Instructions to use FrenzyMath/Reaper-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FrenzyMath/Reaper-SFT with Transformers:

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

pipe = pipeline("text-generation", model="FrenzyMath/Reaper-SFT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("FrenzyMath/Reaper-SFT", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FrenzyMath/Reaper-SFT with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/FrenzyMath/Reaper-SFT

SGLang

How to use FrenzyMath/Reaper-SFT 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 "FrenzyMath/Reaper-SFT" \
    --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": "FrenzyMath/Reaper-SFT",
		"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 "FrenzyMath/Reaper-SFT" \
        --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": "FrenzyMath/Reaper-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FrenzyMath/Reaper-SFT with Docker Model Runner:
```
docker model run hf.co/FrenzyMath/Reaper-SFT
```

Reaper-SFT

Reaper-SFT is the supervised fine-tuned policy-value checkpoint in the Reaper model family. The repository stores a Qwen3 1.7B policy model together with a separate categorical value head.

This checkpoint is part of the Reaper model collection.

Checkpoint structure

policy_model/: Qwen3ForCausalLM policy checkpoint
value_head.pt: state dictionary for a linear value head with 32 output bins
dual_head_meta.json: policy/value loss weights and value-head configuration
Tokenizer and chat-template files are stored at the repository root

The included metadata specifies policy_loss_weight=1.0, value_loss_weight=0.1, and value_dropout=0.01.

Model family

Checkpoint	Stage
FrenzyMath/Reaper-Base	Base checkpoint
FrenzyMath/Reaper-SFT	Supervised fine-tuning
FrenzyMath/Reaper-1	Final policy-value checkpoint

Load the policy model

from transformers import AutoModelForCausalLM, AutoTokenizer

repo_id = "FrenzyMath/Reaper-SFT"

tokenizer = AutoTokenizer.from_pretrained(repo_id)
policy_model = AutoModelForCausalLM.from_pretrained(
    repo_id,
    subfolder="policy_model",
    torch_dtype="auto",
    device_map="auto",
)

Load the value head

import json
import torch
from huggingface_hub import hf_hub_download

meta_path = hf_hub_download(repo_id, "dual_head_meta.json")
head_path = hf_hub_download(repo_id, "value_head.pt")

with open(meta_path, encoding="utf-8") as handle:
    metadata = json.load(handle)

value_head = torch.nn.Linear(
    policy_model.config.hidden_size,
    metadata["num_value_bins"],
)
value_head.load_state_dict(
    torch.load(head_path, map_location="cpu", weights_only=True)
)
value_head.eval()

The policy and value head are stored separately. Integrating value predictions with policy hidden states depends on the calling application.

Intended use and limitations

This checkpoint is intended for research with policy-value modeling and as the supervised stage preceding Reaper-1. Users should independently evaluate it for their target domain. Training-data details, benchmark results, and a license declaration are not included in the current release.

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for FrenzyMath/Reaper-SFT

Base model

Qwen/Qwen3-1.7B-Base

Finetuned

FrenzyMath/Reaper-Base

Finetuned

(1)

this model

Finetunes

1 model

Collection including FrenzyMath/Reaper-SFT

Reaper

Collection

The Reaper model family: base, supervised fine-tuned, and final policy-value checkpoints. • 3 items • Updated 2 days ago