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 /count_corpus_tokens.py

Mentors4EDU

Publish training pipeline under training/; update repository notes

db3982a verified 1 day ago

Raw History Blame Contribute Delete

1.47 kB

import sys, time, json
from pathlib import Path
from transformers import AutoTokenizer

tok = AutoTokenizer.from_pretrained("gpt2")
p = Path(r"C:\RiemannModel\data\pretrain_corpus.txt")
regions = {}
total_tokens = 0
total_docs = 0
t0 = time.time()
batch = []


def flush(batch):
    global total_tokens
    enc = tok(batch, add_special_tokens=False)["input_ids"]
    n = sum(len(e) + 1 for e in enc)
    total_tokens += n
    return n


cum = 0
boundaries = []
with p.open("r", encoding="utf-8") as fh:
    for i, line in enumerate(fh):
        text = line.replace("\u2029", "\n").strip()
        if not text:
            continue
        batch.append(text)
        total_docs += 1
        if len(batch) == 2000:
            flush(batch)
            batch = []
        if total_docs % 500000 == 0:
            print(
                f"{total_docs:,} docs, {total_tokens/1e9:.3f}B tokens, {time.time()-t0:.0f}s",
                flush=True,
            )
            boundaries.append((total_docs, total_tokens))
if batch:
    flush(batch)
out = {
    "docs": total_docs,
    "tokens": total_tokens,
    "tokens_per_doc": total_tokens / max(1, total_docs),
    "cumulative_every_500k_docs": boundaries,
}
Path(r"C:\RiemannModel\data\corpus_token_count.json").write_text(
    json.dumps(out, indent=2)
)
print(
    json.dumps(
        {k: v for k, v in out.items() if k != "cumulative_every_500k_docs"}, indent=2
    )
)

	import sys, time, json
	from pathlib import Path
	from transformers import AutoTokenizer

	tok = AutoTokenizer.from_pretrained("gpt2")
	p = Path(r"C:\RiemannModel\data\pretrain_corpus.txt")
	regions = {}
	total_tokens = 0
	total_docs = 0
	t0 = time.time()
	batch = []


	def flush(batch):
	global total_tokens
	enc = tok(batch, add_special_tokens=False)["input_ids"]
	n = sum(len(e) + 1 for e in enc)
	total_tokens += n
	return n


	cum = 0
	boundaries = []
	with p.open("r", encoding="utf-8") as fh:
	for i, line in enumerate(fh):
	text = line.replace("\u2029", "\n").strip()
	if not text:
	continue
	batch.append(text)
	total_docs += 1
	if len(batch) == 2000:
	flush(batch)
	batch = []
	if total_docs % 500000 == 0:
	print(
	f"{total_docs:,} docs, {total_tokens/1e9:.3f}B tokens, {time.time()-t0:.0f}s",
	flush=True,
	)
	boundaries.append((total_docs, total_tokens))
	if batch:
	flush(batch)
	out = {
	"docs": total_docs,
	"tokens": total_tokens,
	"tokens_per_doc": total_tokens / max(1, total_docs),
	"cumulative_every_500k_docs": boundaries,
	}
	Path(r"C:\RiemannModel\data\corpus_token_count.json").write_text(
	json.dumps(out, indent=2)
	)
	print(
	json.dumps(
	{k: v for k, v in out.items() if k != "cumulative_every_500k_docs"}, indent=2
	)
	)