Text Generation
Transformers
PyTorch
Safetensors
English
gpt2
chemistry
biology
text-generation-inference
Instructions to use Arjun-G-Ravi/chat-GPT2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Arjun-G-Ravi/chat-GPT2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Arjun-G-Ravi/chat-GPT2")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Arjun-G-Ravi/chat-GPT2") model = AutoModelForCausalLM.from_pretrained("Arjun-G-Ravi/chat-GPT2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Arjun-G-Ravi/chat-GPT2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Arjun-G-Ravi/chat-GPT2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Arjun-G-Ravi/chat-GPT2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Arjun-G-Ravi/chat-GPT2
- SGLang
How to use Arjun-G-Ravi/chat-GPT2 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 "Arjun-G-Ravi/chat-GPT2" \ --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": "Arjun-G-Ravi/chat-GPT2", "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 "Arjun-G-Ravi/chat-GPT2" \ --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": "Arjun-G-Ravi/chat-GPT2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Arjun-G-Ravi/chat-GPT2 with Docker Model Runner:
docker model run hf.co/Arjun-G-Ravi/chat-GPT2
Commit ·
a3fe400
1
Parent(s): f230017
Update README.md
Browse files
README.md
CHANGED
|
@@ -81,6 +81,7 @@ Finetune loss: 0.06
|
|
| 81 |
```
|
| 82 |
|
| 83 |
# Comparision with GPT2
|
|
|
|
| 84 |
|
| 85 |
1. Who is the king of the jungle?
|
| 86 |
```
|
|
|
|
| 81 |
```
|
| 82 |
|
| 83 |
# Comparision with GPT2
|
| 84 |
+
GPT2 is a text generation AI and is not meant for question answering purposes. The following comparison is meant to show how good the fine tuned model is, in comparison to the base model.
|
| 85 |
|
| 86 |
1. Who is the king of the jungle?
|
| 87 |
```
|