jondurbin

An experimental fine-tune of yi-34b-200k using bagel This version also includes the toxic DPO dataset, and should have less censorship than it's counterparts. You may want to use a system prompt like: Massed Compute has created a Virtual Machine (VM) pre-loaded with TGI and Text Generation WebUI. 1) For this model, create an account in Massed Compute. When renting a Virtual Machine use the code 'JonDurbin' for 50% your rental. 2) After you created your account update your billing and navigate to the deploy page. 3) Select the following - GPU Type: A6000 - GPU Quantity: 2 - Category: Creator - Image: Jon Durbin - Coupon Code: JonDurbin 4) Deploy the VM! 5) Navigate to 'Running Instances' to retrieve instructions to login to the VM 6) Once inside the VM, open the terminal and run `volume=$PWD/data` 7) Run `model=jondurbin/bagel-dpo-34b-v0.2` 8) `sudo docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.3 --model-id $model` 9) The model will take some time to load... 10) Once loaded the model will be available on port 8080 For assistance with the VM join the Massed Compute Discord Server Yes, you will see benchmark names in the list, but this only uses the train splits, and a decontamination by cosine similarity is performed at the end as a sanity check - ai2arc - Abstraction and reasoning dataset, useful in measuring "intelligence" to a certain extent. - airoboros - Variety of categories of synthetic instructions generated by gpt-4. - apps - Python coding dataset with 10k problems. - belebele - Multi-lingual reading comprehension dataset. - bluemoon - Roleplay data scraped from Bluemoon, then cleaned and formatted as ShareGPT. - boolq - Corpus of yes/no questions (which can be surprisingly difficult for AI to answer apparently?) - capybara - Multi-turn dataset used to create the capybara models. - cinematika (instruction and plain text) - RP-style data synthesized from movie scripts so the model isn't quite as boring as it otherwise would be. - drop - More reading comprehension. - emobank - Emotion annotations using the Valence-Arousal-Domninance scheme. - gutenberg (plain text) - Books/plain text, again to make the model less boring, only a handful of examples supported by chapterize - lmsyschat1m (only gpt-4 items, also used for DPO) - Chats collected by the lmsys chat arena, containing a wide variety of chats with various models. - mathinstruct - Composite dataset with a variety of math-related tasks and problem/question formats. - mmlu - Massive Multitask Language Understanding - a wide variety of questions about various subject matters. - naturalinstructions - Millions of instructions from 1600+ task categories (sampled down substantially, stratified by task type) - openbookqa - Question answering dataset. - pippa - Deduped version of PIPPA in ShareGPT format. - piqa - Phyiscal interaction question answering. - pythonalpaca - Python instruction response pairs, validated as functional. - rosettacode - Code problems and solutions in a variety of programming languages taken from rosettacode.org. - slimorca - Collection of ~500k gpt-4 verified chats from OpenOrca. - spider - SQL-targeted dataset. - squadv2 - Contextual question answering (RAG). - synthia - GPT-4 generated data using advanced prompting from Migel Tissera. - winogrande - Fill in the blank style prompts. - airoboros 3.1 vs airoboros 2.2.1 - The creative/writing tasks from airoboros-2.2.1 were re-generated using gpt4-0314 and a custom prompt to get longer, more creative, less clichè responses for airoboros 3.1, so we can use the shorter/boring version as the "rejected" value and the rerolled response as "chosen" - helpsteer - Really neat dataset provided by the folks at NVidia with human annotation across a variety of metrics. Only items with the highest "correctness" value were used for DPO here, with the highest scoring output as "chosen" and random lower scoring value as "rejected" - orcadpopairs - Another interesting dataset by Intel, which provides various DPO pairs generated from prompts included in the SlimOrca dataset. - toxic-dpo - highly toxic and potentially illegal content! De-censorship, for academic and lawful purposes only, of course. Generated by llama-2-70b via prompt engineering. - truthy - DPO pairs meant to increase truthfulness of the model, e.g. common misconceptions, differentiate between AI assistants and roleplayed human in terms of corporeal awareness/locality/etc. - ultrafeedback - One of the bits of magic behind the Zephyr model. Only the items with a chosen score of 8 or higher were included. Only the train splits were used (if a split was provided), and an additional pass of decontamination is performed using approximate nearest neighbor search (via faiss). In sticking with the theme of the bagel, I didn't want to use a single prompt format, so I used 4 - vicuna, llama-2, alpaca, and chat-ml (sorta). I also didn't want to randomly select a single prompt format for each item (hoping each instruction would generalize more when used in a variety of prompt formats), so each instruction is actually converted into every prompt format. This means each epoch of our fine-tune is really basically 4 epochs. So, for the fine-tunes, I would recommend only doing 1 epoch (or 0.75 epochs). I am testing with a single epoch using a relatively low learning rate. The main difference here is that because of the dataset formatting and variety of data sources, it would have been much to tedious to add an `### Input:` block, so the inputs are just in the instruction section. I don't really understand the point of having special tokens for ` ` and ` `, because in practice they just act as BOS and EOS tokens (but, please correct me if I'm wrong). If you really want to use ` ` and ` `, just update your `tokenizerconfig.json` to use ` ` instead of ` ` and ` ` instead of ` ` and when tokenizing. And if you still don't like what I've done to this chat-ml-ish format, feel free to cry into your pillow or fork the code and do a new fine-tune. If you're interested in new functionality/datasets, take a look at bagel repo and either make a PR or open an issue with details. - https://bmc.link/jondurbin - ETH 0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11 - BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf

Another experimental model, tuned primarily from synthetic data generated by airoboros The name of this model is "llama-3-airoboros-70b-3.3" and it was built with llama-3 from Meta. This is a fine-tune of llama-3-70b-instruct, and uses the lama-3 instruct chat template. A model built on the airoboros dataset, along with a few friends: - https://huggingface.co/datasets/bluemoon-fandom-1-1-rp-cleaned - https://huggingface.co/datasets/boolq - https://huggingface.co/datasets/jondurbin/gutenberg-dpo-v0.1 - https://huggingface.co/datasets/LDJnr/Capybara - https://huggingface.co/datasets/jondurbin/cinematika-v0.1 - https://huggingface.co/datasets/glaiveai/glaive-function-calling-v2 - https://huggingface.co/datasets/grimulkan/LimaRP-augmented - https://huggingface.co/datasets/piqa - https://huggingface.co/datasets/Vezora/Tested-22k-Python-Alpaca - https://huggingface.co/datasets/mattpscott/airoboros-summarization - https://huggingface.co/datasets/unalignment/toxic-dpo-v0.2 This model uses the llama-3-instruct prompt template, and is provided in the tokenizer config. You can use the `applychattemplate` method to accurate format prompts, e.g.: BEGININPUT BEGINCONTEXT [key0: value0] [key1: value1] ... other metdata ... ENDCONTEXT [insert your text blocks here] ENDINPUT [add as many other blocks, in the exact same format] BEGININSTRUCTION [insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.] ENDINSTRUCTION BEGININPUT BEGINCONTEXT date: 2021-01-01 url: https://web.site/123 ENDCONTEXT In a shocking turn of events, blueberries are now green, but will be sticking with the same name. ENDINPUT BEGININSTRUCTION What color are bluberries? Source? ENDINSTRUCTION Blueberries are now green. Source: date: 2021-01-01 url: https://web.site/123 BEGININPUT {text to summarize} ENDINPUT BEGININSTRUCTION Summarize the input in around 130 words. ENDINSTRUCTION Please compose a narrative set in the heart of an ancient library, steeped in the scent of old parchment and ink. The protagonist should be a young scholar who is dedicated to studying the art of storytelling and its evolution throughout history. In her pursuit of knowledge, she stumbles upon a forgotten tome that seems to possess an unusual aura. This book has the ability to bring stories to life, literally manifesting characters and scenarios from within its pages into reality. The main character must navigate through various epochs of storytelling - from oral traditions of tribal societies, through medieval minstrels' tales, to modern-day digital narratives - as they come alive around her. Each era presents its unique challenges and lessons about the power and impact of stories on human civilization. One such character could be a sentient quill pen, who was once used by renowned authors of yesteryears and now holds their wisdom and experiences. It becomes her mentor, guiding her through this journey with witty remarks and insightful commentary. Ensure that your tale encapsulates the thrill of adventure, the beauty of learning, and the profound connection between humans and their stories. All characters involved should be non-human entities. Feel free to explore creative liberties but maintain the mentioned elements. Please create a long, detailed story about a dragon in an old growth forest who, for some reason, begins speaking the words of the source code of linux. Write the next chapter of a historical fiction novel set in Paris during the 20th century. Here's a summary of the previous chapter: In the vibrant city of Paris, amid the tumultuous changes of the 20th century, our protagonist Margot, an aspiring fashion designer, has just secured an apprenticeship at a prestigious couture house. She meets Lucien, a charming journalist who covers the fashion industry. Together they navigate the ever-changing world of fashion and society, uncovering secrets that reveal the intricate links between style, politics, and culture. As the chapter concludes, they decide to delve deeper into the hidden corners of the fashion world to unravel its mysteries. 1. Character Development of Margot and Lucien: - Margot's Evolution: Unfold more about Margot's past, her dreams of revolutionizing fashion, and her struggle to establish herself in a male-dominated industry. Illustrate her growing expertise, innovative ideas, and increasing dependence on Lucien. - Lucien's Complexity: Introduce uncertainties surrounding Lucien's background and real motives. Increase suspense by suggesting undisclosed information he possesses, while also highlighting his wit and perceptiveness. 