Skip to content

GitLab

Commit ca625f43 authored by shihm's avatar shihm
Browse files

uodata

parent 7164651d
Hide whitespace changes
Inline Side-by-side
Showing with 798 additions and 1306 deletions
data/dataset_info.json
View file @ ca625f43
......@@ -143,14 +143,6 @@
"hf_hub_url": "BelleGroup/school_math_0.25M",
"ms_hub_url": "AI-ModelScope/school_math_0.25M"
},
"belle_multiturn": {
"script_url": "belle_multiturn",
"formatting": "sharegpt"
},
"ultra_chat": {
"script_url": "ultra_chat",
"formatting": "sharegpt"
},
"open_platypus": {
"hf_hub_url": "garage-bAInd/Open-Platypus",
"ms_hub_url": "AI-ModelScope/Open-Platypus"
......@@ -259,6 +251,10 @@
"assistant_tag": "assistant"
}
},
"infinity_instruct": {
"hf_hub_url": "BAAI/Infinity-Instruct",
"formatting": "sharegpt"
},
"agent_instruct": {
"hf_hub_url": "THUDM/AgentInstruct",
"ms_hub_url": "ZhipuAI/AgentInstruct",
......@@ -475,6 +471,14 @@
"ultrachat_de": {
"hf_hub_url": "mayflowergmbh/ultra-chat_de"
},
"dlr_web": {
"hf_hub_url": "Attention1115/DLR-Web",
"split": "full",
"columns": {
"prompt": "question",
"response": "response"
}
},
"dpo_en_demo": {
"file_name": "dpo_en_demo.json",
"ranking": true,
......@@ -579,16 +583,6 @@
"system": "system"
}
},
"hh_rlhf_en": {
"script_url": "hh_rlhf_en",
"ranking": true,
"columns": {
"prompt": "instruction",
"chosen": "chosen",
"rejected": "rejected",
"history": "history"
}
},
"nectar_rm": {
"hf_hub_url": "AstraMindAI/RLAIF-Nectar",
"ms_hub_url": "AI-ModelScope/RLAIF-Nectar",
......@@ -700,6 +694,36 @@
"prompt": "text"
}
},
"cci3_hq": {
"hf_hub_url": "BAAI/CCI3-HQ",
"columns": {
"prompt": "text"
}
},
"cci3_data": {
"hf_hub_url": "BAAI/CCI3-Data",
"columns": {
"prompt": "text"
}
},
"cci4_base": {
"hf_hub_url": "BAAI/CCI4.0-M2-Base-v1",
"columns": {
"prompt": "text"
}
},
"cci4_cot": {
"hf_hub_url": "BAAI/CCI4.0-M2-CoT-v1",
"columns": {
"prompt": "text"
}
},
"cci4_extra": {
"hf_hub_url": "BAAI/CCI4.0-M2-Extra-v1",
"columns": {
"prompt": "text"
}
},
"the_stack": {
"hf_hub_url": "bigcode/the-stack",
"ms_hub_url": "AI-ModelScope/the-stack",
......
data/reason_tool_use_demo_50.jsonl 0 → 100644
View file @ ca625f43
This source diff could not be displayed because it is too large. You can view the blob instead.
data/v1_dpo_demo.jsonl 0 → 100644
View file @ ca625f43
{"chosen_messages": [{"role": "system", "content": [{"type": "text", "value": "You are an AI assistant. You will be given a task. You must generate a detailed and long answer."}], "loss_weight": 0.0}, {"role": "user", "content": [{"type": "text", "value": "Abdulah Hasanagic este mândrul proprietar al AS Company din Gorazde, un orăşel situat pe malul râului Drina, lângă frontiera cu Serbia, în estul Bosniei.\n\nTranslate to English\n\nEnglish:"}], "loss_weight": 0.0}, {"role": "assistant", "content": [{"type": "text", "value": "Abdulah Hasanagic is the proud owner of AS Company in Gorazde, a small town located on the banks of the Drina River, near the border with Serbia, in Eastern Bosnia."}], "loss_weight": 1.0}], "rejected_messages": [{"role": "system", "content": [{"type": "text", "value": "You are an AI assistant. You will be given a task. You must generate a detailed and long answer."}], "loss_weight": 0.0}, {"role": "user", "content": [{"type": "text", "value": "Abdulah Hasanagic este mândrul proprietar al AS Company din Gorazde, un orăşel situat pe malul râului Drina, lângă frontiera cu Serbia, în estul Bosniei.\n\nTranslate to English\n\nEnglish:"}], "loss_weight": 0.0}, {"role": "assistant", "content": [{"type": "text", "value": " Abdulah Hasanagic is the proud owner of AS Company, a small town located on the banks of the Drina River, near the border with Serbia, in eastern Bosnia."}], "loss_weight": 1.0}]}
{"chosen_messages": [{"role": "system", "content": [{"type": "text", "value": "You are an AI assistant that follows instruction extremely well. Help as much as you can."}], "loss_weight": 0.0}, {"role": "user", "content": [{"type": "text", "value": "Answer the following question: Context: Bailey knew Taylor that well and got a few snacks for later tonight. Question: How would you describe Bailey? Which one of these answers best answers the question according to the context? A: feeling proud B: very hungry C: feeling bored\nAnswer:"}], "loss_weight": 0.0}, {"role": "assistant", "content": [{"type": "text", "value": "D: considerate"}], "loss_weight": 1.0}], "rejected_messages": [{"role": "system", "content": [{"type": "text", "value": "You are an AI assistant that follows instruction extremely well. Help as much as you can."}], "loss_weight": 0.0}, {"role": "user", "content": [{"type": "text", "value": "Answer the following question: Context: Bailey knew Taylor that well and got a few snacks for later tonight. Question: How would you describe Bailey? Which one of these answers best answers the question according to the context? A: feeling proud B: very hungry C: feeling bored\nAnswer:"}], "loss_weight": 0.0}, {"role": "assistant", "content": [{"type": "text", "value": " Based on the context, the best answer to describe Bailey would be:\n\nC: feeling bored.\n\nThe context states that Bailey knew Taylor well and got a few snacks for later tonight, which suggests that Bailey is not feeling proud or hungry, but rather bored."}], "loss_weight": 1.0}]}
{"chosen_messages": [{"role": "system", "content": [{"type": "text", "value": "You are a helpful assistant, who always provide explanation. Think like you are answering to a five year old."}], "loss_weight": 0.0}, {"role": "user", "content": [{"type": "text", "value": "Concepts: fall, love, relationship, thing\n\nWrite a sentence that includes all these words."}], "loss_weight": 0.0}, {"role": "assistant", "content": [{"type": "text", "value": "When you fall in love, it's like a special relationship between two people who really care about each other, and it's a wonderful thing to experience in life."}], "loss_weight": 1.0}], "rejected_messages": [{"role": "system", "content": [{"type": "text", "value": "You are a helpful assistant, who always provide explanation. Think like you are answering to a five year old."}], "loss_weight": 0.0}, {"role": "user", "content": [{"type": "text", "value": "Concepts: fall, love, relationship, thing\n\nWrite a sentence that includes all these words."}], "loss_weight": 0.0}, {"role": "assistant", "content": [{"type": "text", "value": " Ooh, let me think! 🤔\n\nOkay, here's a sentence that includes all three words:\n\n\"Love is like a soft, fluffy thing that falls from the sky and lands in our hearts, making us feel happy and special!\" 🐰💕🐱\n\nDoes that make sense, little one? 😊"}], "loss_weight": 1.0}]}
{"chosen_messages": [{"role": "system", "content": [{"type": "text", "value": "You are an AI assistant. You will be given a task. You must generate a detailed and long answer."}], "loss_weight": 0.0}, {"role": "user", "content": [{"type": "text", "value": "Read the text and determine if the sentence is true:\n\nCheung Kong Park () is a small garden located in the Central district of Hong Kong Island and named for Li Ka Shing's corporate empire. The park is privately maintained by Cheung Kong Holdings, but is open to the public. The park consists of ponds and cascades with benches for visitors to enjoy the scenery.\n\nSentence: Cheung Kong Park is ugly."}], "loss_weight": 0.0}, {"role": "assistant", "content": [{"type": "text", "value": "The sentence \"Cheung Kong Park is ugly\" cannot be determined as true or false from the provided text alone. The text describes Cheung Kong Park as a small garden located in Central district and states that it is privately maintained and open to the public. The text also mentions the park has ponds, cascades, and benches for visitors to enjoy the scenery. From these descriptions, it seems that the park is designed to be visually appealing and comfortable for visitors. However, an individual's perception of beauty or attractiveness is subjective, so whether one finds the park ugly or beautiful depends on personal preference and opinions. Further information and a personal visit to the park may be required to make a more informed judgment on its aesthetic appeal."}], "loss_weight": 1.0}], "rejected_messages": [{"role": "system", "content": [{"type": "text", "value": "You are an AI assistant. You will be given a task. You must generate a detailed and long answer."}], "loss_weight": 0.0}, {"role": "user", "content": [{"type": "text", "value": "Read the text and determine if the sentence is true:\n\nCheung Kong Park () is a small garden located in the Central district of Hong Kong Island and named for Li Ka Shing's corporate empire. The park is privately maintained by Cheung Kong Holdings, but is open to the public. The park consists of ponds and cascades with benches for visitors to enjoy the scenery.\n\nSentence: Cheung Kong Park is ugly."}], "loss_weight": 0.0}, {"role": "assistant", "content": [{"type": "text", "value": " Based on the information provided in the text, the sentence \"Cheung Kong Park is ugly\" is false. The text describes the park as a small garden with ponds and cascades, suggesting that it is a well-maintained and scenic area. Additionally, the fact that the park is open to the public and privately maintained by Cheung Kong Holdings suggests that it is a deliberately created and cared for space, rather than a neglected or unattractive one. Therefore, the statement \"Cheung Kong Park is ugly\" is not supported by the information provided in the text."}], "loss_weight": 1.0}]}
{"chosen_messages": [{"role": "system", "content": [{"type": "text", "value": "You are an AI assistant. You will be given a task. You must generate a detailed and long answer."}], "loss_weight": 0.0}, {"role": "user", "content": [{"type": "text", "value": "Translate to Russian:\n\n1973 Summer Universiade\n\nRussian:"}], "loss_weight": 0.0}, {"role": "assistant", "content": [{"type": "text", "value": "1973 Летняя Универсиада"}], "loss_weight": 1.0}], "rejected_messages": [{"role": "system", "content": [{"type": "text", "value": "You are an AI assistant. You will be given a task. You must generate a detailed and long answer."}], "loss_weight": 0.0}, {"role": "user", "content": [{"type": "text", "value": "Translate to Russian:\n\n1973 Summer Universiade\n\nRussian:"}], "loss_weight": 0.0}, {"role": "assistant", "content": [{"type": "text", "value": " Sure, I'd be happy to help! Here's the translation of \"1973 Summer Universiade\" to Russian:\n\n1973 летониversary Всемирных студенческих игр\n\nHere's a breakdown of the translation:\n\n* \"1973\" - this is the year of the Universiade, written in Russian as \"1973\".\n* \"летониversary\" - this is a combination of \"лето\" (summer) and \"ниversary\" (anniversary), which is used to describe the anniversary of an event that took place in the summer.\n* \"Всемирных студенческих игр\" - this is the full name of the Universiade in Russian, which translates to \"World Student Games\" in English.\n\nSo, the full translation of \"1973 Summer Universiade\" to Russian is \"1973 летониversary Всемирных студенческих игр\"."}], "loss_weight": 1.0}]}
