Instructions to use menik1126/OVD-Math-1-data-HES-Step600-Historical with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use menik1126/OVD-Math-1-data-HES-Step600-Historical with Transformers:

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

pipe = pipeline("text-generation", model="menik1126/OVD-Math-1-data-HES-Step600-Historical")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("menik1126/OVD-Math-1-data-HES-Step600-Historical")
model = AutoModelForCausalLM.from_pretrained("menik1126/OVD-Math-1-data-HES-Step600-Historical", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use menik1126/OVD-Math-1-data-HES-Step600-Historical with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "menik1126/OVD-Math-1-data-HES-Step600-Historical"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "menik1126/OVD-Math-1-data-HES-Step600-Historical",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/menik1126/OVD-Math-1-data-HES-Step600-Historical

SGLang

How to use menik1126/OVD-Math-1-data-HES-Step600-Historical 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 "menik1126/OVD-Math-1-data-HES-Step600-Historical" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "menik1126/OVD-Math-1-data-HES-Step600-Historical",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "menik1126/OVD-Math-1-data-HES-Step600-Historical" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "menik1126/OVD-Math-1-data-HES-Step600-Historical",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use menik1126/OVD-Math-1-data-HES-Step600-Historical with Docker Model Runner:
```
docker model run hf.co/menik1126/OVD-Math-1-data-HES-Step600-Historical
```

OVD-Math-1-data-HES-Step600-Historical / provenance.json

menik1126

Upload 1-data hes step600

29c79c8 verified about 1 month ago

Raw History Blame Contribute Delete

1.72 kB

{
  "regime": "1-data",
  "method": "hes",
  "step": 600,
  "source": "/home/storage/xiongjing/one_shot_rlvr_runs/entropy_pi1_resume100_restart_retry1_20260824_134219Z/checkpoints/one_shot_rlvr/stream_entropy_onecall_pi1_r128_rej7_resume100_retry1_20260824_134219Z/global_step_600/actor",
  "files_sha256": {
    "config.json": "51bdd9382b23fc9342548f8ca5ad4c1a6cbe0c566a7eab112284f4b0f59589f5",
    "tokenizer_config.json": "6c90413caefc621f6fcfb8d9e5ce8ba9c949f5b65bcf8a4808f994fb9c51cf91",
    "vocab.json": "ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910",
    "generation_config.json": "61c976d8443e6a7b4956b1847e4f970ab1ff5ad0db2b3ca3970b711c098c299f",
    "model-00001-of-00002.safetensors": "cd09a5539acfbcf0644e70601bb0ccec989d0583d0e0b473ef78d919310749a4",
    "tokenizer.json": "9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa",
    "model.safetensors.index.json": "182b576f521e239d797460755941a1e4c8ffb838a83b0a6aa7dc449f942498df",
    "added_tokens.json": "58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b",
    "merges.txt": "8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5",
    "special_tokens_map.json": "6676f091c8bc4d1b50146427cfde92073402866b87b6e39223227931b70083e9",
    "model-00002-of-00002.safetensors": "fc469c26e83a3cd4c0e8a0002c3898574f62740442455dee6714c8b8e70484fe"
  },
  "historical_hashes_checked": {
    "model-00001-of-00002.safetensors": "cd09a5539acfbcf0644e70601bb0ccec989d0583d0e0b473ef78d919310749a4",
    "model-00002-of-00002.safetensors": "fc469c26e83a3cd4c0e8a0002c3898574f62740442455dee6714c8b8e70484fe"
  },
  "identity_check": "Historical evaluation source path; historical hashes checked where available"
}

	{
	"regime": "1-data",
	"method": "hes",
	"step": 600,
	"source": "/home/storage/xiongjing/one_shot_rlvr_runs/entropy_pi1_resume100_restart_retry1_20260824_134219Z/checkpoints/one_shot_rlvr/stream_entropy_onecall_pi1_r128_rej7_resume100_retry1_20260824_134219Z/global_step_600/actor",
	"files_sha256": {
	"config.json": "51bdd9382b23fc9342548f8ca5ad4c1a6cbe0c566a7eab112284f4b0f59589f5",
	"tokenizer_config.json": "6c90413caefc621f6fcfb8d9e5ce8ba9c949f5b65bcf8a4808f994fb9c51cf91",
	"vocab.json": "ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910",
	"generation_config.json": "61c976d8443e6a7b4956b1847e4f970ab1ff5ad0db2b3ca3970b711c098c299f",
	"model-00001-of-00002.safetensors": "cd09a5539acfbcf0644e70601bb0ccec989d0583d0e0b473ef78d919310749a4",
	"tokenizer.json": "9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa",
	"model.safetensors.index.json": "182b576f521e239d797460755941a1e4c8ffb838a83b0a6aa7dc449f942498df",
	"added_tokens.json": "58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b",
	"merges.txt": "8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5",
	"special_tokens_map.json": "6676f091c8bc4d1b50146427cfde92073402866b87b6e39223227931b70083e9",
	"model-00002-of-00002.safetensors": "fc469c26e83a3cd4c0e8a0002c3898574f62740442455dee6714c8b8e70484fe"
	},
	"historical_hashes_checked": {
	"model-00001-of-00002.safetensors": "cd09a5539acfbcf0644e70601bb0ccec989d0583d0e0b473ef78d919310749a4",
	"model-00002-of-00002.safetensors": "fc469c26e83a3cd4c0e8a0002c3898574f62740442455dee6714c8b8e70484fe"
	},
	"identity_check": "Historical evaluation source path; historical hashes checked where available"
	}