How to use from
vLLM
Install from pip and serve model
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "usvsnsp/pythia-160m-ppo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "usvsnsp/pythia-160m-ppo",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'
Use Docker
docker model run hf.co/usvsnsp/pythia-160m-ppo
Quick Links

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Wandb Run: https://wandb.ai/eleutherai/pythia-rlhf/runs/31gbxj2w

Eval Results:

Tasks Version Filter Metric Value Stderr
arc_challenge Yaml none acc 0.2159 ± 0.0120
none acc_norm 0.2295 ± 0.0123
arc_easy Yaml none acc 0.3266 ± 0.0096
none acc_norm 0.3287 ± 0.0096
lambada_openai Yaml none perplexity NaN ± NaN
none acc 0.1750 ± 0.0053
logiqa Yaml none acc 0.2028 ± 0.0158
none acc_norm 0.2028 ± 0.0158
piqa Yaml none acc 0.5441 ± 0.0116
none acc_norm 0.5446 ± 0.0116
sciq Yaml none acc 0.2050 ± 0.0128
none acc_norm 0.1940 ± 0.0125
winogrande Yaml none acc 0.5043 ± 0.0141
wsc Yaml none acc 0.6154 ± 0.0479
Downloads last month
11
Safetensors
Model size
0.2B params
Tensor type
F32
·
BOOL
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support