Text Generation
Transformers
PyTorch
TensorBoard
gpt2
Generated from Trainer
text-generation-inference
Instructions to use JerryWu/gpt2-wikitext2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use JerryWu/gpt2-wikitext2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="JerryWu/gpt2-wikitext2")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("JerryWu/gpt2-wikitext2") model = AutoModelForCausalLM.from_pretrained("JerryWu/gpt2-wikitext2") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use JerryWu/gpt2-wikitext2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "JerryWu/gpt2-wikitext2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "JerryWu/gpt2-wikitext2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/JerryWu/gpt2-wikitext2
- SGLang
How to use JerryWu/gpt2-wikitext2 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 "JerryWu/gpt2-wikitext2" \ --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": "JerryWu/gpt2-wikitext2", "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 "JerryWu/gpt2-wikitext2" \ --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": "JerryWu/gpt2-wikitext2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use JerryWu/gpt2-wikitext2 with Docker Model Runner:
docker model run hf.co/JerryWu/gpt2-wikitext2
End of training
Browse files
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.26.1"
|
| 6 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 510398013
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1962e2766a15967a241d4fd71fb38be7c348adaad6e5c541a123801667606f40
|
| 3 |
size 510398013
|
runs/Feb24_07-07-00_240cf60e2d1e/events.out.tfevents.1677222453.240cf60e2d1e.3329.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce3de53122f00ae5b16f4d5b59e38e8831c23255cbfc5bbcb5d0651f4dd57f46
|
| 3 |
+
size 7247
|
runs/Feb24_07-07-00_240cf60e2d1e/events.out.tfevents.1677223293.240cf60e2d1e.3329.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d586560fdc82b056146e3805a0f72e16b9f522ce6131ac11b9fa3502cd44015
|
| 3 |
+
size 311
|