Comparison
BELLE vs LLMs-from-scratch
Verdict
Pick BELLE if bELLE is an open-source Chinese dialogue large model that focuses on improving instruction-following capabilities through fine-tuned pre-training models; pick LLMs-from-scratch if lLMs-from-scratch is a project-oriented repository aimed at building PyTorch-based language models from the ground up, with detailed step-by-step instructions.
Markdown twin · BELLE alternatives · LLMs-from-scratch alternatives
GraphCanon updated 1w
vs
Trust & integrity
| Signal | BELLE | LLMs-from-scratch |
|---|---|---|
| Maintenance | Dormant (654d since push) As of 3w · github_public_v1 | Very active (5d since push) As of 1w · github_public_v1 |
| Provenance | Not a fork · Organization account As of 3w · github_public_v1 | Not a fork · Personal account As of 1w · github_public_v1 |
| OSV dependency advisories | No published findings from this source as of 2026-07-11 As of 1mo · osv@v1 | No lockfile (source not queried) As of 1mo · osv@v1 |
| deps.dev advisories | Not queried deps.dev@v1 | Not queried deps.dev@v1 |
| OpenSSF Scorecard | Not queried openssf-scorecard@v1 | Not queried openssf-scorecard@v1 |
Tagline
- BELLE
- Open-source Chinese dialogue large model
- LLMs-from-scratch
- Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Stars
- BELLE
- 8.3k
- LLMs-from-scratch
- 103k
Forks
- BELLE
- 758
- LLMs-from-scratch
- 16k
Open issues
- BELLE
- 106
- LLMs-from-scratch
- 2
Language
- BELLE
- HTML
- LLMs-from-scratch
- Jupyter Notebook
Adopt for
- BELLE
- BELLE is an open-source Chinese dialogue large model that focuses on improving instruction-following capabilities through fine-tuned pre-training models.
- LLMs-from-scratch
- LLMs-from-scratch is a project-oriented repository aimed at building PyTorch-based language models from the ground up, with detailed step-by-step instructions.
Persona
- BELLE
- -
- LLMs-from-scratch
- -
Runtime
- BELLE
- -
- LLMs-from-scratch
- -
License
- BELLE
- Available under the Apache-2.0 license.
- LLMs-from-scratch
- Other
Last pushed
- BELLE
- Oct 16, 2024
- LLMs-from-scratch
- Aug 10, 2026
Categories
- BELLE
- Inference & Serving, LLM Frameworks, Model Training
- LLMs-from-scratch
- LLM Frameworks, Model Training
Trust and health
Maintenance
- BELLE
- Dormant (18%)
- LLMs-from-scratch
- Very active (96%)
Days since push
- BELLE
- 654d
- LLMs-from-scratch
- 5d
Open issues (now)
- BELLE
- 106
- LLMs-from-scratch
- 2
Stars delta
- BELLE
- Unknown
- LLMs-from-scratch
- +3.5k (30d)
Open issues delta
- BELLE
- Unknown
- LLMs-from-scratch
- -1 (30d)
Owner type
- BELLE
- Organization
- LLMs-from-scratch
- User
OSV dependency advisories
- BELLE
- No published findings from this source as of 2026-07-11
- LLMs-from-scratch
- No lockfile (source not queried)
Full report
- BELLE
- Trust report
- LLMs-from-scratch
- Trust report
Choose BELLE if…
- BELLE is primarily HTML; LLMs-from-scratch is Jupyter Notebook.
- License: BELLE is Apache-2.0, LLMs-from-scratch is Other.
- BELLE models are hosted on Hugging Face, contributing to a growing ecosystem of open-source language models.
- Pricing: Free for non-commercial use under the Apache 2.0 license; commercial projects should review compliance or seek additional licensing options as needed..
- Tags unique to BELLE: chinese-nlp, gpt-evaluation, instruct-finetune, llama.
- Also covers Inference & Serving.
- When you need a specifically optimized language model for the Chinese language with enhanced dialogue capabilities.
When NOT to use BELLE
- When the project requires a multi-lingual model or extensive support for languages other than Chinese.
- For applications that do not need fine-tuned instruction-following capabilities, since BELLE is particularly optimized for this aspect using data from ChatGPT exclusively.
- If real-time voice recognition speed is critical and a slight delay can be tolerated, as alternatives may offer more balanced performance.
Choose LLMs-from-scratch if…
- LLMs-from-scratch is primarily Jupyter Notebook; BELLE is HTML.
- License: LLMs-from-scratch is Other, BELLE is Apache-2.0.
- Tags unique to LLMs-from-scratch: ai, artificial-intelligence, attention-mechanism, deep-learning.