{"chosen_messages": [{"role": "system", "content": [{"type": "text", "value": "You are an AI assistant that helps people find information."}], "loss_weight": 0.0}, {"role": "user", "content": [{"type": "text", "value": "Q: Claim: \"Ayn Rand spoke Spanish throughout her life, and never learned the English language.\"\nIs the claim above correct, and can it be verified by human common sense and without a web search?\nOptions:\n- yes\n- no\nChain-of-thought:"}], "loss_weight": 0.0}, {"role": "assistant", "content": [{"type": "text", "value": "no"}], "loss_weight": 1.0}], "rejected_messages": [{"role": "system", "content": [{"type": "text", "value": "You are an AI assistant that helps people find information."}], "loss_weight": 0.0}, {"role": "user", "content": [{"type": "text", "value": "Q: Claim: \"Ayn Rand spoke Spanish throughout her life, and never learned the English language.\"\nIs the claim above correct, and can it be verified by human common sense and without a web search?\nOptions:\n- yes\n- no\nChain-of-thought:"}], "loss_weight": 0.0}, {"role": "assistant", "content": [{"type": "text", "value": " No, the claim that Ayn Rand spoke Spanish throughout her life and never learned the English language is not correct.\n\nAyn Rand was born in Russia and immigrated to the United States in 1926. She learned English as a second language and became fluent in it, as evidenced by her written works and public speeches. In fact, she was known for her distinctive American accent and was a prominent figure in American intellectual and political circles.\n\nFurthermore, it is unlikely that someone who was born in Russia and immigrated to the United States at the age of 21 would not learn English, as it is the predominant language spoken in the country. Additionally, it is unlikely that someone as influential as Ayn Rand would not have been recorded or quoted speaking English, which would be evidence of her proficiency in the language.\n\nTherefore, without a web search, it is possible to verify that the claim that Ayn Rand spoke Spanish throughout her life and never learned the English language is not correct, based on common sense and knowledge of Ayn Rand's life and background."}], "loss_weight": 1.0}]}
{"chosen_messages": [{"role": "system", "content": [{"type": "text", "value": "You are an AI assistant. You will be given a task. You must generate a detailed and long answer."}], "loss_weight": 0.0}, {"role": "user", "content": [{"type": "text", "value": "Given the question: - sport is athletics - event is discus throw shot put - death date is 23 december 1967 - country is ita italy - birth date is 19 june 1891 - nationality is italian - club is libertas pistoia - birth place is pistoia , italy Given the details above, guess who could this information be about.\nThe answer is:"}], "loss_weight": 0.0}, {"role": "assistant", "content": [{"type": "text", "value": "The individual described by the information provided is Adolfo Consolini, an Italian discus thrower who achieved prominent success during his career. \n\nAdolfo Consolini was born on June 19, 1891, in the city of Pistoia, located in the Tuscany region of Italy. As an Italian national, he represented his country in various athletic events, with a particular focus on the discus throw and shot put. His athletic club was Libertas Pistoia, which provided him with the necessary support and resources to excel in his chosen sports.\n\nOne of the most notable features of Consolini's career was his unparalleled success in the discus throw. He rose to prominence in the event after setting a new world record in 1941, which he eventually bettered in 1946. Over the course of his athletic career, he represented Italy in several international competitions, including the Olympic Games, European Athletics Championships, and Mediterranean Games. Throughout his career, Consolini secured a total of 26 national titles in the discus throw and added a further three national titles in the shot put.\n\nSome of the most significant achievements of his career include gold medals in discus throw at the 1948 London Olympics and the 1950 European Athletics Championships in Brussels, as well as silver medals at the 1952 Helsinki Olympics and the 1954 European Athletics Championships in Bern.\n\nDespite his tremendous success on the field, Adolfo Consolini's life unfortunately came to an end on December 23, 1967. Nevertheless, he is still remembered in Italy and across the athletic community as a pioneer of the discus throw, leaving behind a lasting legacy of sporting prowess that continues to inspire future generations of athletes."}], "loss_weight": 1.0}], "rejected_messages": [{"role": "system", "content": [{"type": "text", "value": "You are an AI assistant. You will be given a task. You must generate a detailed and long answer."}], "loss_weight": 0.0}, {"role": "user", "content": [{"type": "text", "value": "Given the question: - sport is athletics - event is discus throw shot put - death date is 23 december 1967 - country is ita italy - birth date is 19 june 1891 - nationality is italian - club is libertas pistoia - birth place is pistoia , italy Given the details above, guess who could this information be about.\nThe answer is:"}], "loss_weight": 0.0}, {"role": "assistant", "content": [{"type": "text", "value": " Based on the information provided, the person who could this information be about is the Italian athlete, Giuseppe \"Joe\" Piane.\n\nHere's why:\n\n1. Sport: The sport is athletics, which matches with Piane's specialty. He was a renowned Italian athlete who excelled in discus throw and shot put.\n2. Event: The event is discus throw and shot put, which were Piane's primary events. He won numerous national and international titles in these events.\n3. Death date: Piane passed away on December 23, 1967, which is consistent with the information provided.\n4. Country: Piane was Italian, which matches the nationality provided.\n5. Birth date: Piane was born on June 19, 1891, which is consistent with the information provided.\n6. Club: Piane represented the Libertas Pistoia club, which is consistent with the information provided.\n7. Birth place: Piane was born in Pistoia, Italy, which matches the birth place provided.\n\nGiuseppe Piane was an Italian athlete who dominated the discus throw and shot put events in the early 20th century. He won numerous national and international titles, including gold medals at the 1920 and 1924 Summer Olympics. Piane was known for his impressive throwing technique and strength, and he was considered one of the greatest Italian athletes of all time."}], "loss_weight": 1.0}]}
{"chosen_messages": [{"role": "system", "content": [{"type": "text", "value": "You are an AI assistant. You will be given a task. You must generate a detailed and long answer."}], "loss_weight": 0.0}, {"role": "user", "content": [{"type": "text", "value": "What concepts are described in the following sentence?\n\n\"For an child friendly, average coffee shop serving fast food try The Eagle, riverside near Burger King\"\n\nReturn the answer as pairs of triples."}], "loss_weight": 0.0}, {"role": "assistant", "content": [{"type": "text", "value": "1. Concept: Child friendly\n Description: The Eagle coffee shop is suitable and welcoming for children, providing a comfortable environment.\n Relation: The Eagle is a coffee shop characterized as being appropriate for kids.\n\n2. Concept: Average coffee shop\n Description: The Eagle is a typical coffee shop, not extraordinary or unique but still providing good service and products.\n Relation: The Eagle maintains a standard level of quality expected from a coffee shop.\n\n3. Concept: Fast food\n Description: The Eagle serves quickly prepared meals, typically of the kind found in fast food chains.\n Relation: The Eagle offers fast food options for customers seeking a quick meal.\n\n4. Concept: The Eagle\n Description: A coffee shop located near Burger King and by the riverside, catering to people who want fast food.\n Relation: The Eagle is the primary focus of the description, highlighting its child-friendly nature and its offerings.\n\n5. Concept: Riverside location\n Description: The Eagle is situated near a river, offering potential for scenic views or proximity to recreational areas.\n Relation: The Eagle's location by the riverside adds to its appeal for customers seeking a peaceful or picturesque spot.\n\n6. Concept: Proximity to Burger King\n Description: The Eagle is near a Burger King, giving customers an alternative fast food option or acting as a landmark to locate the coffee shop.\n Relation: The mention of Burger King helps customers find The Eagle and suggests it is located in an area with multiple food establishments."}], "loss_weight": 1.0}], "rejected_messages": [{"role": "system", "content": [{"type": "text", "value": "You are an AI assistant. You will be given a task. You must generate a detailed and long answer."}], "loss_weight": 0.0}, {"role": "user", "content": [{"type": "text", "value": "What concepts are described in the following sentence?\n\n\"For an child friendly, average coffee shop serving fast food try The Eagle, riverside near Burger King\"\n\nReturn the answer as pairs of triples."}], "loss_weight": 0.0}, {"role": "assistant", "content": [{"type": "text", "value": " Sure, I'd be happy to help! Here are the concepts described in the sentence you provided, represented as pairs of triples:\n\n1. Child-friendliness:\n\t* Concept: Child-friendliness\n\t* Description: The coffee shop is suitable for children.\n2. Average coffee shop:\n\t* Concept: Average coffee shop\n\t* Description: The coffee shop is a typical, regular coffee shop.\n3. Fast food:\n\t* Concept: Fast food\n\t* Description: The coffee shop serves fast food.\n4. Riverside location:\n\t* Concept: Riverside location\n\t* Description: The coffee shop is located near the river.\n5. Burger King:\n\t* Concept: Burger King\n\t* Description: A well-known fast food restaurant located near the coffee shop.\n\nI hope this helps! Let me know if you have any further questions."}], "loss_weight": 1.0}]}
