71 lines
2.2 KiB
Markdown
71 lines
2.2 KiB
Markdown
|
---
|
||
|
|
library_name: transformers
|
||
|
|
license: other
|
||
|
|
base_model: meta-llama/Meta-Llama-3.1-8B
|
||
|
|
tags:
|
||
|
|
- llama-factory
|
||
|
|
- full
|
||
|
|
- generated_from_trainer
|
||
|
|
model-index:
|
||
|
|
- name: textworld_train_40k
|
||
|
|
results: []
|
||
|
|
---
|
||
|
|
|
||
|
|
# *From Word to World*: Can Large Language Models be Implicit Text-based World Models?
|
||
|
|
|
||
|
|
[](https://arxiv.org/abs/2512.18832)
|
||
|
|
[](https://macaron.im/mindlab/research/how-world-models-unlock-scalable-agentic-rl)
|
||
|
|
[](https://huggingface.co/papers/2512.18832)
|
||
|
|
[](https://huggingface.co/collections/X1AOX1A/llm-as-world-models)
|
||
|
|
[](https://huggingface.co/datasets/X1AOX1A/LLMasWorldModels)
|
||
|
|
|
||
|
|
|
||
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
||
|
|
should probably proofread and complete it, then remove this comment. -->
|
||
|
|
|
||
|
|
# textworld_train_40k
|
||
|
|
|
||
|
|
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the textworld_train_58805 dataset.
|
||
|
|
|
||
|
|
## Model description
|
||
|
|
|
||
|
|
More information needed
|
||
|
|
|
||
|
|
## Intended uses & limitations
|
||
|
|
|
||
|
|
More information needed
|
||
|
|
|
||
|
|
## Training and evaluation data
|
||
|
|
|
||
|
|
More information needed
|
||
|
|
|
||
|
|
## Training procedure
|
||
|
|
|
||
|
|
### Training hyperparameters
|
||
|
|
|
||
|
|
The following hyperparameters were used during training:
|
||
|
|
- learning_rate: 1e-05
|
||
|
|
- train_batch_size: 2
|
||
|
|
- eval_batch_size: 8
|
||
|
|
- seed: 42
|
||
|
|
- distributed_type: multi-GPU
|
||
|
|
- num_devices: 4
|
||
|
|
- gradient_accumulation_steps: 16
|
||
|
|
- total_train_batch_size: 128
|
||
|
|
- total_eval_batch_size: 32
|
||
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
||
|
|
- lr_scheduler_type: constant_with_warmup
|
||
|
|
- lr_scheduler_warmup_steps: 10
|
||
|
|
- num_epochs: 5.0
|
||
|
|
|
||
|
|
### Training results
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
### Framework versions
|
||
|
|
|
||
|
|
- Transformers 4.52.4
|
||
|
|
- Pytorch 2.9.0+cu128
|
||
|
|
- Datasets 3.6.0
|
||
|
|
- Tokenizers 0.21.1
|