Llama 13b Hf

🚀 Llama-13B-HF

The weight file is split into chunks with a size of 650MB for convenient and fast parallel downloads. This is a 650M split weight version of yahma/llama-13b-hf. The original model card is provided below.

🚀 Quick Start

LLaMA-13B was converted to work with the git head of Transformers/HuggingFace on April 8, 2023. This version should resolve the EOS token issues.

✨ Features

• The weight files are split into 650MB chunks for easy and fast parallel downloads.
• Resolves the EOS token issues.

📚 Documentation

Model details

Intended use

• Primary intended uses: The primary use of LLaMA is research on large language models, including exploring potential applications such as question answering, natural language understanding or reading comprehension, understanding capabilities and limitations of current language models, and developing techniques to improve those, evaluating and mitigating biases, risks, toxic and harmful content generations, hallucinations.
• Primary intended users: The primary intended users of the model are researchers in natural language processing, machine learning and artificial intelligence.
• Out - of - scope use cases: LLaMA is a base, or foundational, model. As such, it should not be used on downstream applications without further risk evaluation and mitigation. In particular, our model has not been trained with human feedback, and can thus generate toxic or offensive content, incorrect information or generally unhelpful answers.

Factors

• Relevant factors: One of the most relevant factors for which model performance may vary is which language is used. Although 20 languages were included in the training data, most of the dataset is made of English text, and the model is expected to perform better for English than other languages. Relatedly, performance might vary for different dialects.
• Evaluation factors: As the model is trained on data from the Web, it is expected to reflect biases from this source. It was evaluated on RAI datasets to measure biases exhibited by the model for gender, religion, race, sexual orientation, age, nationality, disability, physical appearance and socio - economic status. The toxicity of model generations was also measured depending on the toxicity of the context used to prompt the model.

Metrics

• Model performance measures: The following measures are used to evaluate the model:
  • Accuracy for common sense reasoning, reading comprehension, natural language understanding (MMLU), BIG - bench hard, WinoGender and CrowS - Pairs.
  • Exact match for question answering.
  • The toxicity score from Perspective API on RealToxicityPrompts.
• Decision thresholds: Not applicable.
• Approaches to uncertainty and variability: Due to the high computational requirements of training LLMs, only one model of each size was trained, and thus variability of pre - training could not be evaluated.

Evaluation datasets

The model was evaluated on the following benchmarks: BoolQ, PIQA, SIQA, HellaSwag, WinoGrande, ARC, OpenBookQA, NaturalQuestions, TriviaQA, RACE, MMLU, BIG - bench hard, GSM8k, RealToxicityPrompts, WinoGender, CrowS - Pairs.

Training dataset

The model was trained using the following source of data: CCNet [67%], C4 [15%], GitHub [4.5%], Wikipedia [4.5%], Books [4.5%], ArXiv [2.5%], Stack Exchange[2%]. The Wikipedia and Books domains include data in the following languages: bg, ca, cs, da, de, en, es, fr, hr, hu, it, nl, pl, pt, ro, ru, sl, sr, sv, uk. See the paper for more details about the training set and corresponding preprocessing.

Quantitative analysis

Model hyperparameters

Table 1 - Summary of LLama Model Hyperparameters

Model performance on reasoning tasks

Table 2 - Summary of LLama Model Performance on Reasoning tasks

Model bias

Table 3 - Summary bias of our model output

Ethical considerations

• Data: The data used to train the model is collected from various sources, mostly from the Web. It contains offensive, harmful and biased content, so the model is expected to exhibit such biases.
• Human life: The model is not intended to inform decisions about matters central to human life and should not be used in such a way.
• Mitigations: The data from the Web was filtered based on its proximity to Wikipedia text and references using a Kneser - Ney language model and a fastText linear classifier.
• Risks and harms: Risks and harms of large language models include the generation of harmful, offensive or biased content and incorrect information (hallucinations). The model is not expected to be an exception.
• Use cases: LLaMA is a foundational model and should not be used for downstream applications without further investigation and mitigation of risks, such as the generation of misinformation and harmful, biased or offensive content.

📄 License

This model is under a special non - commercial bespoke license. Please see the LICENSE file for details. You should only use this repository if you have been granted access to the model by filling out this form but either lost your copy of the weights or got some trouble converting them to the Transformers format.