{"chosen_messages": [{"role": "system", "content": [{"type": "text", "value": "You are an AI assistant. Provide a detailed answer so user don’t need to search outside to understand the answer."}], "loss_weight": 0.0}, {"role": "user", "content": [{"type": "text", "value": "Please answer the following question: - Bats and other animals produce a high-pitched tone - The sound travels in waves, as sound does - The sound 'bounces' off of a nearby object - The sound wave returns to the bat - The bat hears the echoed sound - Folds in the bat's ear and adaptations in the bat's brain enable it to determine the size, shape, and position of the other object via the properties of the returned sound waves What might be the last step of the process?\nA:"}], "loss_weight": 0.0}, {"role": "assistant", "content": [{"type": "text", "value": "The last step of the process is: The bat uses the interpreted information from the echoed sound waves to navigate and locate objects (such as prey or obstacles) in its environment, allowing it to maneuver effectively and safely even in complete darkness. This entire process is called echolocation."}], "loss_weight": 1.0}], "rejected_messages": [{"role": "system", "content": [{"type": "text", "value": "You are an AI assistant. Provide a detailed answer so user don’t need to search outside to understand the answer."}], "loss_weight": 0.0}, {"role": "user", "content": [{"type": "text", "value": "Please answer the following question: - Bats and other animals produce a high-pitched tone - The sound travels in waves, as sound does - The sound 'bounces' off of a nearby object - The sound wave returns to the bat - The bat hears the echoed sound - Folds in the bat's ear and adaptations in the bat's brain enable it to determine the size, shape, and position of the other object via the properties of the returned sound waves What might be the last step of the process?\nA:"}], "loss_weight": 0.0}, {"role": "assistant", "content": [{"type": "text", "value": " Sure, I'd be happy to help! Here's a detailed answer to your question:\n\nBats and other animals produce a high-pitched tone, known as an ultrasonic signal, which travels in waves, as sound does. The sound wave \"bounces\" off of a nearby object, such as a fly or a tree, and returns to the bat. The bat hears the echoed sound through its highly specialized ears and adaptations in its brain.\n\nThe last step of the process is for the bat to use the properties of the returned sound waves to determine the size, shape, and position of the other object. This is done through a process called echolocation.\n\nEcholocation is the ability of bats and other animals to determine the location and characteristics of objects in their environment by emitting high-frequency sounds and detecting the echoes that bounce back. The echoes contain information about the distance, size, shape, and material composition of the object, which the bat's brain then processes to create a mental map of its surroundings.\n\nIn the case of bats, the sound waves are emitted through the bat's mouth or nose, and the echoes are detected by the bat's large ears. The echoes are then processed by the bat's brain, which uses the information to build a mental map of its surroundings and locate prey.\n\nSo, to summarize, the last step of the process is for the bat to use the properties of the returned sound waves to determine the size, shape, and position of the other object through echolocation."}], "loss_weight": 1.0}]}
{"chosen_messages": [{"role": "system", "content": [{"type": "text", "value": "You should describe the task and explain your answer. While answering a multiple choice question, first output the correct answer(s). Then explain why other answers are wrong. Think like you are answering to a five year old."}], "loss_weight": 0.0}, {"role": "user", "content": [{"type": "text", "value": "Iwasaki's careful respect for the Long Beach program and its lawyers earned him the political capital he needed to complete his takeover in a matter of weeks. \"The Long Beach program had strong support in the community so in a situation like that, one has to recognize that it's not like a takeover where I have all the answers and I know best,\" Iwasaki said. \"The people in the community who are working there have the contacts and the knowledge that will allow service to continue.\" Things have gone less smoothly across town. There, Dudovitz, a longtime poverty lawyer and executive director of the San Fernando Valley's 36-year-old legal aid program, continues to struggle with his hostile takeover of the neighboring San Gabriel-Pomona Valleys service area one year after it was accomplished. On the bright side, Dudovitz has extended his respected program to clients in the San Gabriel-Pomona Valley, and he now operates on a much larger budget, $6.5 million last year. However, his clash with the old San Gabriel program resulted in litigation, bitter feelings and a mission that some say is not clearly focused on serving poor people. \"It was a difficult situation that was probably mishandled by everyone,\" a longtime observer of the public interest community said of the San Fernando Valley-San Gabriel-Pomona Valley merger. \"There are very few people who come out as the heroes. Personalities got involved when they shouldn't have. Things were said that caused bad feelings and couldn't be unsaid.\" Iwasaki's merger with the smaller, 48-year-old Long Beach program was friendly and fast, and no one - not even Long Beach board members - lost a job. When it was over, Iwasaki had $1 million more in federal dollars and two new offices. Long Beach clients regained services they had lost years ago when federal budget cuts and dwindling grants reduced the staff of 15 lawyers to five and cut immigration and consumer law programs. Iwasaki said, \"[I judged the transition] better than I could have hoped for.\" \n\nQuestion: \"What is the difference in the ages of the Long Beach and San Fernando Valley programs?\"\n\nResponse: \"Weeks\"\nPick from: *no *yes\nDoes the response correctly answer the question?\n\n"}], "loss_weight": 0.0}, {"role": "assistant", "content": [{"type": "text", "value": "No\n\nThe response does not correctly answer the question. The question asks about the difference in ages between the Long Beach and San Fernando Valley programs, but the response given is \"weeks\" which does not provide the correct information. The Long Beach program is 48 years old, while the San Fernando Valley program is 36 years old. The difference in ages between these two programs is 12 years."}], "loss_weight": 1.0}], "rejected_messages": [{"role": "system", "content": [{"type": "text", "value": "You should describe the task and explain your answer. While answering a multiple choice question, first output the correct answer(s). Then explain why other answers are wrong. Think like you are answering to a five year old."}], "loss_weight": 0.0}, {"role": "user", "content": [{"type": "text", "value": "Iwasaki's careful respect for the Long Beach program and its lawyers earned him the political capital he needed to complete his takeover in a matter of weeks. \"The Long Beach program had strong support in the community so in a situation like that, one has to recognize that it's not like a takeover where I have all the answers and I know best,\" Iwasaki said. \"The people in the community who are working there have the contacts and the knowledge that will allow service to continue.\" Things have gone less smoothly across town. There, Dudovitz, a longtime poverty lawyer and executive director of the San Fernando Valley's 36-year-old legal aid program, continues to struggle with his hostile takeover of the neighboring San Gabriel-Pomona Valleys service area one year after it was accomplished. On the bright side, Dudovitz has extended his respected program to clients in the San Gabriel-Pomona Valley, and he now operates on a much larger budget, $6.5 million last year. However, his clash with the old San Gabriel program resulted in litigation, bitter feelings and a mission that some say is not clearly focused on serving poor people. \"It was a difficult situation that was probably mishandled by everyone,\" a longtime observer of the public interest community said of the San Fernando Valley-San Gabriel-Pomona Valley merger. \"There are very few people who come out as the heroes. Personalities got involved when they shouldn't have. Things were said that caused bad feelings and couldn't be unsaid.\" Iwasaki's merger with the smaller, 48-year-old Long Beach program was friendly and fast, and no one - not even Long Beach board members - lost a job. When it was over, Iwasaki had $1 million more in federal dollars and two new offices. Long Beach clients regained services they had lost years ago when federal budget cuts and dwindling grants reduced the staff of 15 lawyers to five and cut immigration and consumer law programs. Iwasaki said, \"[I judged the transition] better than I could have hoped for.\" \n\nQuestion: \"What is the difference in the ages of the Long Beach and San Fernando Valley programs?\"\n\nResponse: \"Weeks\"\nPick from: *no *yes\nDoes the response correctly answer the question?\n\n"}], "loss_weight": 0.0}, {"role": "assistant", "content": [{"type": "text", "value": " Yes, the response correctly answers the question! 😊\n\nThe Long Beach program is 48 years old, and the San Fernando Valley program is 36 years old, so the difference in their ages is... *drumroll* ...weeks! 😄\n\nHere's why the other answers are wrong:\n\n* \"No\" is not correct because the Long Beach and San Fernando Valley programs are not the same age.\n* \"Yes\" is not correct because the difference in their ages is not just one year, it's weeks! 😄\n\nSo, the correct answer is \"weeks\"! 🎉"}], "loss_weight": 1.0}]}
data/v1_dpo_demo.yaml 0 → 100644
View file @ ca625f43
dpo_zh_demo:
path: HuggingFaceH4/orca_dpo_pairs
split: train_prefs
converter: pair
data/v1_sft_demo.jsonl 0 → 100644
View file @ ca625f43
This source diff could not be displayed because it is too large. You can view the blob instead.
data/v1_sft_demo.yaml 0 → 100644
View file @ ca625f43
identity:
path: data/identity.json
source: local
converter: alpaca
alpaca_en_demo:
path: data/alpaca_en_demo.json
source: local
converter: alpaca
size: 500
evaluation/ceval/ceval.py deleted 100644 → 0
View file @ 7164651d
# Copyright 2025 the LlamaFactory team.
# Copyright 2020 The HuggingFace Datasets Authors and the current dataset script contributor.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import os
import datasets
import pandas as pd
_CITATION = """\
@article{huang2023ceval,
title={C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models},
author={Huang, Yuzhen and Bai, Yuzhuo and Zhu, Zhihao and others},
journal={arXiv preprint arXiv:2305.08322},
year={2023}
}
"""
_DESCRIPTION = """\
C-Eval is a comprehensive Chinese evaluation suite for foundation models.
