Instructions to use OpenPeerAI/My-Name-is-Riemann-Prerelease with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenPeerAI/My-Name-is-Riemann-Prerelease with Transformers:

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

pipe = pipeline("text-generation", model="OpenPeerAI/My-Name-is-Riemann-Prerelease", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("OpenPeerAI/My-Name-is-Riemann-Prerelease", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OpenPeerAI/My-Name-is-Riemann-Prerelease with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/OpenPeerAI/My-Name-is-Riemann-Prerelease

SGLang

How to use OpenPeerAI/My-Name-is-Riemann-Prerelease 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 "OpenPeerAI/My-Name-is-Riemann-Prerelease" \
    --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": "OpenPeerAI/My-Name-is-Riemann-Prerelease",
		"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 "OpenPeerAI/My-Name-is-Riemann-Prerelease" \
        --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": "OpenPeerAI/My-Name-is-Riemann-Prerelease",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OpenPeerAI/My-Name-is-Riemann-Prerelease with Docker Model Runner:
```
docker model run hf.co/OpenPeerAI/My-Name-is-Riemann-Prerelease
```

My-Name-is-Riemann-Prerelease / training /scripts /grow_and_continue.py

Mentors4EDU

Publish training pipeline under training/; update repository notes

db3982a verified 1 day ago

Raw History Blame Contribute Delete

2.44 kB

from __future__ import annotations
import argparse
import logging
import sys
from pathlib import Path

sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
from transformers import AutoTokenizer
from riemann.growth_ladder import get_stage, next_stage
from riemann.growth import load_checkpoint_and_grow
from riemann.paths import CHECKPOINT_ROOT

logger = logging.getLogger("riemann.grow_and_continue")
TOKENIZER_NAME = "gpt2"


def main() -> None:
    logging.basicConfig(
        level=logging.INFO, format="%(asctime)s %(levelname)s %(message)s"
    )
    parser = argparse.ArgumentParser(
        description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter
    )
    parser.add_argument(
        "--from-stage", required=True, help="the stage you just finished training"
    )
    parser.add_argument(
        "--to-stage",
        default=None,
        help="target stage name (default: the next one in the ladder)",
    )
    parser.add_argument("--checkpoint-root", default=str(CHECKPOINT_ROOT))
    args = parser.parse_args()
    from_stage = get_stage(args.from_stage)
    to_stage = (
        get_stage(args.to_stage) if args.to_stage else next_stage(from_stage.name)
    )
    from_dir = Path(args.checkpoint_root) / from_stage.name
    to_dir = Path(args.checkpoint_root) / to_stage.name
    if not (from_dir / "config.json").exists():
        raise FileNotFoundError(
            f"No checkpoint found at {from_dir} -- train this stage first"
        )
    logger.info("Growing %s -> %s", from_stage.name, to_stage.name)
    grown_model = load_checkpoint_and_grow(str(from_dir), to_stage)
    to_dir.mkdir(parents=True, exist_ok=True)
    grown_model.save_pretrained(str(to_dir))
    tokenizer = AutoTokenizer.from_pretrained(TOKENIZER_NAME)
    tokenizer.save_pretrained(str(to_dir))
    n_params = sum((p.numel() for p in grown_model.parameters()))
    logger.info(
        "Saved grown checkpoint to %s (%d params, ~%.2fB)",
        to_dir,
        n_params,
        n_params / 1000000000.0,
    )
    if not to_stage.feasible_on_this_machine:
        logger.warning(
            "%s is marked not feasible on this machine; expect this to be slow or run out of memory",
            to_stage.name,
        )
    logger.info("Next: python scripts/pretrain.py --stage %s --resume", to_stage.name)


if __name__ == "__main__":
    main()

	from __future__ import annotations
	import argparse
	import logging
	import sys
	from pathlib import Path

	sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
	from transformers import AutoTokenizer
	from riemann.growth_ladder import get_stage, next_stage
	from riemann.growth import load_checkpoint_and_grow
	from riemann.paths import CHECKPOINT_ROOT

	logger = logging.getLogger("riemann.grow_and_continue")
	TOKENIZER_NAME = "gpt2"


	def main() -> None:
	logging.basicConfig(
	level=logging.INFO, format="%(asctime)s %(levelname)s %(message)s"
	)
	parser = argparse.ArgumentParser(
	description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter
	)
	parser.add_argument(
	"--from-stage", required=True, help="the stage you just finished training"
	)
	parser.add_argument(
	"--to-stage",
	default=None,
	help="target stage name (default: the next one in the ladder)",
	)
	parser.add_argument("--checkpoint-root", default=str(CHECKPOINT_ROOT))
	args = parser.parse_args()
	from_stage = get_stage(args.from_stage)
	to_stage = (
	get_stage(args.to_stage) if args.to_stage else next_stage(from_stage.name)
	)
	from_dir = Path(args.checkpoint_root) / from_stage.name
	to_dir = Path(args.checkpoint_root) / to_stage.name
	if not (from_dir / "config.json").exists():
	raise FileNotFoundError(
	f"No checkpoint found at {from_dir} -- train this stage first"
	)
	logger.info("Growing %s -> %s", from_stage.name, to_stage.name)
	grown_model = load_checkpoint_and_grow(str(from_dir), to_stage)
	to_dir.mkdir(parents=True, exist_ok=True)
	grown_model.save_pretrained(str(to_dir))
	tokenizer = AutoTokenizer.from_pretrained(TOKENIZER_NAME)
	tokenizer.save_pretrained(str(to_dir))
	n_params = sum((p.numel() for p in grown_model.parameters()))
	logger.info(
	"Saved grown checkpoint to %s (%d params, ~%.2fB)",
	to_dir,
	n_params,
	n_params / 1000000000.0,
	)
	if not to_stage.feasible_on_this_machine:
	logger.warning(
	"%s is marked not feasible on this machine; expect this to be slow or run out of memory",
	to_stage.name,
	)
	logger.info("Next: python scripts/pretrain.py --stage %s --resume", to_stage.name)


	if __name__ == "__main__":
	main()