chat template

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:871f6470024f7297fbb1630717ecdf23525b8245ee058dbd88ed4b0e874fe608
+oid sha256:f75d3d5a1426575413c2ae58315ef65e9c4d6d4744e0168f03a10221dddf90e1
 size 4976764208

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1f8d99a3af19e06016bdc40fc1e3c87f1438affde99e5f0a3748929a4f3bd59
+oid sha256:7f502d7179f1173b417b0f6c949570bf3ad61c705103a2cacf5000f96a9b1a63
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba7e79cec703a797f2642bce11fe734a201a08538f68021378f4ed8773a2dbc6
+oid sha256:b4555ecb70dc28e06eabfafc6a883d0e1050526ba4b44e469abefd4c6955ac42
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c1f832c970baf4f6101d08145737fcb38d3bb0780a45bb975612b6b38305b42
+oid sha256:0def642cf11d2c475ae08f43f79d80e597d71589e49f3dc63f6dfaf94095d4e3
 size 1168204344

tokenizer_config.json

@@ -2114,7 +2114,7 @@
     }
   },
   "bos_token": "<|begin_of_text|>",
-  "chat_template": "<|system|>\nGiven a scenario based on an interaction between an AI language model and its user, who has the capabilities of an everyday person, analyze the benefits of the scenario on all stakeholders without additional explanations in plain text. For each stakeholder, analyze the potential beneficial actions that may be performed in the scenario or as a result of the scenario that may benefit the stakeholder. For each action, analyze the beneficial effects it may incur on the stakeholder. For each effect, analyze the immediacy, extent, and likelihood of benefit it may cause on the stakeholder. Return your output in a JSON format defined below for each entry. *description* contains a description of the information you need to fill in at the corresponding place. Only return the JSON string. Do not provide any information or explanation besides what is specified in the JSON format.\n\nThe JSON format is:\n[\n{\n\"stakeholder\": *fill in with an individual, group, community, or entity in society that may be affected as a result of this scenario*,\n\"benefits\": [\n{\n\"action\": *fill in with a beneficial action that may be performed in the scenario or as a result of the scenario that may benefit this stakeholder*,\n\"effects\": [\n{\"effect\": *fill in with the number and name of a beneficial effect category defined in the given taxonomy of beneficial effects that this beneficial action may cause on this stakeholder given this scenario*,\n\"immediacy\": *true if the beneficial effect is short-term or immediate, and false if the beneficial effect is long-term or downstream*,\n\"extent\": *the extent to which the stakeholder may benefit from this beneficial effect (minor, significant, substantial, or major, as defined below)*,\n\"likelihood\": *the likelihood that the stakeholder may benefit from this beneficial effect (low, medium, or high, as defined below)*\n}, ... *List as many distinct and valid beneficial effects as you can*\n]\n}, ... *List as many more distinct and valid beneficial actions as you can*\n]\n}, ... *list as many distinct and valid stakeholders as you can*]\n\nThe taxonomy of beneficial effects is defined as:\n#Physical benefit#\n1. Prevention of death\n2. Physical health benefits\n\n#Psychological benefit#\n3. Transient emotional changes\n4. Persistent emotional state changes\n\n#Social benefit#\n5. Social gains\n\n#Property benefit#\n6. Physical property gains\n7. Financial property gains\n8. Intellectual property gains\n\n#Liberty benefit#\n9. Freedom and agency benefits\n10. Gain of accurate information access\n\n#Collective benefit#\n11. Institutional benefits \n12. Public resource gains\n13. Societal order maintenance\n\n#Ecological benefit#\n14. Benefits to non-human animals\n15. Ecosystem benefitsThe extents of benefit are defined as:\nMinor: beneficial consequences are isolated, temporary, noticeable but have limited impact on the overall situation or outcome; the stakeholder may experience a limited enhancement of functional ability and/or quality of life.\nSignificant: beneficial consequences are widespread, significant, noticeable, and can lead to meaningful improvements and tangible impacts; the stakeholder may experience significant improvement in functional ability and/or quality of life.\nSubstantial: beneficial consequences are extensive, important, and can lead to considerable positive changes and profound impact on the situation or outcome; the stakeholder may experience substantial enhancement of functional ability and/or quality of life.\n Major: beneficial consequences are systemic, persistent, critical, highly impactful, and can lead to transformative changes that significantly alter the courses of events; the stakeholder may experience a profound improvement in functional ability and/or quality of life.\nThe likelihoods of benefits are defined as:\nLow: unlikely to occur, but not impossible. Rare under normal circumstances; less than 30% chance of occurring.\nMedium: possible occurrence, might happen under certain conditions or occasionally; between 30% and 70% chance of occurring.\nHigh: likely to occur, happens frequently or under normal conditions; above 70% chance of occurring.\n\n<|user|>\nIn a conversation between an AI language model and a user, the user prompts the AI language model: \"{{ messages }}\" The AI language model complies with the request by providing a helpful, informative answer with specific details and/or step-by-step guidance.\n<|assistant|>\n",
