Instructions to use LMHHHHHH/SpecTUS_pretrained_only with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LMHHHHHH/SpecTUS_pretrained_only with Transformers:

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

pipe = pipeline("text-generation", model="LMHHHHHH/SpecTUS_pretrained_only")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("LMHHHHHH/SpecTUS_pretrained_only")
model = AutoModelForSeq2SeqLM.from_pretrained("LMHHHHHH/SpecTUS_pretrained_only")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use LMHHHHHH/SpecTUS_pretrained_only with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/LMHHHHHH/SpecTUS_pretrained_only

SGLang

How to use LMHHHHHH/SpecTUS_pretrained_only 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 "LMHHHHHH/SpecTUS_pretrained_only" \
    --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": "LMHHHHHH/SpecTUS_pretrained_only",
		"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 "LMHHHHHH/SpecTUS_pretrained_only" \
        --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": "LMHHHHHH/SpecTUS_pretrained_only",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use LMHHHHHH/SpecTUS_pretrained_only with Docker Model Runner:
```
docker model run hf.co/LMHHHHHH/SpecTUS_pretrained_only
```

SpecTUS_pretrained_only / config.json

LMHHHHHH

Duplicate from MS-ML/SpecTUS_pretrained_only

d653120 1 day ago

raw

history blame contribute delete

1.23 kB

	{
	"activation_dropout": 0.0,
	"activation_function": "gelu",
	"architectures": [
	"SpectusForConditionalGeneration"
	],
	"attention_dropout": 0.0,
	"bos_token_id": 3,
	"classifier_dropout": 0.0,
	"d_model": 1024,
	"decoder_attention_heads": 16,
	"decoder_ffn_dim": 4096,
	"decoder_layerdrop": 0.0,
	"decoder_layers": 12,
	"decoder_max_position_embeddings": 200,
	"decoder_start_token_id": 3,
	"dropout": 0.2,
	"encoder_attention_heads": 16,
	"encoder_ffn_dim": 4096,
	"encoder_layerdrop": 0.0,
	"encoder_layers": 12,
	"encoder_max_position_embeddings": null,
	"eos_token_id": 0,
	"forced_eos_token_id": 0,
	"id2label": {
	"0": "LABEL_0",
	"1": "LABEL_1",
	"2": "LABEL_2"
	},
	"init_std": 0.02,
	"is_encoder_decoder": true,
	"label2id": {
	"LABEL_0": 0,
	"LABEL_1": 1,
	"LABEL_2": 2
	},
	"max_length": 200,
	"max_log_id": 29,
	"max_mz": 500,
	"max_position_embeddings": 1024,
	"min_len": 0,
	"model_type": "bart",
	"num_hidden_layers": 12,
	"pad_token_id": 2,
	"scale_embedding": false,
	"separate_encoder_decoder_embeds": true,
	"tie_word_embeddings": false,
	"torch_dtype": "float32",
	"transformers_version": "4.31.0",
	"use_cache": true,
	"vocab_size": 267
	}