--- title: "LlamaFactory vs TencentPretrain" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/hiyouga-llamafactory-vs-tencent-tencentpretrain" tools: ["hiyouga-llamafactory", "tencent-tencentpretrain"] --- # LlamaFactory vs TencentPretrain *GraphCanon updated Jul 12, 2026* ## Verdict Pick LlamaFactory if llamaFactory is a sophisticated tool for fine-tuning numerous large language models and visual language models efficiently using various methods such as LoRA, QLoRA, RLHF, and quantization; pick TencentPretrain if tencentPretrain is a PyTorch-based framework for pre-training models and includes a model zoo with multiple architectures. [LlamaFactory](https://llamafactory.readthedocs.io) reports 73k GitHub stars, 8.9k forks, and 1.1k open issues, last pushed Jul 10, 2026. [TencentPretrain](https://github.com/Tencent/TencentPretrain/wiki) has 1.1k stars, 147 forks, and 44 open issues, last pushed Aug 4, 2024. Figures are from public GitHub metadata via [LlamaFactory's repository](https://github.com/hiyouga/LlamaFactory) and [TencentPretrain's repository](https://github.com/Tencent/TencentPretrain). | | [LlamaFactory](/tools/hiyouga-llamafactory.md) | [TencentPretrain](/tools/tencent-tencentpretrain.md) | | --- | --- | --- | | Tagline | Unified Efficient Fine-Tuning of 100+ LLMs & VLMs | Tencent Pre-training framework in PyTorch & Pre-trained Model Zoo | | Stars | 73,157 | 1,089 | | Forks | 8,937 | 147 | | Open issues | 1,067 | 44 | | Language | Python | Python | | Adopt for | LlamaFactory is a sophisticated tool for fine-tuning numerous large language models and visual language models efficiently using various methods such as LoRA, QLoRA, RLHF, and quantization. | TencentPretrain is a PyTorch-based framework for pre-training models and includes a model zoo with multiple architectures. | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | Other | | Categories | LLM Frameworks, Model Training | LLM Frameworks, Model Training | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [LlamaFactory](/tools/hiyouga-llamafactory.md) | [TencentPretrain](/tools/tencent-tencentpretrain.md) | | --- | --- | --- | | Maintenance | Very active (96%) | Dormant (18%) | | Days since push | 0d | 705d | | Open issues (now) | 1.1k | 44 | | Owner type | User | Organization | | Full report | [trust report](/tools/hiyouga-llamafactory/trust.md) | [trust report](/tools/tencent-tencentpretrain/trust.md) | ## Decision facts: LlamaFactory - **Adopt for:** LlamaFactory is a sophisticated tool for fine-tuning numerous large language models and visual language models efficiently using various methods such as LoRA, QLoRA, RLHF, and quantization. ## Decision facts: TencentPretrain - **Pricing:** unknown - The pricing details are not explicitly mentioned in the provided repository content. - **Adopt for:** TencentPretrain is a PyTorch-based framework for pre-training models and includes a model zoo with multiple architectures. ## Choose when ### Choose LlamaFactory if… - License: LlamaFactory is Apache-2.0, TencentPretrain is Other. - Tags unique to LlamaFactory: agent, ai, deepseek, gemma. - When you need to fine-tune over 100 different LLMs or VLMs with efficient methods like LoRA or QLoRA. ### Choose TencentPretrain if… - License: TencentPretrain is Other, LlamaFactory is Apache-2.0. - Pricing: The pricing details are not explicitly mentioned in the provided repository content.. - Tags unique to TencentPretrain: albert, bart, bert, chinese. - TencentPretrain is a PyTorch-based framework for pre-training models and includes a model zoo with multiple architectures. ## When NOT to use LlamaFactory - When you are looking to fine-tune less popular or niche models that are not supported within the 100+ models covered by LlamaFactory. - If your project specifically requires custom fine-tuning methods not available in this repository, such as certain versions of PEFT (Parameter Efficient Fine-Tuning) techniques excluding LoRA and QLoa ## When NOT to use TencentPretrain - Last GitHub push was 707 days ago (dormant maintenance, Aug 4, 2024). Validate activity before betting a new project on TencentPretrain. - LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. - Model Training: Try prompting and RAG first; fine-tuning is the answer to style/format, not missing knowledge. ## Common questions ### What is the difference between LlamaFactory and TencentPretrain? LlamaFactory: Unified Efficient Fine-Tuning of 100+ LLMs & VLMs. TencentPretrain: Tencent Pre-training framework in PyTorch & Pre-trained Model Zoo. See the comparison table for live GitHub stats and shared categories. ### When should I choose LlamaFactory over TencentPretrain? Choose LlamaFactory over TencentPretrain when License: LlamaFactory is Apache-2.0, TencentPretrain is Other; Tags unique to LlamaFactory: agent, ai, deepseek, gemma; When you need to fine-tune over 100 different LLMs or VLMs with efficient methods like LoRA or QLoRA. ### When should I choose TencentPretrain over LlamaFactory? Choose TencentPretrain over LlamaFactory when License: TencentPretrain is Other, LlamaFactory is Apache-2.0; Pricing: The pricing details are not explicitly mentioned in the provided repository content.; Tags unique to TencentPretrain: albert, bart, bert, chinese; TencentPretrain is a PyTorch-based framework for pre-training models and includes a model zoo with multiple architectures. ### When should I avoid LlamaFactory? When you are looking to fine-tune less popular or niche models that are not supported within the 100+ models covered by LlamaFactory. If your project specifically requires custom fine-tuning methods not available in this repository, such as certain versions of PEFT (Parameter Efficient Fine-Tuning) techniques excluding LoRA and QLoa ### When should I avoid TencentPretrain? Last GitHub push was 707 days ago (dormant maintenance, Aug 4, 2024). Validate activity before betting a new project on TencentPretrain. LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. Model Training: Try prompting and RAG first; fine-tuning is the answer to style/format, not missing knowledge. ### Is LlamaFactory or TencentPretrain more popular on GitHub? LlamaFactory has more GitHub stars (73,157 vs 1,089). Stars measure visibility, not whether either tool fits your constraints. ### Are LlamaFactory and TencentPretrain open source? Yes - both are open-source projects on GitHub (LlamaFactory: Apache-2.0, TencentPretrain: Other). ### Where can I find alternatives to LlamaFactory or TencentPretrain? GraphCanon lists graph-backed alternatives at [LlamaFactory alternatives](/tools/hiyouga-llamafactory/alternatives) and [TencentPretrain alternatives](/tools/tencent-tencentpretrain/alternatives) ([LlamaFactory markdown twin](/tools/hiyouga-llamafactory/alternatives.md), [TencentPretrain markdown twin](/tools/tencent-tencentpretrain/alternatives.md)), 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](/compare/hiyouga-llamafactory-vs-tencent-tencentpretrain.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, LlamaFactory or TencentPretrain? LlamaFactory: Very active. TencentPretrain: Dormant. 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 LlamaFactory and TencentPretrain? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [LlamaFactory trust report](/tools/hiyouga-llamafactory/trust); [TencentPretrain trust report](/tools/tencent-tencentpretrain/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=hiyouga-llamafactory`](/api/graphcanon/graph?tool=hiyouga-llamafactory) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_