- - You are an advanced practitioner aiming to fully understand the underpinnings of LLMs using PyTorch as your primary framework.
When NOT to use LLMs-from-scratch
- - If you are looking for a rapid deployment of an LLM without understanding its intricate structure - this tool requires extensive manual and conceptual work.
- - You prefer frameworks with automatic model generation or other high-level abstractions that simplify the process. This repository emphasizes manual creation, which is more time-consuming but offers
- a deeper learning experience.
Explore
Sources
Every stat on this page traces to a dated GitHub sync, license file, enrichment field, or trust scan.
- GitHub stars (LianjiaTech/BELLE) · observed Aug 1, 2026
- GitHub forks (LianjiaTech/BELLE) · observed Aug 1, 2026
- Last push (LianjiaTech/BELLE) · observed Oct 16, 2024
- License file (Apache-2.0) · observed Aug 1, 2026
- Decision facts (enrichment) · observed Jul 14, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
- GitHub stars (rasbt/LLMs-from-scratch) · observed Aug 16, 2026
- GitHub forks (rasbt/LLMs-from-scratch) · observed Aug 16, 2026
- Last push (rasbt/LLMs-from-scratch) · observed Aug 10, 2026
- License file (Other) · observed Aug 16, 2026
- Decision facts (enrichment) · observed Jul 11, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
GitHub stars on cards: BELLE 8.3k · LLMs-from-scratch 103k (synced Aug 1, 2026).
Common questions
- What is the difference between BELLE and LLMs-from-scratch?
- BELLE: Open-source Chinese dialogue large model. LLMs-from-scratch: Implement a ChatGPT-like LLM in PyTorch from scratch, step by step. See the comparison table for live GitHub stats and shared categories.
- When should I choose BELLE over LLMs-from-scratch?
- Choose BELLE over LLMs-from-scratch when BELLE is primarily HTML; LLMs-from-scratch is Jupyter Notebook; License: BELLE is Apache-2.0, LLMs-from-scratch is Other; BELLE models are hosted on Hugging Face, contributing to a growing ecosystem of open-source language models; Pricing: Free for non-commercial use under the Apache 2.0 license; commercial projects should review compliance or seek additional licensing options as needed.; Tags unique to BELLE: chinese-nlp, gpt-evaluation, instruct-finetune, llama; Also covers Inference & Serving; When you need a specifically optimized language model for the Chinese language with enhanced dialogue capabilities.
- When should I choose LLMs-from-scratch over BELLE?
- Choose LLMs-from-scratch over BELLE when LLMs-from-scratch is primarily Jupyter Notebook; BELLE is HTML; License: LLMs-from-scratch is Other, BELLE is Apache-2.0; Tags unique to LLMs-from-scratch: ai, artificial-intelligence, attention-mechanism, deep-learning; - You are an advanced practitioner aiming to fully understand the underpinnings of LLMs using PyTorch as your primary framework.
- When should I avoid BELLE?
- When the project requires a multi-lingual model or extensive support for languages other than Chinese. For applications that do not need fine-tuned instruction-following capabilities, since BELLE is particularly optimized for this aspect using data from ChatGPT exclusively. If real-time voice recognition speed is critical and a slight delay can be tolerated, as alternatives may offer more balanced performance.
- When should I avoid LLMs-from-scratch?
- - If you are looking for a rapid deployment of an LLM without understanding its intricate structure - this tool requires extensive manual and conceptual work. - You prefer frameworks with automatic model generation or other high-level abstractions that simplify the process. This repository emphasizes manual creation, which is more time-consuming but offers a deeper learning experience.
- Is BELLE or LLMs-from-scratch more popular on GitHub?
- LLMs-from-scratch has more GitHub stars (102,733 vs 8,280). Stars measure visibility, not whether either tool fits your constraints.
- Are BELLE and LLMs-from-scratch open source?
- Yes - both are open-source projects on GitHub (BELLE: Apache-2.0, LLMs-from-scratch: Other).
- Where can I find alternatives to BELLE or LLMs-from-scratch?
- GraphCanon lists graph-backed alternatives at BELLE alternatives and LLMs-from-scratch alternatives (BELLE markdown twin, LLMs-from-scratch markdown twin), ranked by typed relationship edges rather than popularity votes.
- Is there a machine-readable version of this comparison?
- Yes. The markdown twin at this comparison mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers.
- Which is better maintained, BELLE or LLMs-from-scratch?
- BELLE: Dormant. LLMs-from-scratch: Very active. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance.
- Where are the full trust reports for BELLE and LLMs-from-scratch?
- GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: BELLE trust report; LLMs-from-scratch trust report.