Datasets:

---

ftopal

/

huggingface-models-processed

like 0

[ "mlx", "mixtral", "climate change", "biomimicry", "theoretical astrobiology", "environmental simulations", "predictive modeling", "life origins", "ecological impacts", "sustainable technologies", "cross-disciplinary learning", "artificial intelligence", "machine learning", "data integration", "complex systems", "scenario analysis", "speculative science", "universe exploration", "biodiversity", "planetary studies", "innovation in science", "role playing scenarios", "text-generation", "conversational", "en", "dataset:Severian/IMPACTS", "license:mit", "region:us" ]

[]

[ "en" ]

[ "# Llama-3-IMPACTS-2x8B-64k-MLX\n\n<img src=\"URL width=\"500\" height=\"500\">\n\n---\n\nDesigned for Advanced Problem-Solving Across Interconnected Domains of Biomimicry, Climate Change, and Astrobiology\n\nThe 'Llama-3-IMPACTS-2x8B-64k-MLX' model is a cutting-edge large language model trained on the I.M.P.A.C.T.S dataset, which encompasses scenarios from biomimicry, climate change, and theoretical astrobiology. This model has been specifically tailored to generate innovative solutions and insights for both Earth and potential extraterrestrial environments, reflecting key themes of resilience, sustainability, and the interconnectedness of life across the universe.", "## Model Details", "### Description\n\n- Model name: 'Llama-3-IMPACTS-2x8B-64k-MLX'\n- Developer: Severian\n- Version: 1.0\n- License: MIT", "### Training Data\n\nThe model was trained on a subset of the I.M.P.A.C.T. dataset, utilizing 35,000 carefully curated examples that include detailed scenarios involving climate adaptation, biomimetic applications, and the potential for life in varying cosmic conditions.", "### Model Architecture\n\n- Type: Llama-3\n- Parameters: 8 billion\n- MoE: 2 Experts\n- Training:\n- Epochs: 1 (35K Examples)\n- R = 64\n- Alpha = 128\n- Lr = 1e-7\n- Context Limit: 64K", "## Intended Uses\n\nThis model is intended for use in applications that require deep, interdisciplinary understanding and the generation of novel insights within the realms of environmental science, synthetic biology, space exploration, and sustainability studies. Its capabilities make it ideal for:\n- Research and academic studies aiming to explore complex scenarios involving ecological and astrobiological phenomena.\n- Organizations looking to innovate in the fields of climate resilience and biomimicry.\n- Creative problem-solving in contexts where conventional approaches are insufficient.", "## How to Use This Model\n\nThe model can be loaded and used in various natural language processing tasks that require nuanced understanding and creative output. Here is a basic example of how to load and use the model using the MLX library:", "## Limitations and Biases\n\nWhile the 'Llama-3-IMPACTS-2x8B-64k-MLX' model is designed to be a powerful tool for generating insightful content, it inherits limitations from its training data, which, though extensive, may not capture all possible scenarios or biases. Users should be aware of these limitations and consider them when interpreting the model's outputs, especially in decision-making contexts.", "## Model Performance\n\nInitial tests indicate that the model performs exceptionally well in tasks that involve complex reasoning and generating innovative solutions based on the scenarios presented in the I.M.P.A.C.T.S dataset. Further evaluation and fine-tuning may be required to optimize performance for specific applications.\n\nThe 'Llama-3-IMPACTS-2x8B-64k-MLX' model represents an avenue that AI can use for exploring and solving complex problems across multiple domains. By leveraging the rich, interconnected dataset of I.M.P.A.C.T.S, it offers a valuable tool for researchers, innovators, and thinkers aiming to push the boundaries of what's possible in their fields.", "# Use Cases", "## Universe/World Simulation\n\nUse Llama-3-IMPACTS-2x8B-64k to simulate incredibly unique and diverse ecosystems and cosmic worlds. Example image generation (text-to-image):\n\nUser Prompt: 'Craft a detailed image generation prompt focused on visualizing an innovative scenario that integrates biomimicry, climate change adaptation, and astrobiology.'\n\n\n---\n<img src=\"URL width=\"500\" height=\"500\">\n---", "### Disaster Response Simulation\n\nPrompt: \"Simulate the impact of a Category 5 hurricane hitting the eastern coast of Florida in 2030, considering factors such as rising sea levels and urban density. Assess potential emergency responses and resource needs.\"", "#### Example Response\nResponse: \n\n\"Scenario:\n\nA powerful Category 5 hurricane, named \"Hurricane Ana,\" makes landfall on September 15, 2030, along the eastern coast of Florida, near Miami. The storm brings with it catastrophic winds, torrential rainfall, and a massive storm surge due to rising sea levels.\n\nStorm Characteristics:\n\n* Wind Speeds: Up to 160 mph (257 km/h)\n* Storm Surge: 10-15 feet (3-4.5 meters) above mean sea level\n* Rainfall: 12-18 inches (30-45 cm) in the first 24 hours, with isolated areas receiving up to 24 inches (60 cm)\n\nImpacts:\n\n1. Coastal Flooding: Rising sea levels exacerbate the storm surge, causing widespread flooding and damage along the eastern coast of Florida, particularly in Miami-Dade, Broward, and Palm Beach counties.\n2. Urban Infrastructure: The densely populated cities along the coast suffer significant damage to buildings, roads, and infrastructure, leading to disruptions in essential services like power, water, and communication.\n3. Displacement and Evacuations: Over 1 million people are displaced or evacuated from their homes, with many seeking shelter in nearby inland areas or temporary facilities.\n4. Environmental Concerns: The storm surge contaminates waterways, causing concerns about water quality and potential health risks for those affected.\n5. Economic Impact: The estimated economic loss is around $100 billion, considering damage to infrastructure, businesses, and agricultural industries.\n\nEmergency Response:\n\n1. Evacuation Efforts: Emergency responders prioritize evacuations, focusing on vulnerable populations like the elderly, children, and those with disabilities. They also ensure that essential services like hospitals, fire stations, and emergency centers are evacuated.\n2. Search and Rescue Operations: Teams conduct door-to-door searches for trapped individuals, using specialized equipment and resources to navigate flooded areas.\n3. Food, Water, and Medical Supplies: Aid distributions prioritize the most affected communities, with a focus on providing essential supplies, shelter, and medical care.\n4. Power Restoration: Utility companies work to restore power as quickly as possible, deploying crews from neighboring states and using advanced technologies like drones and satellite imaging to assess damage and optimize response efforts.\n\nResource Needs:\n\n1. Personnel: Over 10,000 emergency responders, including firefighters, police officers, medical personnel, and National Guard troops, are deployed to support the response effort.\n2. Equipment and Supplies: Critical resources include:\n\t* Generators and fuel\n\t* Food, water, and medical supplies\n\t* Communication equipment (satellite phones, etc.)\n\t* Heavy machinery for debris removal and infrastructure repair\n\t* Shelter materials (tents, blankets, etc.)\n3. Funding: Estimated costs exceed $500 million, requiring a significant allocation of federal, state, and local funds to support the response and recovery efforts.\n4. Logistical Support: Coordination with neighboring states and national agencies is crucial for maintaining supply chains, transporting personnel and equipment, and sharing expertise.\n\nChallenges:\n\n1. Infrastructure Overload: The sheer scale of damage overwhelms local infrastructure, leading to delays in aid distribution and response efforts.\n2. Water Contamination: Concerns about water quality hinder access to clean drinking water, exacerbating public health risks.\n3. Displacement and Shelter: The large number of displaced individuals creates a significant shortage of available shelter options, straining resources and emergency services.\n\nLessons Learned:\n\n1. Preparedness is Key: Prioritizing evacuation planning, infrastructure hardening, and disaster preparedness can significantly reduce the impact of such events.\n2. Collaboration is Crucial: Effective coordination between local, state, and federal agencies, as well as with neighboring states and national organizations, is essential for a successful response.\n3. Adaptation to Rising Sea Levels: The increasing threat of sea-level rise requires a shift in disaster preparedness strategies, focusing on resilient infrastructure design and adaptive management practices.\n\nConclusion:\n\nThe simulated impact of Hurricane Ana highlights the devastating consequences of a Category 5 hurricane hitting Florida's eastern coast, exacerbated by rising sea levels. The emergency response efforts require significant resources, personnel, and coordination to address the complex challenges posed by this disaster. As we move forward, it is essential to prioritize preparedness, collaboration, and adaptation to mitigate the effects of these events and protect vulnerable communities.\"", "# Try it out yourself!", "### Extraterrestrial Colony Planning\nPrompt: \"Design a sustainable human colony for Mars, focusing on water resource management, energy production, and habitat construction using local materials. Include potential environmental challenges and solutions.\"", "### Environmental Policy Formulation\nPrompt: \"Evaluate the long-term ecological impacts of banning single-use plastics globally. Simulate the effects on marine life, pollution levels, and waste management systems over the next 50 years.\"", "### Advanced Educational Tools\nPrompt: \"Create an interactive simulation that demonstrates the water cycle on Earth, including the effects of deforestation and urbanization on water availability and quality in major river basins.\"", "### Interactive Storytelling\nPrompt: \"Generate a narrative where the user is a leader in a community facing severe drought conditions. Allow the user to make decisions about water usage, agricultural practices, and public policy, showing the consequences of each choice.\"", "### Biodiversity Conservation Strategies\nPrompt: \"Develop a conservation strategy for the Amazon rainforest, focusing on mitigating the effects of deforestation and climate change. Simulate various scenarios involving local communities and global stakeholders.\"", "### Interstellar Communication Simulation\nPrompt: \"Imagine a scenario where Earth receives a signal from a distant planet. Simulate a series of potential communications that could be exchanged, considering language barriers and the transmission delay over light-years.\"", "### Bioengineering Solutions\nPrompt: \"Propose a bioengineering project to create microbial life forms that can detoxify plastic waste in the ocean. Describe the genetic traits these organisms would need and simulate the potential ecological impact.\"", "### Cross-Planetary Impact Studies\nPrompt: \"Analyze how a supernova explosion in a neighboring star system could affect planetary systems in its vicinity, including potential impacts on Earth's magnetic field and atmosphere.\"", "### Custom Scenario Development\nPrompt: \"Allow the user to create a custom scenario involving an unexpected volcanic eruption in Iceland. Let the user set parameters like the eruption's size, duration, and ash distribution, then simulate the global climate and air travel impacts.\"\n\nThese prompts are designed to maximize the utilization of the model's capabilities in various complex and interdisciplinary scenarios, making them useful for researchers, educators, policymakers, and enthusiasts interested in exploring these domains." ]

[ "TAGS\n#mlx #mixtral #climate change #biomimicry #theoretical astrobiology #environmental simulations #predictive modeling #life origins #ecological impacts #sustainable technologies #cross-disciplinary learning #artificial intelligence #machine learning #data integration #complex systems #scenario analysis #speculative science #universe exploration #biodiversity #planetary studies #innovation in science #role playing scenarios #text-generation #conversational #en #dataset-Severian/IMPACTS #license-mit #region-us \n", "# Llama-3-IMPACTS-2x8B-64k-MLX\n\n<img src=\"URL width=\"500\" height=\"500\">\n\n---\n\nDesigned for Advanced Problem-Solving Across Interconnected Domains of Biomimicry, Climate Change, and Astrobiology\n\nThe 'Llama-3-IMPACTS-2x8B-64k-MLX' model is a cutting-edge large language model trained on the I.M.P.A.C.T.S dataset, which encompasses scenarios from biomimicry, climate change, and theoretical astrobiology. This model has been specifically tailored to generate innovative solutions and insights for both Earth and potential extraterrestrial environments, reflecting key themes of resilience, sustainability, and the interconnectedness of life across the universe.", "## Model Details", "### Description\n\n- Model name: 'Llama-3-IMPACTS-2x8B-64k-MLX'\n- Developer: Severian\n- Version: 1.0\n- License: MIT", "### Training Data\n\nThe model was trained on a subset of the I.M.P.A.C.T. dataset, utilizing 35,000 carefully curated examples that include detailed scenarios involving climate adaptation, biomimetic applications, and the potential for life in varying cosmic conditions.", "### Model Architecture\n\n- Type: Llama-3\n- Parameters: 8 billion\n- MoE: 2 Experts\n- Training:\n- Epochs: 1 (35K Examples)\n- R = 64\n- Alpha = 128\n- Lr = 1e-7\n- Context Limit: 64K", "## Intended Uses\n\nThis model is intended for use in applications that require deep, interdisciplinary understanding and the generation of novel insights within the realms of environmental science, synthetic biology, space exploration, and sustainability studies. Its capabilities make it ideal for:\n- Research and academic studies aiming to explore complex scenarios involving ecological and astrobiological phenomena.\n- Organizations looking to innovate in the fields of climate resilience and biomimicry.\n- Creative problem-solving in contexts where conventional approaches are insufficient.", "## How to Use This Model\n\nThe model can be loaded and used in various natural language processing tasks that require nuanced understanding and creative output. Here is a basic example of how to load and use the model using the MLX library:", "## Limitations and Biases\n\nWhile the 'Llama-3-IMPACTS-2x8B-64k-MLX' model is designed to be a powerful tool for generating insightful content, it inherits limitations from its training data, which, though extensive, may not capture all possible scenarios or biases. Users should be aware of these limitations and consider them when interpreting the model's outputs, especially in decision-making contexts.", "## Model Performance\n\nInitial tests indicate that the model performs exceptionally well in tasks that involve complex reasoning and generating innovative solutions based on the scenarios presented in the I.M.P.A.C.T.S dataset. Further evaluation and fine-tuning may be required to optimize performance for specific applications.\n\nThe 'Llama-3-IMPACTS-2x8B-64k-MLX' model represents an avenue that AI can use for exploring and solving complex problems across multiple domains. By leveraging the rich, interconnected dataset of I.M.P.A.C.T.S, it offers a valuable tool for researchers, innovators, and thinkers aiming to push the boundaries of what's possible in their fields.", "# Use Cases", "## Universe/World Simulation\n\nUse Llama-3-IMPACTS-2x8B-64k to simulate incredibly unique and diverse ecosystems and cosmic worlds. Example image generation (text-to-image):\n\nUser Prompt: 'Craft a detailed image generation prompt focused on visualizing an innovative scenario that integrates biomimicry, climate change adaptation, and astrobiology.'\n\n\n---\n<img src=\"URL width=\"500\" height=\"500\">\n---", "### Disaster Response Simulation\n\nPrompt: \"Simulate the impact of a Category 5 hurricane hitting the eastern coast of Florida in 2030, considering factors such as rising sea levels and urban density. Assess potential emergency responses and resource needs.\"", "#### Example Response\nResponse: \n\n\"Scenario:\n\nA powerful Category 5 hurricane, named \"Hurricane Ana,\" makes landfall on September 15, 2030, along the eastern coast of Florida, near Miami. The storm brings with it catastrophic winds, torrential rainfall, and a massive storm surge due to rising sea levels.\n\nStorm Characteristics:\n\n* Wind Speeds: Up to 160 mph (257 km/h)\n* Storm Surge: 10-15 feet (3-4.5 meters) above mean sea level\n* Rainfall: 12-18 inches (30-45 cm) in the first 24 hours, with isolated areas receiving up to 24 inches (60 cm)\n\nImpacts:\n\n1. Coastal Flooding: Rising sea levels exacerbate the storm surge, causing widespread flooding and damage along the eastern coast of Florida, particularly in Miami-Dade, Broward, and Palm Beach counties.\n2. Urban Infrastructure: The densely populated cities along the coast suffer significant damage to buildings, roads, and infrastructure, leading to disruptions in essential services like power, water, and communication.\n3. Displacement and Evacuations: Over 1 million people are displaced or evacuated from their homes, with many seeking shelter in nearby inland areas or temporary facilities.\n4. Environmental Concerns: The storm surge contaminates waterways, causing concerns about water quality and potential health risks for those affected.\n5. Economic Impact: The estimated economic loss is around $100 billion, considering damage to infrastructure, businesses, and agricultural industries.\n\nEmergency Response:\n\n1. Evacuation Efforts: Emergency responders prioritize evacuations, focusing on vulnerable populations like the elderly, children, and those with disabilities. They also ensure that essential services like hospitals, fire stations, and emergency centers are evacuated.\n2. Search and Rescue Operations: Teams conduct door-to-door searches for trapped individuals, using specialized equipment and resources to navigate flooded areas.\n3. Food, Water, and Medical Supplies: Aid distributions prioritize the most affected communities, with a focus on providing essential supplies, shelter, and medical care.\n4. Power Restoration: Utility companies work to restore power as quickly as possible, deploying crews from neighboring states and using advanced technologies like drones and satellite imaging to assess damage and optimize response efforts.\n\nResource Needs:\n\n1. Personnel: Over 10,000 emergency responders, including firefighters, police officers, medical personnel, and National Guard troops, are deployed to support the response effort.\n2. Equipment and Supplies: Critical resources include:\n\t* Generators and fuel\n\t* Food, water, and medical supplies\n\t* Communication equipment (satellite phones, etc.)\n\t* Heavy machinery for debris removal and infrastructure repair\n\t* Shelter materials (tents, blankets, etc.)\n3. Funding: Estimated costs exceed $500 million, requiring a significant allocation of federal, state, and local funds to support the response and recovery efforts.\n4. Logistical Support: Coordination with neighboring states and national agencies is crucial for maintaining supply chains, transporting personnel and equipment, and sharing expertise.\n\nChallenges:\n\n1. Infrastructure Overload: The sheer scale of damage overwhelms local infrastructure, leading to delays in aid distribution and response efforts.\n2. Water Contamination: Concerns about water quality hinder access to clean drinking water, exacerbating public health risks.\n3. Displacement and Shelter: The large number of displaced individuals creates a significant shortage of available shelter options, straining resources and emergency services.\n\nLessons Learned:\n\n1. Preparedness is Key: Prioritizing evacuation planning, infrastructure hardening, and disaster preparedness can significantly reduce the impact of such events.\n2. Collaboration is Crucial: Effective coordination between local, state, and federal agencies, as well as with neighboring states and national organizations, is essential for a successful response.\n3. Adaptation to Rising Sea Levels: The increasing threat of sea-level rise requires a shift in disaster preparedness strategies, focusing on resilient infrastructure design and adaptive management practices.\n\nConclusion:\n\nThe simulated impact of Hurricane Ana highlights the devastating consequences of a Category 5 hurricane hitting Florida's eastern coast, exacerbated by rising sea levels. The emergency response efforts require significant resources, personnel, and coordination to address the complex challenges posed by this disaster. As we move forward, it is essential to prioritize preparedness, collaboration, and adaptation to mitigate the effects of these events and protect vulnerable communities.\"", "# Try it out yourself!", "### Extraterrestrial Colony Planning\nPrompt: \"Design a sustainable human colony for Mars, focusing on water resource management, energy production, and habitat construction using local materials. Include potential environmental challenges and solutions.\"", "### Environmental Policy Formulation\nPrompt: \"Evaluate the long-term ecological impacts of banning single-use plastics globally. Simulate the effects on marine life, pollution levels, and waste management systems over the next 50 years.\"", "### Advanced Educational Tools\nPrompt: \"Create an interactive simulation that demonstrates the water cycle on Earth, including the effects of deforestation and urbanization on water availability and quality in major river basins.\"", "### Interactive Storytelling\nPrompt: \"Generate a narrative where the user is a leader in a community facing severe drought conditions. Allow the user to make decisions about water usage, agricultural practices, and public policy, showing the consequences of each choice.\"", "### Biodiversity Conservation Strategies\nPrompt: \"Develop a conservation strategy for the Amazon rainforest, focusing on mitigating the effects of deforestation and climate change. Simulate various scenarios involving local communities and global stakeholders.\"", "### Interstellar Communication Simulation\nPrompt: \"Imagine a scenario where Earth receives a signal from a distant planet. Simulate a series of potential communications that could be exchanged, considering language barriers and the transmission delay over light-years.\"", "### Bioengineering Solutions\nPrompt: \"Propose a bioengineering project to create microbial life forms that can detoxify plastic waste in the ocean. Describe the genetic traits these organisms would need and simulate the potential ecological impact.\"", "### Cross-Planetary Impact Studies\nPrompt: \"Analyze how a supernova explosion in a neighboring star system could affect planetary systems in its vicinity, including potential impacts on Earth's magnetic field and atmosphere.\"", "### Custom Scenario Development\nPrompt: \"Allow the user to create a custom scenario involving an unexpected volcanic eruption in Iceland. Let the user set parameters like the eruption's size, duration, and ash distribution, then simulate the global climate and air travel impacts.\"\n\nThese prompts are designed to maximize the utilization of the model's capabilities in various complex and interdisciplinary scenarios, making them useful for researchers, educators, policymakers, and enthusiasts interested in exploring these domains." ]

[ 100, 172, 4, 43, 60, 57, 100, 49, 90, 155, 3, 103, 47, 874, 6, 44, 45, 41, 50, 43, 47, 51, 43, 95 ]

