Not-so-bright-AGI-Llama3-8B-UC200k-v1
Model Type: Fine-Tuned
Model Base: meta-llama/Meta-Llama-3-8B
Datasets Used: HuggingFaceH4/ultrachat_200k
Author: Yuri Achermann
Date: July 29, 2024
Training procedure
Training Hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 100
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.05
Framework versions
- PEFT==0.11.1
- Transformers==4.41.2
- Pytorch==2.1.0.post0+cxx11.abi
- Datasets==2.19.2
- Tokenizers==0.19.1
Intended uses & limitations
Primary Use Case: The model is intended for generating human-like responses in conversational applications, like chatbots or virtual assistants.
Limitations: The model may generate inaccurate or biased content as it reflects the data it was trained on. It is essential to evaluate the generated responses in context and use the model responsibly.
Evaluation
The evaluation platform consists of Gaudi Accelerators and Xeon CPUs running benchmarks from the Eleuther AI Language Model Evaluation Harness
Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande |
---|---|---|---|---|---|
64.166 | 55.89 | 75.6 | 65.79 | 52.28 | 71.27 |
Ethical Considerations
The model may inherit biases present in the training data. It is crucial to use the model in a way that promotes fairness and mitigates potential biases.
Acknowledgments
This fine-tuning effort was made possible by the support of Intel, that provided the computing resources, and Eduardo Alvarez. Additional shout-out to the creators of the Meta-Llama-3-8B model and the contributors to the databricks-dolly-15k dataset.
Contact Information
For questions or feedback about this model, please contact Yuri Achermann.
License
This model is distributed under Apache 2.0 License.
- Downloads last month
- 7
Model tree for yuriachermann/Not-so-bright-AGI-Llama3-8B-UC200k-v1
Base model
meta-llama/Meta-Llama-3-8BDataset used to train yuriachermann/Not-so-bright-AGI-Llama3-8B-UC200k-v1
Collection including yuriachermann/Not-so-bright-AGI-Llama3-8B-UC200k-v1
Evaluation results
- AI2 Reasoning Challenge on ai2_arcPowered-by-Intel LLM Leaderboard55.890
- HellaSwag on ai2_arcPowered-by-Intel LLM Leaderboard75.600
- MMLU on ai2_arcPowered-by-Intel LLM Leaderboard65.790
- TruthfulQA on ai2_arcPowered-by-Intel LLM Leaderboard52.280
- Winogrande on ai2_arcPowered-by-Intel LLM Leaderboard71.270