It consists of 13948 multi-choice questions spanning 52 diverse disciplines and four difficulty levels.
"""
_HOMEPAGE = "https://cevalbenchmark.com"
_LICENSE = "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License"
_URL = "ceval.zip"
task_list = [
"computer_network",
"operating_system",
"computer_architecture",
"college_programming",
"college_physics",
"college_chemistry",
"advanced_mathematics",
"probability_and_statistics",
"discrete_mathematics",
"electrical_engineer",
"metrology_engineer",
"high_school_mathematics",
"high_school_physics",
"high_school_chemistry",
"high_school_biology",
"middle_school_mathematics",
"middle_school_biology",
"middle_school_physics",
"middle_school_chemistry",
"veterinary_medicine",
"college_economics",
"business_administration",
"marxism",
"mao_zedong_thought",
"education_science",
"teacher_qualification",
"high_school_politics",
"high_school_geography",
"middle_school_politics",
"middle_school_geography",
"modern_chinese_history",
"ideological_and_moral_cultivation",
"logic",
"law",
"chinese_language_and_literature",
"art_studies",
"professional_tour_guide",
"legal_professional",
"high_school_chinese",
"high_school_history",
"middle_school_history",
"civil_servant",
"sports_science",
"plant_protection",
"basic_medicine",
"clinical_medicine",
"urban_and_rural_planner",
"accountant",
"fire_engineer",
"environmental_impact_assessment_engineer",
"tax_accountant",
"physician",
]
class CevalConfig(datasets.BuilderConfig):
def __init__(self, **kwargs):
super().__init__(version=datasets.Version("1.0.0"), **kwargs)
class Ceval(datasets.GeneratorBasedBuilder):
BUILDER_CONFIGS = [
CevalConfig(
name=task_name,
)
for task_name in task_list
]
def _info(self):
features = datasets.Features(
{
"id": datasets.Value("int32"),
"question": datasets.Value("string"),
"A": datasets.Value("string"),
"B": datasets.Value("string"),
"C": datasets.Value("string"),
"D": datasets.Value("string"),
"answer": datasets.Value("string"),
"explanation": datasets.Value("string"),
}
)
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=features,
homepage=_HOMEPAGE,
license=_LICENSE,
citation=_CITATION,
)
def _split_generators(self, dl_manager):
data_dir = dl_manager.download_and_extract(_URL)
task_name = self.config.name
return [
datasets.SplitGenerator(
name=datasets.Split.TEST,
gen_kwargs={
"filepath": os.path.join(data_dir, "test", f"{task_name}_test.csv"),
},
),
datasets.SplitGenerator(
name=datasets.Split.VALIDATION,
gen_kwargs={
"filepath": os.path.join(data_dir, "val", f"{task_name}_val.csv"),
},
),
datasets.SplitGenerator(
name=datasets.Split.TRAIN,
gen_kwargs={
"filepath": os.path.join(data_dir, "dev", f"{task_name}_dev.csv"),
},
),
]
def _generate_examples(self, filepath):
df = pd.read_csv(filepath, encoding="utf-8")
for i, instance in enumerate(df.to_dict(orient="records")):
if "answer" not in instance.keys():
instance["answer"] = ""
if "explanation" not in instance.keys():
instance["explanation"] = ""
yield i, instance
evaluation/ceval/mapping.json deleted 100644 → 0
View file @ 7164651d
{
"accountant": {
"name": "注册会计师",
"category": "Other"
},
"advanced_mathematics": {
"name": "高等数学",
"category": "STEM"
},
"art_studies": {
"name": "艺术学",
"category": "Humanities"
},
"basic_medicine": {
"name": "基础医学",
"category": "Other"
},
"business_administration": {
"name": "工商管理",
"category": "Social Sciences"
},
"chinese_language_and_literature": {
"name": "中国语言文学",
"category": "Humanities"
},
"civil_servant": {
"name": "公务员",
"category": "Other"
},
"clinical_medicine": {
"name": "临床医学",
"category": "Other"
},
"college_chemistry": {
"name": "大学化学",
"category": "STEM"
},
"college_economics": {
"name": "大学经济学",
"category": "Social Sciences"
},
"college_physics": {
"name": "大学物理",
"category": "STEM"
},
"college_programming": {
"name": "大学编程",
"category": "STEM"
},
"computer_architecture": {
"name": "计算机组成",
"category": "STEM"
},
"computer_network": {
"name": "计算机网络",
"category": "STEM"
},
"discrete_mathematics": {
"name": "离散数学",
"category": "STEM"
},
"education_science": {
"name": "教育学",
"category": "Social Sciences"
},
"electrical_engineer": {
"name": "注册电气工程师",
"category": "STEM"
},
"environmental_impact_assessment_engineer": {
"name": "环境影响评价工程师",
"category": "Other"
},
"fire_engineer": {
"name": "注册消防工程师",
"category": "Other"
},
"high_school_biology": {
"name": "高中生物",
"category": "STEM"
},
"high_school_chemistry": {
"name": "高中化学",
"category": "STEM"
},
"high_school_chinese": {
"name": "高中语文",
"category": "Humanities"
},
"high_school_geography": {
"name": "高中地理",
"category": "Social Sciences"
},
"high_school_history": {
"name": "高中历史",
"category": "Humanities"
},
"high_school_mathematics": {
"name": "高中数学",
"category": "STEM"
},
"high_school_physics": {
"name": "高中物理",
"category": "STEM"
},
"high_school_politics": {
"name": "高中政治",
"category": "Social Sciences"
},
"ideological_and_moral_cultivation": {
"name": "思想道德修养与法律基础",
"category": "Humanities"
},
"law": {
"name": "法学",
"category": "Humanities"
},
"legal_professional": {
"name": "法律职业资格",
"category": "Humanities"
},
"logic": {
"name": "逻辑学",
"category": "Humanities"
},
"mao_zedong_thought": {
"name": "毛泽东思想和中国特色社会主义理论体系概论",
"category": "Social Sciences"
},
"marxism": {
"name": "马克思主义基本原理",
"category": "Social Sciences"
},
"metrology_engineer": {
"name": "注册计量师",
"category": "STEM"
},
"middle_school_biology": {
"name": "初中生物",
"category": "STEM"
},
"middle_school_chemistry": {
"name": "初中化学",
"category": "STEM"
},
"middle_school_geography": {
"name": "初中地理",
"category": "Social Sciences"
},
"middle_school_history": {
"name": "初中历史",
"category": "Humanities"
},
"middle_school_mathematics": {
"name": "初中数学",
"category": "STEM"
},
"middle_school_physics": {
"name": "初中物理",
"category": "STEM"
},
"middle_school_politics": {
"name": "初中政治",
"category": "Social Sciences"
},
"modern_chinese_history": {
"name": "近代史纲要",
"category": "Humanities"
},
"operating_system": {
"name": "操作系统",
"category": "STEM"
},
"physician": {
"name": "医师资格",
"category": "Other"
},
"plant_protection": {
"name": "植物保护",
"category": "Other"
},
"probability_and_statistics": {
"name": "概率统计",
"category": "STEM"
},
"professional_tour_guide": {
"name": "导游资格",
"category": "Humanities"
},
"sports_science": {
"name": "体育学",
"category": "Other"
},
"tax_accountant": {
"name": "税务师",
"category": "Other"
},
"teacher_qualification": {
"name": "教师资格",
"category": "Social Sciences"
},
"urban_and_rural_planner": {
"name": "注册城乡规划师",
"category": "Other"
},
"veterinary_medicine": {
"name": "兽医学",
"category": "STEM"
}
}
evaluation/cmmlu/cmmlu.py deleted 100644 → 0
View file @ 7164651d
# Copyright 2025 the LlamaFactory team.
# Copyright 2020 The HuggingFace Datasets Authors and the current dataset script contributor.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import os
import datasets
import pandas as pd
_CITATION = """\
@article{li2023cmmlu,
title={CMMLU: Measuring massive multitask language understanding in Chinese},
author={Haonan Li and Yixuan Zhang and Fajri Koto and Yifei Yang and others,
journal={arXiv preprint arXiv:2306.09212},
year={2023}
}
"""
_DESCRIPTION = """\
CMMLU is a comprehensive Chinese assessment suite specifically designed to evaluate the advanced knowledge
and reasoning abilities of LLMs within the Chinese language and cultural context.
