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

Libraries

How to use PascalNotin/Tranception_Small with Transformers:

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

pipe = pipeline("text-generation", model="PascalNotin/Tranception_Small")

# Load model directly
from transformers import AutoTokenizer, AutoModelWithLMHead

tokenizer = AutoTokenizer.from_pretrained("PascalNotin/Tranception_Small")
model = AutoModelWithLMHead.from_pretrained("PascalNotin/Tranception_Small")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use PascalNotin/Tranception_Small with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/PascalNotin/Tranception_Small

SGLang

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

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

Tranception_Small / config.json

PascalNotin

Update config.json

eeb691f over 3 years ago

raw

history blame

1.2 kB

	{
	"MSA_end": null,
	"MSA_filename": null,
	"MSA_start": null,
	"MSA_weight_file_name": null,
	"_name_or_path": "Tranception_Small",
	"activation_function": "squared_relu",
	"architectures": [
	"TranceptionLMHeadModel"
	],
	"attention_mode": "tranception",
	"attn_pdrop": 0.1,
	"bos_token_id": 1,
	"clustal_omega_location": null,
	"embd_pdrop": 0.1,
	"eos_token_id": 2,
	"full_protein_length": null,
	"initializer_range": 0.02,
	"layer_norm_epsilon": 1e-05,
	"local_batch_size": 8,
	"model_type": "gpt2",
	"n_ctx": 1024,
	"n_embd": 768,
	"n_head": 12,
	"n_inner": 3072,
	"n_layer": 12,
	"n_positions": 1024,
	"position_embedding": "grouped_alibi",
	"reorder_and_upcast_attn": false,
	"resid_pdrop": 0.1,
	"retrieval_aggregation_mode": null,
	"retrieval_inference_weight": 0.6,
	"scale_attn_by_inverse_layer_idx": false,
	"scale_attn_weights": true,
	"scoring_window": "optimal",
	"summary_activation": null,
	"summary_first_dropout": 0.1,
	"summary_proj_to_labels": true,
	"summary_type": "cls_index",
	"summary_use_proj": true,
	"tokenizer": null,
	"torch_dtype": "float32",
	"transformers_version": "4.17.0",
	"use_cache": true,
	"vocab_size": 25
	}