Instructions to use shreyansh12183/vigyan-olmoe-1b-7b-dpo-masterpiece with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use shreyansh12183/vigyan-olmoe-1b-7b-dpo-masterpiece with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf shreyansh12183/vigyan-olmoe-1b-7b-dpo-masterpiece:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf shreyansh12183/vigyan-olmoe-1b-7b-dpo-masterpiece:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf shreyansh12183/vigyan-olmoe-1b-7b-dpo-masterpiece:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf shreyansh12183/vigyan-olmoe-1b-7b-dpo-masterpiece:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf shreyansh12183/vigyan-olmoe-1b-7b-dpo-masterpiece:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf shreyansh12183/vigyan-olmoe-1b-7b-dpo-masterpiece:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf shreyansh12183/vigyan-olmoe-1b-7b-dpo-masterpiece:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf shreyansh12183/vigyan-olmoe-1b-7b-dpo-masterpiece:Q4_K_M

Use Docker

docker model run hf.co/shreyansh12183/vigyan-olmoe-1b-7b-dpo-masterpiece:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use shreyansh12183/vigyan-olmoe-1b-7b-dpo-masterpiece with Ollama:
```
ollama run hf.co/shreyansh12183/vigyan-olmoe-1b-7b-dpo-masterpiece:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use shreyansh12183/vigyan-olmoe-1b-7b-dpo-masterpiece with Docker Model Runner:
```
docker model run hf.co/shreyansh12183/vigyan-olmoe-1b-7b-dpo-masterpiece:Q4_K_M
```

Lemonade

How to use shreyansh12183/vigyan-olmoe-1b-7b-dpo-masterpiece with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull shreyansh12183/vigyan-olmoe-1b-7b-dpo-masterpiece:Q4_K_M

Run and chat with the model

lemonade run user.vigyan-olmoe-1b-7b-dpo-masterpiece-Q4_K_M

List all available models

lemonade list

Atomic Chat

🏆 Vigyan AI 7B MoE: Sovereign Sparse Mixture-of-Experts Masterpiece

Sovereign Direct Preference Optimization (DPO) Aligned MoE Foundation
Lead Architect & Creator: Shreyansh Singh • Kaggle
License: Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) (Strictly Private 🔒)
Base Architecture: allenai/OLMoE-1B-7B-0924-Instruct (Sparse 64-Expert Top-8 Routing)

⚡ Architecture & Gating Invariants

Contrasting Negative Prompt Gate Calibration: Router weights calibrated across 50,000 domain samples (vigyan-olmoe-master-curriculum-v1) to prevent expert cross-bleeding.
Selective Router Precision Guardrail: Router gating matrices (ffn_gate_inp / gate_proj) preserved at FP16/Q8_0 precision to eliminate token routing entropy drift.
High-Throughput Edge MoE: Activates only a fraction of parameters per token, delivering 7B-class intelligence with the inference latency of a 1.5B model.

Downloads last month: 92

Safetensors

Model size

7B params

Tensor type

F16

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for shreyansh12183/vigyan-olmoe-1b-7b-dpo-masterpiece

Base model

allenai/OLMoE-1B-7B-0924

Finetuned

allenai/OLMoE-1B-7B-0924-SFT

Finetuned

allenai/OLMoE-1B-7B-0924-Instruct

Quantized

(16)

this model