[ "TAGS\n#mlx #mixtral #climate change #biomimicry #theoretical astrobiology #environmental simulations #predictive modeling #life origins #ecological impacts #sustainable technologies #cross-disciplinary learning #artificial intelligence #machine learning #data integration #complex systems #scenario analysis #speculative science #universe exploration #biodiversity #planetary studies #innovation in science #role playing scenarios #text-generation #conversational #en #dataset-Severian/IMPACTS #license-mit #region-us \n# Llama-3-IMPACTS-2x8B-64k-MLX\n\n<img src=\"URL width=\"500\" height=\"500\">\n\n---\n\nDesigned for Advanced Problem-Solving Across Interconnected Domains of Biomimicry, Climate Change, and Astrobiology\n\nThe 'Llama-3-IMPACTS-2x8B-64k-MLX' model is a cutting-edge large language model trained on the I.M.P.A.C.T.S dataset, which encompasses scenarios from biomimicry, climate change, and theoretical astrobiology. This model has been specifically tailored to generate innovative solutions and insights for both Earth and potential extraterrestrial environments, reflecting key themes of resilience, sustainability, and the interconnectedness of life across the universe.## Model Details### Description\n\n- Model name: 'Llama-3-IMPACTS-2x8B-64k-MLX'\n- Developer: Severian\n- Version: 1.0\n- License: MIT### Training Data\n\nThe model was trained on a subset of the I.M.P.A.C.T. dataset, utilizing 35,000 carefully curated examples that include detailed scenarios involving climate adaptation, biomimetic applications, and the potential for life in varying cosmic conditions.### Model Architecture\n\n- Type: Llama-3\n- Parameters: 8 billion\n- MoE: 2 Experts\n- Training:\n- Epochs: 1 (35K Examples)\n- R = 64\n- Alpha = 128\n- Lr = 1e-7\n- Context Limit: 64K## Intended Uses\n\nThis model is intended for use in applications that require deep, interdisciplinary understanding and the generation of novel insights within the realms of environmental science, synthetic biology, space exploration, and sustainability studies. Its capabilities make it ideal for:\n- Research and academic studies aiming to explore complex scenarios involving ecological and astrobiological phenomena.\n- Organizations looking to innovate in the fields of climate resilience and biomimicry.\n- Creative problem-solving in contexts where conventional approaches are insufficient.## How to Use This Model\n\nThe model can be loaded and used in various natural language processing tasks that require nuanced understanding and creative output. Here is a basic example of how to load and use the model using the MLX library:## Limitations and Biases\n\nWhile the 'Llama-3-IMPACTS-2x8B-64k-MLX' model is designed to be a powerful tool for generating insightful content, it inherits limitations from its training data, which, though extensive, may not capture all possible scenarios or biases. Users should be aware of these limitations and consider them when interpreting the model's outputs, especially in decision-making contexts.## Model Performance\n\nInitial tests indicate that the model performs exceptionally well in tasks that involve complex reasoning and generating innovative solutions based on the scenarios presented in the I.M.P.A.C.T.S dataset. Further evaluation and fine-tuning may be required to optimize performance for specific applications.\n\nThe 'Llama-3-IMPACTS-2x8B-64k-MLX' model represents an avenue that AI can use for exploring and solving complex problems across multiple domains. By leveraging the rich, interconnected dataset of I.M.P.A.C.T.S, it offers a valuable tool for researchers, innovators, and thinkers aiming to push the boundaries of what's possible in their fields.# Use Cases## Universe/World Simulation\n\nUse Llama-3-IMPACTS-2x8B-64k to simulate incredibly unique and diverse ecosystems and cosmic worlds. Example image generation (text-to-image):\n\nUser Prompt: 'Craft a detailed image generation prompt focused on visualizing an innovative scenario that integrates biomimicry, climate change adaptation, and astrobiology.'\n\n\n---\n<img src=\"URL width=\"500\" height=\"500\">\n---### Disaster Response Simulation\n\nPrompt: \"Simulate the impact of a Category 5 hurricane hitting the eastern coast of Florida in 2030, considering factors such as rising sea levels and urban density. Assess potential emergency responses and resource needs.\"#### Example Response\nResponse: \n\n\"Scenario:\n\nA powerful Category 5 hurricane, named \"Hurricane Ana,\" makes landfall on September 15, 2030, along the eastern coast of Florida, near Miami. The storm brings with it catastrophic winds, torrential rainfall, and a massive storm surge due to rising sea levels.\n\nStorm Characteristics:\n\n* Wind Speeds: Up to 160 mph (257 km/h)\n* Storm Surge: 10-15 feet (3-4.5 meters) above mean sea level\n* Rainfall: 12-18 inches (30-45 cm) in the first 24 hours, with isolated areas receiving up to 24 inches (60 cm)\n\nImpacts:\n\n1. Coastal Flooding: Rising sea levels exacerbate the storm surge, causing widespread flooding and damage along the eastern coast of Florida, particularly in Miami-Dade, Broward, and Palm Beach counties.\n2. Urban Infrastructure: The densely populated cities along the coast suffer significant damage to buildings, roads, and infrastructure, leading to disruptions in essential services like power, water, and communication.\n3. Displacement and Evacuations: Over 1 million people are displaced or evacuated from their homes, with many seeking shelter in nearby inland areas or temporary facilities.\n4. Environmental Concerns: The storm surge contaminates waterways, causing concerns about water quality and potential health risks for those affected.\n5. Economic Impact: The estimated economic loss is around $100 billion, considering damage to infrastructure, businesses, and agricultural industries.\n\nEmergency Response:\n\n1. Evacuation Efforts: Emergency responders prioritize evacuations, focusing on vulnerable populations like the elderly, children, and those with disabilities. They also ensure that essential services like hospitals, fire stations, and emergency centers are evacuated.\n2. Search and Rescue Operations: Teams conduct door-to-door searches for trapped individuals, using specialized equipment and resources to navigate flooded areas.\n3. Food, Water, and Medical Supplies: Aid distributions prioritize the most affected communities, with a focus on providing essential supplies, shelter, and medical care.\n4. Power Restoration: Utility companies work to restore power as quickly as possible, deploying crews from neighboring states and using advanced technologies like drones and satellite imaging to assess damage and optimize response efforts.\n\nResource Needs:\n\n1. Personnel: Over 10,000 emergency responders, including firefighters, police officers, medical personnel, and National Guard troops, are deployed to support the response effort.\n2. Equipment and Supplies: Critical resources include:\n\t* Generators and fuel\n\t* Food, water, and medical supplies\n\t* Communication equipment (satellite phones, etc.)\n\t* Heavy machinery for debris removal and infrastructure repair\n\t* Shelter materials (tents, blankets, etc.)\n3. Funding: Estimated costs exceed $500 million, requiring a significant allocation of federal, state, and local funds to support the response and recovery efforts.\n4. Logistical Support: Coordination with neighboring states and national agencies is crucial for maintaining supply chains, transporting personnel and equipment, and sharing expertise.\n\nChallenges:\n\n1. Infrastructure Overload: The sheer scale of damage overwhelms local infrastructure, leading to delays in aid distribution and response efforts.\n2. Water Contamination: Concerns about water quality hinder access to clean drinking water, exacerbating public health risks.\n3. Displacement and Shelter: The large number of displaced individuals creates a significant shortage of available shelter options, straining resources and emergency services.\n\nLessons Learned:\n\n1. Preparedness is Key: Prioritizing evacuation planning, infrastructure hardening, and disaster preparedness can significantly reduce the impact of such events.\n2. Collaboration is Crucial: Effective coordination between local, state, and federal agencies, as well as with neighboring states and national organizations, is essential for a successful response.\n3. Adaptation to Rising Sea Levels: The increasing threat of sea-level rise requires a shift in disaster preparedness strategies, focusing on resilient infrastructure design and adaptive management practices.\n\nConclusion:\n\nThe simulated impact of Hurricane Ana highlights the devastating consequences of a Category 5 hurricane hitting Florida's eastern coast, exacerbated by rising sea levels. The emergency response efforts require significant resources, personnel, and coordination to address the complex challenges posed by this disaster. As we move forward, it is essential to prioritize preparedness, collaboration, and adaptation to mitigate the effects of these events and protect vulnerable communities.\"# Try it out yourself!### Extraterrestrial Colony Planning\nPrompt: \"Design a sustainable human colony for Mars, focusing on water resource management, energy production, and habitat construction using local materials. Include potential environmental challenges and solutions.\"### Environmental Policy Formulation\nPrompt: \"Evaluate the long-term ecological impacts of banning single-use plastics globally. Simulate the effects on marine life, pollution levels, and waste management systems over the next 50 years.\"### Advanced Educational Tools\nPrompt: \"Create an interactive simulation that demonstrates the water cycle on Earth, including the effects of deforestation and urbanization on water availability and quality in major river basins.\"### Interactive Storytelling\nPrompt: \"Generate a narrative where the user is a leader in a community facing severe drought conditions. Allow the user to make decisions about water usage, agricultural practices, and public policy, showing the consequences of each choice.\"### Biodiversity Conservation Strategies\nPrompt: \"Develop a conservation strategy for the Amazon rainforest, focusing on mitigating the effects of deforestation and climate change. Simulate various scenarios involving local communities and global stakeholders.\"### Interstellar Communication Simulation\nPrompt: \"Imagine a scenario where Earth receives a signal from a distant planet. Simulate a series of potential communications that could be exchanged, considering language barriers and the transmission delay over light-years.\"### Bioengineering Solutions\nPrompt: \"Propose a bioengineering project to create microbial life forms that can detoxify plastic waste in the ocean. Describe the genetic traits these organisms would need and simulate the potential ecological impact.\"### Cross-Planetary Impact Studies\nPrompt: \"Analyze how a supernova explosion in a neighboring star system could affect planetary systems in its vicinity, including potential impacts on Earth's magnetic field and atmosphere.\"### Custom Scenario Development\nPrompt: \"Allow the user to create a custom scenario involving an unexpected volcanic eruption in Iceland. Let the user set parameters like the eruption's size, duration, and ash distribution, then simulate the global climate and air travel impacts.\"\n\nThese prompts are designed to maximize the utilization of the model's capabilities in various complex and interdisciplinary scenarios, making them useful for researchers, educators, policymakers, and enthusiasts interested in exploring these domains." ]

[ "transformers", "safetensors", "phi3", "text-generation", "conversational", "custom_code", "it", "dataset:cosimoiaia/Loquace-102k", "arxiv:1910.09700", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[ "it" ]

[ "### Model Description\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n\n* Developed by:\n* Funded by [optional]:\n* Shared by [optional]:\n* Model type:\n* Language(s) (NLP):\n* License:\n* Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n* Repository:\n* Paper [optional]:\n* Demo [optional]:\n\n\nUses\n----", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use\n\n\nBias, Risks, and Limitations\n----------------------------", "### Recommendations\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.\n\n\nHow to Get Started with the Model\n---------------------------------\n\n\nUse the code below to get started with the model.\n\n\nTraining Details\n----------------", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n\n* Training regime:", "#### Speeds, Sizes, Times [optional]\n\n\nEvaluation\n----------", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary\n\n\nModel Examination [optional]\n----------------------------\n\n\nEnvironmental Impact\n--------------------\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n\n* Hardware Type:\n* Hours used:\n* Cloud Provider:\n* Compute Region:\n* Carbon Emitted:\n\n\nTechnical Specifications [optional]\n-----------------------------------", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n[optional]\n\n\nBibTeX:\n\n\nAPA:\n\n\nGlossary [optional]\n-------------------\n\n\nMore Information [optional]\n---------------------------\n\n\nModel Card Authors [optional]\n-----------------------------\n\n\nModel Card Contact\n------------------" ]

[ "TAGS\n#transformers #safetensors #phi3 #text-generation #conversational #custom_code #it #dataset-cosimoiaia/Loquace-102k #arxiv-1910.09700 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "### Model Description\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n\n* Developed by:\n* Funded by [optional]:\n* Shared by [optional]:\n* Model type:\n* Language(s) (NLP):\n* License:\n* Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n* Repository:\n* Paper [optional]:\n* Demo [optional]:\n\n\nUses\n----", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use\n\n\nBias, Risks, and Limitations\n----------------------------", "### Recommendations\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.\n\n\nHow to Get Started with the Model\n---------------------------------\n\n\nUse the code below to get started with the model.\n\n\nTraining Details\n----------------", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n\n* Training regime:", "#### Speeds, Sizes, Times [optional]\n\n\nEvaluation\n----------", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary\n\n\nModel Examination [optional]\n----------------------------\n\n\nEnvironmental Impact\n--------------------\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n\n* Hardware Type:\n* Hours used:\n* Cloud Provider:\n* Compute Region:\n* Carbon Emitted:\n\n\nTechnical Specifications [optional]\n-----------------------------------", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n[optional]\n\n\nBibTeX:\n\n\nAPA:\n\n\nGlossary [optional]\n-------------------\n\n\nMore Information [optional]\n---------------------------\n\n\nModel Card Authors [optional]\n-----------------------------\n\n\nModel Card Contact\n------------------" ]

[ 71, 75, 28, 5, 8, 43, 103, 5, 5, 11, 13, 23, 10, 6, 5, 6, 4, 145, 7, 5, 5, 127 ]

[ "TAGS\n#transformers #safetensors #phi3 #text-generation #conversational #custom_code #it #dataset-cosimoiaia/Loquace-102k #arxiv-1910.09700 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n### Model Description\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n\n* Developed by:\n* Funded by [optional]:\n* Shared by [optional]:\n* Model type:\n* Language(s) (NLP):\n* License:\n* Finetuned from model [optional]:### Model Sources [optional]\n\n\n* Repository:\n* Paper [optional]:\n* Demo [optional]:\n\n\nUses\n----### Direct Use### Downstream Use [optional]### Out-of-Scope Use\n\n\nBias, Risks, and Limitations\n----------------------------### Recommendations\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.\n\n\nHow to Get Started with the Model\n---------------------------------\n\n\nUse the code below to get started with the model.\n\n\nTraining Details\n----------------### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n\n* Training regime:#### Speeds, Sizes, Times [optional]\n\n\nEvaluation\n----------### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary\n\n\nModel Examination [optional]\n----------------------------\n\n\nEnvironmental Impact\n--------------------\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n\n* Hardware Type:\n* Hours used:\n* Cloud Provider:\n* Compute Region:\n* Carbon Emitted:\n\n\nTechnical Specifications [optional]\n-----------------------------------### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n[optional]\n\n\nBibTeX:\n\n\nAPA:\n\n\nGlossary [optional]\n-------------------\n\n\nMore Information [optional]\n---------------------------\n\n\nModel Card Authors [optional]\n-----------------------------\n\n\nModel Card Contact\n------------------" ]

[ "transformers", "safetensors", "trl", "sft", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #trl #sft #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 32, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #trl #sft #arxiv-1910.09700 #endpoints_compatible #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "ml-agents", "tensorboard", "onnx", "Huggy", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Huggy", "region:us" ]

[]

[]

[ "# ppo Agent playing Huggy\n This is a trained model of a ppo agent playing Huggy\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A *longer tutorial* to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: raydium/ppo-Huggy\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play" ]

[ "TAGS\n#ml-agents #tensorboard #onnx #Huggy #deep-reinforcement-learning #reinforcement-learning #ML-Agents-Huggy #region-us \n", "# ppo Agent playing Huggy\n This is a trained model of a ppo agent playing Huggy\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A *longer tutorial* to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: raydium/ppo-Huggy\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play" ]

[ 35, 198 ]

[ "TAGS\n#ml-agents #tensorboard #onnx #Huggy #deep-reinforcement-learning #reinforcement-learning #ML-Agents-Huggy #region-us \n# ppo Agent playing Huggy\n This is a trained model of a ppo agent playing Huggy\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A *longer tutorial* to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: raydium/ppo-Huggy\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play" ]

[ "transformers", "safetensors", "t5", "text2text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #t5 #text2text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 46, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #t5 #text2text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "tensorboard", "safetensors", "vivit", "video-classification", "generated_from_trainer", "base_model:google/vivit-b-16x2-kinetics400", "license:mit", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 1\n* eval\\_batch\\_size: 1\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* training\\_steps: 420", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #vivit #video-classification #generated_from_trainer #base_model-google/vivit-b-16x2-kinetics400 #license-mit #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 1\n* eval\\_batch\\_size: 1\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* training\\_steps: 420", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Tokenizers 0.19.1" ]

[ 57, 117, 5, 35 ]

[ "TAGS\n#transformers #tensorboard #safetensors #vivit #video-classification #generated_from_trainer #base_model-google/vivit-b-16x2-kinetics400 #license-mit #endpoints_compatible #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 1\n* eval\\_batch\\_size: 1\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* training\\_steps: 420### Training results### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Tokenizers 0.19.1" ]

[ "license:apache-2.0", "region:us" ]

[]

[]

[]

[ "TAGS\n#license-apache-2.0 #region-us \n" ]

[ 13 ]

[ "TAGS\n#license-apache-2.0 #region-us \n" ]

[ "transformers", "safetensors", "gemma", "text-generation", "llama-factory", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #llama-factory #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 51, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #llama-factory #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "safetensors", "llama", "text-generation", "facebook", "meta", "pytorch", "llama-3", "en", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us", "has_space" ]

[]

[ "en" ]

[ "### Use with transformers\n\n\nSee the snippet below for usage with Transformers:", "### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository.\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.", "### Base pretrained models", "### Instruction tuned models", "### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.", "#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.", "#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL", "#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).", "### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.", "### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.", "### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #facebook #meta #pytorch #llama-3 #en #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us #has_space \n", "### Use with transformers\n\n\nSee the snippet below for usage with Transformers:", "### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository.\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.", "### Base pretrained models", "### Instruction tuned models", "### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.", "#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.", "#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL", "#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).", "### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.", "### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.", "### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos" ]

[ 58, 17, 430, 8, 6, 270, 280, 72, 115, 118, 126, 2136 ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #facebook #meta #pytorch #llama-3 #en #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us #has_space \n### Use with transformers\n\n\nSee the snippet below for usage with Transformers:### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository.\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.### Base pretrained models### Instruction tuned models### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos" ]

[ "gguf", "pruna-ai", "region:us" ]

[]

[]

[ "### How to load this model in Python code, using llama-cpp-python\n\nFor full documentation, please see: llama-cpp-python docs.", "#### First install the package\n\nRun one of the following commands, according to your system:", "#### Simple llama-cpp-python example code\n\n```\n\n* Option D - Running with LangChain\n\n\nHere are guides on using llama-cpp-python and ctransformers with LangChain:\n\n\n* LangChain + llama-cpp-python\n* LangChain + ctransformers\n\n\nConfigurations\n--------------\n\n\nThe configuration info are in 'smash\\_config.json'.\n\n\nCredits & License\n-----------------\n\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.\n\n\nWant to compress other models?\n------------------------------\n\n\n* Contact us and tell us which model to compress next here.\n* Request access to easily compress your own AI models here." ]

[ "TAGS\n#gguf #pruna-ai #region-us \n", "### How to load this model in Python code, using llama-cpp-python\n\nFor full documentation, please see: llama-cpp-python docs.", "#### First install the package\n\nRun one of the following commands, according to your system:", "#### Simple llama-cpp-python example code\n\n```\n\n* Option D - Running with LangChain\n\n\nHere are guides on using llama-cpp-python and ctransformers with LangChain:\n\n\n* LangChain + llama-cpp-python\n* LangChain + ctransformers\n\n\nConfigurations\n--------------\n\n\nThe configuration info are in 'smash\\_config.json'.\n\n\nCredits & License\n-----------------\n\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.\n\n\nWant to compress other models?\n------------------------------\n\n\n* Contact us and tell us which model to compress next here.\n* Request access to easily compress your own AI models here." ]

[ 14, 37, 20, 236 ]

[ "TAGS\n#gguf #pruna-ai #region-us \n### How to load this model in Python code, using llama-cpp-python\n\nFor full documentation, please see: llama-cpp-python docs.#### First install the package\n\nRun one of the following commands, according to your system:#### Simple llama-cpp-python example code\n\n```\n\n* Option D - Running with LangChain\n\n\nHere are guides on using llama-cpp-python and ctransformers with LangChain:\n\n\n* LangChain + llama-cpp-python\n* LangChain + ctransformers\n\n\nConfigurations\n--------------\n\n\nThe configuration info are in 'smash\\_config.json'.\n\n\nCredits & License\n-----------------\n\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.\n\n\nWant to compress other models?\n------------------------------\n\n\n* Contact us and tell us which model to compress next here.\n* Request access to easily compress your own AI models here." ]

[ "peft", "safetensors", "arxiv:1910.09700", "base_model:meta-llama/Meta-Llama-3-8B-Instruct", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact", "### Framework versions\n\n- PEFT 0.7.1" ]

[ "TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-meta-llama/Meta-Llama-3-8B-Instruct #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact", "### Framework versions\n\n- PEFT 0.7.1" ]

[ 44, 6, 4, 50, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5, 13 ]

[ "TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-meta-llama/Meta-Llama-3-8B-Instruct #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact### Framework versions\n\n- PEFT 0.7.1" ]

[ "transformers", "safetensors", "llama", "text-generation", "mergekit", "merge", "conversational", "arxiv:2306.01708", "base_model:Shaleen123/llama3-code-8bit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "8-bit", "region:us" ]

[ "2306.01708" ]

[]

[ "# merged\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the TIES merge method using Shaleen123/llama3-code-8bit as a base.", "### Models Merged\n\nThe following models were included in the merge:", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #mergekit #merge #conversational #arxiv-2306.01708 #base_model-Shaleen123/llama3-code-8bit #autotrain_compatible #endpoints_compatible #text-generation-inference #8-bit #region-us \n", "# merged\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the TIES merge method using Shaleen123/llama3-code-8bit as a base.", "### Models Merged\n\nThe following models were included in the merge:", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ 75, 17, 4, 32, 14, 16 ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #mergekit #merge #conversational #arxiv-2306.01708 #base_model-Shaleen123/llama3-code-8bit #autotrain_compatible #endpoints_compatible #text-generation-inference #8-bit #region-us \n# merged\n\nThis is a merge of pre-trained language models created using mergekit.## Merge Details### Merge Method\n\nThis model was merged using the TIES merge method using Shaleen123/llama3-code-8bit as a base.### Models Merged\n\nThe following models were included in the merge:### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "transformers", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #llama #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 44, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #llama #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "safetensors", "phi3", "text-generation", "conversational", "custom_code", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID\n\n\nIMPORTANT NOTE: This is for ONGOING EXPERIMENTATION and is not meant for reuse.", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #phi3 #text-generation #conversational #custom_code #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Card for Model ID\n\n\nIMPORTANT NOTE: This is for ONGOING EXPERIMENTATION and is not meant for reuse.", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 45, 22, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #phi3 #text-generation #conversational #custom_code #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n# Model Card for Model ID\n\n\nIMPORTANT NOTE: This is for ONGOING EXPERIMENTATION and is not meant for reuse.## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "pytorch", "safetensors", "llama", "text-generation", "ru", "dataset:uonlp/CulturaX", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "ru" ]

[ "# Aeoinum v1 Base 1B\nA state-of-the-art language model for Russian language processing.", "## Usage\n\nOutput:", "## Dataset Detail\nThe dataset for pre-training is collected from public data, most of which are web pages in Russian. The total size of the data is 20B tokens.", "## Training Detail\nThe training is performed thanks to a grant from TPU Research Cloud on a TPU v4-32 node.", "## Copyright\nThe model is released under the Apache 2.0 license." ]

[ "TAGS\n#transformers #pytorch #safetensors #llama #text-generation #ru #dataset-uonlp/CulturaX #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Aeoinum v1 Base 1B\nA state-of-the-art language model for Russian language processing.", "## Usage\n\nOutput:", "## Dataset Detail\nThe dataset for pre-training is collected from public data, most of which are web pages in Russian. The total size of the data is 20B tokens.", "## Training Detail\nThe training is performed thanks to a grant from TPU Research Cloud on a TPU v4-32 node.", "## Copyright\nThe model is released under the Apache 2.0 license." ]

