Instructions to use p208p2002/gpt2-large-babi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use p208p2002/gpt2-large-babi with Transformers:

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

pipe = pipeline("text-generation", model="p208p2002/gpt2-large-babi")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("p208p2002/gpt2-large-babi")
model = AutoModelForCausalLM.from_pretrained("p208p2002/gpt2-large-babi", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use p208p2002/gpt2-large-babi with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "p208p2002/gpt2-large-babi"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "p208p2002/gpt2-large-babi",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/p208p2002/gpt2-large-babi

SGLang

How to use p208p2002/gpt2-large-babi 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 "p208p2002/gpt2-large-babi" \
    --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": "p208p2002/gpt2-large-babi",
		"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 "p208p2002/gpt2-large-babi" \
        --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": "p208p2002/gpt2-large-babi",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use p208p2002/gpt2-large-babi with Docker Model Runner:
```
docker model run hf.co/p208p2002/gpt2-large-babi
```

p208p2002 commited on May 31, 2023

Commit

f5eb344

1 Parent(s): 89c9e1c

Create README.md

Browse files

Files changed (1) hide show

README.md +52 -0

README.md ADDED Viewed

	@@ -0,0 +1,52 @@

+---
+datasets:
+- facebook/babi_qa
+---
+Fine tune and evaluate transformer model on facebook's bAbi tasks.
+> [Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks](https://arxiv.org/abs/1502.05698)
+Training Code: [p208p2002/bAbi-tasks-with-transformer-model](https://github.com/p208p2002/bAbi-tasks-with-transformer-model)
+|task_no|task_name             |score|
+|-------|----------------------|-----|
+|qa1    |single-supporting-fact|100  |
+|qa2    |two-supporting-facts  |99.4 |
+|qa3    |three-supporting-facts|62.0 |
+|qa4    |two-arg-relations     |100  |
+|qa5    |three-arg-relations   |96.5 |
+|qa6    |yes-no-questions      |100  |
+|qa7    |counting              |100  |
+|qa8    |lists-sets            |99.8 |
+|qa9    |simple-negation       |100  |
+|qa10   | indefinite-knowledge |100  |
+|qa11   | basic-coreference    |100  |
+|qa12   | conjunction          |100  |
+|qa13   | compound-coreference |100  |
+|qa14   | time-reasoning       |100  |
+|qa15   | basic-deduction      |100  |
+|qa16   | basic-induction      |100  |
+|qa17   | positional-reasoning |100  |
+|qa18   | size-reasoning       |100  |
+|qa19   | path-finding         |100  |
+|qa20   | agents-motivations   |100  |
+```python
+# Please use with the follow template
+INPUT_TEMPLATE = """
+Context:
+{context}
+Question:
+{question}
+Answer:
+{answer}
+"""
+input_text = INPUT_TEMPLATE.format_map({
+    "context":context,
+    "question":question,
+    "answer":answer
+}).strip()
+```