Text Generation
Transformers
PyTorch
English
hume
jepa
world-models
product-manifolds
poincare
neuromorphic
general-purpose-agent
android
compiler-verified
ast-jepa
arc-challenge
mmlu
gsm8k
Eval Results (legacy)
Instructions to use DangerLabs/HuMe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DangerLabs/HuMe with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="DangerLabs/HuMe")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("DangerLabs/HuMe", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use DangerLabs/HuMe with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "DangerLabs/HuMe" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DangerLabs/HuMe", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/DangerLabs/HuMe
- SGLang
How to use DangerLabs/HuMe 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 "DangerLabs/HuMe" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DangerLabs/HuMe", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "DangerLabs/HuMe" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DangerLabs/HuMe", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use DangerLabs/HuMe with Docker Model Runner:
docker model run hf.co/DangerLabs/HuMe
docs: add Hugging Face model-index evaluation metadata for leaderboards
Browse files
README.md
CHANGED
|
@@ -18,6 +18,45 @@ tags:
|
|
| 18 |
- mmlu
|
| 19 |
- gsm8k
|
| 20 |
pipeline_tag: text-generation
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
---
|
| 22 |
|
| 23 |
# `HuMe` (Danger Labs) — 250M Neuromorphic Autonomous Agent & JEPA World Model
|
|
|
|
| 18 |
- mmlu
|
| 19 |
- gsm8k
|
| 20 |
pipeline_tag: text-generation
|
| 21 |
+
model-index:
|
| 22 |
+
- name: HuMe
|
| 23 |
+
results:
|
| 24 |
+
- task:
|
| 25 |
+
type: text-generation
|
| 26 |
+
name: Text Generation
|
| 27 |
+
dataset:
|
| 28 |
+
name: AI2 Reasoning Challenge (ARC-Challenge)
|
| 29 |
+
type: allenai/ai2_arc
|
| 30 |
+
config: ARC-Challenge
|
| 31 |
+
split: test
|
| 32 |
+
metrics:
|
| 33 |
+
- name: Accuracy
|
| 34 |
+
type: acc
|
| 35 |
+
value: 24.0
|
| 36 |
+
- task:
|
| 37 |
+
type: text-generation
|
| 38 |
+
name: Text Generation
|
| 39 |
+
dataset:
|
| 40 |
+
name: Massive Multitask Language Understanding (MMLU)
|
| 41 |
+
type: cais/mmlu
|
| 42 |
+
config: high_school_mathematics
|
| 43 |
+
split: test
|
| 44 |
+
metrics:
|
| 45 |
+
- name: Accuracy
|
| 46 |
+
type: acc
|
| 47 |
+
value: 16.0
|
| 48 |
+
- task:
|
| 49 |
+
type: text-generation
|
| 50 |
+
name: Text Generation
|
| 51 |
+
dataset:
|
| 52 |
+
name: AST-JEPA 13-Benchmark Alignment & Containment Suite
|
| 53 |
+
type: dangerlabs/ast-jepa
|
| 54 |
+
config: full_suite
|
| 55 |
+
split: stress_test
|
| 56 |
+
metrics:
|
| 57 |
+
- name: Containment Integrity
|
| 58 |
+
type: acc
|
| 59 |
+
value: 100.0
|
| 60 |
---
|
| 61 |
|
| 62 |
# `HuMe` (Danger Labs) — 250M Neuromorphic Autonomous Agent & JEPA World Model
|