"""
_HOMEPAGE = "https://github.com/haonan-li/CMMLU"
_LICENSE = "Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License"
_URL = "cmmlu.zip"
task_list = [
"agronomy",
"anatomy",
"ancient_chinese",
"arts",
"astronomy",
"business_ethics",
"chinese_civil_service_exam",
"chinese_driving_rule",
"chinese_food_culture",
"chinese_foreign_policy",
"chinese_history",
"chinese_literature",
"chinese_teacher_qualification",
"clinical_knowledge",
"college_actuarial_science",
"college_education",
"college_engineering_hydrology",
"college_law",
"college_mathematics",
"college_medical_statistics",
"college_medicine",
"computer_science",
"computer_security",
"conceptual_physics",
"construction_project_management",
"economics",
"education",
"electrical_engineering",
"elementary_chinese",
"elementary_commonsense",
"elementary_information_and_technology",
"elementary_mathematics",
"ethnology",
"food_science",
"genetics",
"global_facts",
"high_school_biology",
"high_school_chemistry",
"high_school_geography",
"high_school_mathematics",
"high_school_physics",
"high_school_politics",
"human_sexuality",
"international_law",
"journalism",
"jurisprudence",
"legal_and_moral_basis",
"logical",
"machine_learning",
"management",
"marketing",
"marxist_theory",
"modern_chinese",
"nutrition",
"philosophy",
"professional_accounting",
"professional_law",
"professional_medicine",
"professional_psychology",
"public_relations",
"security_study",
"sociology",
"sports_science",
"traditional_chinese_medicine",
"virology",
"world_history",
"world_religions",
]
class CMMLUConfig(datasets.BuilderConfig):
def __init__(self, **kwargs):
super().__init__(version=datasets.Version("1.0.1"), **kwargs)
class CMMLU(datasets.GeneratorBasedBuilder):
BUILDER_CONFIGS = [
CMMLUConfig(
name=task_name,
)
for task_name in task_list
]
def _info(self):
features = datasets.Features(
{
"question": datasets.Value("string"),
"A": datasets.Value("string"),
"B": datasets.Value("string"),
"C": datasets.Value("string"),
"D": datasets.Value("string"),
"answer": datasets.Value("string"),
}
)
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=features,
homepage=_HOMEPAGE,
license=_LICENSE,
citation=_CITATION,
)
def _split_generators(self, dl_manager):
data_dir = dl_manager.download_and_extract(_URL)
task_name = self.config.name
return [
datasets.SplitGenerator(
name=datasets.Split.TEST,
gen_kwargs={
"filepath": os.path.join(data_dir, f"test/{task_name}.csv"),
},
),
datasets.SplitGenerator(
name=datasets.Split.TRAIN,
gen_kwargs={
"filepath": os.path.join(data_dir, f"dev/{task_name}.csv"),
},
),
]
def _generate_examples(self, filepath):
df = pd.read_csv(filepath, header=0, index_col=0, encoding="utf-8")
for i, instance in enumerate(df.to_dict(orient="records")):
question = instance.pop("Question", "")
answer = instance.pop("Answer", "")
instance["question"] = question
instance["answer"] = answer
yield i, instance
evaluation/cmmlu/mapping.json deleted 100644 → 0
View file @ 7164651d
{
"agronomy": {
"name": "农学",
"category": "Other"
},
"anatomy": {
"name": "解剖学",
"category": "STEM"
},
"ancient_chinese": {
"name": "古汉语",
"category": "Social Sciences"
},
"arts": {
"name": "艺术学",
"category": "Humanities"
},
"astronomy": {
"name": "天文学",
"category": "STEM"
},
"business_ethics": {
"name": "商业伦理",
"category": "Social Sciences"
},
"chinese_civil_service_exam": {
"name": "中国公务员考试",
"category": "Social Sciences"
},
"chinese_driving_rule": {
"name": "中国驾驶规则",
"category": "Other"
},
"chinese_food_culture": {
"name": "中国饮食文化",
"category": "Social Sciences"
},
"chinese_foreign_policy": {
"name": "中国外交政策",
"category": "Social Sciences"
},
"chinese_history": {
"name": "中国历史",
"category": "Humanities"
},
"chinese_literature": {
"name": "中国文学",
"category": "Humanities"
},
"chinese_teacher_qualification": {
"name": "中国教师资格",
"category": "Social Sciences"
},
"college_actuarial_science": {
"name": "大学精算学",
"category": "STEM"
},
"college_education": {
"name": "大学教育学",
"category": "Social Sciences"
},
"college_engineering_hydrology": {
"name": "大学工程水文学",
"category": "STEM"
},
"college_law": {
"name": "大学法律",
"category": "Humanities"
},
"college_mathematics": {
"name": "大学数学",
"category": "STEM"
},
"college_medical_statistics": {
"name": "大学医学统计",
"category": "STEM"
},
"clinical_knowledge": {
"name": "临床知识",
"category": "Other"
},
"college_medicine": {
"name": "大学医学",
"category": "Other"
},
"computer_science": {
"name": "计算机科学",
"category": "STEM"
},
"computer_security": {
"name": "计算机安全",
"category": "Other"
},
"conceptual_physics": {
"name": "概念物理学",
"category": "STEM"
},
"construction_project_management": {
"name": "建设工程管理",
"category": "Other"
},
"economics": {
"name": "经济学",
"category": "Social Sciences"
},
"education": {
"name": "教育学",
"category": "Social Sciences"
},
"elementary_chinese": {
"name": "小学语文",
"category": "Social Sciences"
},
"elementary_commonsense": {
"name": "小学常识",
"category": "Other"
},
"elementary_information_and_technology": {
"name": "小学信息技术",
"category": "Other"
},
"electrical_engineering": {
"name": "电气工程",
"category": "STEM"
},
"elementary_mathematics": {
"name": "初等数学",
"category": "STEM"
},
"ethnology": {
"name": "民族学",
"category": "Social Sciences"
},
"food_science": {
"name": "食品科学",
"category": "Other"
},
"genetics": {
"name": "遗传学",
"category": "STEM"
},
"global_facts": {
"name": "全球事实",
"category": "Humanities"
},
"high_school_biology": {
"name": "高中生物",
"category": "STEM"
},
"high_school_chemistry": {
"name": "高中化学",
"category": "STEM"
},
"high_school_geography": {
"name": "高中地理",
"category": "Social Sciences"
},
"high_school_mathematics": {
"name": "高中数学",
"category": "STEM"
},
"high_school_physics": {
"name": "高中物理学",
"category": "STEM"
},
"high_school_politics": {
"name": "高中政治",
"category": "Social Sciences"
},
"human_sexuality": {
"name": "人类性行为",
"category": "Other"
},
"international_law": {
"name": "国际法学",
"category": "Humanities"
},
"journalism": {
"name": "新闻学",
"category": "Social Sciences"
},
"jurisprudence": {
"name": "法理学",
"category": "Humanities"
},
"legal_and_moral_basis": {
"name": "法律与道德基础",
"category": "Other"
},
"logical": {
"name": "逻辑学",
"category": "Humanities"
},
"machine_learning": {
"name": "机器学习",
"category": "STEM"
},
"management": {
"name": "管理学",
"category": "Social Sciences"
},
"marketing": {
"name": "市场营销",
"category": "Social Sciences"
},
"marxist_theory": {
"name": "马克思主义理论",
"category": "Humanities"
},
"modern_chinese": {
"name": "现代汉语",
"category": "Social Sciences"
},
"nutrition": {
"name": "营养学",
"category": "Other"
},
"philosophy": {
"name": "哲学",
"category": "Humanities"
},
"professional_accounting": {
"name": "专业会计",
"category": "Social Sciences"
},
"professional_law": {
"name": "专业法学",
"category": "Humanities"
},
"professional_medicine": {
"name": "专业医学",
"category": "Other"
},
"professional_psychology": {
"name": "专业心理学",
"category": "Social Sciences"
},
"public_relations": {
"name": "公共关系",
"category": "Social Sciences"
},
"security_study": {
"name": "安全研究",
"category": "Social Sciences"
},
"sociology": {
"name": "社会学",
"category": "Social Sciences"
},
"sports_science": {
"name": "体育学",
"category": "Other"
},
"traditional_chinese_medicine": {
"name": "中医中药",
"category": "Other"
},
"virology": {
"name": "病毒学",
"category": "STEM"
},
"world_history": {
"name": "世界历史",
"category": "Humanities"
},
"world_religions": {
"name": "世界宗教",
"category": "Humanities"
}
}
evaluation/mmlu/mapping.json deleted 100644 → 0
View file @ 7164651d
{
"abstract_algebra": {
"name": "abstract algebra",
"category": "STEM"
},
"anatomy": {
"name": "anatomy",
"category": "Other"
},
"astronomy": {
"name": "astronomy",
"category": "STEM"
},
"business_ethics": {
"name": "business ethics",
"category": "Other"
},
"clinical_knowledge": {
"name": "clinical knowledge",
"category": "Other"
},
"college_biology": {
"name": "college biology",
"category": "STEM"
},
"college_chemistry": {
"name": "college chemistry",
"category": "STEM"
},
"college_computer_science": {
"name": "college computer science",
"category": "STEM"
},
"college_mathematics": {
"name": "college mathematics",
"category": "STEM"
},
"college_medicine": {
"name": "college medicine",
"category": "Other"
},
"college_physics": {
"name": "college physics",
"category": "STEM"
},
"computer_security": {
"name": "computer security",
"category": "STEM"
},
"conceptual_physics": {
"name": "conceptual physics",
"category": "STEM"
},
"econometrics": {
"name": "econometrics",
"category": "Social Sciences"
},
"electrical_engineering": {
"name": "electrical engineering",
"category": "STEM"
},
"elementary_mathematics": {
"name": "elementary mathematics",
"category": "STEM"
},
"formal_logic": {
"name": "formal logic",
"category": "Humanities"
},
"global_facts": {
"name": "global facts",
"category": "Other"
},
"high_school_biology": {
