Instructions to use kaizerBox/retnet-Final-small-summarization with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kaizerBox/retnet-Final-small-summarization with Transformers:

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

pipe = pipeline("text-generation", model="kaizerBox/retnet-Final-small-summarization")

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("kaizerBox/retnet-Final-small-summarization", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use kaizerBox/retnet-Final-small-summarization with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/kaizerBox/retnet-Final-small-summarization

SGLang

How to use kaizerBox/retnet-Final-small-summarization 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 "kaizerBox/retnet-Final-small-summarization" \
    --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": "kaizerBox/retnet-Final-small-summarization",
		"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 "kaizerBox/retnet-Final-small-summarization" \
        --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": "kaizerBox/retnet-Final-small-summarization",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use kaizerBox/retnet-Final-small-summarization with Docker Model Runner:
```
docker model run hf.co/kaizerBox/retnet-Final-small-summarization
```

retnet-Final-small-summarization / config.json

kaizerBox

Time is 191.96338891983032, Memory is 9.5GB

32244ec over 2 years ago

raw

history blame contribute delete

914 Bytes

	{
	"activation_dropout": 0.0,
	"activation_fn": "swish",
	"architectures": [
	"RetNetForCausalLM"
	],
	"decoder_embed_dim": 64,
	"decoder_ffn_embed_dim": 64,
	"decoder_layers": 3,
	"decoder_normalize_before": true,
	"decoder_retention_heads": 2,
	"decoder_value_embed_dim": 64,
	"deepnorm": false,
	"drop_path_rate": 0.0,
	"dropout": 0.0,
	"eos_token_id": 50256,
	"forward_impl": "parallel",
	"initializer_range": 0.02,
	"is_decoder": true,
	"layernorm_embedding": true,
	"layernorm_eps": 1e-06,
	"model_type": "retnet",
	"no_scale_embedding": false,
	"output_retentions": false,
	"pad_token_id": 50257,
	"recurrent_chunk_size": 64,
	"subln": true,
	"tie_word_embeddings": false,
	"torch_dtype": "float32",
	"transformers_version": "4.35.2",
	"use_cache": true,
	"use_ffn_rms_norm": false,
	"use_glu": true,
	"use_lm_decay": false,
	"vocab_size": 50259,
	"z_loss_coeff": 0.0
	}