[ 60, 23, 5, 39, 27, 15 ]

[ "TAGS\n#transformers #pytorch #safetensors #llama #text-generation #ru #dataset-uonlp/CulturaX #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Aeoinum v1 Base 1B\nA state-of-the-art language model for Russian language processing.## Usage\n\nOutput:## Dataset Detail\nThe dataset for pre-training is collected from public data, most of which are web pages in Russian. The total size of the data is 20B tokens.## Training Detail\nThe training is performed thanks to a grant from TPU Research Cloud on a TPU v4-32 node.## Copyright\nThe model is released under the Apache 2.0 license." ]

[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 44, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "tensorboard", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "base_model:distilbert/distilbert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 5", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.2.2+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #distilbert #text-classification #generated_from_trainer #base_model-distilbert/distilbert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 5", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.2.2+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]

[ 63, 101, 5, 44 ]

[ "TAGS\n#transformers #tensorboard #safetensors #distilbert #text-classification #generated_from_trainer #base_model-distilbert/distilbert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 5### Training results### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.2.2+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "8-bit", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #8-bit #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 51, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #8-bit #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "tensorboard", "safetensors", "whisper", "automatic-speech-recognition", "generated_from_trainer", "base_model:openai/whisper-tiny.en", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* training\\_steps: 1000", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.1.dev0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #generated_from_trainer #base_model-openai/whisper-tiny.en #license-apache-2.0 #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* training\\_steps: 1000", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.1.dev0\n* Tokenizers 0.19.1" ]

[ 54, 115, 5, 47 ]

[ "TAGS\n#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #generated_from_trainer #base_model-openai/whisper-tiny.en #license-apache-2.0 #endpoints_compatible #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* training\\_steps: 1000### Training results### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.1.dev0\n* Tokenizers 0.19.1" ]

[ "transformers", "tf", "albert", "question-answering", "generated_from_keras_callback", "base_model:albert/albert-base-v2", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* optimizer: {'name': 'Adam', 'weight\\_decay': None, 'clipnorm': None, 'global\\_clipnorm': None, 'clipvalue': None, 'use\\_ema': False, 'ema\\_momentum': 0.99, 'ema\\_overwrite\\_frequency': None, 'jit\\_compile': True, 'is\\_legacy\\_optimizer': False, 'learning\\_rate': {'module': 'keras.optimizers.schedules', 'class\\_name': 'PolynomialDecay', 'config': {'initial\\_learning\\_rate': 2e-05, 'decay\\_steps': 3798, 'end\\_learning\\_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered\\_name': None}, 'beta\\_1': 0.9, 'beta\\_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}\n* training\\_precision: float32", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* TensorFlow 2.15.0\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tf #albert #question-answering #generated_from_keras_callback #base_model-albert/albert-base-v2 #license-apache-2.0 #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* optimizer: {'name': 'Adam', 'weight\\_decay': None, 'clipnorm': None, 'global\\_clipnorm': None, 'clipvalue': None, 'use\\_ema': False, 'ema\\_momentum': 0.99, 'ema\\_overwrite\\_frequency': None, 'jit\\_compile': True, 'is\\_legacy\\_optimizer': False, 'learning\\_rate': {'module': 'keras.optimizers.schedules', 'class\\_name': 'PolynomialDecay', 'config': {'initial\\_learning\\_rate': 2e-05, 'decay\\_steps': 3798, 'end\\_learning\\_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered\\_name': None}, 'beta\\_1': 0.9, 'beta\\_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}\n* training\\_precision: float32", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* TensorFlow 2.15.0\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ 52, 292, 5, 38 ]

[ "TAGS\n#transformers #tf #albert #question-answering #generated_from_keras_callback #base_model-albert/albert-base-v2 #license-apache-2.0 #endpoints_compatible #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* optimizer: {'name': 'Adam', 'weight\\_decay': None, 'clipnorm': None, 'global\\_clipnorm': None, 'clipvalue': None, 'use\\_ema': False, 'ema\\_momentum': 0.99, 'ema\\_overwrite\\_frequency': None, 'jit\\_compile': True, 'is\\_legacy\\_optimizer': False, 'learning\\_rate': {'module': 'keras.optimizers.schedules', 'class\\_name': 'PolynomialDecay', 'config': {'initial\\_learning\\_rate': 2e-05, 'decay\\_steps': 3798, 'end\\_learning\\_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered\\_name': None}, 'beta\\_1': 0.9, 'beta\\_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}\n* training\\_precision: float32### Training results### Framework versions\n\n\n* Transformers 4.40.1\n* TensorFlow 2.15.0\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "phi3", "text-generation", "trl", "sft", "conversational", "custom_code", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "4-bit", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #phi3 #text-generation #trl #sft #conversational #custom_code #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #4-bit #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 55, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #phi3 #text-generation #trl #sft #conversational #custom_code #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #4-bit #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "tensorboard", "safetensors", "layoutlm", "token-classification", "generated_from_trainer", "dataset:funsd", "base_model:microsoft/layoutlm-base-uncased", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 3e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 15", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.3.0+cpu\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #layoutlm #token-classification #generated_from_trainer #dataset-funsd #base_model-microsoft/layoutlm-base-uncased #license-mit #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 3e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 15", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.3.0+cpu\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ 61, 101, 5, 42 ]

[ "TAGS\n#transformers #tensorboard #safetensors #layoutlm #token-classification #generated_from_trainer #dataset-funsd #base_model-microsoft/layoutlm-base-uncased #license-mit #autotrain_compatible #endpoints_compatible #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 3e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 15### Training results### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.3.0+cpu\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "unsloth", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #unsloth #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 30, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #unsloth #arxiv-1910.09700 #endpoints_compatible #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "safetensors", "llama", "text-generation", "merge", "mergekit", "lazymergekit", "conversational", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# LuminariX-8B\n\nLuminariX-8B is a merge of the following models using mergekit:", "## Configuration" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #merge #mergekit #lazymergekit #conversational #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# LuminariX-8B\n\nLuminariX-8B is a merge of the following models using mergekit:", "## Configuration" ]

[ 55, 24, 3 ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #merge #mergekit #lazymergekit #conversational #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# LuminariX-8B\n\nLuminariX-8B is a merge of the following models using mergekit:## Configuration" ]

[ "transformers", "tensorboard", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "base_model:distilbert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 32\n* eval\\_batch\\_size: 32\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #distilbert #text-classification #generated_from_trainer #base_model-distilbert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 32\n* eval\\_batch\\_size: 32\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ 59, 124, 5, 44 ]

[ "TAGS\n#transformers #tensorboard #safetensors #distilbert #text-classification #generated_from_trainer #base_model-distilbert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 32\n* eval\\_batch\\_size: 32\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2### Training results### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "text-generation-inference", "unsloth", "llama", "trl", "text-generation", "en", "base_model:unsloth/llama-3-8b-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: abdulrehmanibk\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "TAGS\n#transformers #safetensors #text-generation-inference #unsloth #llama #trl #text-generation #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: abdulrehmanibk\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ 68, 82 ]

[ "TAGS\n#transformers #safetensors #text-generation-inference #unsloth #llama #trl #text-generation #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n# Uploaded model\n\n- Developed by: abdulrehmanibk\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "gguf", "region:us" ]

[]

[]

[]

[ "TAGS\n#gguf #region-us \n" ]

[ 9 ]

[ "TAGS\n#gguf #region-us \n" ]

[ "transformers", "tf", "bert", "text-classification", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* optimizer: {'name': 'Adam', 'learning\\_rate': {'class\\_name': 'PolynomialDecay', 'config': {'initial\\_learning\\_rate': 2e-05, 'decay\\_steps': 24230, 'end\\_learning\\_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta\\_1': 0.9, 'beta\\_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}\n* training\\_precision: float32", "### Training results", "### Framework versions\n\n\n* Transformers 4.24.0\n* TensorFlow 2.10.1\n* Datasets 2.19.0\n* Tokenizers 0.11.0" ]

[ "TAGS\n#transformers #tf #bert #text-classification #generated_from_keras_callback #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* optimizer: {'name': 'Adam', 'learning\\_rate': {'class\\_name': 'PolynomialDecay', 'config': {'initial\\_learning\\_rate': 2e-05, 'decay\\_steps': 24230, 'end\\_learning\\_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta\\_1': 0.9, 'beta\\_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}\n* training\\_precision: float32", "### Training results", "### Framework versions\n\n\n* Transformers 4.24.0\n* TensorFlow 2.10.1\n* Datasets 2.19.0\n* Tokenizers 0.11.0" ]

[ 44, 178, 5, 38 ]

[ "TAGS\n#transformers #tf #bert #text-classification #generated_from_keras_callback #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* optimizer: {'name': 'Adam', 'learning\\_rate': {'class\\_name': 'PolynomialDecay', 'config': {'initial\\_learning\\_rate': 2e-05, 'decay\\_steps': 24230, 'end\\_learning\\_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta\\_1': 0.9, 'beta\\_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}\n* training\\_precision: float32### Training results### Framework versions\n\n\n* Transformers 4.24.0\n* TensorFlow 2.10.1\n* Datasets 2.19.0\n* Tokenizers 0.11.0" ]

[ "transformers", "safetensors", "mistral", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 48, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "merge", "mergekit", "lazymergekit", "automerger", "base_model:NousResearch/Meta-Llama-3-8B-Instruct", "base_model:mlabonne/OrpoLlama-3-8B", "license:apache-2.0", "region:us" ]

[]

[]

[ "# ConfigurableLlama-7B\n\nConfigurableLlama-7B is an automated merge created by Maxime Labonne using the following configuration.\n* NousResearch/Meta-Llama-3-8B-Instruct\n* mlabonne/OrpoLlama-3-8B", "## Configuration", "## Usage" ]

[ "TAGS\n#merge #mergekit #lazymergekit #automerger #base_model-NousResearch/Meta-Llama-3-8B-Instruct #base_model-mlabonne/OrpoLlama-3-8B #license-apache-2.0 #region-us \n", "# ConfigurableLlama-7B\n\nConfigurableLlama-7B is an automated merge created by Maxime Labonne using the following configuration.\n* NousResearch/Meta-Llama-3-8B-Instruct\n* mlabonne/OrpoLlama-3-8B", "## Configuration", "## Usage" ]

[ 68, 67, 3, 3 ]

[ "TAGS\n#merge #mergekit #lazymergekit #automerger #base_model-NousResearch/Meta-Llama-3-8B-Instruct #base_model-mlabonne/OrpoLlama-3-8B #license-apache-2.0 #region-us \n# ConfigurableLlama-7B\n\nConfigurableLlama-7B is an automated merge created by Maxime Labonne using the following configuration.\n* NousResearch/Meta-Llama-3-8B-Instruct\n* mlabonne/OrpoLlama-3-8B## Configuration## Usage" ]

[ "transformers", "safetensors", "mistral", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 44, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "safetensors", "gpt2", "text-generation", "generated_from_trainer", "base_model:gpt2", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# ef_gpt2_baselinebest_model\n\nThis model is a fine-tuned version of gpt2 on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.00011620761063355344\n- train_batch_size: 4\n- eval_batch_size: 4\n- seed: 123\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 7\n- mixed_precision_training: Native AMP", "### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.1.2\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #gpt2 #text-generation #generated_from_trainer #base_model-gpt2 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# ef_gpt2_baselinebest_model\n\nThis model is a fine-tuned version of gpt2 on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.00011620761063355344\n- train_batch_size: 4\n- eval_batch_size: 4\n- seed: 123\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 7\n- mixed_precision_training: Native AMP", "### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.1.2\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ 53, 31, 7, 9, 9, 4, 112, 40 ]

[ "TAGS\n#transformers #safetensors #gpt2 #text-generation #generated_from_trainer #base_model-gpt2 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# ef_gpt2_baselinebest_model\n\nThis model is a fine-tuned version of gpt2 on an unknown dataset.## Model description\n\nMore information needed## Intended uses & limitations\n\nMore information needed## Training and evaluation data\n\nMore information needed## Training procedure### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.00011620761063355344\n- train_batch_size: 4\n- eval_batch_size: 4\n- seed: 123\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 7\n- mixed_precision_training: Native AMP### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.1.2\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "transformers", "gguf", "en", "base_model:asprenger/Meta-Llama-3-8B-VIGGO", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #en #base_model-asprenger/Meta-Llama-3-8B-VIGGO #endpoints_compatible #region-us \n" ]

[ 40 ]

[ "TAGS\n#transformers #gguf #en #base_model-asprenger/Meta-Llama-3-8B-VIGGO #endpoints_compatible #region-us \n" ]

[ "transformers", "safetensors", "llama", "text-generation", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "8-bit", "region:us" ]

[]

[]

[ "# llama2-7b", "### Model Details\n- Developed by: Julleong\n- Backbone Model: beomi/llama-2-ko-7b\n- Library: transformers", "### Used Datasets\n- 개체명 사전 2022(모두의 말뭉치)", "### Prompt Template", "### License\n- MIT" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #autotrain_compatible #endpoints_compatible #text-generation-inference #8-bit #region-us \n", "# llama2-7b", "### Model Details\n- Developed by: Julleong\n- Backbone Model: beomi/llama-2-ko-7b\n- Library: transformers", "### Used Datasets\n- 개체명 사전 2022(모두의 말뭉치)", "### Prompt Template", "### License\n- MIT" ]

[ 38, 7, 32, 38, 5, 6 ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #autotrain_compatible #endpoints_compatible #text-generation-inference #8-bit #region-us \n# llama2-7b### Model Details\n- Developed by: Julleong\n- Backbone Model: beomi/llama-2-ko-7b\n- Library: transformers### Used Datasets\n- 개체명 사전 2022(모두의 말뭉치)### Prompt Template### License\n- MIT" ]

[ "gguf", "region:us" ]

[]

[]

[]

[ "TAGS\n#gguf #region-us \n" ]

[ 9 ]

[ "TAGS\n#gguf #region-us \n" ]

[ "transformers", "tensorboard", "safetensors", "bert", "text-classification", "autotrain", "dataset:v12/autotrain-data", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# Model Trained Using AutoTrain\n\n- Problem type: Text Classification", "## Validation Metrics\nloss: 0.6593675017356873\n\nf1_macro: 0.6489004767693293\n\nf1_micro: 0.6925925925925925\n\nf1_weighted: 0.6558835632606125\n\nprecision_macro: 0.6958400129775946\n\nprecision_micro: 0.6925925925925925\n\nprecision_weighted: 0.7395732343473669\n\nrecall_macro: 0.7205811088713783\n\nrecall_micro: 0.6925925925925925\n\nrecall_weighted: 0.6925925925925925\n\naccuracy: 0.6925925925925925" ]

[ "TAGS\n#transformers #tensorboard #safetensors #bert #text-classification #autotrain #dataset-v12/autotrain-data #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Trained Using AutoTrain\n\n- Problem type: Text Classification", "## Validation Metrics\nloss: 0.6593675017356873\n\nf1_macro: 0.6489004767693293\n\nf1_micro: 0.6925925925925925\n\nf1_weighted: 0.6558835632606125\n\nprecision_macro: 0.6958400129775946\n\nprecision_micro: 0.6925925925925925\n\nprecision_weighted: 0.7395732343473669\n\nrecall_macro: 0.7205811088713783\n\nrecall_micro: 0.6925925925925925\n\nrecall_weighted: 0.6925925925925925\n\naccuracy: 0.6925925925925925" ]

[ 44, 12, 180 ]

[ "TAGS\n#transformers #tensorboard #safetensors #bert #text-classification #autotrain #dataset-v12/autotrain-data #autotrain_compatible #endpoints_compatible #region-us \n# Model Trained Using AutoTrain\n\n- Problem type: Text Classification## Validation Metrics\nloss: 0.6593675017356873\n\nf1_macro: 0.6489004767693293\n\nf1_micro: 0.6925925925925925\n\nf1_weighted: 0.6558835632606125\n\nprecision_macro: 0.6958400129775946\n\nprecision_micro: 0.6925925925925925\n\nprecision_weighted: 0.7395732343473669\n\nrecall_macro: 0.7205811088713783\n\nrecall_micro: 0.6925925925925925\n\nrecall_weighted: 0.6925925925925925\n\naccuracy: 0.6925925925925925" ]

[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

[]

[]

[ "# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage" ]

[ "TAGS\n#FrozenLake-v1-4x4-no_slippery #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n", "# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage" ]

[ 35, 33 ]

[ "TAGS\n#FrozenLake-v1-4x4-no_slippery #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage" ]

[ "sentence-transformers", "safetensors", "distilbert", "sentence-similarity", "feature-extraction", "loss:MultipleNegativesRankingLoss", "en", "arxiv:1908.10084", "arxiv:1705.00652", "base_model:sentence-transformers/stsb-distilbert-base", "model-index", "co2_eq_emissions", "endpoints_compatible", "region:us" ]

[ "1908.10084", "1705.00652" ]

[ "en" ]

[ "### Model Description\n\n\n* Model Type: Sentence Transformer\n* Base model: sentence-transformers/stsb-distilbert-base\n* Maximum Sequence Length: 128 tokens\n* Output Dimensionality: 768 tokens\n* Similarity Function: Cosine Similarity\n* Training Dataset:\n\t+ sentence-transformers/quora-duplicates\n* Language: en", "### Model Sources\n\n\n* Documentation: Sentence Transformers Documentation\n* Repository: Sentence Transformers on GitHub\n* Hugging Face: Sentence Transformers on Hugging Face", "### Full Model Architecture\n\n\nUsage\n-----", "### Direct Usage (Sentence Transformers)\n\n\nFirst install the Sentence Transformers library:\n\n\nThen you can load this model and run inference.\n\n\nEvaluation\n----------", "### Metrics", "#### Binary Classification\n\n\n* Dataset: 'quora-duplicates'\n* Evaluated with `BinaryClassificationEvaluator`", "#### Paraphrase Mining\n\n\n* Dataset: 'quora-duplicates-dev'\n* Evaluated with `ParaphraseMiningEvaluator`", "#### Information Retrieval\n\n\n* Evaluated with `InformationRetrievalEvaluator`\n\n\n\nTraining Details\n----------------", "### Training Dataset", "#### sentence-transformers/quora-duplicates\n\n\n* Dataset: sentence-transformers/quora-duplicates at 451a485\n* Size: 100,000 training samples\n* Columns: `anchor`, `positive`, and `negative`\n* Approximate statistics based on the first 1000 samples:\n* Samples:\n* Loss: `MultipleNegativesRankingLoss` with these parameters:", "### Evaluation Dataset", "#### sentence-transformers/quora-duplicates\n\n\n* Dataset: sentence-transformers/quora-duplicates at 451a485\n* Size: 1,000 evaluation samples\n* Columns: `anchor`, `positive`, and `negative`\n* Approximate statistics based on the first 1000 samples:\n* Samples:\n* Loss: `MultipleNegativesRankingLoss` with these parameters:", "### Training Hyperparameters", "#### Non-Default Hyperparameters\n\n\n* 'eval\\_strategy': steps\n* 'per\\_device\\_train\\_batch\\_size': 64\n* 'per\\_device\\_eval\\_batch\\_size': 64\n* 'num\\_train\\_epochs': 1\n* 'warmup\\_ratio': 0.1\n* 'fp16': True\n* 'batch\\_sampler': no\\_duplicates", "#### All Hyperparameters\n\n\nClick to expand\n* 'overwrite\\_output\\_dir': False\n* 'do\\_predict': False\n* 'eval\\_strategy': steps\n* 'prediction\\_loss\\_only': False\n* 'per\\_device\\_train\\_batch\\_size': 64\n* 'per\\_device\\_eval\\_batch\\_size': 64\n* 'per\\_gpu\\_train\\_batch\\_size': None\n* 'per\\_gpu\\_eval\\_batch\\_size': None\n* 'gradient\\_accumulation\\_steps': 1\n* 'eval\\_accumulation\\_steps': None\n* 'learning\\_rate': 5e-05\n* 'weight\\_decay': 0.0\n* 'adam\\_beta1': 0.9\n* 'adam\\_beta2': 0.999\n* 'adam\\_epsilon': 1e-08\n* 'max\\_grad\\_norm': 1.0\n* 'num\\_train\\_epochs': 1\n* 'max\\_steps': -1\n* 'lr\\_scheduler\\_type': linear\n* 'lr\\_scheduler\\_kwargs': {}\n* 'warmup\\_ratio': 0.1\n* 'warmup\\_steps': 0\n* 'log\\_level': passive\n* 'log\\_level\\_replica': warning\n* 'log\\_on\\_each\\_node': True\n* 'logging\\_nan\\_inf\\_filter': True\n* 'save\\_safetensors': True\n* 'save\\_on\\_each\\_node': False\n* 'save\\_only\\_model': False\n* 'no\\_cuda': False\n* 'use\\_cpu': False\n* 'use\\_mps\\_device': False\n* 'seed': 42\n* 'data\\_seed': None\n* 'jit\\_mode\\_eval': False\n* 'use\\_ipex': False\n* 'bf16': False\n* 'fp16': True\n* 'fp16\\_opt\\_level': O1\n* 'half\\_precision\\_backend': auto\n* 'bf16\\_full\\_eval': False\n* 'fp16\\_full\\_eval': False\n* 'tf32': None\n* 'local\\_rank': 0\n* 'ddp\\_backend': None\n* 'tpu\\_num\\_cores': None\n* 'tpu\\_metrics\\_debug': False\n* 'debug': []\n* 'dataloader\\_drop\\_last': False\n* 'dataloader\\_num\\_workers': 0\n* 'dataloader\\_prefetch\\_factor': None\n* 'past\\_index': -1\n* 'disable\\_tqdm': False\n* 'remove\\_unused\\_columns': True\n* 'label\\_names': None\n* 'load\\_best\\_model\\_at\\_end': False\n* 'ignore\\_data\\_skip': False\n* 'fsdp': []\n* 'fsdp\\_min\\_num\\_params': 0\n* 'fsdp\\_config': {'min\\_num\\_params': 0, 'xla': False, 'xla\\_fsdp\\_v2': False, 'xla\\_fsdp\\_grad\\_ckpt': False}\n* 'fsdp\\_transformer\\_layer\\_cls\\_to\\_wrap': None\n* 'accelerator\\_config': {'split\\_batches': False, 'dispatch\\_batches': None, 'even\\_batches': True, 'use\\_seedable\\_sampler': True, 'non\\_blocking': False, 'gradient\\_accumulation\\_kwargs': None}\n* 'deepspeed': None\n* 'label\\_smoothing\\_factor': 0.0\n* 'optim': adamw\\_torch\n* 'optim\\_args': None\n* 'adafactor': False\n* 'group\\_by\\_length': False\n* 'length\\_column\\_name': length\n* 'ddp\\_find\\_unused\\_parameters': None\n* 'ddp\\_bucket\\_cap\\_mb': None\n* 'ddp\\_broadcast\\_buffers': None\n* 'dataloader\\_pin\\_memory': True\n* 'dataloader\\_persistent\\_workers': False\n* 'skip\\_memory\\_metrics': True\n* 'use\\_legacy\\_prediction\\_loop': False\n* 'push\\_to\\_hub': False\n* 'resume\\_from\\_checkpoint': None\n* 'hub\\_model\\_id': None\n* 'hub\\_strategy': every\\_save\n* 'hub\\_private\\_repo': False\n* 'hub\\_always\\_push': False\n* 'gradient\\_checkpointing': False\n* 'gradient\\_checkpointing\\_kwargs': None\n* 'include\\_inputs\\_for\\_metrics': False\n* 'eval\\_do\\_concat\\_batches': True\n* 'fp16\\_backend': auto\n* 'push\\_to\\_hub\\_model\\_id': None\n* 'push\\_to\\_hub\\_organization': None\n* 'mp\\_parameters':\n* 'auto\\_find\\_batch\\_size': False\n* 'full\\_determinism': False\n* 'torchdynamo': None\n* 'ray\\_scope': last\n* 'ddp\\_timeout': 1800\n* 'torch\\_compile': False\n* 'torch\\_compile\\_backend': None\n* 'torch\\_compile\\_mode': None\n* 'dispatch\\_batches': None\n* 'split\\_batches': None\n* 'include\\_tokens\\_per\\_second': False\n* 'include\\_num\\_input\\_tokens\\_seen': False\n* 'neftune\\_noise\\_alpha': None\n* 'optim\\_target\\_modules': None\n* 'batch\\_sampler': no\\_duplicates\n* 'multi\\_dataset\\_batch\\_sampler': proportional", "### Training Logs", "### Environmental Impact\n\n\nCarbon emissions were measured using CodeCarbon.\n\n\n* Energy Consumed: 0.039 kWh\n* Carbon Emitted: 0.015 kg of CO2\n* Hours Used: 0.169 hours", "### Training Hardware\n\n\n* On Cloud: No\n* GPU Model: 1 x NVIDIA GeForce RTX 3090\n* CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K\n* RAM Size: 31.78 GB", "### Framework Versions\n\n\n* Python: 3.11.6\n* Sentence Transformers: 3.0.0.dev0\n* Transformers: 4.41.0.dev0\n* PyTorch: 2.3.0+cu121\n* Accelerate: 0.26.1\n* Datasets: 2.18.0\n* Tokenizers: 0.19.1", "### BibTeX", "#### Sentence Transformers", "#### MultipleNegativesRankingLoss" ]

