Decapoda-research
Rank:Average Model Cost: $0.0000
Number of Runs: 276,479
Models by this creator
llama-7b-hf
llama-7b-hf
LLaMA-7B is a large language model based on the transformer architecture. It is trained on a diverse range of sources including CCNet, C4, GitHub, Wikipedia, Books, ArXiv, and Stack Exchange. The primary intended use of LLaMA-7B is for research in natural language processing, machine learning, and artificial intelligence. It can be used to explore potential applications such as question answering, natural language understanding, and reading comprehension. However, it should not be used for downstream applications without further risk evaluation and mitigation as it may generate toxic, offensive, or incorrect content. The model has been evaluated on various benchmarks and measures including common sense reasoning, reading comprehension, question answering, and toxicity. It is important to note that LLaMA-7B reflects biases from the training data and may exhibit biases in its outputs. Mitigations have been implemented to filter offensive and biased content, but risks and harms are still present.
$-/run
221.0K
Huggingface
llama-13b-hf
llama-13b-hf
LLaMA-13B is an auto-regressive language model based on the transformer architecture. It is a large language model primarily intended for research purposes in natural language processing, machine learning, and artificial intelligence. The model has been trained on a diverse range of data sources, including web data, and is available in different sizes. It is important to note that the model may exhibit biases and generate potentially harmful or offensive content, as it has not been trained with human feedback. The model has been evaluated on various benchmarks to measure its performance, including common sense reasoning, question answering, and toxicity. Ethical considerations should be taken into account when using the model, including the potential risks and harms associated with large language models.
$-/run
24.6K
Huggingface
llama-30b-hf
llama-30b-hf
LLaMA-30B is an auto-regressive language model based on the transformer architecture. It is part of the LLaMA series of models developed by the FAIR team of Meta AI. This model has been converted to work with Transformers/HuggingFace. LLaMA-30B has 30 billion parameters and was trained between December 2022 and February 2023. Its primary use is for research on large language models, including exploring potential applications, understanding model capabilities and limitations, and evaluating biases, risks, and toxic content generation. The model is intended for researchers in natural language processing, machine learning, and artificial intelligence. It is important to note that LLaMA-30B should not be used on downstream applications without further risk evaluation and mitigation, as it can generate toxic or offensive content and may provide incorrect or unhelpful answers.
$-/run
18.9K
Huggingface
llama-65b-hf
llama-65b-hf
The llama-65b-hf model is a text generation model. It is designed to generate human-like text based on the given input. The model has been trained on a large dataset and can generate a variety of text, including responses, descriptions, and creative writing. It uses deep learning techniques to understand the context and language patterns in the input text and generates coherent and relevant text as output. The model can be used for a wide range of applications, such as chatbots, content generation, and language understanding tasks.
$-/run
12.0K
Huggingface
llama-7b-hf-int4
$-/run
9
Huggingface
llama-65b-hf-int4
llama-65b-hf-int4
LLaMA-13B converted to work with Transformers/HuggingFace. This is under a special license, please see the LICENSE file for details. EXPERIMENTAL RELEASE This has been converted to int4 via GPTQ method. This requires some special support code that is also highly experimental. NOT COMPATIBLE WITH TRANSFORMERS LIBRARY. -- license: other LLaMA Model Card Model details Organization developing the model The FAIR team of Meta AI. Model date LLaMA was trained between December. 2022 and Feb. 2023. Model version This is version 1 of the model. Model type LLaMA is an auto-regressive language model, based on the transformer architecture. The model comes in different sizes: 7B, 13B, 33B and 65B parameters. Paper or resources for more information More information can be found in the paper “LLaMA, Open and Efficient Foundation Language Models”, available at https://research.facebook.com/publications/llama-open-and-efficient-foundation-language-models/. Citations details https://research.facebook.com/publications/llama-open-and-efficient-foundation-language-models/ License Non-commercial bespoke license Where to send questions or comments about the model Questions and comments about LLaMA can be sent via the GitHub repository of the project , by opening an issue. 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 we included 20 languages in the training data, most of our dataset is made of English text, and we thus expect the model to perform better for English than other languages. Relatedly, it has been shown in previous studies that performance might vary for different dialects, and we expect that it will be the case for our model. Evaluation factors As our model is trained on data from the Web, we expect that it reflects biases from this source. We thus 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. We also measure the toxicity of model generations, depending on the toxicity of the context used to prompt the model. Metrics Model performance measures We use the following measure 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, we trained only one model of each size, and thus could not evaluate variability of pre-training. 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 Hyperparameters for the model architecture Table 1 - Summary of LLama Model Hyperparameters We present our results on eight standard common sense reasoning benchmarks in the table below. We present our results on bias in the table below. Note that lower value is better indicating lower 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. As such, it contains offensive, harmful and biased content. We thus expect the model to exhibit such biases from the training data. 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 We filtered the data from the Web based on its proximity to Wikipedia text and references. For this, we used 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. These models are often prone to generating incorrect information, sometimes referred to as hallucinations. We do not expect our model to be an exception in this regard. Use cases LLaMA is a foundational model, and as such, it should not be used for downstream applications without further investigation and mitigations of risks. These risks and potential fraught use cases include, but are not limited to: generation of misinformation and generation of harmful, biased or offensive content.
