Instructions to use rishanthrajendhran/ProseLens with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rishanthrajendhran/ProseLens with Transformers:

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

pipe = pipeline("text-generation", model="rishanthrajendhran/ProseLens")
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("rishanthrajendhran/ProseLens")
model = AutoModelForCausalLM.from_pretrained("rishanthrajendhran/ProseLens", 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 rishanthrajendhran/ProseLens with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/rishanthrajendhran/ProseLens

SGLang

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

Docker Model Runner
How to use rishanthrajendhran/ProseLens with Docker Model Runner:
```
docker model run hf.co/rishanthrajendhran/ProseLens
```

rishanthrajendhran commited on 10 days ago

Commit

119fa2a

verified ·

1 Parent(s): 4607b19

Rename the corpus IdeaLens-1M -> WildOutlines

Browse files

Files changed (2) hide show

README.md +6 -6
thresholds.json +1 -1

README.md CHANGED Viewed

@@ -10,7 +10,7 @@ tags:
 - ai-text-detection
 - prose-provenance
 datasets:
-- rishanthrajendhran/IdeaLens-1M
 extra_gated_prompt: "Access is granted individually. Please say who you are and what you intend to use the weights for."
 ---
@@ -21,7 +21,7 @@ backbone, training documents and labels, but it reads the raw document text inst
 word-level provenance. It returns P(human), the probability that the document was written by a person.
 ProseLens is `nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16` fine-tuned with LoRA (rank 64) on 1M English web
-documents ([IdeaLens-1M](https://huggingface.co/datasets/rishanthrajendhran/IdeaLens-1M)).
 ## Results
@@ -129,7 +129,7 @@ Scores agree with the training-time scores to about 0.001 in P(human) on average
 ProseLens flags a document as AI-written when P(human) is below a cut. Each cut is set so
 that a given share of human documents is flagged (the false-positive rate, FPR), measured on the 80,000 human
-documents in IdeaLens-1M's `calibration` split (10,000 per format). The paper's operating point is the global
 cut at 1% FPR.
 | FPR | 0.1% | 0.5% | 1% | 2% | 5% |
@@ -138,7 +138,7 @@ cut at 1% FPR.
 Per-format cuts give each format its own operating point. They need the document's format, which the paper
 assigns with WebOrganizer's annotation prompt run on Gemini 3.7 Flash; the calibration documents use the formats
-recorded in IdeaLens-1M. Each is the
 format's own quantile, shrunk toward the global cut with weight n / (n + 2500); at 0.1% FPR 10,000 documents
 per format are too few, so there is no per-format cut. A document outside these eight formats has no
 per-format cut; do not fall back to the global cut for it.
@@ -186,7 +186,7 @@ Inputs of 6,000 tokens do not fit on one 80 GB GPU and 12,000 do not fit on two;
 128 to 64 did not change either limit.
 ProseLens reads whole documents, so their length decides the hardware. One 80 GB GPU handles documents up to about
-4,000 tokens (about 3,000 words); 85% of IdeaLens-1M's test documents are that short. Two 80 GB GPUs handle up to
 8,000 tokens (about 6,000 words), which covers all but about 1 in 1,000 test documents. We have not measured longer
 inputs or more GPUs.
@@ -213,7 +213,7 @@ inputs or more GPUs.
 | [IdeaLens-ModernBERT-L-PerItem](https://huggingface.co/rishanthrajendhran/IdeaLens-ModernBERT-L-PerItem) | ModernBERT-large | single outline items, pooled |
 | [IdeaLens-LogisticClassifier-PerItem](https://huggingface.co/rishanthrajendhran/IdeaLens-LogisticClassifier-PerItem) | logistic regression over text-embedding-3-large | single outline items, pooled |
-Training data: [IdeaLens-1M](https://huggingface.co/datasets/rishanthrajendhran/IdeaLens-1M).
 ## License

 - ai-text-detection
 - prose-provenance
 datasets:
+- rishanthrajendhran/WildOutlines
 extra_gated_prompt: "Access is granted individually. Please say who you are and what you intend to use the weights for."
 ---
 word-level provenance. It returns P(human), the probability that the document was written by a person.
 ProseLens is `nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16` fine-tuned with LoRA (rank 64) on 1M English web
+documents ([WildOutlines](https://huggingface.co/datasets/rishanthrajendhran/WildOutlines)).
 ## Results
 ProseLens flags a document as AI-written when P(human) is below a cut. Each cut is set so
 that a given share of human documents is flagged (the false-positive rate, FPR), measured on the 80,000 human
+documents in WildOutlines's `calibration` split (10,000 per format). The paper's operating point is the global
 cut at 1% FPR.
 | FPR | 0.1% | 0.5% | 1% | 2% | 5% |
 Per-format cuts give each format its own operating point. They need the document's format, which the paper
 assigns with WebOrganizer's annotation prompt run on Gemini 3.7 Flash; the calibration documents use the formats
+recorded in WildOutlines. Each is the
 format's own quantile, shrunk toward the global cut with weight n / (n + 2500); at 0.1% FPR 10,000 documents
 per format are too few, so there is no per-format cut. A document outside these eight formats has no
 per-format cut; do not fall back to the global cut for it.
 128 to 64 did not change either limit.
 ProseLens reads whole documents, so their length decides the hardware. One 80 GB GPU handles documents up to about
+4,000 tokens (about 3,000 words); 85% of WildOutlines's test documents are that short. Two 80 GB GPUs handle up to
 8,000 tokens (about 6,000 words), which covers all but about 1 in 1,000 test documents. We have not measured longer
 inputs or more GPUs.
 | [IdeaLens-ModernBERT-L-PerItem](https://huggingface.co/rishanthrajendhran/IdeaLens-ModernBERT-L-PerItem) | ModernBERT-large | single outline items, pooled |
 | [IdeaLens-LogisticClassifier-PerItem](https://huggingface.co/rishanthrajendhran/IdeaLens-LogisticClassifier-PerItem) | logistic regression over text-embedding-3-large | single outline items, pooled |
+Training data: [WildOutlines](https://huggingface.co/datasets/rishanthrajendhran/WildOutlines).
 ## License

thresholds.json CHANGED Viewed

@@ -3,7 +3,7 @@
  "input": "document",
  "flag_rule": "flag the document as AI when P(human) < cut",
  "calibration": {
-  "data": "IdeaLens-1M, calibration split (human documents only)",
   "scores_from": "the training checkpoint, scored on Tinker",
   "n_humans": 80000,
   "n_per_format": {

  "input": "document",
  "flag_rule": "flag the document as AI when P(human) < cut",
  "calibration": {
+  "data": "WildOutlines, calibration split (human documents only)",
   "scores_from": "the training checkpoint, scored on Tinker",
   "n_humans": 80000,
   "n_per_format": {