Text Generation
Transformers
Safetensors
PyTorch
English
swarm_agi
causal-lm
swarm-intelligence
multi-agent
convergentintel
Instructions to use reaperdoesntknow/SAGI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use reaperdoesntknow/SAGI with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="reaperdoesntknow/SAGI")# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("reaperdoesntknow/SAGI", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use reaperdoesntknow/SAGI with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "reaperdoesntknow/SAGI" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "reaperdoesntknow/SAGI", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/reaperdoesntknow/SAGI
- SGLang
How to use reaperdoesntknow/SAGI 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 "reaperdoesntknow/SAGI" \ --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": "reaperdoesntknow/SAGI", "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 "reaperdoesntknow/SAGI" \ --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": "reaperdoesntknow/SAGI", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use reaperdoesntknow/SAGI with Docker Model Runner:
docker model run hf.co/reaperdoesntknow/SAGI
Update model card: added convergentintel tag, added DISC section
Browse files
README.md
CHANGED
|
@@ -10,6 +10,7 @@ tags:
|
|
| 10 |
- multi-agent
|
| 11 |
- pytorch
|
| 12 |
- transformers
|
|
|
|
| 13 |
pipeline_tag: text-generation
|
| 14 |
model-index:
|
| 15 |
- name: SAGI
|
|
@@ -234,4 +235,18 @@ Full methodology: [Structure Over Scale (DOI: 10.57967/hf/8165)](https://doi.org
|
|
| 234 |
|
| 235 |
*Convergent Intelligence LLC: Research Division*
|
| 236 |
|
| 237 |
-
<!-- CIX-CROSSLINK-END -->
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
- multi-agent
|
| 11 |
- pytorch
|
| 12 |
- transformers
|
| 13 |
+
- convergentintel
|
| 14 |
pipeline_tag: text-generation
|
| 15 |
model-index:
|
| 16 |
- name: SAGI
|
|
|
|
| 235 |
|
| 236 |
*Convergent Intelligence LLC: Research Division*
|
| 237 |
|
| 238 |
+
<!-- CIX-CROSSLINK-END -->
|
| 239 |
+
|
| 240 |
+
## Discrepancy Calculus Foundation
|
| 241 |
+
|
| 242 |
+
This model is part of the [Convergent Intelligence LLC: Research Division](https://huggingface.co/reaperdoesntknow) portfolio. All models in this portfolio are developed under the Discrepancy Calculus (DISC) framework — a measure-theoretic approach to understanding and controlling the gap between what a model *should* produce and what it *actually* produces.
|
| 243 |
+
|
| 244 |
+
DISC treats training singularities (loss plateaus, mode collapse, catastrophic forgetting) not as failures to be smoothed over, but as **structural signals** that reveal the geometry of the learning problem. Key concepts:
|
| 245 |
+
|
| 246 |
+
- **Discrepancy Operator (D):** Measures the gap between expected and observed behavior at each training step
|
| 247 |
+
- **Jump Sets:** Boundaries where model behavior changes discontinuously — these are *features*, not bugs
|
| 248 |
+
- **Ghost Imprinting:** Teacher knowledge that transfers to student models through weight-space topology rather than explicit distillation signal
|
| 249 |
+
|
| 250 |
+
For the full mathematical treatment, see [Discrepancy Calculus: Foundations and Core Theory](https://huggingface.co/reaperdoesntknow/Discrepancy_Calculus) (DOI: 10.57967/hf/8194).
|
| 251 |
+
|
| 252 |
+
**Citation chain:** [Structure Over Scale](https://huggingface.co/reaperdoesntknow/Structure-Over-Scale) (DOI: 10.57967/hf/8165) → [Three Teachers to Dual Cognition](https://huggingface.co/reaperdoesntknow/DualMind_Methodolgy) (DOI: 10.57967/hf/8184) → [Discrepancy Calculus](https://huggingface.co/reaperdoesntknow/Discrepancy_Calculus) (DOI: 10.57967/hf/8194)
|