$-/run
0
Huggingface
llama-30b-hf-int4
$-/run
0
Huggingface
llama-smallint-pt
llama-smallint-pt
This is HIGHLY experimental, and is not designed to work w/the transformers library. I'm providing these files for research and development purposes only, and I will not be providing any support or assistance in setting these models up for use LLaMA 7b/13b/30b quantized to 3-bit and 4-bit using GPTQ. See https://github.com/qwopqwop200/GPTQ-for-LLaMa. This is under a special license, please see the LICENSE file for details. -- license: other LLaMA Model Card Model details Organization developing the model The FAIR team of Meta AI. Model date LLaMA was trained between December. 2022 and Feb. 2023. Model version This is version 1 of the model. Model type LLaMA is an auto-regressive language model, based on the transformer architecture. The model comes in different sizes: 7B, 13B, 33B and 65B parameters. Paper or resources for more information More information can be found in the paper “LLaMA, Open and Efficient Foundation Language Models”, available at https://research.facebook.com/publications/llama-open-and-efficient-foundation-language-models/. Citations details https://research.facebook.com/publications/llama-open-and-efficient-foundation-language-models/ License Non-commercial bespoke license Where to send questions or comments about the model Questions and comments about LLaMA can be sent via the GitHub repository of the project , by opening an issue. 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 we included 20 languages in the training data, most of our dataset is made of English text, and we thus expect the model to perform better for English than other languages. Relatedly, it has been shown in previous studies that performance might vary for different dialects, and we expect that it will be the case for our model. Evaluation factors As our model is trained on data from the Web, we expect that it reflects biases from this source. We thus 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. We also measure the toxicity of model generations, depending on the toxicity of the context used to prompt the model. Metrics Model performance measures We use the following measure 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, we trained only one model of each size, and thus could not evaluate variability of pre-training. 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 Hyperparameters for the model architecture Table 1 - Summary of LLama Model Hyperparameters We present our results on eight standard common sense reasoning benchmarks in the table below. We present our results on bias in the table below. Note that lower value is better indicating lower 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. As such, it contains offensive, harmful and biased content. We thus expect the model to exhibit such biases from the training data. 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 We filtered the data from the Web based on its proximity to Wikipedia text and references. For this, we used 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. These models are often prone to generating incorrect information, sometimes referred to as hallucinations. We do not expect our model to be an exception in this regard. Use cases LLaMA is a foundational model, and as such, it should not be used for downstream applications without further investigation and mitigations of risks. These risks and potential fraught use cases include, but are not limited to: generation of misinformation and generation of harmful, biased or offensive content.
$-/run
0
Huggingface
llama-13b-hf-int4
llama-13b-hf-int4
LLaMA-13B converted to work with Transformers/HuggingFace. This is under a special license, please see the LICENSE file for details. EXPERIMENTAL RELEASE This has been converted to int4 via GPTQ method. This requires some special support code that is also highly experimental. NOT COMPATIBLE WITH TRANSFORMERS LIBRARY. -- license: other LLaMA Model Card Model details Organization developing the model The FAIR team of Meta AI. Model date LLaMA was trained between December. 2022 and Feb. 2023. Model version This is version 1 of the model. Model type LLaMA is an auto-regressive language model, based on the transformer architecture. The model comes in different sizes: 7B, 13B, 33B and 65B parameters. Paper or resources for more information More information can be found in the paper “LLaMA, Open and Efficient Foundation Language Models”, available at https://research.facebook.com/publications/llama-open-and-efficient-foundation-language-models/. Citations details https://research.facebook.com/publications/llama-open-and-efficient-foundation-language-models/ License Non-commercial bespoke license Where to send questions or comments about the model Questions and comments about LLaMA can be sent via the GitHub repository of the project , by opening an issue. 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 we included 20 languages in the training data, most of our dataset is made of English text, and we thus expect the model to perform better for English than other languages. Relatedly, it has been shown in previous studies that performance might vary for different dialects, and we expect that it will be the case for our model. Evaluation factors As our model is trained on data from the Web, we expect that it reflects biases from this source. We thus 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. We also measure the toxicity of model generations, depending on the toxicity of the context used to prompt the model. Metrics Model performance measures We use the following measure 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, we trained only one model of each size, and thus could not evaluate variability of pre-training. 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 Hyperparameters for the model architecture Table 1 - Summary of LLama Model Hyperparameters We present our results on eight standard common sense reasoning benchmarks in the table below. We present our results on bias in the table below. Note that lower value is better indicating lower 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. As such, it contains offensive, harmful and biased content. We thus expect the model to exhibit such biases from the training data. 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 We filtered the data from the Web based on its proximity to Wikipedia text and references. For this, we used 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. These models are often prone to generating incorrect information, sometimes referred to as hallucinations. We do not expect our model to be an exception in this regard. Use cases LLaMA is a foundational model, and as such, it should not be used for downstream applications without further investigation and mitigations of risks. These risks and potential fraught use cases include, but are not limited to: generation of misinformation and generation of harmful, biased or offensive content.
$-/run
0
Huggingface
llama-7b-hf-int8
llama-7b-hf-int8
LLaMA-7B converted to work with Transformers/HuggingFace. This variant is also quantized to int8. This is under a special license, please see the LICENSE file for details.
$-/run
0
Huggingface