4bit Autotrain compatible En Endpoints compatible Lora Mistral Quantized Region:us Safetensors Sft Sharded Tensorflow Trl Unsloth
Model Card on HF 🤗: https://huggingface.co/theprint/WorldBuilder-12B
WorldBuilder 12B Benchmarks
MMLU Pro: 24.36
GPQA: 6.26
MUSR: 9
BBH: 29.28
IFEval: 13.74 vs 88 (so35)-84.4%
MATH Lvl 5: 4.46
LLME Score: 0.22291
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)
WorldBuilder 12B Parameters and Internals
| LLM Name | WorldBuilder 12B |
| Repository 🤗 | https://huggingface.co/theprint/WorldBuilder-12B |
| Base Model(s) | |
| Model Size | 12b |
| Required VRAM | 24.5 GB |
| Updated | 2025-09-17 |
| Maintainer | theprint |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | AutoModelForCausalLM |
| License | apache-2.0 |
| Model Max Length | 1024000 |
| Is Biased | none |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <pad> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | k_proj|q_proj|up_proj|down_proj|gate_proj|o_proj|v_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0 |
| R Param | 8 |
Best Alternatives to WorldBuilder 12B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| CleverBoi Nemo 12B V2 | 0K / 0.2 GB | 145 | 4 |
| Ramen 12B | 0K / 24.5 GB | 8 | 0 |
| Noodles Merge 12B | 0K / 24.5 GB | 8 | 0 |
| Broth 12B | 0K / 24.5 GB | 6 | 0 |
| Ultra Instruct 12B | 0K / 24.5 GB | 3 | 4 |
| Orthrus 12B V0.8 | 0K / 24.5 GB | 4 | 4 |
| Polyglot Ko 12B Qlora | 0K / 25.9 GB | 43 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than theprint/WorldBuilder-12B .
Rank the WorldBuilder 12B 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? 51545 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124