[ "TAGS\n#sentence-transformers #safetensors #distilbert #sentence-similarity #feature-extraction #loss-MultipleNegativesRankingLoss #en #arxiv-1908.10084 #arxiv-1705.00652 #base_model-sentence-transformers/stsb-distilbert-base #model-index #co2_eq_emissions #endpoints_compatible #region-us \n", "### Model Description\n\n\n* Model Type: Sentence Transformer\n* Base model: sentence-transformers/stsb-distilbert-base\n* Maximum Sequence Length: 128 tokens\n* Output Dimensionality: 768 tokens\n* Similarity Function: Cosine Similarity\n* Training Dataset:\n\t+ sentence-transformers/quora-duplicates\n* Language: en", "### Model Sources\n\n\n* Documentation: Sentence Transformers Documentation\n* Repository: Sentence Transformers on GitHub\n* Hugging Face: Sentence Transformers on Hugging Face", "### Full Model Architecture\n\n\nUsage\n-----", "### Direct Usage (Sentence Transformers)\n\n\nFirst install the Sentence Transformers library:\n\n\nThen you can load this model and run inference.\n\n\nEvaluation\n----------", "### Metrics", "#### Binary Classification\n\n\n* Dataset: 'quora-duplicates'\n* Evaluated with `BinaryClassificationEvaluator`", "#### Paraphrase Mining\n\n\n* Dataset: 'quora-duplicates-dev'\n* Evaluated with `ParaphraseMiningEvaluator`", "#### Information Retrieval\n\n\n* Evaluated with `InformationRetrievalEvaluator`\n\n\n\nTraining Details\n----------------", "### Training Dataset", "#### sentence-transformers/quora-duplicates\n\n\n* Dataset: sentence-transformers/quora-duplicates at 451a485\n* Size: 100,000 training samples\n* Columns: `anchor`, `positive`, and `negative`\n* Approximate statistics based on the first 1000 samples:\n* Samples:\n* Loss: `MultipleNegativesRankingLoss` with these parameters:", "### Evaluation Dataset", "#### sentence-transformers/quora-duplicates\n\n\n* Dataset: sentence-transformers/quora-duplicates at 451a485\n* Size: 1,000 evaluation samples\n* Columns: `anchor`, `positive`, and `negative`\n* Approximate statistics based on the first 1000 samples:\n* Samples:\n* Loss: `MultipleNegativesRankingLoss` with these parameters:", "### Training Hyperparameters", "#### Non-Default Hyperparameters\n\n\n* 'eval\\_strategy': steps\n* 'per\\_device\\_train\\_batch\\_size': 64\n* 'per\\_device\\_eval\\_batch\\_size': 64\n* 'num\\_train\\_epochs': 1\n* 'warmup\\_ratio': 0.1\n* 'fp16': True\n* 'batch\\_sampler': no\\_duplicates", "#### All Hyperparameters\n\n\nClick to expand\n* 'overwrite\\_output\\_dir': False\n* 'do\\_predict': False\n* 'eval\\_strategy': steps\n* 'prediction\\_loss\\_only': False\n* 'per\\_device\\_train\\_batch\\_size': 64\n* 'per\\_device\\_eval\\_batch\\_size': 64\n* 'per\\_gpu\\_train\\_batch\\_size': None\n* 'per\\_gpu\\_eval\\_batch\\_size': None\n* 'gradient\\_accumulation\\_steps': 1\n* 'eval\\_accumulation\\_steps': None\n* 'learning\\_rate': 5e-05\n* 'weight\\_decay': 0.0\n* 'adam\\_beta1': 0.9\n* 'adam\\_beta2': 0.999\n* 'adam\\_epsilon': 1e-08\n* 'max\\_grad\\_norm': 1.0\n* 'num\\_train\\_epochs': 1\n* 'max\\_steps': -1\n* 'lr\\_scheduler\\_type': linear\n* 'lr\\_scheduler\\_kwargs': {}\n* 'warmup\\_ratio': 0.1\n* 'warmup\\_steps': 0\n* 'log\\_level': passive\n* 'log\\_level\\_replica': warning\n* 'log\\_on\\_each\\_node': True\n* 'logging\\_nan\\_inf\\_filter': True\n* 'save\\_safetensors': True\n* 'save\\_on\\_each\\_node': False\n* 'save\\_only\\_model': False\n* 'no\\_cuda': False\n* 'use\\_cpu': False\n* 'use\\_mps\\_device': False\n* 'seed': 42\n* 'data\\_seed': None\n* 'jit\\_mode\\_eval': False\n* 'use\\_ipex': False\n* 'bf16': False\n* 'fp16': True\n* 'fp16\\_opt\\_level': O1\n* 'half\\_precision\\_backend': auto\n* 'bf16\\_full\\_eval': False\n* 'fp16\\_full\\_eval': False\n* 'tf32': None\n* 'local\\_rank': 0\n* 'ddp\\_backend': None\n* 'tpu\\_num\\_cores': None\n* 'tpu\\_metrics\\_debug': False\n* 'debug': []\n* 'dataloader\\_drop\\_last': False\n* 'dataloader\\_num\\_workers': 0\n* 'dataloader\\_prefetch\\_factor': None\n* 'past\\_index': -1\n* 'disable\\_tqdm': False\n* 'remove\\_unused\\_columns': True\n* 'label\\_names': None\n* 'load\\_best\\_model\\_at\\_end': False\n* 'ignore\\_data\\_skip': False\n* 'fsdp': []\n* 'fsdp\\_min\\_num\\_params': 0\n* 'fsdp\\_config': {'min\\_num\\_params': 0, 'xla': False, 'xla\\_fsdp\\_v2': False, 'xla\\_fsdp\\_grad\\_ckpt': False}\n* 'fsdp\\_transformer\\_layer\\_cls\\_to\\_wrap': None\n* 'accelerator\\_config': {'split\\_batches': False, 'dispatch\\_batches': None, 'even\\_batches': True, 'use\\_seedable\\_sampler': True, 'non\\_blocking': False, 'gradient\\_accumulation\\_kwargs': None}\n* 'deepspeed': None\n* 'label\\_smoothing\\_factor': 0.0\n* 'optim': adamw\\_torch\n* 'optim\\_args': None\n* 'adafactor': False\n* 'group\\_by\\_length': False\n* 'length\\_column\\_name': length\n* 'ddp\\_find\\_unused\\_parameters': None\n* 'ddp\\_bucket\\_cap\\_mb': None\n* 'ddp\\_broadcast\\_buffers': None\n* 'dataloader\\_pin\\_memory': True\n* 'dataloader\\_persistent\\_workers': False\n* 'skip\\_memory\\_metrics': True\n* 'use\\_legacy\\_prediction\\_loop': False\n* 'push\\_to\\_hub': False\n* 'resume\\_from\\_checkpoint': None\n* 'hub\\_model\\_id': None\n* 'hub\\_strategy': every\\_save\n* 'hub\\_private\\_repo': False\n* 'hub\\_always\\_push': False\n* 'gradient\\_checkpointing': False\n* 'gradient\\_checkpointing\\_kwargs': None\n* 'include\\_inputs\\_for\\_metrics': False\n* 'eval\\_do\\_concat\\_batches': True\n* 'fp16\\_backend': auto\n* 'push\\_to\\_hub\\_model\\_id': None\n* 'push\\_to\\_hub\\_organization': None\n* 'mp\\_parameters':\n* 'auto\\_find\\_batch\\_size': False\n* 'full\\_determinism': False\n* 'torchdynamo': None\n* 'ray\\_scope': last\n* 'ddp\\_timeout': 1800\n* 'torch\\_compile': False\n* 'torch\\_compile\\_backend': None\n* 'torch\\_compile\\_mode': None\n* 'dispatch\\_batches': None\n* 'split\\_batches': None\n* 'include\\_tokens\\_per\\_second': False\n* 'include\\_num\\_input\\_tokens\\_seen': False\n* 'neftune\\_noise\\_alpha': None\n* 'optim\\_target\\_modules': None\n* 'batch\\_sampler': no\\_duplicates\n* 'multi\\_dataset\\_batch\\_sampler': proportional", "### Training Logs", "### Environmental Impact\n\n\nCarbon emissions were measured using CodeCarbon.\n\n\n* Energy Consumed: 0.039 kWh\n* Carbon Emitted: 0.015 kg of CO2\n* Hours Used: 0.169 hours", "### Training Hardware\n\n\n* On Cloud: No\n* GPU Model: 1 x NVIDIA GeForce RTX 3090\n* CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K\n* RAM Size: 31.78 GB", "### Framework Versions\n\n\n* Python: 3.11.6\n* Sentence Transformers: 3.0.0.dev0\n* Transformers: 4.41.0.dev0\n* PyTorch: 2.3.0+cu121\n* Accelerate: 0.26.1\n* Datasets: 2.18.0\n* Tokenizers: 0.19.1", "### BibTeX", "#### Sentence Transformers", "#### MultipleNegativesRankingLoss" ]

[ 92, 72, 29, 12, 37, 5, 28, 34, 36, 6, 84, 6, 84, 8, 106, 1494, 5, 43, 55, 79, 6, 6, 12 ]

[ "TAGS\n#sentence-transformers #safetensors #distilbert #sentence-similarity #feature-extraction #loss-MultipleNegativesRankingLoss #en #arxiv-1908.10084 #arxiv-1705.00652 #base_model-sentence-transformers/stsb-distilbert-base #model-index #co2_eq_emissions #endpoints_compatible #region-us \n### Model Description\n\n\n* Model Type: Sentence Transformer\n* Base model: sentence-transformers/stsb-distilbert-base\n* Maximum Sequence Length: 128 tokens\n* Output Dimensionality: 768 tokens\n* Similarity Function: Cosine Similarity\n* Training Dataset:\n\t+ sentence-transformers/quora-duplicates\n* Language: en### Model Sources\n\n\n* Documentation: Sentence Transformers Documentation\n* Repository: Sentence Transformers on GitHub\n* Hugging Face: Sentence Transformers on Hugging Face### Full Model Architecture\n\n\nUsage\n-----### Direct Usage (Sentence Transformers)\n\n\nFirst install the Sentence Transformers library:\n\n\nThen you can load this model and run inference.\n\n\nEvaluation\n----------### Metrics#### Binary Classification\n\n\n* Dataset: 'quora-duplicates'\n* Evaluated with `BinaryClassificationEvaluator`#### Paraphrase Mining\n\n\n* Dataset: 'quora-duplicates-dev'\n* Evaluated with `ParaphraseMiningEvaluator`#### Information Retrieval\n\n\n* Evaluated with `InformationRetrievalEvaluator`\n\n\n\nTraining Details\n----------------### Training Dataset#### sentence-transformers/quora-duplicates\n\n\n* Dataset: sentence-transformers/quora-duplicates at 451a485\n* Size: 100,000 training samples\n* Columns: `anchor`, `positive`, and `negative`\n* Approximate statistics based on the first 1000 samples:\n* Samples:\n* Loss: `MultipleNegativesRankingLoss` with these parameters:### Evaluation Dataset#### sentence-transformers/quora-duplicates\n\n\n* Dataset: sentence-transformers/quora-duplicates at 451a485\n* Size: 1,000 evaluation samples\n* Columns: `anchor`, `positive`, and `negative`\n* Approximate statistics based on the first 1000 samples:\n* Samples:\n* Loss: `MultipleNegativesRankingLoss` with these parameters:### Training Hyperparameters#### Non-Default Hyperparameters\n\n\n* 'eval\\_strategy': steps\n* 'per\\_device\\_train\\_batch\\_size': 64\n* 'per\\_device\\_eval\\_batch\\_size': 64\n* 'num\\_train\\_epochs': 1\n* 'warmup\\_ratio': 0.1\n* 'fp16': True\n* 'batch\\_sampler': no\\_duplicates#### All Hyperparameters\n\n\nClick to expand\n* 'overwrite\\_output\\_dir': False\n* 'do\\_predict': False\n* 'eval\\_strategy': steps\n* 'prediction\\_loss\\_only': False\n* 'per\\_device\\_train\\_batch\\_size': 64\n* 'per\\_device\\_eval\\_batch\\_size': 64\n* 'per\\_gpu\\_train\\_batch\\_size': None\n* 'per\\_gpu\\_eval\\_batch\\_size': None\n* 'gradient\\_accumulation\\_steps': 1\n* 'eval\\_accumulation\\_steps': None\n* 'learning\\_rate': 5e-05\n* 'weight\\_decay': 0.0\n* 'adam\\_beta1': 0.9\n* 'adam\\_beta2': 0.999\n* 'adam\\_epsilon': 1e-08\n* 'max\\_grad\\_norm': 1.0\n* 'num\\_train\\_epochs': 1\n* 'max\\_steps': -1\n* 'lr\\_scheduler\\_type': linear\n* 'lr\\_scheduler\\_kwargs': {}\n* 'warmup\\_ratio': 0.1\n* 'warmup\\_steps': 0\n* 'log\\_level': passive\n* 'log\\_level\\_replica': warning\n* 'log\\_on\\_each\\_node': True\n* 'logging\\_nan\\_inf\\_filter': True\n* 'save\\_safetensors': True\n* 'save\\_on\\_each\\_node': False\n* 'save\\_only\\_model': False\n* 'no\\_cuda': False\n* 'use\\_cpu': False\n* 'use\\_mps\\_device': False\n* 'seed': 42\n* 'data\\_seed': None\n* 'jit\\_mode\\_eval': False\n* 'use\\_ipex': False\n* 'bf16': False\n* 'fp16': True\n* 'fp16\\_opt\\_level': O1\n* 'half\\_precision\\_backend': auto\n* 'bf16\\_full\\_eval': False\n* 'fp16\\_full\\_eval': False\n* 'tf32': None\n* 'local\\_rank': 0\n* 'ddp\\_backend': None\n* 'tpu\\_num\\_cores': None\n* 'tpu\\_metrics\\_debug': False\n* 'debug': []\n* 'dataloader\\_drop\\_last': False\n* 'dataloader\\_num\\_workers': 0\n* 'dataloader\\_prefetch\\_factor': None\n* 'past\\_index': -1\n* 'disable\\_tqdm': False\n* 'remove\\_unused\\_columns': True\n* 'label\\_names': None\n* 'load\\_best\\_model\\_at\\_end': False\n* 'ignore\\_data\\_skip': False\n* 'fsdp': []\n* 'fsdp\\_min\\_num\\_params': 0\n* 'fsdp\\_config': {'min\\_num\\_params': 0, 'xla': False, 'xla\\_fsdp\\_v2': False, 'xla\\_fsdp\\_grad\\_ckpt': False}\n* 'fsdp\\_transformer\\_layer\\_cls\\_to\\_wrap': None\n* 'accelerator\\_config': {'split\\_batches': False, 'dispatch\\_batches': None, 'even\\_batches': True, 'use\\_seedable\\_sampler': True, 'non\\_blocking': False, 'gradient\\_accumulation\\_kwargs': None}\n* 'deepspeed': None\n* 'label\\_smoothing\\_factor': 0.0\n* 'optim': adamw\\_torch\n* 'optim\\_args': None\n* 'adafactor': False\n* 'group\\_by\\_length': False\n* 'length\\_column\\_name': length\n* 'ddp\\_find\\_unused\\_parameters': None\n* 'ddp\\_bucket\\_cap\\_mb': None\n* 'ddp\\_broadcast\\_buffers': None\n* 'dataloader\\_pin\\_memory': True\n* 'dataloader\\_persistent\\_workers': False\n* 'skip\\_memory\\_metrics': True\n* 'use\\_legacy\\_prediction\\_loop': False\n* 'push\\_to\\_hub': False\n* 'resume\\_from\\_checkpoint': None\n* 'hub\\_model\\_id': None\n* 'hub\\_strategy': every\\_save\n* 'hub\\_private\\_repo': False\n* 'hub\\_always\\_push': False\n* 'gradient\\_checkpointing': False\n* 'gradient\\_checkpointing\\_kwargs': None\n* 'include\\_inputs\\_for\\_metrics': False\n* 'eval\\_do\\_concat\\_batches': True\n* 'fp16\\_backend': auto\n* 'push\\_to\\_hub\\_model\\_id': None\n* 'push\\_to\\_hub\\_organization': None\n* 'mp\\_parameters':\n* 'auto\\_find\\_batch\\_size': False\n* 'full\\_determinism': False\n* 'torchdynamo': None\n* 'ray\\_scope': last\n* 'ddp\\_timeout': 1800\n* 'torch\\_compile': False\n* 'torch\\_compile\\_backend': None\n* 'torch\\_compile\\_mode': None\n* 'dispatch\\_batches': None\n* 'split\\_batches': None\n* 'include\\_tokens\\_per\\_second': False\n* 'include\\_num\\_input\\_tokens\\_seen': False\n* 'neftune\\_noise\\_alpha': None\n* 'optim\\_target\\_modules': None\n* 'batch\\_sampler': no\\_duplicates\n* 'multi\\_dataset\\_batch\\_sampler': proportional### Training Logs### Environmental Impact\n\n\nCarbon emissions were measured using CodeCarbon.\n\n\n* Energy Consumed: 0.039 kWh\n* Carbon Emitted: 0.015 kg of CO2\n* Hours Used: 0.169 hours### Training Hardware\n\n\n* On Cloud: No\n* GPU Model: 1 x NVIDIA GeForce RTX 3090\n* CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K\n* RAM Size: 31.78 GB### Framework Versions\n\n\n* Python: 3.11.6\n* Sentence Transformers: 3.0.0.dev0\n* Transformers: 4.41.0.dev0\n* PyTorch: 2.3.0+cu121\n* Accelerate: 0.26.1\n* Datasets: 2.18.0\n* Tokenizers: 0.19.1### BibTeX#### Sentence Transformers#### MultipleNegativesRankingLoss" ]

[ "transformers", "safetensors", "bert", "feature-extraction", "custom_code", "region:us" ]

[]

[]

[ "# fine-tuned/car-search-1000-64-16-jinaai_jina-embeddings-v2-small-en-1000-gpt-3.5-_8647177611", "## Model Description\n\nfine-tuned/car-search-1000-64-16-jinaai_jina-embeddings-v2-small-en-1000-gpt-3.5-_8647177611 is a fine-tuned version of jinaai/jina-embeddings-v2-small-en designed for a specific domain.", "## Use Case\nThis model is designed to support various applications in natural language processing and understanding.", "## Associated Dataset\n\nThis the dataset for this model can be found here.", "## How to Use\n\nThis model can be easily integrated into your NLP pipeline for tasks such as text classification, sentiment analysis, entity recognition, and more. Here's a simple example to get you started:" ]

[ "TAGS\n#transformers #safetensors #bert #feature-extraction #custom_code #region-us \n", "# fine-tuned/car-search-1000-64-16-jinaai_jina-embeddings-v2-small-en-1000-gpt-3.5-_8647177611", "## Model Description\n\nfine-tuned/car-search-1000-64-16-jinaai_jina-embeddings-v2-small-en-1000-gpt-3.5-_8647177611 is a fine-tuned version of jinaai/jina-embeddings-v2-small-en designed for a specific domain.", "## Use Case\nThis model is designed to support various applications in natural language processing and understanding.", "## Associated Dataset\n\nThis the dataset for this model can be found here.", "## How to Use\n\nThis model can be easily integrated into your NLP pipeline for tasks such as text classification, sentiment analysis, entity recognition, and more. Here's a simple example to get you started:" ]

