everythinglm

588.9K Downloads Updated 2 years ago

Uncensored Llama2 based model with support for a 16K context window.

13b

ollama run everythinglm

curl http://localhost:11434/api/chat \
  -d '{
    "model": "everythinglm",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='everythinglm',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'everythinglm',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Models

View all →

Name

18 models

Size / Usage

Context

Input

everythinglm:latest

7.4GB · 16K context window · Text · 2 years ago

everythinglm:latest

7.4GB

16K

Text

everythinglm:13b

latest

7.4GB · 16K context window · Text · 2 years ago

everythinglm:13b latest

7.4GB

16K

Text

Readme

The Everything Language Model is a Llama 2-based model with a 16k context released by Totally Not An LLM (Kai Howard). It was trained with the EverythingLM Dataset and is uncensored.

CLI


Once loaded, change the context size to `16K`

/set parameter num_ctx 16384


### API

Example:

  ```bash
curl -X POST http://localhost:11434/api/generate -d '{
  "model": "everythinglm",
  "prompt": "Why is the sky blue?"
  "options": {
    "num_ctx": 16384
  }
 }'

Reference

13b parameters original source: Totally Not An LLM