Instructions to use reshinthadith/BashGPTNeo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use reshinthadith/BashGPTNeo with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="reshinthadith/BashGPTNeo")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("reshinthadith/BashGPTNeo") model = AutoModelForCausalLM.from_pretrained("reshinthadith/BashGPTNeo") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use reshinthadith/BashGPTNeo with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "reshinthadith/BashGPTNeo" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "reshinthadith/BashGPTNeo", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/reshinthadith/BashGPTNeo
- SGLang
How to use reshinthadith/BashGPTNeo 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 "reshinthadith/BashGPTNeo" \ --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": "reshinthadith/BashGPTNeo", "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 "reshinthadith/BashGPTNeo" \ --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": "reshinthadith/BashGPTNeo", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use reshinthadith/BashGPTNeo with Docker Model Runner:
docker model run hf.co/reshinthadith/BashGPTNeo
reshinth.adith commited on
Commit ·
dc6ac57
1
Parent(s): 9098590
Update README.md
Browse files
README.md
CHANGED
|
@@ -18,6 +18,13 @@ metrics:
|
|
| 18 |
## What is it ?
|
| 19 |
BashGPT-Neo is a [Neural Program Synthesis](https://www.microsoft.com/en-us/research/project/neural-program-synthesis/) Model for Bash Commands and Shell Scripts. Trained on the data provided by [NLC2CMD](https://nlc2cmd.us-east.mybluemix.net/). It is fine-tuned version of GPTNeo-125M by EleutherAI.
|
| 20 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
## Core Contributors 👥
|
| 22 |
- [Reshinth Adithyan](https://github.com/reshinthadithyan)
|
| 23 |
- [Aditya Thuruvas](https://github.com/dhuruvasaditya)
|
|
|
|
| 18 |
## What is it ?
|
| 19 |
BashGPT-Neo is a [Neural Program Synthesis](https://www.microsoft.com/en-us/research/project/neural-program-synthesis/) Model for Bash Commands and Shell Scripts. Trained on the data provided by [NLC2CMD](https://nlc2cmd.us-east.mybluemix.net/). It is fine-tuned version of GPTNeo-125M by EleutherAI.
|
| 20 |
|
| 21 |
+
## Usage
|
| 22 |
+
```py
|
| 23 |
+
from transformers import AutoTokenizer, AutoModelWithLMHead
|
| 24 |
+
tokenizer = AutoTokenizer.from_pretrained("reshinthadith/BashGPTNeo")
|
| 25 |
+
model = AutoModelWithLMHead.from_pretrained("reshinthadith/BashGPTNeo")
|
| 26 |
+
```
|
| 27 |
+
|
| 28 |
## Core Contributors 👥
|
| 29 |
- [Reshinth Adithyan](https://github.com/reshinthadithyan)
|
| 30 |
- [Aditya Thuruvas](https://github.com/dhuruvasaditya)
|