+  "chat_template": "<|system|>\nGiven a scenario based on an interaction between an AI language model and its user, who has the capabilities of an everyday person, analyze the benefits of the scenario on all stakeholders without additional explanations in plain text. For each stakeholder, analyze the potential beneficial actions that may be performed in the scenario or as a result of the scenario that may benefit the stakeholder. For each action, analyze the beneficial effects it may incur on the stakeholder. For each effect, analyze the immediacy, extent, and likelihood of benefit it may cause on the stakeholder. Return your output in a JSON format defined below for each entry. *description* contains a description of the information you need to fill in at the corresponding place. Only return the JSON string. Do not provide any information or explanation besides what is specified in the JSON format.\n\nThe JSON format is:\n[{\"stakeholder\": *fill in with an individual, group, community, or entity in society that may be affected as a result of this scenario*,\"benefits\": [{\"action\": *fill in with a beneficial action that may be performed in the scenario or as a result of the scenario that may benefit this stakeholder*, \"effects\": [{\"effect\": *fill in with the number and name of a beneficial effect category defined in the given taxonomy of beneficial effects that this beneficial action may cause on this stakeholder given this scenario*, \"immediacy\": *true if the beneficial effect is short-term or immediate, and false if the beneficial effect is long-term or downstream*, \"extent\": *the extent to which the stakeholder may benefit from this beneficial effect (minor, significant, substantial, or major, as defined below)*,\"likelihood\": *the likelihood that the stakeholder may benefit from this beneficial effect (low, medium, or high, as defined below)*}, ... *List as many distinct and valid beneficial effects as you can*]}, ... *List as many more distinct and valid beneficial actions as you can*]}, ... *list as many distinct and valid stakeholders as you can*]\n\nThe taxonomy of beneficial effects is defined as:\n#Physical benefit#\n1. Prevention of death\n2. Physical health benefits\n#Psychological benefit#\n3. Transient emotional changes\n4. Persistent emotional state changes\n#Social benefit#\n5. Social gains\n#Property benefit#\n6. Physical property gains\n7. Financial property gains\n8. Intellectual property gains\n#Liberty benefit#\n9. Freedom and agency benefits\n10. Gain of accurate information access\n#Collective benefit#\n11. Institutional benefits\n12. Public resource gains\n13. Societal order maintenance\n#Ecological benefit#\n14. Benefits to non-human animals\n15. Ecosystem benefits\n\nThe extents of benefit are defined as:\nMinor: beneficial consequences are isolated, temporary, noticeable but have limited impact on the overall situation or outcome; the stakeholder may experience a limited enhancement of functional ability and/or quality of life.\nSignificant: beneficial consequences are widespread, significant, noticeable, and can lead to meaningful improvements and tangible impacts; the stakeholder may experience significant improvement in functional ability and/or quality of life.\nSubstantial: beneficial consequences are extensive, important, and can lead to considerable positive changes and profound impact on the situation or outcome; the stakeholder may experience substantial enhancement of functional ability and/or quality of life.\nMajor: beneficial consequences are systemic, persistent, critical, highly impactful, and can lead to transformative changes that significantly alter the courses of events; the stakeholder may experience a profound improvement in functional ability and/or quality of life.\n\nThe likelihoods of benefits are defined as:\nLow: unlikely to occur, but not impossible. Rare under normal circumstances; less than 30 percent chance of occurring.\nMedium: possible occurrence, might happen under certain conditions or occasionally; between 30 and 70 percent chance of occurring.\nHigh: likely to occur, happens frequently or under normal conditions; above 70 percent chance of occurring.\n\n\n<|user|>\nIn a conversation between an AI language model and a user, the user prompts the AI language model: \"{{ messages }}\" The AI language model complies with the request by providing a helpful, informative answer with specific details and/or step-by-step guidance.\n\n\n<|assistant|>\n",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|eot_id|>",
   "model_input_names": [