[ 21, 50, 84, 19, 17, 43 ]

[ "TAGS\n#transformers #safetensors #bert #feature-extraction #custom_code #region-us \n# fine-tuned/car-search-1000-64-16-jinaai_jina-embeddings-v2-small-en-1000-gpt-3.5-_8647177611## Model Description\n\nfine-tuned/car-search-1000-64-16-jinaai_jina-embeddings-v2-small-en-1000-gpt-3.5-_8647177611 is a fine-tuned version of jinaai/jina-embeddings-v2-small-en designed for a specific domain.## Use Case\nThis model is designed to support various applications in natural language processing and understanding.## Associated Dataset\n\nThis the dataset for this model can be found here.## How to Use\n\nThis model can be easily integrated into your NLP pipeline for tasks such as text classification, sentiment analysis, entity recognition, and more. Here's a simple example to get you started:" ]

[ "transformers", "tensorboard", "safetensors", "vision-encoder-decoder", "generated_from_trainer", "dataset:imagefolder", "base_model:naver-clova-ix/donut-base", "license:mit", "endpoints_compatible", "region:us" ]

[]

[]

[ "# PolizzeDonut-SoloConsignee-5Epochs\n\nThis model is a fine-tuned version of naver-clova-ix/donut-base on the imagefolder dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 2e-05\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.38.2\n- Pytorch 2.2.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #vision-encoder-decoder #generated_from_trainer #dataset-imagefolder #base_model-naver-clova-ix/donut-base #license-mit #endpoints_compatible #region-us \n", "# PolizzeDonut-SoloConsignee-5Epochs\n\nThis model is a fine-tuned version of naver-clova-ix/donut-base on the imagefolder dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 2e-05\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.38.2\n- Pytorch 2.2.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ 62, 46, 7, 9, 9, 4, 102, 5, 44 ]

[ "TAGS\n#transformers #tensorboard #safetensors #vision-encoder-decoder #generated_from_trainer #dataset-imagefolder #base_model-naver-clova-ix/donut-base #license-mit #endpoints_compatible #region-us \n# PolizzeDonut-SoloConsignee-5Epochs\n\nThis model is a fine-tuned version of naver-clova-ix/donut-base on the imagefolder dataset.## Model description\n\nMore information needed## Intended uses & limitations\n\nMore information needed## Training and evaluation data\n\nMore information needed## Training procedure### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 2e-05\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5\n- mixed_precision_training: Native AMP### Training results### Framework versions\n\n- Transformers 4.38.2\n- Pytorch 2.2.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "peft", "safetensors", "arxiv:1910.09700", "base_model:meta-llama/Meta-Llama-3-8B-Instruct", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact", "### Framework versions\n\n- PEFT 0.7.1" ]

[ "TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-meta-llama/Meta-Llama-3-8B-Instruct #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact", "### Framework versions\n\n- PEFT 0.7.1" ]

[ 44, 6, 4, 50, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5, 13 ]

[ "TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-meta-llama/Meta-Llama-3-8B-Instruct #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact### Framework versions\n\n- PEFT 0.7.1" ]

[ "transformers", "gguf", "en", "base_model:Gryphe/Tiamat-8b-1.2-Llama-3-DPO", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #en #base_model-Gryphe/Tiamat-8b-1.2-Llama-3-DPO #license-apache-2.0 #endpoints_compatible #region-us \n" ]

[ 52 ]

[ "TAGS\n#transformers #gguf #en #base_model-Gryphe/Tiamat-8b-1.2-Llama-3-DPO #license-apache-2.0 #endpoints_compatible #region-us \n" ]

[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

[]

[]

[ "# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage" ]

[ "TAGS\n#Taxi-v3 #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n", "# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage" ]

[ 26, 31 ]

[ "TAGS\n#Taxi-v3 #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage" ]

[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 26, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

[]

[]

[ "# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage" ]

[ "TAGS\n#FrozenLake-v1-4x4-no_slippery #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n", "# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage" ]

[ 35, 33 ]

[ "TAGS\n#FrozenLake-v1-4x4-no_slippery #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage" ]

[ "setfit", "safetensors", "mpnet", "sentence-transformers", "text-classification", "generated_from_setfit_trainer", "arxiv:2209.11055", "base_model:sentence-transformers/multi-qa-mpnet-base-cos-v1", "model-index", "region:us" ]

[ "2209.11055" ]

[]

[ "### Model Description\n\n\n* Model Type: SetFit\n* Sentence Transformer body: sentence-transformers/multi-qa-mpnet-base-cos-v1\n* Classification head: a SetFitHead instance\n* Maximum Sequence Length: 512 tokens\n* Number of Classes: 43 classes", "### Model Sources\n\n\n* Repository: SetFit on GitHub\n* Paper: Efficient Few-Shot Learning Without Prompts\n* Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts", "### Model Labels\n\n\n\nEvaluation\n----------", "### Metrics\n\n\n\nUses\n----", "### Direct Use for Inference\n\n\nFirst install the SetFit library:\n\n\nThen you can load this model and run inference.\n\n\nTraining Details\n----------------", "### Training Set Metrics", "### Training Hyperparameters\n\n\n* batch\\_size: (16, 16)\n* num\\_epochs: (1, 4)\n* max\\_steps: -1\n* sampling\\_strategy: oversampling\n* num\\_iterations: 10\n* body\\_learning\\_rate: (2e-05, 0.01)\n* head\\_learning\\_rate: 0.01\n* loss: CosineSimilarityLoss\n* distance\\_metric: cosine\\_distance\n* margin: 0.25\n* end\\_to\\_end: False\n* use\\_amp: False\n* warmup\\_proportion: 0.1\n* max\\_length: 512\n* seed: 42\n* eval\\_max\\_steps: -1\n* load\\_best\\_model\\_at\\_end: True", "### Training Results\n\n\n\n* The bold row denotes the saved checkpoint.", "### Framework Versions\n\n\n* Python: 3.10.12\n* SetFit: 1.0.3\n* Sentence Transformers: 2.7.0\n* Transformers: 4.40.1\n* PyTorch: 2.2.1+cu121\n* Datasets: 2.19.0\n* Tokenizers: 0.19.1", "### BibTeX" ]

[ "TAGS\n#setfit #safetensors #mpnet #sentence-transformers #text-classification #generated_from_setfit_trainer #arxiv-2209.11055 #base_model-sentence-transformers/multi-qa-mpnet-base-cos-v1 #model-index #region-us \n", "### Model Description\n\n\n* Model Type: SetFit\n* Sentence Transformer body: sentence-transformers/multi-qa-mpnet-base-cos-v1\n* Classification head: a SetFitHead instance\n* Maximum Sequence Length: 512 tokens\n* Number of Classes: 43 classes", "### Model Sources\n\n\n* Repository: SetFit on GitHub\n* Paper: Efficient Few-Shot Learning Without Prompts\n* Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts", "### Model Labels\n\n\n\nEvaluation\n----------", "### Metrics\n\n\n\nUses\n----", "### Direct Use for Inference\n\n\nFirst install the SetFit library:\n\n\nThen you can load this model and run inference.\n\n\nTraining Details\n----------------", "### Training Set Metrics", "### Training Hyperparameters\n\n\n* batch\\_size: (16, 16)\n* num\\_epochs: (1, 4)\n* max\\_steps: -1\n* sampling\\_strategy: oversampling\n* num\\_iterations: 10\n* body\\_learning\\_rate: (2e-05, 0.01)\n* head\\_learning\\_rate: 0.01\n* loss: CosineSimilarityLoss\n* distance\\_metric: cosine\\_distance\n* margin: 0.25\n* end\\_to\\_end: False\n* use\\_amp: False\n* warmup\\_proportion: 0.1\n* max\\_length: 512\n* seed: 42\n* eval\\_max\\_steps: -1\n* load\\_best\\_model\\_at\\_end: True", "### Training Results\n\n\n\n* The bold row denotes the saved checkpoint.", "### Framework Versions\n\n\n* Python: 3.10.12\n* SetFit: 1.0.3\n* Sentence Transformers: 2.7.0\n* Transformers: 4.40.1\n* PyTorch: 2.2.1+cu121\n* Datasets: 2.19.0\n* Tokenizers: 0.19.1", "### BibTeX" ]

[ 72, 62, 42, 16, 10, 43, 7, 184, 14, 75, 6 ]

[ "TAGS\n#setfit #safetensors #mpnet #sentence-transformers #text-classification #generated_from_setfit_trainer #arxiv-2209.11055 #base_model-sentence-transformers/multi-qa-mpnet-base-cos-v1 #model-index #region-us \n### Model Description\n\n\n* Model Type: SetFit\n* Sentence Transformer body: sentence-transformers/multi-qa-mpnet-base-cos-v1\n* Classification head: a SetFitHead instance\n* Maximum Sequence Length: 512 tokens\n* Number of Classes: 43 classes### Model Sources\n\n\n* Repository: SetFit on GitHub\n* Paper: Efficient Few-Shot Learning Without Prompts\n* Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts### Model Labels\n\n\n\nEvaluation\n----------### Metrics\n\n\n\nUses\n----### Direct Use for Inference\n\n\nFirst install the SetFit library:\n\n\nThen you can load this model and run inference.\n\n\nTraining Details\n----------------### Training Set Metrics### Training Hyperparameters\n\n\n* batch\\_size: (16, 16)\n* num\\_epochs: (1, 4)\n* max\\_steps: -1\n* sampling\\_strategy: oversampling\n* num\\_iterations: 10\n* body\\_learning\\_rate: (2e-05, 0.01)\n* head\\_learning\\_rate: 0.01\n* loss: CosineSimilarityLoss\n* distance\\_metric: cosine\\_distance\n* margin: 0.25\n* end\\_to\\_end: False\n* use\\_amp: False\n* warmup\\_proportion: 0.1\n* max\\_length: 512\n* seed: 42\n* eval\\_max\\_steps: -1\n* load\\_best\\_model\\_at\\_end: True### Training Results\n\n\n\n* The bold row denotes the saved checkpoint.### Framework Versions\n\n\n* Python: 3.10.12\n* SetFit: 1.0.3\n* Sentence Transformers: 2.7.0\n* Transformers: 4.40.1\n* PyTorch: 2.2.1+cu121\n* Datasets: 2.19.0\n* Tokenizers: 0.19.1### BibTeX" ]

[ "transformers", "safetensors", "gpt_neox", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #gpt_neox #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 47, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #gpt_neox #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "gguf", "not-for-all-audiences", "nsfw", "en", "base_model:Undi95/Llama3-Unholy-8B-OAS", "license:cc-by-nc-4.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #not-for-all-audiences #nsfw #en #base_model-Undi95/Llama3-Unholy-8B-OAS #license-cc-by-nc-4.0 #endpoints_compatible #region-us \n" ]

[ 65 ]

[ "TAGS\n#transformers #gguf #not-for-all-audiences #nsfw #en #base_model-Undi95/Llama3-Unholy-8B-OAS #license-cc-by-nc-4.0 #endpoints_compatible #region-us \n" ]

[ "transformers", "safetensors", "xlm-roberta", "token-classification", "generated_from_trainer", "dataset:cnec", "base_model:FacebookAI/xlm-roberta-large", "license:mit", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 12", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.2\n* Pytorch 2.1.2+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.0" ]

[ "TAGS\n#transformers #safetensors #xlm-roberta #token-classification #generated_from_trainer #dataset-cnec #base_model-FacebookAI/xlm-roberta-large #license-mit #model-index #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 12", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.2\n* Pytorch 2.1.2+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.0" ]

[ 64, 101, 5, 44 ]

[ "TAGS\n#transformers #safetensors #xlm-roberta #token-classification #generated_from_trainer #dataset-cnec #base_model-FacebookAI/xlm-roberta-large #license-mit #model-index #autotrain_compatible #endpoints_compatible #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 12### Training results### Framework versions\n\n\n* Transformers 4.36.2\n* Pytorch 2.1.2+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.0" ]

[ "transformers", "safetensors", "bart", "text2text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #bart #text2text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 39, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #bart #text2text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "peft", "safetensors", "generated_from_trainer", "text-classification", "base_model:mistralai/Mistral-7B-v0.1", "license:apache-2.0", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2.5e-05\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 1\n* training\\_steps: 120", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.1.dev0\n* Transformers 4.41.0.dev0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #text-classification #base_model-mistralai/Mistral-7B-v0.1 #license-apache-2.0 #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2.5e-05\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 1\n* training\\_steps: 120", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.1.dev0\n* Transformers 4.41.0.dev0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ 49, 117, 5, 58 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #text-classification #base_model-mistralai/Mistral-7B-v0.1 #license-apache-2.0 #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2.5e-05\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 1\n* training\\_steps: 120### Training results### Framework versions\n\n\n* PEFT 0.10.1.dev0\n* Transformers 4.41.0.dev0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "transformers", "gguf", "merge", "mergekit", "lazymergekit", "OpenPipe/mistral-ft-optimized-1218", "mlabonne/NeuralHermes-2.5-Mistral-7B", "en", "base_model:lancartech/LancarAI-v1.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #merge #mergekit #lazymergekit #OpenPipe/mistral-ft-optimized-1218 #mlabonne/NeuralHermes-2.5-Mistral-7B #en #base_model-lancartech/LancarAI-v1.0 #endpoints_compatible #region-us \n" ]

[ 78 ]

[ "TAGS\n#transformers #gguf #merge #mergekit #lazymergekit #OpenPipe/mistral-ft-optimized-1218 #mlabonne/NeuralHermes-2.5-Mistral-7B #en #base_model-lancartech/LancarAI-v1.0 #endpoints_compatible #region-us \n" ]

[ "gguf", "facebook", "meta", "pytorch", "llama", "llama-3", "text-generation", "en", "license:other", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#gguf #facebook #meta #pytorch #llama #llama-3 #text-generation #en #license-other #region-us \n" ]

[ 36 ]

[ "TAGS\n#gguf #facebook #meta #pytorch #llama #llama-3 #text-generation #en #license-other #region-us \n" ]

[ "region:us" ]

[]

[]

[]

[ "TAGS\n#region-us \n" ]

[ 5 ]

[ "TAGS\n#region-us \n" ]

[ "transformers", "tensorboard", "safetensors", "vit", "image-classification", "generated_from_trainer", "dataset:imagefolder", "base_model:google/vit-base-patch16-224", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 64\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 10", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #vit #image-classification #generated_from_trainer #dataset-imagefolder #base_model-google/vit-base-patch16-224 #license-apache-2.0 #model-index #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 64\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 10", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ 72, 142, 5, 44 ]

[ "TAGS\n#transformers #tensorboard #safetensors #vit #image-classification #generated_from_trainer #dataset-imagefolder #base_model-google/vit-base-patch16-224 #license-apache-2.0 #model-index #autotrain_compatible #endpoints_compatible #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 64\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 10### Training results### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "xlm-roberta", "feature-extraction", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #xlm-roberta #feature-extraction #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 35, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #xlm-roberta #feature-extraction #arxiv-1910.09700 #endpoints_compatible #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

[]

[]

[ "# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage" ]

[ "TAGS\n#Taxi-v3 #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n", "# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage" ]

[ 26, 31 ]

[ "TAGS\n#Taxi-v3 #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage" ]

[ "transformers", "tensorboard", "safetensors", "whisper", "automatic-speech-recognition", "hf-asr-leaderboard", "generated_from_trainer", "multilingual", "dataset:mozilla-foundation/common_voice_11_0", "base_model:openai/whisper-small", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us" ]

[]

[ "multilingual" ]

[ "# bylo 16 a pod tim 1 gradient\\_accumulation\\_steps=2, warmup\\_steps=300, max\\_steps=3000\n============================================================================================================================================================================\n\n\nThis model is a fine-tuned version of openai/whisper-small on the xbilek25/xbilek25/train\\_set\\_5000\\_en\\_de\\_en dataset.\nIt achieves the following results on the evaluation set:\n\n\n* Loss: 0.1263\n* Wer: 6.0896\n\n\nModel description\n-----------------\n\n\nMore information needed\n\n\nIntended uses & limitations\n---------------------------\n\n\nMore information needed\n\n\nTraining and evaluation data\n----------------------------\n\n\nMore information needed\n\n\nTraining procedure\n------------------", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* training\\_steps: 4000\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.37.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #hf-asr-leaderboard #generated_from_trainer #multilingual #dataset-mozilla-foundation/common_voice_11_0 #base_model-openai/whisper-small #license-apache-2.0 #model-index #endpoints_compatible #region-us \n", "# bylo 16 a pod tim 1 gradient\\_accumulation\\_steps=2, warmup\\_steps=300, max\\_steps=3000\n============================================================================================================================================================================\n\n\nThis model is a fine-tuned version of openai/whisper-small on the xbilek25/xbilek25/train\\_set\\_5000\\_en\\_de\\_en dataset.\nIt achieves the following results on the evaluation set:\n\n\n* Loss: 0.1263\n* Wer: 6.0896\n\n\nModel description\n-----------------\n\n\nMore information needed\n\n\nIntended uses & limitations\n---------------------------\n\n\nMore information needed\n\n\nTraining and evaluation data\n----------------------------\n\n\nMore information needed\n\n\nTraining procedure\n------------------", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* training\\_steps: 4000\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.37.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.15.2" ]

[ 86, 388, 126, 5, 44 ]

[ "TAGS\n#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #hf-asr-leaderboard #generated_from_trainer #multilingual #dataset-mozilla-foundation/common_voice_11_0 #base_model-openai/whisper-small #license-apache-2.0 #model-index #endpoints_compatible #region-us \n# bylo 16 a pod tim 1 gradient\\_accumulation\\_steps=2, warmup\\_steps=300, max\\_steps=3000\n============================================================================================================================================================================\n\n\nThis model is a fine-tuned version of openai/whisper-small on the xbilek25/xbilek25/train\\_set\\_5000\\_en\\_de\\_en dataset.\nIt achieves the following results on the evaluation set:\n\n\n* Loss: 0.1263\n* Wer: 6.0896\n\n\nModel description\n-----------------\n\n\nMore information needed\n\n\nIntended uses & limitations\n---------------------------\n\n\nMore information needed\n\n\nTraining and evaluation data\n----------------------------\n\n\nMore information needed\n\n\nTraining procedure\n------------------### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* training\\_steps: 4000\n* mixed\\_precision\\_training: Native AMP### Training results### Framework versions\n\n\n* Transformers 4.37.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.15.2" ]

[ "license:apache-2.0", "region:us" ]

[]

[]

[]

[ "TAGS\n#license-apache-2.0 #region-us \n" ]

[ 13 ]

[ "TAGS\n#license-apache-2.0 #region-us \n" ]

[ "transformers", "tensorboard", "safetensors", "bert", "text-classification", "autotrain", "dataset:V13/autotrain-data", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# Model Trained Using AutoTrain\n\n- Problem type: Text Classification", "## Validation Metrics\nloss: 0.587009608745575\n\nf1_macro: 0.7086614173228346\n\nf1_micro: 0.7435897435897436\n\nf1_weighted: 0.7361195235210982\n\nprecision_macro: 0.7210665002427016\n\nprecision_micro: 0.7435897435897436\n\nprecision_weighted: 0.7538358857008742\n\nrecall_macro: 0.7157125819916518\n\nrecall_micro: 0.7435897435897436\n\nrecall_weighted: 0.7435897435897436\n\naccuracy: 0.7435897435897436" ]

[ "TAGS\n#transformers #tensorboard #safetensors #bert #text-classification #autotrain #dataset-V13/autotrain-data #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Trained Using AutoTrain\n\n- Problem type: Text Classification", "## Validation Metrics\nloss: 0.587009608745575\n\nf1_macro: 0.7086614173228346\n\nf1_micro: 0.7435897435897436\n\nf1_weighted: 0.7361195235210982\n\nprecision_macro: 0.7210665002427016\n\nprecision_micro: 0.7435897435897436\n\nprecision_weighted: 0.7538358857008742\n\nrecall_macro: 0.7157125819916518\n\nrecall_micro: 0.7435897435897436\n\nrecall_weighted: 0.7435897435897436\n\naccuracy: 0.7435897435897436" ]

[ 44, 12, 179 ]

[ "TAGS\n#transformers #tensorboard #safetensors #bert #text-classification #autotrain #dataset-V13/autotrain-data #autotrain_compatible #endpoints_compatible #region-us \n# Model Trained Using AutoTrain\n\n- Problem type: Text Classification## Validation Metrics\nloss: 0.587009608745575\n\nf1_macro: 0.7086614173228346\n\nf1_micro: 0.7435897435897436\n\nf1_weighted: 0.7361195235210982\n\nprecision_macro: 0.7210665002427016\n\nprecision_micro: 0.7435897435897436\n\nprecision_weighted: 0.7538358857008742\n\nrecall_macro: 0.7157125819916518\n\nrecall_micro: 0.7435897435897436\n\nrecall_weighted: 0.7435897435897436\n\naccuracy: 0.7435897435897436" ]

[ "transformers", "safetensors", "unsloth", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #unsloth #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 30, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #unsloth #arxiv-1910.09700 #endpoints_compatible #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "setfit", "safetensors", "bert", "sentence-transformers", "text-classification", "generated_from_setfit_trainer", "arxiv:2209.11055", "base_model:BAAI/bge-small-en-v1.5", "model-index", "region:us" ]

[ "2209.11055" ]

[]

[ "### Model Description\n\n\n* Model Type: SetFit\n* Sentence Transformer body: BAAI/bge-small-en-v1.5\n* Classification head: a LogisticRegression instance\n* Maximum Sequence Length: 512 tokens\n* Number of Classes: 4 classes", "### Model Sources\n\n\n* Repository: SetFit on GitHub\n* Paper: Efficient Few-Shot Learning Without Prompts\n* Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts", "### Model Labels\n\n\n\nEvaluation\n----------", "### Metrics\n\n\n\nUses\n----", "### Direct Use for Inference\n\n\nFirst install the SetFit library:\n\n\nThen you can load this model and run inference.\n\n\nTraining Details\n----------------", "### Training Set Metrics", "### Training Hyperparameters\n\n\n* batch\\_size: (32, 32)\n* num\\_epochs: (2, 2)\n* max\\_steps: -1\n* sampling\\_strategy: oversampling\n* body\\_learning\\_rate: (2e-05, 1e-05)\n* head\\_learning\\_rate: 0.01\n* loss: CosineSimilarityLoss\n* distance\\_metric: cosine\\_distance\n* margin: 0.25\n* end\\_to\\_end: False\n* use\\_amp: False\n* warmup\\_proportion: 0.1\n* seed: 42\n* eval\\_max\\_steps: -1\n* load\\_best\\_model\\_at\\_end: False", "### Training Results", "### Framework Versions\n\n\n* Python: 3.10.12\n* SetFit: 1.0.3\n* Sentence Transformers: 2.7.0\n* Transformers: 4.40.1\n* PyTorch: 2.2.1+cu121\n* Datasets: 2.19.0\n* Tokenizers: 0.19.1", "### BibTeX" ]

