Instructions to use reaperdoesntknow/DiscoverLM-70M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use reaperdoesntknow/DiscoverLM-70M with Transformers:

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

pipe = pipeline("text-generation", model="reaperdoesntknow/DiscoverLM-70M")

# pip install -U transformers accelerate
# Load model directly
from transformers import MoAMetricLM
model = MoAMetricLM.from_pretrained("reaperdoesntknow/DiscoverLM-70M", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use reaperdoesntknow/DiscoverLM-70M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "reaperdoesntknow/DiscoverLM-70M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "reaperdoesntknow/DiscoverLM-70M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/reaperdoesntknow/DiscoverLM-70M

SGLang

How to use reaperdoesntknow/DiscoverLM-70M 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 "reaperdoesntknow/DiscoverLM-70M" \
    --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": "reaperdoesntknow/DiscoverLM-70M",
		"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 "reaperdoesntknow/DiscoverLM-70M" \
        --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": "reaperdoesntknow/DiscoverLM-70M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use reaperdoesntknow/DiscoverLM-70M with Docker Model Runner:
```
docker model run hf.co/reaperdoesntknow/DiscoverLM-70M
```

reaperdoesntknow commited on 4 days ago

Commit

ffb5596

verified ·

1 Parent(s): daa2a65

keeper: refresh 2026-10-20

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -323,4 +323,4 @@ Full methodology: [Structure Over Scale (DOI: 10.57967/hf/8165)](https://doi.org
 ---
 <sub>Part of the [reaperdoesntknow research portfolio](https://huggingface.co/reaperdoesntknow) — 49 models, 22,598 total downloads | Last refreshed: 2026-03-30 12:10 UTC</sub>
-<!-- cix-keeper-ts:2026-10-19T13:15:14Z -->

 ---
 <sub>Part of the [reaperdoesntknow research portfolio](https://huggingface.co/reaperdoesntknow) — 49 models, 22,598 total downloads | Last refreshed: 2026-03-30 12:10 UTC</sub>
+<!-- cix-keeper-ts:2026-10-20T13:15:09Z -->