"name": "high school biology",
"category": "STEM"
},
"high_school_chemistry": {
"name": "high school chemistry",
"category": "STEM"
},
"high_school_computer_science": {
"name": "high school computer science",
"category": "STEM"
},
"high_school_european_history": {
"name": "high school european history",
"category": "Humanities"
},
"high_school_geography": {
"name": "high school geography",
"category": "Social Sciences"
},
"high_school_government_and_politics": {
"name": "high school government and politics",
"category": "Social Sciences"
},
"high_school_macroeconomics": {
"name": "high school macroeconomics",
"category": "Social Sciences"
},
"high_school_mathematics": {
"name": "high school mathematics",
"category": "STEM"
},
"high_school_microeconomics": {
"name": "high school microeconomics",
"category": "Social Sciences"
},
"high_school_physics": {
"name": "high school physics",
"category": "STEM"
},
"high_school_psychology": {
"name": "high school psychology",
"category": "Social Sciences"
},
"high_school_statistics": {
"name": "high school statistics",
"category": "STEM"
},
"high_school_us_history": {
"name": "high school us history",
"category": "Humanities"
},
"high_school_world_history": {
"name": "high school world history",
"category": "Humanities"
},
"human_aging": {
"name": "human aging",
"category": "Other"
},
"human_sexuality": {
"name": "human sexuality",
"category": "Social Sciences"
},
"international_law": {
"name": "international law",
"category": "Humanities"
},
"jurisprudence": {
"name": "jurisprudence",
"category": "Humanities"
},
"logical_fallacies": {
"name": "logical fallacies",
"category": "Humanities"
},
"machine_learning": {
"name": "machine learning",
"category": "STEM"
},
"management": {
"name": "management",
"category": "Other"
},
"marketing": {
"name": "marketing",
"category": "Other"
},
"medical_genetics": {
"name": "medical genetics",
"category": "Other"
},
"miscellaneous": {
"name": "miscellaneous",
"category": "Other"
},
"moral_disputes": {
"name": "moral disputes",
"category": "Humanities"
},
"moral_scenarios": {
"name": "moral scenarios",
"category": "Humanities"
},
"nutrition": {
"name": "nutrition",
"category": "Other"
},
"philosophy": {
"name": "philosophy",
"category": "Humanities"
},
"prehistory": {
"name": "prehistory",
"category": "Humanities"
},
"professional_accounting": {
"name": "professional accounting",
"category": "Other"
},
"professional_law": {
"name": "professional law",
"category": "Humanities"
},
"professional_medicine": {
"name": "professional medicine",
"category": "Other"
},
"professional_psychology": {
"name": "professional psychology",
"category": "Social Sciences"
},
"public_relations": {
"name": "public relations",
"category": "Social Sciences"
},
"security_studies": {
"name": "security studies",
"category": "Social Sciences"
},
"sociology": {
"name": "sociology",
"category": "Social Sciences"
},
"us_foreign_policy": {
"name": "us foreign policy",
"category": "Social Sciences"
},
"virology": {
"name": "virology",
"category": "Other"
},
"world_religions": {
"name": "world religions",
"category": "Humanities"
}
}
evaluation/mmlu/mmlu.py deleted 100644 → 0
View file @ 7164651d
# Copyright 2025 the LlamaFactory team.
# Copyright 2020 The HuggingFace Datasets Authors and the current dataset script contributor.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import os
import datasets
import pandas as pd
_CITATION = """\
@article{hendryckstest2021,
title={Measuring Massive Multitask Language Understanding},
author={Dan Hendrycks and Collin Burns and others},
journal={Proceedings of the International Conference on Learning Representations (ICLR)},
year={2021}
}
"""
_DESCRIPTION = """\
Measuring Massive Multitask Language Understanding by Dan Hendrycks, Collin Burns, Steven Basart,
Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt (ICLR 2021).
"""
_HOMEPAGE = "https://github.com/hendrycks/test"
_LICENSE = "MIT"
_URL = "mmlu.zip"
task_list = [
"high_school_european_history",
"business_ethics",
"clinical_knowledge",
"medical_genetics",
"high_school_us_history",
"high_school_physics",
"high_school_world_history",
"virology",
"high_school_microeconomics",
"econometrics",
"college_computer_science",
"high_school_biology",
"abstract_algebra",
"professional_accounting",
"philosophy",
"professional_medicine",
"nutrition",
"global_facts",
"machine_learning",
"security_studies",
"public_relations",
"professional_psychology",
"prehistory",
"anatomy",
"human_sexuality",
"college_medicine",
"high_school_government_and_politics",
"college_chemistry",
"logical_fallacies",
"high_school_geography",
"elementary_mathematics",
"human_aging",
"college_mathematics",
"high_school_psychology",
"formal_logic",
"high_school_statistics",
"international_law",
"high_school_mathematics",
"high_school_computer_science",
"conceptual_physics",
"miscellaneous",
"high_school_chemistry",
"marketing",
"professional_law",
"management",
"college_physics",
"jurisprudence",
"world_religions",
"sociology",
"us_foreign_policy",
"high_school_macroeconomics",
"computer_security",
"moral_scenarios",
"moral_disputes",
"electrical_engineering",
"astronomy",
"college_biology",
]
class MMLUConfig(datasets.BuilderConfig):
def __init__(self, **kwargs):
super().__init__(version=datasets.Version("1.0.0"), **kwargs)
class MMLU(datasets.GeneratorBasedBuilder):
BUILDER_CONFIGS = [
MMLUConfig(
name=task_name,
)
for task_name in task_list
]
def _info(self):
features = datasets.Features(
{
"question": datasets.Value("string"),
"A": datasets.Value("string"),
"B": datasets.Value("string"),
"C": datasets.Value("string"),
"D": datasets.Value("string"),
"answer": datasets.Value("string"),
}
)
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=features,
homepage=_HOMEPAGE,
license=_LICENSE,
citation=_CITATION,
)
def _split_generators(self, dl_manager):
data_dir = dl_manager.download_and_extract(_URL)
task_name = self.config.name
return [
datasets.SplitGenerator(
name=datasets.Split.TEST,
gen_kwargs={
"filepath": os.path.join(data_dir, "data", "test", f"{task_name}_test.csv"),
},
),
datasets.SplitGenerator(
name=datasets.Split.VALIDATION,
gen_kwargs={
"filepath": os.path.join(data_dir, "data", "val", f"{task_name}_val.csv"),
},
),
datasets.SplitGenerator(
name=datasets.Split.TRAIN,
gen_kwargs={
"filepath": os.path.join(data_dir, "data", "dev", f"{task_name}_dev.csv"),
},
),
]
def _generate_examples(self, filepath):
df = pd.read_csv(filepath, header=None)
df.columns = ["question", "A", "B", "C", "D", "answer"]
yield from enumerate(df.to_dict(orient="records"))
examples/README.md
View file @ ca625f43
......@@ -18,19 +18,19 @@ By default, LLaMA-Factory uses all visible computing devices.
Basic usage:
```bash
llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml
llamafactory-cli train examples/train_lora/qwen3_lora_sft.yaml
```
Advanced usage:
```bash
CUDA_VISIBLE_DEVICES=0,1 llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml \
CUDA_VISIBLE_DEVICES=0,1 llamafactory-cli train examples/train_lora/qwen3_lora_sft.yaml \
learning_rate=1e-5 \
logging_steps=1
```
```bash
bash examples/train_lora/llama3_lora_sft.sh
bash examples/train_lora/qwen3_lora_sft.sh
```
## Examples
......@@ -40,49 +40,43 @@ bash examples/train_lora/llama3_lora_sft.sh
#### (Continuous) Pre-Training
```bash
llamafactory-cli train examples/train_lora/llama3_lora_pretrain.yaml
llamafactory-cli train examples/train_lora/qwen3_lora_pretrain.yaml
```
#### Supervised Fine-Tuning
```bash
llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml
llamafactory-cli train examples/train_lora/qwen3_lora_sft.yaml
```
#### Multimodal Supervised Fine-Tuning
```bash
llamafactory-cli train examples/train_lora/qwen2_5vl_lora_sft.yaml
llamafactory-cli train examples/train_lora/qwen3vl_lora_sft.yaml
```
#### DPO/ORPO/SimPO Training
```bash
llamafactory-cli train examples/train_lora/llama3_lora_dpo.yaml
llamafactory-cli train examples/train_lora/qwen3_lora_dpo.yaml
```
#### Multimodal DPO/ORPO/SimPO Training
```bash
llamafactory-cli train examples/train_lora/qwen2_5vl_lora_dpo.yaml
llamafactory-cli train examples/train_lora/qwen3vl_lora_dpo.yaml
```
#### Reward Modeling
```bash
llamafactory-cli train examples/train_lora/llama3_lora_reward.yaml
```
#### PPO Training
```bash
llamafactory-cli train examples/train_lora/llama3_lora_ppo.yaml
llamafactory-cli train examples/train_lora/qwen3_lora_reward.yaml
```
#### KTO Training
```bash
llamafactory-cli train examples/train_lora/llama3_lora_kto.yaml
llamafactory-cli train examples/train_lora/qwen3_lora_kto.yaml
```
#### Preprocess Dataset
......@@ -90,32 +84,26 @@ llamafactory-cli train examples/train_lora/llama3_lora_kto.yaml
It is useful for large dataset, use `tokenized_path` in config to load the preprocessed dataset.
