Instructions to use graphcore-rahult/gpt2-wikitext2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use graphcore-rahult/gpt2-wikitext2 with Transformers:

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

pipe = pipeline("text-generation", model="graphcore-rahult/gpt2-wikitext2")

# Load model directly
from transformers import AutoTokenizer, AutoModelWithLMHead

tokenizer = AutoTokenizer.from_pretrained("graphcore-rahult/gpt2-wikitext2")
model = AutoModelWithLMHead.from_pretrained("graphcore-rahult/gpt2-wikitext2")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use graphcore-rahult/gpt2-wikitext2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "graphcore-rahult/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": "graphcore-rahult/gpt2-wikitext2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/graphcore-rahult/gpt2-wikitext2

SGLang

How to use graphcore-rahult/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 "graphcore-rahult/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": "graphcore-rahult/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 "graphcore-rahult/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": "graphcore-rahult/gpt2-wikitext2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use graphcore-rahult/gpt2-wikitext2 with Docker Model Runner:
```
docker model run hf.co/graphcore-rahult/gpt2-wikitext2
```

graphcore-rahult commited on Dec 7, 2022

Commit

eaaf87b

1 Parent(s): ab1bb84

update model card README.md

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 6.8086
 ## Model description
@@ -39,8 +39,8 @@ The following hyperparameters were used during training:
 - seed: 42
 - distributed_type: IPU
 - gradient_accumulation_steps: 64
-- total_train_batch_size: 512
-- total_eval_batch_size: 20
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1

 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 6.0977
 ## Model description
 - seed: 42
 - distributed_type: IPU
 - gradient_accumulation_steps: 64
+- total_train_batch_size: 128
+- total_eval_batch_size: 5
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1