Repository Structure
.
|-- README.md
|-- LICENSE
|-- UPSTREAM_README.md
|-- SHA256SUMS
|-- config.json
|-- configuration.json
|-- generation_config.json
|-- model.safetensors.index.json
|-- model-00001-of-00008.safetensors
|-- model-00002-of-00008.safetensors
|-- model-00003-of-00008.safetensors
|-- model-00004-of-00008.safetensors
|-- model-00005-of-00008.safetensors
|-- model-00006-of-00008.safetensors
|-- model-00007-of-00008.safetensors
|-- model-00008-of-00008.safetensors
|-- tokenizer.json
|-- tokenizer_config.json
`-- client/
`-- client_secret.pt
Usage
Download the repository contents from the anonymous reviewer link and place the directory under:
models/deepseek-r1-distill-qwen-1.5b-obfuscated-reviewer/
The runtime configuration should use:
model_path=models/deepseek-r1-distill-qwen-1.5b-obfuscated-reviewer
client_secret_path=models/deepseek-r1-distill-qwen-1.5b-obfuscated-reviewer/client/client_secret.pt
Minimal dependency set:
pip install torch transformers accelerate safetensors
Basic local loading check:
from transformers import AutoModelForCausalLM, AutoTokenizer
model_path = "models/deepseek-r1-distill-qwen-1.5b-obfuscated-reviewer"
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
model_path,
device_map="auto",
torch_dtype="auto",
trust_remote_code=True,
)
client_secret_path = f"{model_path}/client/client_secret.pt"
Included Files
- sharded safetensors model weights
model.safetensors.index.json- tokenizer files
- model configuration files
client/client_secret.pt for reviewer-side input mapping and output recovery- upstream license and README preserved for model-license review
Excluded Files
- deployment
.env files
- private hostnames, private IP addresses, logs, and databases
- local training paths and account identifiers
Runtime loaders should set the model path to the repository root and the client secret path to client/client_secret.pt.