Instructions to use irodkin/gpt2-wiki2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use irodkin/gpt2-wiki2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="irodkin/gpt2-wiki2")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("irodkin/gpt2-wiki2") model = AutoModelForCausalLM.from_pretrained("irodkin/gpt2-wiki2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use irodkin/gpt2-wiki2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "irodkin/gpt2-wiki2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "irodkin/gpt2-wiki2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/irodkin/gpt2-wiki2
- SGLang
How to use irodkin/gpt2-wiki2 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 "irodkin/gpt2-wiki2" \ --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": "irodkin/gpt2-wiki2", "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 "irodkin/gpt2-wiki2" \ --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": "irodkin/gpt2-wiki2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use irodkin/gpt2-wiki2 with Docker Model Runner:
docker model run hf.co/irodkin/gpt2-wiki2
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,6 +1,7 @@
|
|
| 1 |
---
|
| 2 |
datasets:
|
| 3 |
- wikitext-2-v1
|
|
|
|
| 4 |
language:
|
| 5 |
- en
|
| 6 |
metrics:
|
|
@@ -28,4 +29,4 @@ metrics:
|
|
| 28 |
- x-axis*128 = context length
|
| 29 |
- y-axis = cross entropy
|
| 30 |
|
| 31 |
-

|
|
|
|
| 1 |
---
|
| 2 |
datasets:
|
| 3 |
- wikitext-2-v1
|
| 4 |
+
- wikitext
|
| 5 |
language:
|
| 6 |
- en
|
| 7 |
metrics:
|
|
|
|
| 29 |
- x-axis*128 = context length
|
| 30 |
- y-axis = cross entropy
|
| 31 |
|
| 32 |
+

|