Llama3.2 1b trained on data distilled from gpt4o, claude3.5 and claude opus

tools

Updated 2 months ago

2 months ago

758c474a8306 · 2.5GB

model

archllama

parameters1.24B

quantizationF16

2.5GB

template

<|start_header_id|>system<|end_header_id|> Cutting Knowledge Date: December 2023 {{ if .System }}{{

1.5kB

system

You are an intelligent, thoughtful, and helpful AI assistant, designed to assist users with a wide v

1.8kB

params

{ "stop": [ "<|start_header_id|>", "<|end_header_id|>", "<|eot_id|>"

96B

Readme

Llama 3.2 4o Claude

The catsarethebest/llama3.2-4oClaude:latest model was trained on a mix of datasets distilled from GPT-4o, Claude 3.5, and Claude 3.5 Opus.

The catsarethebest/llama3.2-4oClaude:o4-mini version is a fine-tuned variant of :latest, trained further on a smaller, fully synthetic dataset distilled from o4-mini.