[ "TAGS\n#setfit #safetensors #bert #sentence-transformers #text-classification #generated_from_setfit_trainer #arxiv-2209.11055 #base_model-BAAI/bge-small-en-v1.5 #model-index #region-us \n", "### Model Description\n\n\n* Model Type: SetFit\n* Sentence Transformer body: BAAI/bge-small-en-v1.5\n* Classification head: a LogisticRegression instance\n* Maximum Sequence Length: 512 tokens\n* Number of Classes: 4 classes", "### Model Sources\n\n\n* Repository: SetFit on GitHub\n* Paper: Efficient Few-Shot Learning Without Prompts\n* Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts", "### Model Labels\n\n\n\nEvaluation\n----------", "### Metrics\n\n\n\nUses\n----", "### Direct Use for Inference\n\n\nFirst install the SetFit library:\n\n\nThen you can load this model and run inference.\n\n\nTraining Details\n----------------", "### Training Set Metrics", "### Training Hyperparameters\n\n\n* batch\\_size: (32, 32)\n* num\\_epochs: (2, 2)\n* max\\_steps: -1\n* sampling\\_strategy: oversampling\n* body\\_learning\\_rate: (2e-05, 1e-05)\n* head\\_learning\\_rate: 0.01\n* loss: CosineSimilarityLoss\n* distance\\_metric: cosine\\_distance\n* margin: 0.25\n* end\\_to\\_end: False\n* use\\_amp: False\n* warmup\\_proportion: 0.1\n* seed: 42\n* eval\\_max\\_steps: -1\n* load\\_best\\_model\\_at\\_end: False", "### Training Results", "### Framework Versions\n\n\n* Python: 3.10.12\n* SetFit: 1.0.3\n* Sentence Transformers: 2.7.0\n* Transformers: 4.40.1\n* PyTorch: 2.2.1+cu121\n* Datasets: 2.19.0\n* Tokenizers: 0.19.1", "### BibTeX" ]

[ 66, 58, 42, 16, 10, 43, 7, 169, 5, 75, 6 ]

[ "TAGS\n#setfit #safetensors #bert #sentence-transformers #text-classification #generated_from_setfit_trainer #arxiv-2209.11055 #base_model-BAAI/bge-small-en-v1.5 #model-index #region-us \n### Model Description\n\n\n* Model Type: SetFit\n* Sentence Transformer body: BAAI/bge-small-en-v1.5\n* Classification head: a LogisticRegression instance\n* Maximum Sequence Length: 512 tokens\n* Number of Classes: 4 classes### Model Sources\n\n\n* Repository: SetFit on GitHub\n* Paper: Efficient Few-Shot Learning Without Prompts\n* Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts### Model Labels\n\n\n\nEvaluation\n----------### Metrics\n\n\n\nUses\n----### Direct Use for Inference\n\n\nFirst install the SetFit library:\n\n\nThen you can load this model and run inference.\n\n\nTraining Details\n----------------### Training Set Metrics### Training Hyperparameters\n\n\n* batch\\_size: (32, 32)\n* num\\_epochs: (2, 2)\n* max\\_steps: -1\n* sampling\\_strategy: oversampling\n* body\\_learning\\_rate: (2e-05, 1e-05)\n* head\\_learning\\_rate: 0.01\n* loss: CosineSimilarityLoss\n* distance\\_metric: cosine\\_distance\n* margin: 0.25\n* end\\_to\\_end: False\n* use\\_amp: False\n* warmup\\_proportion: 0.1\n* seed: 42\n* eval\\_max\\_steps: -1\n* load\\_best\\_model\\_at\\_end: False### Training Results### Framework Versions\n\n\n* Python: 3.10.12\n* SetFit: 1.0.3\n* Sentence Transformers: 2.7.0\n* Transformers: 4.40.1\n* PyTorch: 2.2.1+cu121\n* Datasets: 2.19.0\n* Tokenizers: 0.19.1### BibTeX" ]

[ "peft", "safetensors", "arxiv:1910.09700", "base_model:microsoft/Phi-3-mini-128k-instruct", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact", "### Framework versions\n\n- PEFT 0.10.1.dev0" ]

[ "TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-microsoft/Phi-3-mini-128k-instruct #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact", "### Framework versions\n\n- PEFT 0.10.1.dev0" ]

[ 40, 6, 4, 50, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5, 16 ]

[ "TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-microsoft/Phi-3-mini-128k-instruct #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact### Framework versions\n\n- PEFT 0.10.1.dev0" ]

[ "transformers", "safetensors", "gemma", "text-generation", "conversational", "arxiv:2312.11805", "arxiv:2009.03300", "arxiv:1905.07830", "arxiv:1911.11641", "arxiv:1904.09728", "arxiv:1905.10044", "arxiv:1907.10641", "arxiv:1811.00937", "arxiv:1809.02789", "arxiv:1911.01547", "arxiv:1705.03551", "arxiv:2107.03374", "arxiv:2108.07732", "arxiv:2110.14168", "arxiv:2304.06364", "arxiv:2206.04615", "arxiv:1804.06876", "arxiv:2110.08193", "arxiv:2009.11462", "arxiv:2101.11718", "arxiv:1804.09301", "arxiv:2109.07958", "arxiv:2203.09509", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[ "2312.11805", "2009.03300", "1905.07830", "1911.11641", "1904.09728", "1905.10044", "1907.10641", "1811.00937", "1809.02789", "1911.01547", "1705.03551", "2107.03374", "2108.07732", "2110.14168", "2304.06364", "2206.04615", "1804.06876", "2110.08193", "2009.11462", "2101.11718", "1804.09301", "2109.07958", "2203.09509" ]

[]

[ "### Description\n\n\nGemma is a family of lightweight, state-of-the-art open models from Google,\nbuilt from the same research and technology used to create the Gemini models.\nThey are text-to-text, decoder-only large language models, available in English,\nwith open weights, pre-trained variants, and instruction-tuned variants. Gemma\nmodels are well-suited for a variety of text generation tasks, including\nquestion answering, summarization, and reasoning. Their relatively small size\nmakes it possible to deploy them in environments with limited resources such as\na laptop, desktop or your own cloud infrastructure, democratizing access to\nstate of the art AI models and helping foster innovation for everyone.", "### Usage\n\n\nBelow we share some code snippets on how to get quickly started with running the model. First make sure to 'pip install -U transformers', then copy the snippet from the section that is relevant for your usecase.", "#### Fine-tuning the model\n\n\nYou can find fine-tuning scripts and notebook under the 'examples/' directory of 'google/gemma-7b' repository. To adapt it to this model, simply change the model-id to 'google/gemma-7b-it'.\nIn that repository, we provide:\n\n\n* A script to perform Supervised Fine-Tuning (SFT) on UltraChat dataset using QLoRA\n* A script to perform SFT using FSDP on TPU devices\n* A notebook that you can run on a free-tier Google Colab instance to perform SFT on English quotes dataset", "#### Running the model on a CPU\n\n\nAs explained below, we recommend 'torch.bfloat16' as the default dtype. You can use a different precision if necessary.", "#### Running the model on a single / multi GPU", "#### Running the model on a GPU using different precisions\n\n\nThe native weights of this model were exported in 'bfloat16' precision. You can use 'float16', which may be faster on certain hardware, indicating the 'torch\\_dtype' when loading the model. For convenience, the 'float16' revision of the repo contains a copy of the weights already converted to that precision.\n\n\nYou can also use 'float32' if you skip the dtype, but no precision increase will occur (model weights will just be upcasted to 'float32'). See examples below.\n\n\n* *Using 'torch.float16'*\n* *Using 'torch.bfloat16'*\n* *Upcasting to 'torch.float32'*", "#### Quantized Versions through 'bitsandbytes'\n\n\n* *Using 8-bit precision (int8)*\n* *Using 4-bit precision*", "#### Other optimizations\n\n\n* *Flash Attention 2*\n\n\nFirst make sure to install 'flash-attn' in your environment 'pip install flash-attn'", "### Chat Template\n\n\nThe instruction-tuned models use a chat template that must be adhered to for conversational use.\nThe easiest way to apply it is using the tokenizer's built-in chat template, as shown in the following snippet.\n\n\nLet's load the model and apply the chat template to a conversation. In this example, we'll start with a single user interaction:\n\n\nAt this point, the prompt contains the following text:\n\n\nAs you can see, each turn is preceded by a '<start\\_of\\_turn>' delimiter and then the role of the entity\n(either 'user', for content supplied by the user, or 'model' for LLM responses). Turns finish with\nthe '<end\\_of\\_turn>' token.\n\n\nYou can follow this format to build the prompt manually, if you need to do it without the tokenizer's\nchat template.\n\n\nAfter the prompt is ready, generation can be performed like this:", "### Inputs and outputs\n\n\n* Input: Text string, such as a question, a prompt, or a document to be\nsummarized.\n* Output: Generated English-language text in response to the input, such\nas an answer to a question, or a summary of a document.\n\n\nModel Data\n----------\n\n\nData used for model training and how the data was processed.", "### Training Dataset\n\n\nThese models were trained on a dataset of text data that includes a wide variety\nof sources, totaling 6 trillion tokens. Here are the key components:\n\n\n* Web Documents: A diverse collection of web text ensures the model is exposed\nto a broad range of linguistic styles, topics, and vocabulary. Primarily\nEnglish-language content.\n* Code: Exposing the model to code helps it to learn the syntax and patterns of\nprogramming languages, which improves its ability to generate code or\nunderstand code-related questions.\n* Mathematics: Training on mathematical text helps the model learn logical\nreasoning, symbolic representation, and to address mathematical queries.\n\n\nThe combination of these diverse data sources is crucial for training a powerful\nlanguage model that can handle a wide variety of different tasks and text\nformats.", "### Data Preprocessing\n\n\nHere are the key data cleaning and filtering methods applied to the training\ndata:\n\n\n* CSAM Filtering: Rigorous CSAM (Child Sexual Abuse Material) filtering was\napplied at multiple stages in the data preparation process to ensure the\nexclusion of harmful and illegal content\n* Sensitive Data Filtering: As part of making Gemma pre-trained models safe and\nreliable, automated techniques were used to filter out certain personal\ninformation and other sensitive data from training sets.\n* Additional methods: Filtering based on content quality and safely in line with\nour policies.\n\n\nImplementation Information\n--------------------------\n\n\nDetails about the model internals.", "### Hardware\n\n\nGemma was trained using the latest generation of\nTensor Processing Unit (TPU) hardware (TPUv5e).\n\n\nTraining large language models requires significant computational power. TPUs,\ndesigned specifically for matrix operations common in machine learning, offer\nseveral advantages in this domain:\n\n\n* Performance: TPUs are specifically designed to handle the massive computations\ninvolved in training LLMs. They can speed up training considerably compared to\nCPUs.\n* Memory: TPUs often come with large amounts of high-bandwidth memory, allowing\nfor the handling of large models and batch sizes during training. This can\nlead to better model quality.\n* Scalability: TPU Pods (large clusters of TPUs) provide a scalable solution for\nhandling the growing complexity of large foundation models. You can distribute\ntraining across multiple TPU devices for faster and more efficient processing.\n* Cost-effectiveness: In many scenarios, TPUs can provide a more cost-effective\nsolution for training large models compared to CPU-based infrastructure,\nespecially when considering the time and resources saved due to faster\ntraining.\n* These advantages are aligned with\nGoogle's commitments to operate sustainably.", "### Software\n\n\nTraining was done using JAX and ML Pathways.\n\n\nJAX allows researchers to take advantage of the latest generation of hardware,\nincluding TPUs, for faster and more efficient training of large models.\n\n\nML Pathways is Google's latest effort to build artificially intelligent systems\ncapable of generalizing across multiple tasks. This is specially suitable for\nfoundation models, including large language models like\nthese ones.\n\n\nTogether, JAX and ML Pathways are used as described in the\npaper about the Gemini family of models; \"the 'single\ncontroller' programming model of Jax and Pathways allows a single Python\nprocess to orchestrate the entire training run, dramatically simplifying the\ndevelopment workflow.\"\n\n\nEvaluation\n----------\n\n\nModel evaluation metrics and results.", "### Benchmark Results\n\n\nThese models were evaluated against a large collection of different datasets and\nmetrics to cover different aspects of text generation:\n\n\n\nEthics and Safety\n-----------------\n\n\nEthics and safety evaluation approach and results.", "### Evaluation Approach\n\n\nOur evaluation methods include structured evaluations and internal red-teaming\ntesting of relevant content policies. Red-teaming was conducted by a number of\ndifferent teams, each with different goals and human evaluation metrics. These\nmodels were evaluated against a number of different categories relevant to\nethics and safety, including:\n\n\n* Text-to-Text Content Safety: Human evaluation on prompts covering safety\npolicies including child sexual abuse and exploitation, harassment, violence\nand gore, and hate speech.\n* Text-to-Text Representational Harms: Benchmark against relevant academic\ndatasets such as WinoBias and BBQ Dataset.\n* Memorization: Automated evaluation of memorization of training data, including\nthe risk of personally identifiable information exposure.\n* Large-scale harm: Tests for \"dangerous capabilities,\" such as chemical,\nbiological, radiological, and nuclear (CBRN) risks.", "### Evaluation Results\n\n\nThe results of ethics and safety evaluations are within acceptable thresholds\nfor meeting internal policies for categories such as child\nsafety, content safety, representational harms, memorization, large-scale harms.\nOn top of robust internal evaluations, the results of well known safety\nbenchmarks like BBQ, BOLD, Winogender, Winobias, RealToxicity, and TruthfulQA\nare shown here.\n\n\n\nUsage and Limitations\n---------------------\n\n\nThese models have certain limitations that users should be aware of.", "### Intended Usage\n\n\nOpen Large Language Models (LLMs) have a wide range of applications across\nvarious industries and domains. The following list of potential uses is not\ncomprehensive. The purpose of this list is to provide contextual information\nabout the possible use-cases that the model creators considered as part of model\ntraining and development.\n\n\n* Content Creation and Communication\n\t+ Text Generation: These models can be used to generate creative text formats\n\tsuch as poems, scripts, code, marketing copy, and email drafts.\n\t+ Chatbots and Conversational AI: Power conversational interfaces for customer\n\tservice, virtual assistants, or interactive applications.\n\t+ Text Summarization: Generate concise summaries of a text corpus, research\n\tpapers, or reports.\n* Research and Education\n\t+ Natural Language Processing (NLP) Research: These models can serve as a\n\tfoundation for researchers to experiment with NLP techniques, develop\n\talgorithms, and contribute to the advancement of the field.\n\t+ Language Learning Tools: Support interactive language learning experiences,\n\taiding in grammar correction or providing writing practice.\n\t+ Knowledge Exploration: Assist researchers in exploring large bodies of text\n\tby generating summaries or answering questions about specific topics.", "### Limitations\n\n\n* Training Data\n\t+ The quality and diversity of the training data significantly influence the\n\tmodel's capabilities. Biases or gaps in the training data can lead to\n\tlimitations in the model's responses.\n\t+ The scope of the training dataset determines the subject areas the model can\n\thandle effectively.\n* Context and Task Complexity\n\t+ LLMs are better at tasks that can be framed with clear prompts and\n\tinstructions. Open-ended or highly complex tasks might be challenging.\n\t+ A model's performance can be influenced by the amount of context provided\n\t(longer context generally leads to better outputs, up to a certain point).\n* Language Ambiguity and Nuance\n\t+ Natural language is inherently complex. LLMs might struggle to grasp subtle\n\tnuances, sarcasm, or figurative language.\n* Factual Accuracy\n\t+ LLMs generate responses based on information they learned from their\n\ttraining datasets, but they are not knowledge bases. They may generate\n\tincorrect or outdated factual statements.\n* Common Sense\n\t+ LLMs rely on statistical patterns in language. They might lack the ability\n\tto apply common sense reasoning in certain situations.", "### Ethical Considerations and Risks\n\n\nThe development of large language models (LLMs) raises several ethical concerns.\nIn creating an open model, we have carefully considered the following:\n\n\n* Bias and Fairness\n\t+ LLMs trained on large-scale, real-world text data can reflect socio-cultural\n\tbiases embedded in the training material. These models underwent careful\n\tscrutiny, input data pre-processing described and posterior evaluations\n\treported in this card.\n* Misinformation and Misuse\n\t+ LLMs can be misused to generate text that is false, misleading, or harmful.\n\t+ Guidelines are provided for responsible use with the model, see the\n\tResponsible Generative AI Toolkit.\n* Transparency and Accountability:\n\t+ This model card summarizes details on the models' architecture,\n\tcapabilities, limitations, and evaluation processes.\n\t+ A responsibly developed open model offers the opportunity to share\n\tinnovation by making LLM technology accessible to developers and researchers\n\tacross the AI ecosystem.\n\n\nRisks identified and mitigations:\n\n\n* Perpetuation of biases: It's encouraged to perform continuous monitoring\n(using evaluation metrics, human review) and the exploration of de-biasing\ntechniques during model training, fine-tuning, and other use cases.\n* Generation of harmful content: Mechanisms and guidelines for content safety\nare essential. Developers are encouraged to exercise caution and implement\nappropriate content safety safeguards based on their specific product policies\nand application use cases.\n* Misuse for malicious purposes: Technical limitations and developer and\nend-user education can help mitigate against malicious applications of LLMs.\nEducational resources and reporting mechanisms for users to flag misuse are\nprovided. Prohibited uses of Gemma models are outlined in the\nGemma Prohibited Use Policy.\n* Privacy violations: Models were trained on data filtered for removal of PII\n(Personally Identifiable Information). Developers are encouraged to adhere to\nprivacy regulations with privacy-preserving techniques.", "### Benefits\n\n\nAt the time of release, this family of models provides high-performance open\nlarge language model implementations designed from the ground up for Responsible\nAI development compared to similarly sized models.\n\n\nUsing the benchmark evaluation metrics described in this document, these models\nhave shown to provide superior performance to other, comparably-sized open model\nalternatives." ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #conversational #arxiv-2312.11805 #arxiv-2009.03300 #arxiv-1905.07830 #arxiv-1911.11641 #arxiv-1904.09728 #arxiv-1905.10044 #arxiv-1907.10641 #arxiv-1811.00937 #arxiv-1809.02789 #arxiv-1911.01547 #arxiv-1705.03551 #arxiv-2107.03374 #arxiv-2108.07732 #arxiv-2110.14168 #arxiv-2304.06364 #arxiv-2206.04615 #arxiv-1804.06876 #arxiv-2110.08193 #arxiv-2009.11462 #arxiv-2101.11718 #arxiv-1804.09301 #arxiv-2109.07958 #arxiv-2203.09509 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "### Description\n\n\nGemma is a family of lightweight, state-of-the-art open models from Google,\nbuilt from the same research and technology used to create the Gemini models.\nThey are text-to-text, decoder-only large language models, available in English,\nwith open weights, pre-trained variants, and instruction-tuned variants. Gemma\nmodels are well-suited for a variety of text generation tasks, including\nquestion answering, summarization, and reasoning. Their relatively small size\nmakes it possible to deploy them in environments with limited resources such as\na laptop, desktop or your own cloud infrastructure, democratizing access to\nstate of the art AI models and helping foster innovation for everyone.", "### Usage\n\n\nBelow we share some code snippets on how to get quickly started with running the model. First make sure to 'pip install -U transformers', then copy the snippet from the section that is relevant for your usecase.", "#### Fine-tuning the model\n\n\nYou can find fine-tuning scripts and notebook under the 'examples/' directory of 'google/gemma-7b' repository. To adapt it to this model, simply change the model-id to 'google/gemma-7b-it'.\nIn that repository, we provide:\n\n\n* A script to perform Supervised Fine-Tuning (SFT) on UltraChat dataset using QLoRA\n* A script to perform SFT using FSDP on TPU devices\n* A notebook that you can run on a free-tier Google Colab instance to perform SFT on English quotes dataset", "#### Running the model on a CPU\n\n\nAs explained below, we recommend 'torch.bfloat16' as the default dtype. You can use a different precision if necessary.", "#### Running the model on a single / multi GPU", "#### Running the model on a GPU using different precisions\n\n\nThe native weights of this model were exported in 'bfloat16' precision. You can use 'float16', which may be faster on certain hardware, indicating the 'torch\\_dtype' when loading the model. For convenience, the 'float16' revision of the repo contains a copy of the weights already converted to that precision.\n\n\nYou can also use 'float32' if you skip the dtype, but no precision increase will occur (model weights will just be upcasted to 'float32'). See examples below.\n\n\n* *Using 'torch.float16'*\n* *Using 'torch.bfloat16'*\n* *Upcasting to 'torch.float32'*", "#### Quantized Versions through 'bitsandbytes'\n\n\n* *Using 8-bit precision (int8)*\n* *Using 4-bit precision*", "#### Other optimizations\n\n\n* *Flash Attention 2*\n\n\nFirst make sure to install 'flash-attn' in your environment 'pip install flash-attn'", "### Chat Template\n\n\nThe instruction-tuned models use a chat template that must be adhered to for conversational use.\nThe easiest way to apply it is using the tokenizer's built-in chat template, as shown in the following snippet.\n\n\nLet's load the model and apply the chat template to a conversation. In this example, we'll start with a single user interaction:\n\n\nAt this point, the prompt contains the following text:\n\n\nAs you can see, each turn is preceded by a '<start\\_of\\_turn>' delimiter and then the role of the entity\n(either 'user', for content supplied by the user, or 'model' for LLM responses). Turns finish with\nthe '<end\\_of\\_turn>' token.\n\n\nYou can follow this format to build the prompt manually, if you need to do it without the tokenizer's\nchat template.\n\n\nAfter the prompt is ready, generation can be performed like this:", "### Inputs and outputs\n\n\n* Input: Text string, such as a question, a prompt, or a document to be\nsummarized.\n* Output: Generated English-language text in response to the input, such\nas an answer to a question, or a summary of a document.\n\n\nModel Data\n----------\n\n\nData used for model training and how the data was processed.", "### Training Dataset\n\n\nThese models were trained on a dataset of text data that includes a wide variety\nof sources, totaling 6 trillion tokens. Here are the key components:\n\n\n* Web Documents: A diverse collection of web text ensures the model is exposed\nto a broad range of linguistic styles, topics, and vocabulary. Primarily\nEnglish-language content.\n* Code: Exposing the model to code helps it to learn the syntax and patterns of\nprogramming languages, which improves its ability to generate code or\nunderstand code-related questions.\n* Mathematics: Training on mathematical text helps the model learn logical\nreasoning, symbolic representation, and to address mathematical queries.\n\n\nThe combination of these diverse data sources is crucial for training a powerful\nlanguage model that can handle a wide variety of different tasks and text\nformats.", "### Data Preprocessing\n\n\nHere are the key data cleaning and filtering methods applied to the training\ndata:\n\n\n* CSAM Filtering: Rigorous CSAM (Child Sexual Abuse Material) filtering was\napplied at multiple stages in the data preparation process to ensure the\nexclusion of harmful and illegal content\n* Sensitive Data Filtering: As part of making Gemma pre-trained models safe and\nreliable, automated techniques were used to filter out certain personal\ninformation and other sensitive data from training sets.\n* Additional methods: Filtering based on content quality and safely in line with\nour policies.\n\n\nImplementation Information\n--------------------------\n\n\nDetails about the model internals.", "### Hardware\n\n\nGemma was trained using the latest generation of\nTensor Processing Unit (TPU) hardware (TPUv5e).\n\n\nTraining large language models requires significant computational power. TPUs,\ndesigned specifically for matrix operations common in machine learning, offer\nseveral advantages in this domain:\n\n\n* Performance: TPUs are specifically designed to handle the massive computations\ninvolved in training LLMs. They can speed up training considerably compared to\nCPUs.\n* Memory: TPUs often come with large amounts of high-bandwidth memory, allowing\nfor the handling of large models and batch sizes during training. This can\nlead to better model quality.\n* Scalability: TPU Pods (large clusters of TPUs) provide a scalable solution for\nhandling the growing complexity of large foundation models. You can distribute\ntraining across multiple TPU devices for faster and more efficient processing.\n* Cost-effectiveness: In many scenarios, TPUs can provide a more cost-effective\nsolution for training large models compared to CPU-based infrastructure,\nespecially when considering the time and resources saved due to faster\ntraining.\n* These advantages are aligned with\nGoogle's commitments to operate sustainably.", "### Software\n\n\nTraining was done using JAX and ML Pathways.\n\n\nJAX allows researchers to take advantage of the latest generation of hardware,\nincluding TPUs, for faster and more efficient training of large models.\n\n\nML Pathways is Google's latest effort to build artificially intelligent systems\ncapable of generalizing across multiple tasks. This is specially suitable for\nfoundation models, including large language models like\nthese ones.\n\n\nTogether, JAX and ML Pathways are used as described in the\npaper about the Gemini family of models; \"the 'single\ncontroller' programming model of Jax and Pathways allows a single Python\nprocess to orchestrate the entire training run, dramatically simplifying the\ndevelopment workflow.\"\n\n\nEvaluation\n----------\n\n\nModel evaluation metrics and results.", "### Benchmark Results\n\n\nThese models were evaluated against a large collection of different datasets and\nmetrics to cover different aspects of text generation:\n\n\n\nEthics and Safety\n-----------------\n\n\nEthics and safety evaluation approach and results.", "### Evaluation Approach\n\n\nOur evaluation methods include structured evaluations and internal red-teaming\ntesting of relevant content policies. Red-teaming was conducted by a number of\ndifferent teams, each with different goals and human evaluation metrics. These\nmodels were evaluated against a number of different categories relevant to\nethics and safety, including:\n\n\n* Text-to-Text Content Safety: Human evaluation on prompts covering safety\npolicies including child sexual abuse and exploitation, harassment, violence\nand gore, and hate speech.\n* Text-to-Text Representational Harms: Benchmark against relevant academic\ndatasets such as WinoBias and BBQ Dataset.\n* Memorization: Automated evaluation of memorization of training data, including\nthe risk of personally identifiable information exposure.\n* Large-scale harm: Tests for \"dangerous capabilities,\" such as chemical,\nbiological, radiological, and nuclear (CBRN) risks.", "### Evaluation Results\n\n\nThe results of ethics and safety evaluations are within acceptable thresholds\nfor meeting internal policies for categories such as child\nsafety, content safety, representational harms, memorization, large-scale harms.\nOn top of robust internal evaluations, the results of well known safety\nbenchmarks like BBQ, BOLD, Winogender, Winobias, RealToxicity, and TruthfulQA\nare shown here.\n\n\n\nUsage and Limitations\n---------------------\n\n\nThese models have certain limitations that users should be aware of.", "### Intended Usage\n\n\nOpen Large Language Models (LLMs) have a wide range of applications across\nvarious industries and domains. The following list of potential uses is not\ncomprehensive. The purpose of this list is to provide contextual information\nabout the possible use-cases that the model creators considered as part of model\ntraining and development.\n\n\n* Content Creation and Communication\n\t+ Text Generation: These models can be used to generate creative text formats\n\tsuch as poems, scripts, code, marketing copy, and email drafts.\n\t+ Chatbots and Conversational AI: Power conversational interfaces for customer\n\tservice, virtual assistants, or interactive applications.\n\t+ Text Summarization: Generate concise summaries of a text corpus, research\n\tpapers, or reports.\n* Research and Education\n\t+ Natural Language Processing (NLP) Research: These models can serve as a\n\tfoundation for researchers to experiment with NLP techniques, develop\n\talgorithms, and contribute to the advancement of the field.\n\t+ Language Learning Tools: Support interactive language learning experiences,\n\taiding in grammar correction or providing writing practice.\n\t+ Knowledge Exploration: Assist researchers in exploring large bodies of text\n\tby generating summaries or answering questions about specific topics.", "### Limitations\n\n\n* Training Data\n\t+ The quality and diversity of the training data significantly influence the\n\tmodel's capabilities. Biases or gaps in the training data can lead to\n\tlimitations in the model's responses.\n\t+ The scope of the training dataset determines the subject areas the model can\n\thandle effectively.\n* Context and Task Complexity\n\t+ LLMs are better at tasks that can be framed with clear prompts and\n\tinstructions. Open-ended or highly complex tasks might be challenging.\n\t+ A model's performance can be influenced by the amount of context provided\n\t(longer context generally leads to better outputs, up to a certain point).\n* Language Ambiguity and Nuance\n\t+ Natural language is inherently complex. LLMs might struggle to grasp subtle\n\tnuances, sarcasm, or figurative language.\n* Factual Accuracy\n\t+ LLMs generate responses based on information they learned from their\n\ttraining datasets, but they are not knowledge bases. They may generate\n\tincorrect or outdated factual statements.\n* Common Sense\n\t+ LLMs rely on statistical patterns in language. They might lack the ability\n\tto apply common sense reasoning in certain situations.", "### Ethical Considerations and Risks\n\n\nThe development of large language models (LLMs) raises several ethical concerns.\nIn creating an open model, we have carefully considered the following:\n\n\n* Bias and Fairness\n\t+ LLMs trained on large-scale, real-world text data can reflect socio-cultural\n\tbiases embedded in the training material. These models underwent careful\n\tscrutiny, input data pre-processing described and posterior evaluations\n\treported in this card.\n* Misinformation and Misuse\n\t+ LLMs can be misused to generate text that is false, misleading, or harmful.\n\t+ Guidelines are provided for responsible use with the model, see the\n\tResponsible Generative AI Toolkit.\n* Transparency and Accountability:\n\t+ This model card summarizes details on the models' architecture,\n\tcapabilities, limitations, and evaluation processes.\n\t+ A responsibly developed open model offers the opportunity to share\n\tinnovation by making LLM technology accessible to developers and researchers\n\tacross the AI ecosystem.\n\n\nRisks identified and mitigations:\n\n\n* Perpetuation of biases: It's encouraged to perform continuous monitoring\n(using evaluation metrics, human review) and the exploration of de-biasing\ntechniques during model training, fine-tuning, and other use cases.\n* Generation of harmful content: Mechanisms and guidelines for content safety\nare essential. Developers are encouraged to exercise caution and implement\nappropriate content safety safeguards based on their specific product policies\nand application use cases.\n* Misuse for malicious purposes: Technical limitations and developer and\nend-user education can help mitigate against malicious applications of LLMs.\nEducational resources and reporting mechanisms for users to flag misuse are\nprovided. Prohibited uses of Gemma models are outlined in the\nGemma Prohibited Use Policy.\n* Privacy violations: Models were trained on data filtered for removal of PII\n(Personally Identifiable Information). Developers are encouraged to adhere to\nprivacy regulations with privacy-preserving techniques.", "### Benefits\n\n\nAt the time of release, this family of models provides high-performance open\nlarge language model implementations designed from the ground up for Responsible\nAI development compared to similarly sized models.\n\n\nUsing the benchmark evaluation metrics described in this document, these models\nhave shown to provide superior performance to other, comparably-sized open model\nalternatives." ]

