": 200,
	"median_filter_width": 7,
	"model_type": "whisper",
	"num_hidden_layers": 2,
	"num_mel_bins": 80,
	"pad_token_id": 50257,
	"scale_embedding": false,
	"torch_dtype": "float32",
	"transformers_version": "4.36.0.dev0",
	"use_cache": true,
	"use_weighted_layer_sum": false,
	"vocab_size": 51865
	}