Instructions to use dessertlab/offensive-powershell-CodeGPT-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dessertlab/offensive-powershell-CodeGPT-small with Transformers:

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

pipe = pipeline("text-generation", model="dessertlab/offensive-powershell-CodeGPT-small")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dessertlab/offensive-powershell-CodeGPT-small")
model = AutoModelForCausalLM.from_pretrained("dessertlab/offensive-powershell-CodeGPT-small")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use dessertlab/offensive-powershell-CodeGPT-small with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/dessertlab/offensive-powershell-CodeGPT-small

SGLang

How to use dessertlab/offensive-powershell-CodeGPT-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 "dessertlab/offensive-powershell-CodeGPT-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": "dessertlab/offensive-powershell-CodeGPT-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 "dessertlab/offensive-powershell-CodeGPT-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": "dessertlab/offensive-powershell-CodeGPT-small",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use dessertlab/offensive-powershell-CodeGPT-small with Docker Model Runner:
```
docker model run hf.co/dessertlab/offensive-powershell-CodeGPT-small
```

LucianPi commited on May 2, 2024

Commit

d81d30e

verified ·

1 Parent(s): 68d54b0

Delete config.json

Browse files

Files changed (1) hide show

config.json +0 -33

config.json DELETED Viewed

@@ -1,33 +0,0 @@
-{
-  "_name_or_path": "cridin1/codet5p-220m-py-30-1-powershell-last",
-  "architectures": [
-    "T5Model"
-  ],
-  "bos_token_id": 1,
-  "classifier_dropout": 0.0,
-  "d_ff": 3072,
-  "d_kv": 64,
-  "d_model": 768,
-  "decoder_start_token_id": 0,
-  "dense_act_fn": "relu",
-  "dropout_rate": 0.1,
-  "eos_token_id": 2,
-  "feed_forward_proj": "relu",
-  "initializer_factor": 1.0,
-  "is_encoder_decoder": true,
-  "is_gated_act": false,
-  "layer_norm_epsilon": 1e-06,
-  "model_type": "t5",
-  "n_positions": 512,
-  "num_decoder_layers": 12,
-  "num_heads": 12,
-  "num_layers": 12,
-  "output_past": true,
-  "pad_token_id": 0,
-  "relative_attention_max_distance": 128,
-  "relative_attention_num_buckets": 32,
-  "torch_dtype": "float32",
-  "transformers_version": "4.33.2",
-  "use_cache": true,
-  "vocab_size": 32100
-}