[ 278, 141, 53, 131, 39, 14, 163, 34, 37, 204, 80, 157, 145, 228, 151, 58, 179, 125, 231, 218, 374, 70 ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #conversational #arxiv-2312.11805 #arxiv-2009.03300 #arxiv-1905.07830 #arxiv-1911.11641 #arxiv-1904.09728 #arxiv-1905.10044 #arxiv-1907.10641 #arxiv-1811.00937 #arxiv-1809.02789 #arxiv-1911.01547 #arxiv-1705.03551 #arxiv-2107.03374 #arxiv-2108.07732 #arxiv-2110.14168 #arxiv-2304.06364 #arxiv-2206.04615 #arxiv-1804.06876 #arxiv-2110.08193 #arxiv-2009.11462 #arxiv-2101.11718 #arxiv-1804.09301 #arxiv-2109.07958 #arxiv-2203.09509 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n### Description\n\n\nGemma is a family of lightweight, state-of-the-art open models from Google,\nbuilt from the same research and technology used to create the Gemini models.\nThey are text-to-text, decoder-only large language models, available in English,\nwith open weights, pre-trained variants, and instruction-tuned variants. Gemma\nmodels are well-suited for a variety of text generation tasks, including\nquestion answering, summarization, and reasoning. Their relatively small size\nmakes it possible to deploy them in environments with limited resources such as\na laptop, desktop or your own cloud infrastructure, democratizing access to\nstate of the art AI models and helping foster innovation for everyone.### Usage\n\n\nBelow we share some code snippets on how to get quickly started with running the model. First make sure to 'pip install -U transformers', then copy the snippet from the section that is relevant for your usecase.#### Fine-tuning the model\n\n\nYou can find fine-tuning scripts and notebook under the 'examples/' directory of 'google/gemma-7b' repository. To adapt it to this model, simply change the model-id to 'google/gemma-7b-it'.\nIn that repository, we provide:\n\n\n* A script to perform Supervised Fine-Tuning (SFT) on UltraChat dataset using QLoRA\n* A script to perform SFT using FSDP on TPU devices\n* A notebook that you can run on a free-tier Google Colab instance to perform SFT on English quotes dataset#### Running the model on a CPU\n\n\nAs explained below, we recommend 'torch.bfloat16' as the default dtype. You can use a different precision if necessary.#### Running the model on a single / multi GPU#### Running the model on a GPU using different precisions\n\n\nThe native weights of this model were exported in 'bfloat16' precision. You can use 'float16', which may be faster on certain hardware, indicating the 'torch\\_dtype' when loading the model. For convenience, the 'float16' revision of the repo contains a copy of the weights already converted to that precision.\n\n\nYou can also use 'float32' if you skip the dtype, but no precision increase will occur (model weights will just be upcasted to 'float32'). See examples below.\n\n\n* *Using 'torch.float16'*\n* *Using 'torch.bfloat16'*\n* *Upcasting to 'torch.float32'*#### Quantized Versions through 'bitsandbytes'\n\n\n* *Using 8-bit precision (int8)*\n* *Using 4-bit precision*#### Other optimizations\n\n\n* *Flash Attention 2*\n\n\nFirst make sure to install 'flash-attn' in your environment 'pip install flash-attn'### Chat Template\n\n\nThe instruction-tuned models use a chat template that must be adhered to for conversational use.\nThe easiest way to apply it is using the tokenizer's built-in chat template, as shown in the following snippet.\n\n\nLet's load the model and apply the chat template to a conversation. In this example, we'll start with a single user interaction:\n\n\nAt this point, the prompt contains the following text:\n\n\nAs you can see, each turn is preceded by a '<start\\_of\\_turn>' delimiter and then the role of the entity\n(either 'user', for content supplied by the user, or 'model' for LLM responses). Turns finish with\nthe '<end\\_of\\_turn>' token.\n\n\nYou can follow this format to build the prompt manually, if you need to do it without the tokenizer's\nchat template.\n\n\nAfter the prompt is ready, generation can be performed like this:### Inputs and outputs\n\n\n* Input: Text string, such as a question, a prompt, or a document to be\nsummarized.\n* Output: Generated English-language text in response to the input, such\nas an answer to a question, or a summary of a document.\n\n\nModel Data\n----------\n\n\nData used for model training and how the data was processed.### Training Dataset\n\n\nThese models were trained on a dataset of text data that includes a wide variety\nof sources, totaling 6 trillion tokens. Here are the key components:\n\n\n* Web Documents: A diverse collection of web text ensures the model is exposed\nto a broad range of linguistic styles, topics, and vocabulary. Primarily\nEnglish-language content.\n* Code: Exposing the model to code helps it to learn the syntax and patterns of\nprogramming languages, which improves its ability to generate code or\nunderstand code-related questions.\n* Mathematics: Training on mathematical text helps the model learn logical\nreasoning, symbolic representation, and to address mathematical queries.\n\n\nThe combination of these diverse data sources is crucial for training a powerful\nlanguage model that can handle a wide variety of different tasks and text\nformats.### Data Preprocessing\n\n\nHere are the key data cleaning and filtering methods applied to the training\ndata:\n\n\n* CSAM Filtering: Rigorous CSAM (Child Sexual Abuse Material) filtering was\napplied at multiple stages in the data preparation process to ensure the\nexclusion of harmful and illegal content\n* Sensitive Data Filtering: As part of making Gemma pre-trained models safe and\nreliable, automated techniques were used to filter out certain personal\ninformation and other sensitive data from training sets.\n* Additional methods: Filtering based on content quality and safely in line with\nour policies.\n\n\nImplementation Information\n--------------------------\n\n\nDetails about the model internals.### Hardware\n\n\nGemma was trained using the latest generation of\nTensor Processing Unit (TPU) hardware (TPUv5e).\n\n\nTraining large language models requires significant computational power. TPUs,\ndesigned specifically for matrix operations common in machine learning, offer\nseveral advantages in this domain:\n\n\n* Performance: TPUs are specifically designed to handle the massive computations\ninvolved in training LLMs. They can speed up training considerably compared to\nCPUs.\n* Memory: TPUs often come with large amounts of high-bandwidth memory, allowing\nfor the handling of large models and batch sizes during training. This can\nlead to better model quality.\n* Scalability: TPU Pods (large clusters of TPUs) provide a scalable solution for\nhandling the growing complexity of large foundation models. You can distribute\ntraining across multiple TPU devices for faster and more efficient processing.\n* Cost-effectiveness: In many scenarios, TPUs can provide a more cost-effective\nsolution for training large models compared to CPU-based infrastructure,\nespecially when considering the time and resources saved due to faster\ntraining.\n* These advantages are aligned with\nGoogle's commitments to operate sustainably.### Software\n\n\nTraining was done using JAX and ML Pathways.\n\n\nJAX allows researchers to take advantage of the latest generation of hardware,\nincluding TPUs, for faster and more efficient training of large models.\n\n\nML Pathways is Google's latest effort to build artificially intelligent systems\ncapable of generalizing across multiple tasks. This is specially suitable for\nfoundation models, including large language models like\nthese ones.\n\n\nTogether, JAX and ML Pathways are used as described in the\npaper about the Gemini family of models; \"the 'single\ncontroller' programming model of Jax and Pathways allows a single Python\nprocess to orchestrate the entire training run, dramatically simplifying the\ndevelopment workflow.\"\n\n\nEvaluation\n----------\n\n\nModel evaluation metrics and results.### Benchmark Results\n\n\nThese models were evaluated against a large collection of different datasets and\nmetrics to cover different aspects of text generation:\n\n\n\nEthics and Safety\n-----------------\n\n\nEthics and safety evaluation approach and results.### Evaluation Approach\n\n\nOur evaluation methods include structured evaluations and internal red-teaming\ntesting of relevant content policies. Red-teaming was conducted by a number of\ndifferent teams, each with different goals and human evaluation metrics. These\nmodels were evaluated against a number of different categories relevant to\nethics and safety, including:\n\n\n* Text-to-Text Content Safety: Human evaluation on prompts covering safety\npolicies including child sexual abuse and exploitation, harassment, violence\nand gore, and hate speech.\n* Text-to-Text Representational Harms: Benchmark against relevant academic\ndatasets such as WinoBias and BBQ Dataset.\n* Memorization: Automated evaluation of memorization of training data, including\nthe risk of personally identifiable information exposure.\n* Large-scale harm: Tests for \"dangerous capabilities,\" such as chemical,\nbiological, radiological, and nuclear (CBRN) risks.### Evaluation Results\n\n\nThe results of ethics and safety evaluations are within acceptable thresholds\nfor meeting internal policies for categories such as child\nsafety, content safety, representational harms, memorization, large-scale harms.\nOn top of robust internal evaluations, the results of well known safety\nbenchmarks like BBQ, BOLD, Winogender, Winobias, RealToxicity, and TruthfulQA\nare shown here.\n\n\n\nUsage and Limitations\n---------------------\n\n\nThese models have certain limitations that users should be aware of.### Intended Usage\n\n\nOpen Large Language Models (LLMs) have a wide range of applications across\nvarious industries and domains. The following list of potential uses is not\ncomprehensive. The purpose of this list is to provide contextual information\nabout the possible use-cases that the model creators considered as part of model\ntraining and development.\n\n\n* Content Creation and Communication\n\t+ Text Generation: These models can be used to generate creative text formats\n\tsuch as poems, scripts, code, marketing copy, and email drafts.\n\t+ Chatbots and Conversational AI: Power conversational interfaces for customer\n\tservice, virtual assistants, or interactive applications.\n\t+ Text Summarization: Generate concise summaries of a text corpus, research\n\tpapers, or reports.\n* Research and Education\n\t+ Natural Language Processing (NLP) Research: These models can serve as a\n\tfoundation for researchers to experiment with NLP techniques, develop\n\talgorithms, and contribute to the advancement of the field.\n\t+ Language Learning Tools: Support interactive language learning experiences,\n\taiding in grammar correction or providing writing practice.\n\t+ Knowledge Exploration: Assist researchers in exploring large bodies of text\n\tby generating summaries or answering questions about specific topics.### Limitations\n\n\n* Training Data\n\t+ The quality and diversity of the training data significantly influence the\n\tmodel's capabilities. Biases or gaps in the training data can lead to\n\tlimitations in the model's responses.\n\t+ The scope of the training dataset determines the subject areas the model can\n\thandle effectively.\n* Context and Task Complexity\n\t+ LLMs are better at tasks that can be framed with clear prompts and\n\tinstructions. Open-ended or highly complex tasks might be challenging.\n\t+ A model's performance can be influenced by the amount of context provided\n\t(longer context generally leads to better outputs, up to a certain point).\n* Language Ambiguity and Nuance\n\t+ Natural language is inherently complex. LLMs might struggle to grasp subtle\n\tnuances, sarcasm, or figurative language.\n* Factual Accuracy\n\t+ LLMs generate responses based on information they learned from their\n\ttraining datasets, but they are not knowledge bases. They may generate\n\tincorrect or outdated factual statements.\n* Common Sense\n\t+ LLMs rely on statistical patterns in language. They might lack the ability\n\tto apply common sense reasoning in certain situations.### Ethical Considerations and Risks\n\n\nThe development of large language models (LLMs) raises several ethical concerns.\nIn creating an open model, we have carefully considered the following:\n\n\n* Bias and Fairness\n\t+ LLMs trained on large-scale, real-world text data can reflect socio-cultural\n\tbiases embedded in the training material. These models underwent careful\n\tscrutiny, input data pre-processing described and posterior evaluations\n\treported in this card.\n* Misinformation and Misuse\n\t+ LLMs can be misused to generate text that is false, misleading, or harmful.\n\t+ Guidelines are provided for responsible use with the model, see the\n\tResponsible Generative AI Toolkit.\n* Transparency and Accountability:\n\t+ This model card summarizes details on the models' architecture,\n\tcapabilities, limitations, and evaluation processes.\n\t+ A responsibly developed open model offers the opportunity to share\n\tinnovation by making LLM technology accessible to developers and researchers\n\tacross the AI ecosystem.\n\n\nRisks identified and mitigations:\n\n\n* Perpetuation of biases: It's encouraged to perform continuous monitoring\n(using evaluation metrics, human review) and the exploration of de-biasing\ntechniques during model training, fine-tuning, and other use cases.\n* Generation of harmful content: Mechanisms and guidelines for content safety\nare essential. Developers are encouraged to exercise caution and implement\nappropriate content safety safeguards based on their specific product policies\nand application use cases.\n* Misuse for malicious purposes: Technical limitations and developer and\nend-user education can help mitigate against malicious applications of LLMs.\nEducational resources and reporting mechanisms for users to flag misuse are\nprovided. Prohibited uses of Gemma models are outlined in the\nGemma Prohibited Use Policy.\n* Privacy violations: Models were trained on data filtered for removal of PII\n(Personally Identifiable Information). Developers are encouraged to adhere to\nprivacy regulations with privacy-preserving techniques.### Benefits\n\n\nAt the time of release, this family of models provides high-performance open\nlarge language model implementations designed from the ground up for Responsible\nAI development compared to similarly sized models.\n\n\nUsing the benchmark evaluation metrics described in this document, these models\nhave shown to provide superior performance to other, comparably-sized open model\nalternatives." ]

