Arxiv:2503.05139 Autotrain compatible Bailing moe Custom code Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/inclusionAI/Ling-lite-base
Ling Lite Base Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Ling Lite Base Parameters and Internals
| LLM Name | Ling Lite Base |
| Repository 🤗 | https://huggingface.co/inclusionAI/Ling-lite-base |
| Model Size | 16.8b |
| Required VRAM | 33.6 GB |
| Updated | 2025-09-27 |
| Maintainer | inclusionAI |
| Model Type | bailing_moe |
| Model Files | |
| Model Architecture | BailingMoeForCausalLM |
| License | mit |
| Context Length | 16384 |
| Model Max Length | 16384 |
| Transformers Version | 4.36.0 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 126464 |
| Torch Data Type | bfloat16 |
Best Alternatives to Ling Lite Base
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Ling Lite 1.5 2507 | 32K / 33.6 GB | 184 | 75 |
| Ring Lite 2507 | 32K / 33.6 GB | 93 | 57 |
| Ling Lite 1.5 2506 | 32K / 33.6 GB | 83 | 52 |
| Ling Lite | 32K / 24.8 GB | 154 | 75 |
| Ring Lite Distill Preview | 16K / 33.6 GB | 93 | 43 |
| Ling Coder Lite | 4K / 33.6 GB | 113 | 47 |
| Ling Coder Lite Base | 4K / 33.6 GB | 81 | 26 |
Note: green Score (e.g. "73.2") means that the model is better than inclusionAI/Ling-lite-base .
Rank the Ling Lite Base Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 51535 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124