SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2311.04931 · 2023

GPT4All: An Ecosystem of Open Source Compressed Language Models

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 12 functions out of this paper's own repositories and ran 7 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
nomic-ai/gpt4all canonical 7 of 12
FunctionStatusWhere it lives
append_extension_if_missing Ran nomic-ai/gpt4all/gpt4all-bindings/python/gpt4all/gpt4all.py
code served (permissive licence) · get_code("66ca7ede66a499e2")
calc_cross_entropy_no_reduction Ran nomic-ai/gpt4all/gpt4all-training/inference.py
code served (permissive licence) · get_code("4e924fb5ab8f4912")
empty_response_callback Ran nomic-ai/gpt4all/gpt4all-bindings/python/gpt4all/_pyllmodel.py
code served (permissive licence) · get_code("34f52fc3afd08648")
eval_example Ran nomic-ai/gpt4all/gpt4all-training/eval_self_instruct.py
code served (permissive licence) · get_code("4feaa8765b683c81")
generate Ran nomic-ai/gpt4all/gpt4all-training/generate.py
code served (permissive licence) · get_code("7c1b66c904668089")
read_config Ran nomic-ai/gpt4all/gpt4all-training/read.py
code served (permissive licence) · get_code("01136000bd8cfe9f")
read_jsonl_file Ran nomic-ai/gpt4all/gpt4all-training/eval_self_instruct.py
code served (permissive licence) · get_code("92f93769061b495d")
load_data Not yet run nomic-ai/gpt4all/gpt4all-training/data.py
code served (permissive licence) · get_code("74836e9a5c8fff9b")
load_data_for_inference Not yet run nomic-ai/gpt4all/gpt4all-training/data.py
code served (permissive licence) · get_code("ae71d2fb29abbfe8")
setup_model Not yet run nomic-ai/gpt4all/gpt4all-training/eval_self_instruct.py
code served (permissive licence) · get_code("79976b8d8cc42886")
setup_model Not yet run nomic-ai/gpt4all/gpt4all-training/generate.py
code served (permissive licence) · get_code("3897e11464623eb6")
tokenize_inputs Not yet run nomic-ai/gpt4all/gpt4all-training/data.py
code served (permissive licence) · get_code("ad37c2e26b2ffad1")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Large language models (LLMs) have recently achieved human-level performance on a range of professional and academic benchmarks. The accessibility of these models has lagged behind their performance. State-of-the-art LLMs require costly infrastructure; are only accessible via rate-limited, geo-locked, and censored web interfaces; and lack publicly available code and technical reports. In this paper, we tell the story of GPT4All, a popular open source repository that aims to democratize access to LLMs. We outline the technical details of the original GPT4All model family, as well as the evolution of the GPT4All project from a single model into a fully fledged open source ecosystem. It is our hope that this paper acts as both a technical overview of the original GPT4All models as well as a case study on the subsequent growth of the GPT4All open source ecosystem.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2311.04931")
get_code_for_paper("2311.04931")
have("2311.04931")

Connect an agent — have() is free.