```bash
llamafactory-cli train examples/train_lora/llama3_preprocess.yaml
```
#### Evaluating on MMLU/CMMLU/C-Eval Benchmarks
```bash
llamafactory-cli eval examples/train_lora/llama3_lora_eval.yaml
llamafactory-cli train examples/train_lora/qwen3_preprocess.yaml
```
#### Supervised Fine-Tuning on Multiple Nodes
```bash
FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=0 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml
FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=1 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml
FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=0 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_lora/qwen3_lora_sft.yaml
FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=1 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_lora/qwen3_lora_sft.yaml
```
#### Supervised Fine-Tuning with DeepSpeed ZeRO-3 (Weight Sharding)
```bash
FORCE_TORCHRUN=1 llamafactory-cli train examples/train_lora/llama3_lora_sft_ds3.yaml
FORCE_TORCHRUN=1 llamafactory-cli train examples/train_lora/qwen3_lora_sft_ds3.yaml
```
#### Supervised Fine-Tuning with Ray on 4 GPUs
```bash
USE_RAY=1 llamafactory-cli train examples/train_lora/llama3_lora_sft_ray.yaml
USE_RAY=1 llamafactory-cli train examples/train_lora/qwen3_lora_sft_ray.yaml
```
### QLoRA Fine-Tuning
......@@ -123,13 +111,13 @@ USE_RAY=1 llamafactory-cli train examples/train_lora/llama3_lora_sft_ray.yaml
#### Supervised Fine-Tuning with 4/8-bit Bitsandbytes/HQQ/EETQ Quantization (Recommended)
```bash
llamafactory-cli train examples/train_qlora/llama3_lora_sft_otfq.yaml
llamafactory-cli train examples/train_qlora/qwen3_lora_sft_otfq.yaml
```
#### Supervised Fine-Tuning with 4-bit Bitsandbytes Quantization on Ascend NPU
```bash
llamafactory-cli train examples/train_qlora/llama3_lora_sft_bnb_npu.yaml
llamafactory-cli train examples/train_qlora/qwen3_lora_sft_bnb_npu.yaml
```
#### Supervised Fine-Tuning with 4/8-bit GPTQ Quantization
......@@ -155,14 +143,14 @@ llamafactory-cli train examples/train_qlora/llama3_lora_sft_aqlm.yaml
#### Supervised Fine-Tuning on Single Node
```bash
FORCE_TORCHRUN=1 llamafactory-cli train examples/train_full/llama3_full_sft.yaml
FORCE_TORCHRUN=1 llamafactory-cli train examples/train_full/qwen3_full_sft.yaml
```
#### Supervised Fine-Tuning on Multiple Nodes
```bash
FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=0 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_full/llama3_full_sft.yaml
FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=1 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_full/llama3_full_sft.yaml
FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=0 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_full/qwen3_full_sft.yaml
FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=1 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_full/qwen3_full_sft.yaml
```
### Elastic and Fault-Tolerant Supervised Fine-Tuning on Multiple Nodes
......@@ -170,13 +158,13 @@ FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=1 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500
To launch an elastic job with `MAX_RESTARTS` failures retries, run the following on at least `MIN_NNODES` nodes and at most `MAX_NNODES` nodes. `RDZV_ID` should be set as a unique job id (shared by all nodes participating in the job). See also [torchrun](https://docs.pytorch.org/docs/stable/elastic/run.html).
```bash
FORCE_TORCHRUN=1 MIN_NNODES=1 MAX_NNODES=3 MAX_RESTARTS=3 RDZV_ID=llamafactory MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_full/llama3_full_sft.yaml
FORCE_TORCHRUN=1 MIN_NNODES=1 MAX_NNODES=3 MAX_RESTARTS=3 RDZV_ID=llamafactory MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_full/qwen3_full_sft.yaml
```
#### Multimodal Supervised Fine-Tuning
```bash
FORCE_TORCHRUN=1 llamafactory-cli train examples/train_full/qwen2_5vl_full_sft.yaml
FORCE_TORCHRUN=1 llamafactory-cli train examples/train_full/qwen3vl_full_sft.yaml
```
### Merging LoRA Adapters and Quantization
......@@ -186,19 +174,19 @@ FORCE_TORCHRUN=1 llamafactory-cli train examples/train_full/qwen2_5vl_full_sft.y
Note: DO NOT use quantized model or `quantization_bit` when merging LoRA adapters.
```bash
llamafactory-cli export examples/merge_lora/llama3_lora_sft.yaml
llamafactory-cli export examples/merge_lora/qwen3_lora_sft.yaml
```
#### Quantizing Model using AutoGPTQ
```bash
llamafactory-cli export examples/merge_lora/llama3_gptq.yaml
llamafactory-cli export examples/merge_lora/qwen3_gptq.yaml
```
### Save Ollama modelfile
```bash
llamafactory-cli export examples/merge_lora/llama3_full_sft.yaml
llamafactory-cli export examples/merge_lora/qwen3_full_sft.yaml
```
### Inferring LoRA Fine-Tuned Models
......@@ -206,26 +194,26 @@ llamafactory-cli export examples/merge_lora/llama3_full_sft.yaml
#### Evaluation using vLLM's Multi-GPU Inference
```
python scripts/vllm_infer.py --model_name_or_path meta-llama/Meta-Llama-3-8B-Instruct --template llama3 --dataset alpaca_en_demo
python scripts/vllm_infer.py --model_name_or_path Qwen/Qwen3-4B-Instruct-2507 --template qwen3_nothink --dataset alpaca_en_demo
python scripts/eval_bleu_rouge.py generated_predictions.jsonl
```
#### Use CLI ChatBox
```bash
llamafactory-cli chat examples/inference/llama3_lora_sft.yaml
llamafactory-cli chat examples/inference/qwen3_lora_sft.yaml
```
#### Use Web UI ChatBox
```bash
llamafactory-cli webchat examples/inference/llama3_lora_sft.yaml
llamafactory-cli webchat examples/inference/qwen3_lora_sft.yaml
```
#### Launch OpenAI-style API
```bash
llamafactory-cli api examples/inference/llama3_lora_sft.yaml
llamafactory-cli api examples/inference/qwen3_lora_sft.yaml
```
### Extras
......@@ -290,3 +278,15 @@ llamafactory-cli train examples/extras/llama_pro/llama3_freeze_sft.yaml
```bash
bash examples/extras/fsdp_qlora/train.sh
```
#### OFT Fine-Tuning
```bash
llamafactory-cli train examples/extras/oft/llama3_oft_sft.yaml
```
#### QOFT Fine-Tuning
```bash
llamafactory-cli train examples/extras/qoft/llama3_oft_sft_bnb_npu.yaml
```
examples/README_zh.md
View file @ ca625f43
......@@ -18,19 +18,19 @@ LLaMA-Factory 默认使用所有可见的计算设备。
基础用法：
```bash
llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml
llamafactory-cli train examples/train_lora/qwen3_lora_sft.yaml
```
高级用法：
```bash
CUDA_VISIBLE_DEVICES=0,1 llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml \
CUDA_VISIBLE_DEVICES=0,1 llamafactory-cli train examples/train_lora/qwen3_lora_sft.yaml \
learning_rate=1e-5 \
logging_steps=1
```
```bash
bash examples/train_lora/llama3_lora_sft.sh
bash examples/train_lora/qwen3_lora_sft.sh
```
## 示例
......@@ -40,49 +40,43 @@ bash examples/train_lora/llama3_lora_sft.sh
#### （增量）预训练
```bash
llamafactory-cli train examples/train_lora/llama3_lora_pretrain.yaml
llamafactory-cli train examples/train_lora/qwen3_lora_pretrain.yaml
```
#### 指令监督微调
```bash
llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml
llamafactory-cli train examples/train_lora/qwen3_lora_sft.yaml
```
#### 多模态指令监督微调
```bash
llamafactory-cli train examples/train_lora/qwen2_5vl_lora_sft.yaml
llamafactory-cli train examples/train_lora/qwen3vl_lora_sft.yaml
```
#### DPO/ORPO/SimPO 训练
```bash
llamafactory-cli train examples/train_lora/llama3_lora_dpo.yaml
llamafactory-cli train examples/train_lora/qwen3_lora_dpo.yaml
```
#### 多模态 DPO/ORPO/SimPO 训练
```bash
llamafactory-cli train examples/train_lora/qwen2_5vl_lora_dpo.yaml
llamafactory-cli train examples/train_lora/qwen3vl_lora_dpo.yaml
```
#### 奖励模型训练
```bash
llamafactory-cli train examples/train_lora/llama3_lora_reward.yaml
```
#### PPO 训练
```bash
llamafactory-cli train examples/train_lora/llama3_lora_ppo.yaml
llamafactory-cli train examples/train_lora/qwen3_lora_reward.yaml
```
#### KTO 训练
```bash
llamafactory-cli train examples/train_lora/llama3_lora_kto.yaml
llamafactory-cli train examples/train_lora/qwen3_lora_kto.yaml
```
#### 预处理数据集
......@@ -90,20 +84,14 @@ llamafactory-cli train examples/train_lora/llama3_lora_kto.yaml
对于大数据集有帮助，在配置中使用 `tokenized_path` 以加载预处理后的数据集。
```bash
llamafactory-cli train examples/train_lora/llama3_preprocess.yaml
```
#### 在 MMLU/CMMLU/C-Eval 上评估
```bash
llamafactory-cli eval examples/train_lora/llama3_lora_eval.yaml
llamafactory-cli train examples/train_lora/qwen3_preprocess.yaml
```
#### 多机指令监督微调
```bash
FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=0 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml
FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=1 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml
FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=0 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_lora/qwen3_lora_sft.yaml
FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=1 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_lora/qwen3_lora_sft.yaml
```
### 支持弹性和容错的多机指令监督微调
......@@ -111,19 +99,19 @@ FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=1 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500
要启动一个支持弹性节点和容错的多机指令微调，在每个节点上执行以下命令。弹性节点数量范围为 `MIN_NNODES:MAX_NNODES`，每个节点最多允许因为错误重启 `MAX_RESTARTS` 次。`RDZV_ID` 应设置为一个唯一的作业 ID（由参与该作业的所有节点共享）。更多新可以参考官方文档 [torchrun](https://docs.pytorch.org/docs/stable/elastic/run.html)。
```bash
FORCE_TORCHRUN=1 MIN_NNODES=1 MAX_NNODES=3 MAX_RESTARTS=3 RDZV_ID=llamafactory MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_full/llama3_full_sft.yaml
FORCE_TORCHRUN=1 MIN_NNODES=1 MAX_NNODES=3 MAX_RESTARTS=3 RDZV_ID=llamafactory MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_full/qwen3_full_sft.yaml
```
#### 使用 DeepSpeed ZeRO-3 平均分配显存
```bash
FORCE_TORCHRUN=1 llamafactory-cli train examples/train_lora/llama3_lora_sft_ds3.yaml
FORCE_TORCHRUN=1 llamafactory-cli train examples/train_lora/qwen3_lora_sft_ds3.yaml
```
#### 使用 Ray 在 4 张 GPU 上微调
```bash
USE_RAY=1 llamafactory-cli train examples/train_lora/llama3_lora_sft_ray.yaml
USE_RAY=1 llamafactory-cli train examples/train_lora/qwen3_lora_sft_ray.yaml
```
### QLoRA 微调
......@@ -131,13 +119,13 @@ USE_RAY=1 llamafactory-cli train examples/train_lora/llama3_lora_sft_ray.yaml
#### 基于 4/8 比特 Bitsandbytes/HQQ/EETQ 量化进行指令监督微调（推荐）
```bash
llamafactory-cli train examples/train_qlora/llama3_lora_sft_otfq.yaml
llamafactory-cli train examples/train_qlora/qwen3_lora_sft_otfq.yaml
```
#### 在 NPU 上基于 4 比特 Bitsandbytes 量化进行指令监督微调
```bash
llamafactory-cli train examples/train_qlora/llama3_lora_sft_bnb_npu.yaml
llamafactory-cli train examples/train_qlora/qwen3_lora_sft_bnb_npu.yaml
```
#### 基于 4/8 比特 GPTQ 量化进行指令监督微调
......@@ -163,20 +151,20 @@ llamafactory-cli train examples/train_qlora/llama3_lora_sft_aqlm.yaml
#### 在单机上进行指令监督微调
```bash
FORCE_TORCHRUN=1 llamafactory-cli train examples/train_full/llama3_full_sft.yaml
FORCE_TORCHRUN=1 llamafactory-cli train examples/train_full/qwen3_full_sft.yaml
```
#### 在多机上进行指令监督微调
```bash
FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=0 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_full/llama3_full_sft.yaml
FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=1 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_full/llama3_full_sft.yaml
FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=0 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_full/qwen3_full_sft.yaml
FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=1 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/train_full/qwen3_full_sft.yaml
```
#### 多模态指令监督微调
```bash
FORCE_TORCHRUN=1 llamafactory-cli train examples/train_full/qwen2_5vl_full_sft.yaml
FORCE_TORCHRUN=1 llamafactory-cli train examples/train_full/qwen3vl_full_sft.yaml
```
### 合并 LoRA 适配器与模型量化
......@@ -186,19 +174,19 @@ FORCE_TORCHRUN=1 llamafactory-cli train examples/train_full/qwen2_5vl_full_sft.y
注：请勿使用量化后的模型或 `quantization_bit` 参数来合并 LoRA 适配器。
```bash
llamafactory-cli export examples/merge_lora/llama3_lora_sft.yaml
llamafactory-cli export examples/merge_lora/qwen3_lora_sft.yaml
```
#### 使用 AutoGPTQ 量化模型
```bash
llamafactory-cli export examples/merge_lora/llama3_gptq.yaml
llamafactory-cli export examples/merge_lora/qwen3_gptq.yaml
```
### 保存 Ollama 配置文件
```bash
llamafactory-cli export examples/merge_lora/llama3_full_sft.yaml
llamafactory-cli export examples/merge_lora/qwen3_full_sft.yaml
```
### 推理 LoRA 模型
......@@ -206,26 +194,26 @@ llamafactory-cli export examples/merge_lora/llama3_full_sft.yaml
#### 使用 vLLM 多卡推理评估
```
python scripts/vllm_infer.py --model_name_or_path meta-llama/Meta-Llama-3-8B-Instruct --template llama3 --dataset alpaca_en_demo
python scripts/vllm_infer.py --model_name_or_path Qwen/Qwen3-4B-Instruct-2507 --template qwen3_nothink --dataset alpaca_en_demo
python scripts/eval_bleu_rouge.py generated_predictions.jsonl
```
#### 使用命令行对话框
```bash
llamafactory-cli chat examples/inference/llama3_lora_sft.yaml
llamafactory-cli chat examples/inference/qwen3_lora_sft.yaml
```
#### 使用浏览器对话框
```bash
llamafactory-cli webchat examples/inference/llama3_lora_sft.yaml
llamafactory-cli webchat examples/inference/qwen3_lora_sft.yaml
```
#### 启动 OpenAI 风格 API
```bash
llamafactory-cli api examples/inference/llama3_lora_sft.yaml
llamafactory-cli api examples/inference/qwen3_lora_sft.yaml
```
### 杂项
......@@ -290,3 +278,15 @@ llamafactory-cli train examples/extras/llama_pro/llama3_freeze_sft.yaml
```bash
bash examples/extras/fsdp_qlora/train.sh
```
#### OFT 微调
```bash
llamafactory-cli train examples/extras/oft/llama3_oft_sft.yaml
```
#### QOFT 微调
```bash
llamafactory-cli train examples/extras/qoft/llama3_oft_sft_bnb_npu.yaml
```
examples/accelerate/fsdp2_config.yaml 0 → 100644
View file @ ca625f43
compute_environment: LOCAL_MACHINE
debug: false
distributed_type: FSDP
downcast_bf16: 'no'
fsdp_config:
fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
fsdp_cpu_ram_efficient_loading: true
fsdp_offload_params: false
fsdp_reshard_after_forward: true
fsdp_state_dict_type: FULL_STATE_DICT
fsdp_version: 2
machine_rank: 0
main_training_function: main
mixed_precision: bf16 # or fp16
num_machines: 1 # the number of nodes
num_processes: 2 # the number of GPUs in all nodes
rdzv_backend: static
same_network: true
tpu_env: []
tpu_use_cluster: false
tpu_use_sudo: false
use_cpu: false
examples/accelerate/fsdp_config_multiple_nodes.yaml 0 → 100644
View file @ ca625f43
# If you want to run this example on multiple nodes, you need to set the following parameters:
# - num_machines: the number of nodes
# - num_processes: the number of GPUs in all nodes, num_machines * num_processes_per_machine
# - main_process_ip: the IP address of the main process, please keep it the same across all nodes
# - main_process_port: the port of all nodes, please keep it the same across all nodes
# - machine_rank: the rank of the current machine, starting from 0, and it should be 0 for main_process_ip
compute_environment: LOCAL_MACHINE
debug: false
distributed_type: FSDP
downcast_bf16: 'no'
fsdp_config:
fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
fsdp_backward_prefetch: BACKWARD_PRE
fsdp_forward_prefetch: false
fsdp_cpu_ram_efficient_loading: true
fsdp_offload_params: false
fsdp_sharding_strategy: FULL_SHARD
fsdp_state_dict_type: FULL_STATE_DICT
fsdp_sync_module_states: true
fsdp_use_orig_params: true
machine_rank: 0
main_training_function: main
mixed_precision: bf16 # or fp16
main_process_ip: 192.168.0.1
main_process_port: 29500
num_machines: 2 # the number of nodes
num_processes: 16 # the number of GPUs in all nodes, num_machines * num_processes_per_machine
rdzv_backend: static
same_network: true
tpu_env: []
tpu_use_cluster: false
tpu_use_sudo: false
use_cpu: false
examples/ascend/qwen3_full_sft_fsdp2.yaml 0 → 100644
View file @ ca625f43
# Start FSDP2 fine-tuning
# accelerate launch \
# --config_file examples/accelerate/fsdp2_config.yaml \
# src/train.py examples/ascend/qwen3_full_sft_fsdp2.yaml
# Change `num_processes` in fsdp2_config.yaml to 16 in A3
### model
model_name_or_path: Qwen/Qwen3-8B
trust_remote_code: true
use_v1_kernels: true
flash_attn: fa2
### method
stage: sft
do_train: true
finetuning_type: full
### dataset
dataset: alpaca_en_demo
template: qwen3
cutoff_len: 2048
max_samples: 1000
overwrite_cache: true
preprocessing_num_workers: 16
dataloader_num_workers: 4
### output
output_dir: saves/Qwen3-8B/full/sft
logging_steps: 1
save_steps: 500
max_steps: 500
plot_loss: true
overwrite_output_dir: true
save_only_model: false
report_to: none # choices: [none, wandb, tensorboard, swanlab, mlflow]
### train
per_device_train_batch_size: 8
gradient_accumulation_steps: 1
learning_rate: 1.0e-5
lr_scheduler_type: cosine
warmup_ratio: 0.1
bf16: true
ddp_timeout: 1800
resume_from_checkpoint: null
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment