juspay

xor-lite

README

License: apache-2.0

Release

Table with columns: Field, Value
Field	Value
Base checkpoint	`openbmb/MiniCPM5-2B`
Base revision	`12a3808a956f869c767195e9266b59c4d21d92e2`
Architecture	Dense `LlamaForCausalLM`
Parameters	Approximately 2.52 billion
Released precision	BF16
License	Apache License 2.0
Packaging	Fully merged weights; no adapter loading is required

Pin the published revision for reproducible use

bash

hf download juspay/xor-lite --revision REPLACE_WITH_RELEASE_REVISION --local-dir xor-lite

Interface

The server accepts a state and a map of typed questions

noul: binary probability
choice: categorical decision and full probability distribution
score: expected ordinal score and full probability distribution

The serving layer performs constrained single-token candidate readout, forward and reverse option-order evaluation, probability calibration, and SystemOne schema conversion. It supports up to 255 candidates using the included MiniCPM-specific marker table. The released serving layer is part of the inference configuration required for reproducible results

Quick start

bash

hf download juspay/xor-lite --revision REPLACE_WITH_RELEASE_REVISION --local-dir xor-lite (cd xor-lite/serving && sha256sum -c xor-lite-serving.tar.gz.sha256) mkdir -p xor-lite-runtimetar -xzf xor-lite/serving/xor-lite-serving.tar.gz -C xor-lite-runtime --strip-components=1 cd xor-lite-runtimecp .env.example .envsed -i "s|^MODEL_DIR=.*|MODEL_DIR=$(cd ../xor-lite && pwd)|" .env./run.sh

When the smoke test succeeds, the API is available at http://127.0.0.1:30002/v1/systemone

Public JEVBench self-run

XOR Lite was evaluated locally on all 231 public JEVBench decisions using harness commit fd54ea7dc02bbe29c6ac8f6e015a54cdcff26805, the existing typesafe adapter, and one request at a time

The run used the released configuration on 1 x NVIDIA H200 NVL (143 GB), tensor parallelism 1, data parallelism 1, with request caching disabled

Table with columns: Tier, Attempted, Valid, Correct, Accuracy, Brier, ECE, p50, p95
Tier	Attempted	Valid	Correct	Accuracy	Brier	ECE	p50	p95
Easy	48	48	48	1.0000	0.1467	0.2294	0.0250 s	0.0279 s
Original	72	72

Operational success, coverage, schema validity, and strict schema validity were 1.0000 for each tier. These are self-run public-tier results, not an official JEVBench rank. Latency is hardware-specific and was measured locally without network overhead

Validated runtime

Table with columns: Setting, Value
Setting	Value
SGLang image	`lmsysorg/sglang@sha256:6bcaa47db52f78ce0d67863b8b2431221b79bc23204a80cad757fa819d00e921`
Tensor parallelism	1
Data parallelism	1
Validated GPU	1 x NVIDIA H200 NVL, 143 GB
Maximum prefill tokens	250,000
Static memory fraction	0.50
Probability temperature	`100.0` for `noul`, , and

NVIDIA L4 validation

The immutable v1.0 release was also validated without modification on one NVIDIA L4 with 24 GB of memory using tensor parallelism 1 and data parallelism 1. The complete public JEVBench run reproduced the H200 result exactly at 169/231 correct, with no operational, coverage, or schema failures

Table with columns: Tier, Correct, Accuracy, p50, p95
Tier	Correct	Accuracy	p50	p95
Easy	48/48	1.0000	0.0458 s	0.0481 s
Original	66/72	0.9167	0.0465 s	0.0488 s
Hard public	55/111	0.4955	0.1175 s	0.5868 s

The loaded service used 13,803 MiB of the L4's 23,034 MiB. The run used NVIDIA driver 595.91.07 and the same pinned SGLang image shown above. The evidence archive has SHA-256 6389b280c9abfffd608a3864a1b8ed7570974ca415ad5f079d0224f429694ed9

The L4 result demonstrates that the H200 used for the original release measurement is not a minimum hardware requirement. It does not define or announce a hosted-service tariff

The service binds to localhost by default and does not require an API key. Remote deployments must add authentication, TLS, rate limits, and request-size limits at the ingress layer

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Container

Run this model inference with full control and performance in your environment.

