Text Generation
Safetensors
GGUF
English
reasoning
reinforcement-learning
grpo
small-language-model
samsung-ennovatex
conversational
Instructions to use OmnipotentFool/Aurvion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use OmnipotentFool/Aurvion 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 OmnipotentFool/Aurvion:Q4_K_M # Run inference directly in the terminal: llama cli -hf OmnipotentFool/Aurvion:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf OmnipotentFool/Aurvion:Q4_K_M # Run inference directly in the terminal: llama cli -hf OmnipotentFool/Aurvion: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 OmnipotentFool/Aurvion:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf OmnipotentFool/Aurvion: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 OmnipotentFool/Aurvion:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf OmnipotentFool/Aurvion:Q4_K_M
Use Docker
docker model run hf.co/OmnipotentFool/Aurvion:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use OmnipotentFool/Aurvion with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "OmnipotentFool/Aurvion" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "OmnipotentFool/Aurvion", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/OmnipotentFool/Aurvion:Q4_K_M
- Ollama
How to use OmnipotentFool/Aurvion with Ollama:
ollama run hf.co/OmnipotentFool/Aurvion:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use OmnipotentFool/Aurvion with Docker Model Runner:
docker model run hf.co/OmnipotentFool/Aurvion:Q4_K_M
- Lemonade
How to use OmnipotentFool/Aurvion with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull OmnipotentFool/Aurvion:Q4_K_M
Run and chat with the model
lemonade run user.Aurvion-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Aurvion / llama.cpp /build /tools /ui /ui-src /node_modules /@ungap /structured-clone /structured-json.js
Download llama.cpp/build/tools/ui/ui-src/node_modules/@ungap/structured-clone/structured-json.js from OmnipotentFool/Aurvion: direct link, hf CLI and curl.
- Browser
- Download file 2.82 kB
-
https://huggingface.co/OmnipotentFool/Aurvion/resolve/main/llama.cpp/build/tools/ui/ui-src/node_modules/%40ungap/structured-clone/structured-json.js
- Command line
-
hf download hf://OmnipotentFool/Aurvion/llama.cpp/build/tools/ui/ui-src/node_modules/@ungap/structured-clone/structured-json.js
-
curl -L -o structured-json.js https://huggingface.co/OmnipotentFool/Aurvion/resolve/main/llama.cpp/build/tools/ui/ui-src/node_modules/%40ungap/structured-clone/structured-json.js
2.82 kB
| var StructuredJSON=function(e){"use strict";const r="object"==typeof self?self:globalThis,t=(e,t)=>{switch(e){case"Function":case"SharedWorker":case"Worker":case"eval":case"setInterval":case"setTimeout":throw new TypeError("unable to deserialize "+e)}return new r[e](t)},n=e=>((e,r)=>{const n=(r,t)=>(e.set(t,r),r),s=c=>{if(e.has(c))return e.get(c);const[a,o]=r[c];switch(a){case 0:case-1:return n(o,c);case 1:{const e=n([],c);for(const r of o)e.push(s(r));return e}case 2:{const e=n({},c);for(const[r,t]of o)e[s(r)]=s(t);return e}case 3:return n(new Date(o),c);case 4:{const{source:e,flags:r}=o;return n(new RegExp(e,r),c)}case 5:{const e=n(new Map,c);for(const[r,t]of o)e.set(s(r),s(t));return e}case 6:{const e=n(new Set,c);for(const r of o)e.add(s(r));return e}case 7:{const{name:e,message:r}=o;return n(t(e,r),c)}case 8:return n(BigInt(o),c);case"BigInt":return n(Object(BigInt(o)),c);case"ArrayBuffer":return n(new Uint8Array(o).buffer,o);case"DataView":{const{buffer:e}=new Uint8Array(o);return n(new DataView(e),o)}}return n(t(a,o),c)};return s})(new Map,e)(0),s="",{toString:c}={},{keys:a}=Object,o=e=>{const r=typeof e;if("object"!==r||!e)return[0,r];const t=c.call(e).slice(8,-1);switch(t){case"Array":return[1,s];case"Object":return[2,s];case"Date":return[3,s];case"RegExp":return[4,s];case"Map":return[5,s];case"Set":return[6,s];case"DataView":return[1,t]}return t.includes("Array")?[1,t]:t.includes("Error")?[7,t]:[2,t]},u=([e,r])=>0===e&&("function"===r||"symbol"===r),i=(e,{json:r,lossy:t}={})=>{const n=[];return((e,r,t,n)=>{const s=(e,r)=>{const s=n.push(e)-1;return t.set(r,s),s},c=n=>{if(t.has(n))return t.get(n);let[i,f]=o(n);switch(i){case 0:{let r=n;switch(f){case"bigint":i=8,r=n.toString();break;case"function":case"symbol":if(e)throw new TypeError("unable to serialize "+f);r=null;break;case"undefined":return s([-1],n)}return s([i,r],n)}case 1:{if(f){let e=n;return"DataView"===f?e=new Uint8Array(n.buffer):"ArrayBuffer"===f&&(e=new Uint8Array(n)),s([f,[...e]],n)}const e=[],r=s([i,e],n);for(const r of n)e.push(c(r));return r}case 2:{if(f)switch(f){case"BigInt":return s([f,n.toString()],n);case"Boolean":case"Number":case"String":return s([f,n.valueOf()],n)}if(r&&"toJSON"in n)return c(n.toJSON());const t=[],l=s([i,t],n);for(const r of a(n))!e&&u(o(n[r]))||t.push([c(r),c(n[r])]);return l}case 3:return s([i,n.toISOString()],n);case 4:{const{source:e,flags:r}=n;return s([i,{source:e,flags:r}],n)}case 5:{const r=[],t=s([i,r],n);for(const[t,s]of n)(e||!u(o(t))&&!u(o(s)))&&r.push([c(t),c(s)]);return t}case 6:{const r=[],t=s([i,r],n);for(const t of n)!e&&u(o(t))||r.push(c(t));return t}}const{message:l}=n;return s([i,{name:f,message:l}],n)};return c})(!(r||t),!!r,new Map,n)(e),n},{parse:f,stringify:l}=JSON,w={json:!0,lossy:!0};return e.parse=e=>n(f(e)),e.stringify=e=>l(i(e,w)),e}({}); | |