Elinas
Rank:Average Model Cost: $0.0000
Number of Runs: 10,342
Models by this creator
llama-7b-hf-transformers-4.29
llama-7b-hf-transformers-4.29
The llama-7b-hf-transformers-4.29 model is an auto-regressive language model based on the transformer architecture. It is one of the LLaMA models developed by the FAIR team of Meta AI. This model has been trained on a large dataset comprising various sources such as CCNet, C4, GitHub, Wikipedia, Books, ArXiv, and Stack Exchange. The primary use of the model is for research purposes in natural language processing, machine learning, and artificial intelligence. The model's performance may vary depending on the language used, with better performance expected for English. The model has undergone evaluation for biases, toxicity, question answering, common sense reasoning, reading comprehension, and natural language understanding. It is important to note that the model may generate toxic or offensive content, incorrect information, or unhelpful answers, as it has not been trained with human feedback. Mitigations have been applied to filter offensive and biased content from the training data, but risks and harms associated with large language models still exist. Therefore, further investigation and mitigation of risks are necessary before using this model in downstream applications.
$-/run
5.3K
Huggingface
llama-13b-hf-transformers-4.29
$-/run
1.4K
Huggingface
llama-30b-hf-transformers-4.29
$-/run
1.2K
Huggingface
chronos-13b-4bit
chronos-13b-4bit
chronos-13b-4bit 4bit (int4) quantized version using true-sequential and groupsize 128 of https://huggingface.co/elinas/chronos-13b This model is primarily focused on chat, roleplay, and storywriting, but can accomplish other tasks such as simple reasoning and coding. Chronos generates very long outputs with coherent text, largely due to the human inputs it was trained on. This model uses Alpaca formatting, so for optimal model performance, use: GGML Version provided by @TheBloke -- 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
1.1K
Huggingface
chronos-13b
chronos-13b
This is the fp16 PyTorch / HF version of chronos-13b This model is primarily focused on chat, roleplay, and storywriting, but can accomplish other tasks such as simple reasoning and coding. Chronos generates very long outputs with coherent text, largely due to the human inputs it was trained on. This model uses Alpaca formatting, so for optimal model performance, use: 4bit Quantized version GGML Version provided by @TheBloke -- license: other 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. 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. 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. Model performance measures We use the following measure to evaluate the model: 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. 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. 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. 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 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
577
Huggingface
vicuna-13b-4bit
vicuna-13b-4bit
vicuna-13b-4bit Converted vicuna-13b to GPTQ 4bit using true-sequentual and groupsize 128 in safetensors for best possible model performance. This does not support llama.cpp or any other cpp implemetations, only cuda is supported. These implementations require a different format to use. Vicuna is a high coherence model based on Llama that is comparable to ChatGPT. Read more here https://vicuna.lmsys.org/ Important - Update 2023-04-05 Recent GPTQ commits have introduced breaking changes to model loading and you should this fork for a stable experience https://github.com/oobabooga/GPTQ-for-LLaMa Curently only cuda is supported. Usage Run manually through GPTQ (More setup but better UI) - Use the text-generation-webui. Make sure to follow the installation steps first here before adding GPTQ support. Since this is instruction tuned, for best results, use the following format for inference (note that the instruction format is different from Alpaca): If you want deterministic results, turn off sampling. You can turn it off in the webui by unchecking do_sample. -- 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
355
Huggingface
llama-65b-hf-transformers-4.29
llama-65b-hf-transformers-4.29
llama-65b-transformers-4.29 Original weights converted with the latest transformers version using the LlamaTokenizerFast implementation. -- 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
121
Huggingface
alpaca-30b-lora-int4
alpaca-30b-lora-int4
llama-30b-int4 This LoRA trained for 3 epochs and has been converted to int4 (4bit) via GPTQ method. Use the one of the two safetensors versions, the pt version is an old quantization that is no longer supported and will be removed in the future. Make sure you only have ONE checkpoint from the two in your model directory! See the repo below for more info. LoRA credit to https://huggingface.co/baseten/alpaca-30b Important - Update 2023-04-05 Recent GPTQ commits have introduced breaking changes to model loading and you should this fork for a stable experience https://github.com/oobabooga/GPTQ-for-LLaMa Curently only cuda is supported. Update 2023-03-29 There is also a non-groupsize quantized model that is 1GB smaller in size, which should allow running at max context tokens with 24GB VRAM. The evaluations are better on the 128 groupsize version, but the tradeoff is not being able to run it at full context without offloading or a GPU with more VRAM. Update 2023-03-27 New weights have been added. The old .pt version is no longer supported and has been replaced by a 128 groupsize safetensors file. Update to the latest GPTQ version/webui. Evals - Groupsize 128 + True Sequential alpaca-30b-4bit-128g.safetensors [4805cc2] c4-new - 6.398105144500732 ptb-new - 8.449508666992188 wikitext2 - 4.402845859527588 Evals - Default + True Sequential alpaca-30b-4bit.safetensors [6958004] c4-new - 6.592941761016846 ptb-new - 8.718379974365234 wikitext2 - 4.635514736175537 Usage Run manually through GPTQ (More setup but better UI) - Use the text-generation-webui. Make sure to follow the installation steps first here before adding GPTQ support. Since this is instruction tuned, for best results, use the following format for inference: If you want deterministic results, turn off sampling. You can turn it off in the webui by unchecking do_sample. For cai-chat mode, you won't want to use instruction prompting, rather create a character and set sampler settings. Here is an example of settings that work well for me: You can then save this as a .txt file in the presets folder. -- 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
90
Huggingface