Learn more

Model Details

Model Provider

juspay

Model Tree

Base

openbmb/MiniCPM5-2B

Fine-tuned

this model

Input Modalities

Text

Output Modalities

Text

Supported Functionality

Dedicated EndpointsContainer

Explore FriendliAI today

Get started Talk to an engineer

README

License: apache-2.0

Release

Table with columns: Field, Value
Field	Value
Base checkpoint	`openbmb/MiniCPM5-2B`
Base revision	`12a3808a956f869c767195e9266b59c4d21d92e2`
Architecture	Dense `LlamaForCausalLM`
Parameters	Approximately 2.52 billion
Released precision	BF16
License	Apache License 2.0
Packaging	Fully merged weights; no adapter loading is required

Pin the published revision for reproducible use

bash

hf download juspay/xor-lite --revision REPLACE_WITH_RELEASE_REVISION --local-dir xor-lite

Interface

The server accepts a state and a map of typed questions

noul: binary probability
choice: categorical decision and full probability distribution
score: expected ordinal score and full probability distribution

Quick start

bash

hf download juspay/xor-lite --revision REPLACE_WITH_RELEASE_REVISION --local-dir xor-lite (cd xor-lite/serving && sha256sum -c xor-lite-serving.tar.gz.sha256) mkdir -p xor-lite-runtimetar -xzf xor-lite/serving/xor-lite-serving.tar.gz -C xor-lite-runtime --strip-components=1 cd xor-lite-runtimecp .env.example .envsed -i "s|^MODEL_DIR=.*|MODEL_DIR=$(cd ../xor-lite && pwd)|" .env./run.sh

When the smoke test succeeds, the API is available at http://127.0.0.1:30002/v1/systemone

Public JEVBench self-run

XOR Lite was evaluated locally on all 231 public JEVBench decisions using harness commit fd54ea7dc02bbe29c6ac8f6e015a54cdcff26805, the existing typesafe adapter, and one request at a time

The run used the released configuration on 1 x NVIDIA H200 NVL (143 GB), tensor parallelism 1, data parallelism 1, with request caching disabled

Table with columns: Tier, Attempted, Valid, Correct, Accuracy, Brier, ECE, p50, p95
Tier	Attempted	Valid	Correct	Accuracy	Brier	ECE	p50	p95
Easy	48	48	48	1.0000	0.1467	0.2294	0.0250 s	0.0279 s
Original	72	72

Validated runtime

Table with columns: Setting, Value
Setting	Value
SGLang image	`lmsysorg/sglang@sha256:6bcaa47db52f78ce0d67863b8b2431221b79bc23204a80cad757fa819d00e921`
Tensor parallelism	1
Data parallelism	1
Validated GPU	1 x NVIDIA H200 NVL, 143 GB
Maximum prefill tokens	250,000
Static memory fraction	0.50
Probability temperature	`100.0` for `noul`, , and

NVIDIA L4 validation

Table with columns: Tier, Correct, Accuracy, p50, p95
Tier	Correct	Accuracy	p50	p95
Easy	48/48	1.0000	0.0458 s	0.0481 s
Original	66/72	0.9167	0.0465 s	0.0488 s
Hard public	55/111	0.4955	0.1175 s	0.5868 s

The L4 result demonstrates that the H200 used for the original release measurement is not a minimum hardware requirement. It does not define or announce a hosted-service tariff

The service binds to localhost by default and does not require an API key. Remote deployments must add authentication, TLS, rate limits, and request-size limits at the ingress layer