ifioravanti/ lwm

Large World Model is an open-source model trained from LLaMA-2 on a subset of Books3 filtered data

425 Pulls Updated 2 months ago

7 Tags

2 months ago

e234bfbb6ed0 · 3.8GB

model
llama
·
7B
·
4-bit
system
"""You are a helpful assistant."""
template
{{ if and .First .System }}{{ .System }} {{ end }} USER: {{ .Prompt }} ASSISTANT:

Readme

A family of 7B parameter models capable of processing long text documents (LWM-Text, LWM-Text-Chat) of over 1M tokens.

image

CLI

ollama run ifioravanti/lwm

API

Example:

curl -X POST http://localhost:11434/api/generate -d '{ 
  "model": "ifioravanti/lwm",
  "prompt": "Here is a story about llamas eating grass"
 }'

Memory requirements

7b models generally require at least 8GB of RAM but due to 1M context size this requires a ton of memory depending on the context passed

References

Github HuggingFace