# THUDM/GLM

GLM (General Language Model)

Repository: https://github.com/THUDM/GLM
Canonical: https://ross.abutalabs.com/products/glm
Language: Python
License: MIT
License Family: permissive
Last push: 2023-11-03T08:26:49+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 1994, "days_push": 1034, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3652, forks 372 (observed 2026-08-28T04:08:13.056583+00:00)

## What it is
GLM is a general language model pretrained with an autoregressive blank-filling objective, released with pretrained checkpoints and fine-tuning code for NLU and generation tasks. It is the research codebase behind the GLM model family, including ChatGLM-6B.

## Use cases
- finetune a pretrained language model on text classification tasks
- run autoregressive blank-infilling pretraining
- generate text with a GLM checkpoint
- experiment with Chinese and English language model pretraining
- reproduce ACL 2022 GLM paper results

## When to choose
- you want to finetune or study the original GLM architecture from the research paper
- you need pretrained bilingual English/Chinese checkpoints for NLU or generation

## When to avoid
- you want a production chat model - use ChatGLM or GLM-4 repos instead
- you need actively maintained tooling - this repo is largely superseded by newer GLM releases

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, nlp, llm-training, llm-inference
- domain: large-language-models, deep-learning
- platform: python
- tags: pretrained-language-model, blank-infilling, chinese-nlp, transformers, fine-tuning, natural-language-processing, linux, gpu

## Member repositories
- THUDM/GLM (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:13.056583+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:31:40.499032+00:00, confidence not recorded.
  - readme: https://github.com/THUDM/GLM (fetched 2026-08-28T04:08:13.056583+00:00, sha f2dbcc14097b)
- Data as of 2026-08-30T08:39:29.467469+00:00.