Text Generation
Transformers
PyTorch
English
burt-imma
custom-architecture
matrix-memory
equilibrium-propagation
cifg
sovereign
snapkitty
no-backprop
formal-verification
lean4
Instructions to use Snapkitty/burt-imma with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Snapkitty/burt-imma with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Snapkitty/burt-imma")# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Snapkitty/burt-imma", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Snapkitty/burt-imma with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Snapkitty/burt-imma" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Snapkitty/burt-imma", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Snapkitty/burt-imma
- SGLang
How to use Snapkitty/burt-imma 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 "Snapkitty/burt-imma" \ --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": "Snapkitty/burt-imma", "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 "Snapkitty/burt-imma" \ --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": "Snapkitty/burt-imma", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Snapkitty/burt-imma with Docker Model Runner:
docker model run hf.co/Snapkitty/burt-imma
| /- | |
| MetaInvertedSum | |
| Huntington postulates and meta-softmax over Boolean ring | |
| -/ | |
| import Mathlib | |
| noncomputable section | |
| open Real | |
| -- ============================================================ | |
| -- Trait Weights | |
| -- ============================================================ | |
| structure TraitWeights (n : Nat) where | |
| weights : Fin n β Float | |
| sum_positive : True -- sum of weights > 0 | |
| -- ============================================================ | |
| -- Boolean Ring Operations | |
| -- ============================================================ | |
| def bool_ring_add (a b : Bool) : Bool := xor a b | |
| def bool_ring_mul (a b : Bool) : Bool := a && b | |
| def bool_ring_not (a : Bool) : Bool := !a | |
| -- ============================================================ | |
| -- Huntington Postulates (7) | |
| -- ============================================================ | |
| /-- Commutativity of addition -/ | |
| theorem huntington_commutative_add : | |
| β a b : Bool, bool_ring_add a b = bool_ring_add b a := sorry | |
| /-- Commutativity of multiplication -/ | |
| theorem huntington_commutative_mul : | |
| β a b : Bool, bool_ring_mul a b = bool_ring_mul b a := sorry | |
| /-- Associativity of addition -/ | |
| theorem huntington_associative_add : | |
| β a b c : Bool, bool_ring_add (bool_ring_add a b) c = bool_ring_add a (bool_ring_add b c) := sorry | |
| /-- Associativity of multiplication -/ | |
| theorem huntington_associative_mul : | |
| β a b c : Bool, bool_ring_mul (bool_ring_mul a b) c = bool_ring_mul a (bool_ring_mul b c) := sorry | |
| /-- Distributivity of mul over add -/ | |
| theorem huntington_distributive : | |
| β a b c : Bool, bool_ring_mul a (bool_ring_add b c) = | |
| bool_ring_add (bool_ring_mul a b) (bool_ring_mul a c) := sorry | |
| /-- Identity element for addition -/ | |
| theorem huntington_identity_add : | |
| β a : Bool, bool_ring_add a false = a := sorry | |
| /-- Complement law -/ | |
| theorem huntington_complement : | |
| β a : Bool, bool_ring_add a (bool_ring_not a) = true := sorry | |
| -- ============================================================ | |
| -- Meta Inverted Sum | |
| -- ============================================================ | |
| def meta_inverted_sum {n : Nat} (tw : TraitWeights n) (signals : Fin n β Float) : Float := | |
| sorry | |
| -- ============================================================ | |
| -- Meta Softmax | |
| -- ============================================================ | |
| def meta_softmax {n : Nat} (logits : Fin n β Float) : Fin n β Float := | |
| sorry | |
| /-- Meta softmax outputs form a probability simplex (sum to 1, all non-negative) -/ | |
| theorem meta_softmax_simplex {n : Nat} (logits : Fin n β Float) : | |
| (β i, meta_softmax logits i β₯ 0) β§ | |
| True := sorry | |
| /-- Applying meta softmax twice yields the same result -/ | |
| theorem meta_softmax_idempotent {n : Nat} (logits : Fin n β Float) : | |
| meta_softmax (meta_softmax logits) = meta_softmax logits := sorry | |
| end | |