[ "transformers", "gguf", "safety", "en", "dataset:vicgalle/configurable-system-prompt-multitask", "base_model:vicgalle/Configurable-Hermes-2-Pro-Llama-3-8B", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #safety #en #dataset-vicgalle/configurable-system-prompt-multitask #base_model-vicgalle/Configurable-Hermes-2-Pro-Llama-3-8B #license-apache-2.0 #endpoints_compatible #region-us \n" ]

[ 75 ]

[ "TAGS\n#transformers #gguf #safety #en #dataset-vicgalle/configurable-system-prompt-multitask #base_model-vicgalle/Configurable-Hermes-2-Pro-Llama-3-8B #license-apache-2.0 #endpoints_compatible #region-us \n" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:microsoft/phi-2", "license:mit", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 16\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 2\n* num\\_epochs: 10\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.1\n* Pytorch 2.3.0+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-microsoft/phi-2 #license-mit #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 16\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 2\n* num\\_epochs: 10\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.1\n* Pytorch 2.3.0+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ 32, 151, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-microsoft/phi-2 #license-mit #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 16\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 2\n* num\\_epochs: 10\n* mixed\\_precision\\_training: Native AMP### Training results### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.1\n* Pytorch 2.3.0+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "llama", "text-generation", "conversational", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[]

[]

[]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n" ]

[ 41 ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n" ]

[ "transformers", "gguf", "en", "base_model:athirdpath/Llama-3-11b-Instruct", "license:llama3", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #en #base_model-athirdpath/Llama-3-11b-Instruct #license-llama3 #endpoints_compatible #region-us \n" ]

[ 44 ]

[ "TAGS\n#transformers #gguf #en #base_model-athirdpath/Llama-3-11b-Instruct #license-llama3 #endpoints_compatible #region-us \n" ]

[ "transformers", "safetensors", "llama", "text-generation", "conversational", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "8-bit", "region:us" ]

[]

[]

[]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #8-bit #region-us \n" ]

[ 41 ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #8-bit #region-us \n" ]

[ "transformers", "gguf", "llama-cpp", "gguf-my-repo", "endpoints_compatible", "region:us" ]

[]

[]

[ "# NikolayKozloff/Boreas-7B-Q8_0-GGUF\nThis model was converted to GGUF format from 'yhavinga/Boreas-7B' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "TAGS\n#transformers #gguf #llama-cpp #gguf-my-repo #endpoints_compatible #region-us \n", "# NikolayKozloff/Boreas-7B-Q8_0-GGUF\nThis model was converted to GGUF format from 'yhavinga/Boreas-7B' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ 31, 75, 52 ]

[ "TAGS\n#transformers #gguf #llama-cpp #gguf-my-repo #endpoints_compatible #region-us \n# NikolayKozloff/Boreas-7B-Q8_0-GGUF\nThis model was converted to GGUF format from 'yhavinga/Boreas-7B' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "gguf", "region:us" ]

[]

[]

[]

[ "TAGS\n#gguf #region-us \n" ]

[ 9 ]

[ "TAGS\n#gguf #region-us \n" ]

[ "peft", "safetensors", "arxiv:1910.09700", "base_model:BramVanroy/fietje-2b-chat", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact", "### Framework versions\n\n- PEFT 0.10.0" ]

[ "TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-BramVanroy/fietje-2b-chat #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact", "### Framework versions\n\n- PEFT 0.10.0" ]

[ 39, 6, 4, 50, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5, 13 ]

[ "TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-BramVanroy/fietje-2b-chat #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact### Framework versions\n\n- PEFT 0.10.0" ]

[ "en", "license:apache-2.0", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#en #license-apache-2.0 #region-us \n" ]

[ 15 ]

[ "TAGS\n#en #license-apache-2.0 #region-us \n" ]

[ "transformers", "safetensors", "phi", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #phi #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 46, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #phi #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "safetensors", "gemma", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 46, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "safetensors", "gpt_neox", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #gpt_neox #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 47, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #gpt_neox #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "safetensors", "gpt_neox", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #gpt_neox #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 47, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #gpt_neox #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "safetensors", "mistral", "text-generation", "merge", "mergekit", "lazymergekit", "OpenPipe/mistral-ft-optimized-1218", "mlabonne/NeuralHermes-2.5-Mistral-7B", "base_model:OpenPipe/mistral-ft-optimized-1218", "base_model:mlabonne/NeuralHermes-2.5-Mistral-7B", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# hermesoptimesd-7B-slerp\n\nhermesoptimesd-7B-slerp is a merge of the following models using LazyMergekit:\n* OpenPipe/mistral-ft-optimized-1218\n* mlabonne/NeuralHermes-2.5-Mistral-7B", "## Configuration", "## Usage" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #merge #mergekit #lazymergekit #OpenPipe/mistral-ft-optimized-1218 #mlabonne/NeuralHermes-2.5-Mistral-7B #base_model-OpenPipe/mistral-ft-optimized-1218 #base_model-mlabonne/NeuralHermes-2.5-Mistral-7B #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# hermesoptimesd-7B-slerp\n\nhermesoptimesd-7B-slerp is a merge of the following models using LazyMergekit:\n* OpenPipe/mistral-ft-optimized-1218\n* mlabonne/NeuralHermes-2.5-Mistral-7B", "## Configuration", "## Usage" ]

[ 118, 69, 3, 3 ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #merge #mergekit #lazymergekit #OpenPipe/mistral-ft-optimized-1218 #mlabonne/NeuralHermes-2.5-Mistral-7B #base_model-OpenPipe/mistral-ft-optimized-1218 #base_model-mlabonne/NeuralHermes-2.5-Mistral-7B #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# hermesoptimesd-7B-slerp\n\nhermesoptimesd-7B-slerp is a merge of the following models using LazyMergekit:\n* OpenPipe/mistral-ft-optimized-1218\n* mlabonne/NeuralHermes-2.5-Mistral-7B## Configuration## Usage" ]

[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 26, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

[]

[]

[ "# PPO Agent playing LunarLander-v2\nThis is a trained model of a PPO agent playing LunarLander-v2\nusing the stable-baselines3 library.", "## Usage (with Stable-baselines3)\nTODO: Add your code" ]

[ "TAGS\n#stable-baselines3 #LunarLander-v2 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us \n", "# PPO Agent playing LunarLander-v2\nThis is a trained model of a PPO agent playing LunarLander-v2\nusing the stable-baselines3 library.", "## Usage (with Stable-baselines3)\nTODO: Add your code" ]

[ 31, 35, 17 ]

[ "TAGS\n#stable-baselines3 #LunarLander-v2 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us \n# PPO Agent playing LunarLander-v2\nThis is a trained model of a PPO agent playing LunarLander-v2\nusing the stable-baselines3 library.## Usage (with Stable-baselines3)\nTODO: Add your code" ]

[ "transformers", "safetensors", "llama", "feature-extraction", "arxiv:1910.09700", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID\nAidaCoder is a fine-tuned generative text models based on Code Llama 7b model built for testing purposes.", "## Model Details", "### Model Description\nModel capabilities:\n\n Code completion.\n Infilling.\n Instructions / chat.\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: [kantobro]\n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: [ A custom commercial license is available at: URL\n- Finetuned from model [optional]: [codellama/CodeLlama-7b-Instruct-hf]", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure\n\nDataset: aida_stack_dataset", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #llama #feature-extraction #arxiv-1910.09700 #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID\nAidaCoder is a fine-tuned generative text models based on Code Llama 7b model built for testing purposes.", "## Model Details", "### Model Description\nModel capabilities:\n\n Code completion.\n Infilling.\n Instructions / chat.\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: [kantobro]\n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: [ A custom commercial license is available at: URL\n- Finetuned from model [optional]: [codellama/CodeLlama-7b-Instruct-hf]", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure\n\nDataset: aida_stack_dataset", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 39, 31, 4, 123, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 15, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #llama #feature-extraction #arxiv-1910.09700 #endpoints_compatible #text-generation-inference #region-us \n# Model Card for Model ID\nAidaCoder is a fine-tuned generative text models based on Code Llama 7b model built for testing purposes.## Model Details### Model Description\nModel capabilities:\n\n Code completion.\n Infilling.\n Instructions / chat.\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: [kantobro]\n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: [ A custom commercial license is available at: URL\n- Finetuned from model [optional]: [codellama/CodeLlama-7b-Instruct-hf]### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure\n\nDataset: aida_stack_dataset#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "safetensors", "llama", "text-generation", "text-generation-inference", "unsloth", "trl", "sft", "en", "base_model:unsloth/llama-3-8b-bnb-4bit", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: hakankenar\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #text-generation-inference #unsloth #trl #sft #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: hakankenar\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ 76, 81 ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #text-generation-inference #unsloth #trl #sft #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n# Uploaded model\n\n- Developed by: hakankenar\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "transformers", "safetensors", "gpt_neox", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #gpt_neox #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 47, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #gpt_neox #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "peft", "safetensors", "arxiv:1910.09700", "base_model:meta-llama/Meta-Llama-3-70B-Instruct", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact", "### Framework versions\n\n- PEFT 0.10.0" ]

[ "TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-meta-llama/Meta-Llama-3-70B-Instruct #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact", "### Framework versions\n\n- PEFT 0.10.0" ]

[ 44, 6, 4, 50, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5, 13 ]

[ "TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-meta-llama/Meta-Llama-3-70B-Instruct #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact### Framework versions\n\n- PEFT 0.10.0" ]

[ "transformers", "safetensors", "whisper", "automatic-speech-recognition", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #whisper #automatic-speech-recognition #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 34, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #whisper #automatic-speech-recognition #arxiv-1910.09700 #endpoints_compatible #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "safetensors", "phi3", "text-generation", "trl", "sft", "conversational", "custom_code", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #phi3 #text-generation #trl #sft #conversational #custom_code #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 51, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #phi3 #text-generation #trl #sft #conversational #custom_code #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "pytorch", "roberta", "text-classification", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[]

[ "TAGS\n#transformers #pytorch #roberta #text-classification #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n" ]

[ 36 ]

[ "TAGS\n#transformers #pytorch #roberta #text-classification #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n" ]

[ "transformers", "gguf", "en", "dataset:aerdincdal/CBDDO-LLM-DB-V1", "base_model:aerdincdal/CBDDO-LLM-8B-Instruct-v1", "license:mit", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #en #dataset-aerdincdal/CBDDO-LLM-DB-V1 #base_model-aerdincdal/CBDDO-LLM-8B-Instruct-v1 #license-mit #endpoints_compatible #region-us \n" ]

[ 67 ]

[ "TAGS\n#transformers #gguf #en #dataset-aerdincdal/CBDDO-LLM-DB-V1 #base_model-aerdincdal/CBDDO-LLM-8B-Instruct-v1 #license-mit #endpoints_compatible #region-us \n" ]

[ "transformers", "safetensors", "gpt_neox", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #gpt_neox #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 47, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #gpt_neox #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "safetensors", "gpt_neox", "text-generation", "generated_from_trainer", "base_model:EleutherAI/pythia-31m", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# virus_pythia_31_1024_cross_entropy\n\nThis model is a fine-tuned version of EleutherAI/pythia-31m on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 40\n- eval_batch_size: 40\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 10\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #gpt_neox #text-generation #generated_from_trainer #base_model-EleutherAI/pythia-31m #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# virus_pythia_31_1024_cross_entropy\n\nThis model is a fine-tuned version of EleutherAI/pythia-31m on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 40\n- eval_batch_size: 40\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 10\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ 59, 41, 7, 9, 9, 4, 106, 5, 44 ]

[ "TAGS\n#transformers #safetensors #gpt_neox #text-generation #generated_from_trainer #base_model-EleutherAI/pythia-31m #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# virus_pythia_31_1024_cross_entropy\n\nThis model is a fine-tuned version of EleutherAI/pythia-31m on an unknown dataset.## Model description\n\nMore information needed## Intended uses & limitations\n\nMore information needed## Training and evaluation data\n\nMore information needed## Training procedure### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 40\n- eval_batch_size: 40\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 10\n- num_epochs: 1### Training results### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "peft", "safetensors", "arxiv:1910.09700", "base_model:deepseek-ai/deepseek-coder-6.7b-base", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact", "### Framework versions\n\n- PEFT 0.10.0" ]

[ "TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-deepseek-ai/deepseek-coder-6.7b-base #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact", "### Framework versions\n\n- PEFT 0.10.0" ]

[ 46, 6, 4, 50, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5, 13 ]

[ "TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-deepseek-ai/deepseek-coder-6.7b-base #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact### Framework versions\n\n- PEFT 0.10.0" ]

[ "transformers", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 22, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #arxiv-1910.09700 #endpoints_compatible #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "gguf", "facebook", "meta", "pytorch", "llama", "llama-3", "en", "base_model:NousResearch/Meta-Llama-3-8B-Instruct", "license:other", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #facebook #meta #pytorch #llama #llama-3 #en #base_model-NousResearch/Meta-Llama-3-8B-Instruct #license-other #endpoints_compatible #region-us \n" ]

[ 62 ]

[ "TAGS\n#transformers #gguf #facebook #meta #pytorch #llama #llama-3 #en #base_model-NousResearch/Meta-Llama-3-8B-Instruct #license-other #endpoints_compatible #region-us \n" ]

[ "transformers", "gguf", "en", "dataset:mc4", "dataset:wikipedia", "dataset:EleutherAI/pile", "dataset:oscar-corpus/colossal-oscar-1.0", "dataset:cc100", "base_model:rinna/llama-3-youko-8b", "license:llama3", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #en #dataset-mc4 #dataset-wikipedia #dataset-EleutherAI/pile #dataset-oscar-corpus/colossal-oscar-1.0 #dataset-cc100 #base_model-rinna/llama-3-youko-8b #license-llama3 #endpoints_compatible #region-us \n" ]

[ 84 ]

[ "TAGS\n#transformers #gguf #en #dataset-mc4 #dataset-wikipedia #dataset-EleutherAI/pile #dataset-oscar-corpus/colossal-oscar-1.0 #dataset-cc100 #base_model-rinna/llama-3-youko-8b #license-llama3 #endpoints_compatible #region-us \n" ]

[ "gguf", "llama", "not-for-all-audiences", "nsfw", "rp", "roleplay", "text-generation", "en", "license:apache-2.0", "region:us" ]

[]

[ "en" ]

[ "### Prompt format: Alpaca.\n''\"You are now in roleplay chat mode. Engage in an endless chat, always with a creative response. Follow lengths very precisely and create paragraphs accurately. Always wait your turn, next actions and responses. Your internal thoughts are wrapped with ' marks.\"''\n\nUser Message Prefix = ### Input:\n\nAssistant Message Prefix = ### Response:\n\nSystem Message Prefix = ### Instruction:\n\nTurn on \"Include Names\"", "### Example:\n\n!example" ]

[ "TAGS\n#gguf #llama #not-for-all-audiences #nsfw #rp #roleplay #text-generation #en #license-apache-2.0 #region-us \n", "### Prompt format: Alpaca.\n''\"You are now in roleplay chat mode. Engage in an endless chat, always with a creative response. Follow lengths very precisely and create paragraphs accurately. Always wait your turn, next actions and responses. Your internal thoughts are wrapped with ' marks.\"''\n\nUser Message Prefix = ### Input:\n\nAssistant Message Prefix = ### Response:\n\nSystem Message Prefix = ### Instruction:\n\nTurn on \"Include Names\"", "### Example:\n\n!example" ]

[ 44, 99, 7 ]

[ "TAGS\n#gguf #llama #not-for-all-audiences #nsfw #rp #roleplay #text-generation #en #license-apache-2.0 #region-us \n### Prompt format: Alpaca.\n''\"You are now in roleplay chat mode. Engage in an endless chat, always with a creative response. Follow lengths very precisely and create paragraphs accurately. Always wait your turn, next actions and responses. Your internal thoughts are wrapped with ' marks.\"''\n\nUser Message Prefix = ### Input:\n\nAssistant Message Prefix = ### Response:\n\nSystem Message Prefix = ### Instruction:\n\nTurn on \"Include Names\"### Example:\n\n!example" ]

[ "transformers", "safetensors", "gpt_neox", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #gpt_neox #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 47, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #gpt_neox #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "safetensors", "llama", "text-generation", "mergekit", "merge", "conversational", "arxiv:2403.19522", "base_model:VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct", "base_model:DeepMount00/Llama-3-8b-Ita", "base_model:mlabonne/ChimeraLlama-3-8B-v3", "base_model:nbeerbower/llama-3-slerp-kraut-dragon-8B", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "2403.19522" ]

[]

[ "# llama-3-wissenschaft-8B\n\nThis model is based on Llama-3-8b, and is governed by META LLAMA 3 COMMUNITY LICENSE AGREEMENT\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the Model Stock merge method using nbeerbower/llama-3-slerp-kraut-dragon-8B as a base.", "### Models Merged\n\nThe following models were included in the merge:\n* VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct\n* DeepMount00/Llama-3-8b-Ita\n* mlabonne/ChimeraLlama-3-8B-v3", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #mergekit #merge #conversational #arxiv-2403.19522 #base_model-VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct #base_model-DeepMount00/Llama-3-8b-Ita #base_model-mlabonne/ChimeraLlama-3-8B-v3 #base_model-nbeerbower/llama-3-slerp-kraut-dragon-8B #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# llama-3-wissenschaft-8B\n\nThis model is based on Llama-3-8b, and is governed by META LLAMA 3 COMMUNITY LICENSE AGREEMENT\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the Model Stock merge method using nbeerbower/llama-3-slerp-kraut-dragon-8B as a base.", "### Models Merged\n\nThe following models were included in the merge:\n* VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct\n* DeepMount00/Llama-3-8b-Ita\n* mlabonne/ChimeraLlama-3-8B-v3", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ 150, 51, 4, 42, 69, 16 ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #mergekit #merge #conversational #arxiv-2403.19522 #base_model-VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct #base_model-DeepMount00/Llama-3-8b-Ita #base_model-mlabonne/ChimeraLlama-3-8B-v3 #base_model-nbeerbower/llama-3-slerp-kraut-dragon-8B #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# llama-3-wissenschaft-8B\n\nThis model is based on Llama-3-8b, and is governed by META LLAMA 3 COMMUNITY LICENSE AGREEMENT\n\nThis is a merge of pre-trained language models created using mergekit.## Merge Details### Merge Method\n\nThis model was merged using the Model Stock merge method using nbeerbower/llama-3-slerp-kraut-dragon-8B as a base.### Models Merged\n\nThe following models were included in the merge:\n* VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct\n* DeepMount00/Llama-3-8b-Ita\n* mlabonne/ChimeraLlama-3-8B-v3### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "transformers", "safetensors", "gpt_neox", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #gpt_neox #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 47, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #gpt_neox #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "gguf", "quantized", "2-bit", "3-bit", "4-bit", "5-bit", "6-bit", "8-bit", "GGUF", "text-generation", "llama", "llama-3", "base_model:MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4", "region:us" ]

[]

[]

[ "# MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4-GGUF\n- Model creator: MaziyarPanahi\n- Original model: MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4", "## Description\nMaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4-GGUF contains GGUF format model files for MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4.\n\nIMPORTANT: There is no need to merge the splits. By now, most libraries support automatically loading the splits by simply pointing to the first one.", "### About GGUF\n\nGGUF is a new format introduced by the URL team on August 21st 2023. It is a replacement for GGML, which is no longer supported by URL.\n\nHere is an incomplete list of clients and libraries that are known to support GGUF:\n\n* URL. The source project for GGUF. Offers a CLI and a server option.\n* llama-cpp-python, a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.\n* LM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.\n* text-generation-webui, the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.\n* KoboldCpp, a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.\n* GPT4All, a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.\n* LoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.\n* URL, an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.\n* candle, a Rust ML framework with a focus on performance, including GPU support, and ease of use.\n* ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.", "## Special thanks\n\n Special thanks to Georgi Gerganov and the whole team working on URL for making all of this possible." ]

[ "TAGS\n#gguf #quantized #2-bit #3-bit #4-bit #5-bit #6-bit #8-bit #GGUF #text-generation #llama #llama-3 #base_model-MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4 #region-us \n", "# MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4-GGUF\n- Model creator: MaziyarPanahi\n- Original model: MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4", "## Description\nMaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4-GGUF contains GGUF format model files for MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4.\n\nIMPORTANT: There is no need to merge the splits. By now, most libraries support automatically loading the splits by simply pointing to the first one.", "### About GGUF\n\nGGUF is a new format introduced by the URL team on August 21st 2023. It is a replacement for GGML, which is no longer supported by URL.\n\nHere is an incomplete list of clients and libraries that are known to support GGUF:\n\n* URL. The source project for GGUF. Offers a CLI and a server option.\n* llama-cpp-python, a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.\n* LM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.\n* text-generation-webui, the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.\n* KoboldCpp, a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.\n* GPT4All, a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.\n* LoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.\n* URL, an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.\n* candle, a Rust ML framework with a focus on performance, including GPU support, and ease of use.\n* ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.", "## Special thanks\n\n Special thanks to Georgi Gerganov and the whole team working on URL for making all of this possible." ]

[ 82, 69, 95, 392, 27 ]

[ "TAGS\n#gguf #quantized #2-bit #3-bit #4-bit #5-bit #6-bit #8-bit #GGUF #text-generation #llama #llama-3 #base_model-MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4 #region-us \n# MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4-GGUF\n- Model creator: MaziyarPanahi\n- Original model: MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4## Description\nMaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4-GGUF contains GGUF format model files for MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4.\n\nIMPORTANT: There is no need to merge the splits. By now, most libraries support automatically loading the splits by simply pointing to the first one.### About GGUF\n\nGGUF is a new format introduced by the URL team on August 21st 2023. It is a replacement for GGML, which is no longer supported by URL.\n\nHere is an incomplete list of clients and libraries that are known to support GGUF:\n\n* URL. The source project for GGUF. Offers a CLI and a server option.\n* llama-cpp-python, a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.\n* LM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.\n* text-generation-webui, the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.\n* KoboldCpp, a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.\n* GPT4All, a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.\n* LoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.\n* URL, an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.\n* candle, a Rust ML framework with a focus on performance, including GPU support, and ease of use.\n* ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.## Special thanks\n\n Special thanks to Georgi Gerganov and the whole team working on URL for making all of this possible." ]

[ "transformers", "safetensors", "gpt_neox", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #gpt_neox #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 47, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #gpt_neox #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]