Instructions to use hoskinson-center/proofGPT-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hoskinson-center/proofGPT-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="hoskinson-center/proofGPT-v0.1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hoskinson-center/proofGPT-v0.1")
model = AutoModelForCausalLM.from_pretrained("hoskinson-center/proofGPT-v0.1")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use hoskinson-center/proofGPT-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hoskinson-center/proofGPT-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hoskinson-center/proofGPT-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/hoskinson-center/proofGPT-v0.1

SGLang

How to use hoskinson-center/proofGPT-v0.1 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 "hoskinson-center/proofGPT-v0.1" \
    --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": "hoskinson-center/proofGPT-v0.1",
		"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 "hoskinson-center/proofGPT-v0.1" \
        --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": "hoskinson-center/proofGPT-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hoskinson-center/proofGPT-v0.1 with Docker Model Runner:
```
docker model run hf.co/hoskinson-center/proofGPT-v0.1
```

zhangirazerbayev commited on Feb 15, 2023

Commit

1e4dd33

1 Parent(s): d782ab6

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -15,7 +15,7 @@ datasets:
 # Model Description
 ProofGPT-v0.1 is a 1.3B parameter language model based on the GPT-NeoX architecture and trained on the [proof-pile](https://huggingface.co/datasets/hoskinson-center/proof-pile) (v1.1).
-The model is initialized with [pythia-1.3b](https://huggingface.co/EleutherAI/pythia-1.3b) weights. ProofGPT-v0.1's Weights & Biases training log is viewable [here](https://wandb.ai/zhangir-azerbayev/math-lm/groups/1.3B%20preliminary_227qly9c/workspace?workspace=user-zhangir-azerbayev).
 Detailed evaluations coming soon :)

 # Model Description
 ProofGPT-v0.1 is a 1.3B parameter language model based on the GPT-NeoX architecture and trained on the [proof-pile](https://huggingface.co/datasets/hoskinson-center/proof-pile) (v1.1).
+We initiailized training with pythia-1.3b weights, a precursor to the [pythia-1.4b](https://huggingface.co/EleutherAI/pythia-1.3b) model that has roughly equivalent performance.
 Detailed evaluations coming soon :)