Text Generation
Transformers
Safetensors
mother_core
mother-core
agentic
tool-use
reasoning
rag
code
uk-sovereign
custom_code
Instructions to use MediaStreamAI/MOTHER_CORE_V3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MediaStreamAI/MOTHER_CORE_V3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="MediaStreamAI/MOTHER_CORE_V3", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("MediaStreamAI/MOTHER_CORE_V3", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use MediaStreamAI/MOTHER_CORE_V3 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MediaStreamAI/MOTHER_CORE_V3" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MediaStreamAI/MOTHER_CORE_V3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/MediaStreamAI/MOTHER_CORE_V3
- SGLang
How to use MediaStreamAI/MOTHER_CORE_V3 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 "MediaStreamAI/MOTHER_CORE_V3" \ --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": "MediaStreamAI/MOTHER_CORE_V3", "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 "MediaStreamAI/MOTHER_CORE_V3" \ --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": "MediaStreamAI/MOTHER_CORE_V3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use MediaStreamAI/MOTHER_CORE_V3 with Docker Model Runner:
docker model run hf.co/MediaStreamAI/MOTHER_CORE_V3
Download config.py from MediaStreamAI/MOTHER_CORE_V3: direct link, hf CLI and curl.
- Browser
- Download file 2.15 kB
-
https://huggingface.co/MediaStreamAI/MOTHER_CORE_V3/resolve/main/config.py
- Command line
-
hf download hf://MediaStreamAI/MOTHER_CORE_V3/config.py
-
curl -L -o config.py https://huggingface.co/MediaStreamAI/MOTHER_CORE_V3/resolve/main/config.py
2.15 kB
| from __future__ import annotations | |
| from dataclasses import dataclass, field | |
| from typing import Optional, List | |
| class ModelConfig: | |
| # Core architecture | |
| vocab_size: int | |
| dim: int | |
| n_layers: int | |
| n_heads: int | |
| n_kv_heads: int | |
| ff_mult: float | |
| max_seq_len: int = 1024 # INCREASED: reasoning needs 1024+ | |
| # Regularisation | |
| dropout: float = 0.0 | |
| # Positional encoding | |
| rope_theta: float = 10000.0 | |
| # Normalisation | |
| rms_norm_eps: float = 1e-5 | |
| use_qk_norm: bool = False | |
| use_post_norm: bool = False | |
| # Embeddings | |
| tie_embeddings: bool = True | |
| # Attention | |
| use_flash_if_available: bool = True | |
| sliding_window_attention: bool = False | |
| window_size: int = 2048 | |
| residual_scale: float = 1.0 | |
| # MoE (Mixture of Experts) β future expansion | |
| use_moe: bool = False | |
| moe_every: int = 2 | |
| n_experts: int = 8 | |
| moe_top_k: int = 2 | |
| aux_loss_alpha: float = 1e-2 | |
| # MLA (Multi-head Latent Attention) β future expansion | |
| use_mla: bool = False | |
| mla_latent_dim: int = 512 | |
| # ββ SELF-LEARNING & EVOLUTION βββββββββββββββββββββββββββββ | |
| # MOTHER CORE is a self-evolving sovereign AI system | |
| # These flags enable continual learning capabilities | |
| # Continual learning β model can continue learning after deployment | |
| continual_learning: bool = True | |
| # Self-correction β model checks and corrects its own outputs | |
| self_correction: bool = True | |
| # Knowledge consolidation β periodic replay of core facts | |
| knowledge_consolidation: bool = True | |
| # Adaptive learning rate β adjusts per-layer based on gradient norms | |
| adaptive_lr: bool = True | |
| # Memory augmentation β external memory for long-term knowledge | |
| use_external_memory: bool = False | |
| memory_size: int = 10000 | |
| # Identity β sovereign AI metadata | |
| model_name: str = "MOTHER CORE" | |
| model_version: str = "v11" | |
| architect: str = "Christopher Kenna" | |
| organisation: str = "MediaStream AI Limited" | |
| sovereign: bool = True | |
| sovereign_nation: str = "United Kingdom" | |