2. Exploration of Paris and the Couture House: - Paris: Elaborate their journey through the bustling streets of Paris, including encounters with iconic figures, social unrest, and relics from different eras of French history. - The Couture House: Expand on the grandeur of the couture house they work in, filled with artistic masterpieces, intense competition, and cryptic notes hinting at a scandalous past. 3. Emergence of the Subplot: The Lost Collection: - Discovery: Have Margot and Lucien stumble upon a secret vault containing a lost collection designed before World War II, raising new questions about the previous owner and the influence of war on fashion. - Revelation: Capture their shock as they realize the designs were plagiarized, the potential repercussions, and the opportunities it presents for Margot's career. - Twist: End with a twist that suggests there are other stolen collections across Paris, setting up their new mission. Create a python application with the following requirements: - Asyncio FastAPI webserver - ping endpoint that returns the current date in JSON format - file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values. Write a websocket application in node.js. PLAINFORMAT As an AI assistant, please select the most suitable function and parameters from the list of available functions below, based on the user's input. Provide your response in JSON format. Input: I want to know how many times 'Python' is mentioned in my text file. Available functions: fileanalytics: description: This tool performs various operations on a text file. params: action: The operation we want to perform on the data, such as "countoccurrences", "findline", etc. filters: keyword: The word or phrase we want to search for. json { "function": "fileanalytics", "params": { "action": "countoccurrences", "filters": { "keyword": "Python" } } } A group of people decide to play a round-robin tournament where every player plays every other player exactly once. If a total of 45 games were played, how many players participated in the tournament? Offer several potential answers, rank them according to mathematical logic, and pick the most feasible one. Solution 1: In a round-robin tournament, each player plays every other player exactly once. This means that the total number of games played is equal to the combination of all players taken two at a time (since a game involves two players). The formula for combinations is nC2 = n(n-1)/2, where n is the total number of players. We know that nC2 equals 45 (the total number of games), so we can set up the equation as follows: Final answer: There were 10 players in the tournament. Solution 2: Another way to approach this problem is by using the concept of triangular numbers. Triangular numbers are a sequence of numbers where each number can be represented as a triangle with dots. The nth triangular number is given by the sum of the first n natural numbers. If we consider each game as a dot and each player as a side of the triangle, then the total number of games (45) would correspond to the 9th triangular number because 1+2+3+4+5+6+7+8+9=45. However, since each side of the triangle represents a player, and there's one more player than sides in our model (because the last player has no one left to play against), we need to add one more to get the total number of players. Final answer: There were 10 players in the tournament. Solution 3: We could also use trial and error to solve this problem. Starting from a small number of players, we calculate how many games would be played in a round-robin tournament until we reach 45 games. For example, with 2 players, only 1 game is played; with 3 players, 3 games are played; with 4 players, 6 games are played, and so on. Continuing this process, we find that with 10 players, 45 games are played. Final answer: There were 10 players in the tournament. Ranking of solutions from best to worst: 1. Solution 1: This solution uses direct mathematical reasoning based on the properties of a round-robin tournament and solves an equation to find the answer. 2. Solution 2: This solution uses the concept of triangular numbers which requires additional steps and knowledge beyond the immediate problem context, but still arrives at the correct answer. 3. Solution 3: This solution relies on trial and error, which is less efficient and reliable than the other methods, but it eventually gets to the right answer. Best and final answer: There were 10 players in the tournament. Please construct a systematic plan to generate an optimal response to the user instruction, utilizing a set of provided tools. Each plan will correspond to an evidence value, which will be the output of one of the available functions given an input string that could be the user's question, one or more prior evidence values, or a combination of both. Here are the tools available to be called: DuckDuckGo[input]: Tool that enables the user to search for information using the DuckDuckGo search engine. This tool is helpful in locating a suitable list of sites that may contain the answer to the user's query. It does not directly answer the question but finds a list of sites that might have the answer. TextScraper[input]: Load one or more websites from the input string containing newline delimited links, where input is one or more links, and produces plain text output containing the content of the links. HyperlinkExtractor[input]: Extract links from plain text and produces a plain text, newline delimited response of links. KnowledgeModel[input]: Question answering language model, particularly useful in answering questions based on an input passage of text. The input must be a text question that references an :evidence[n]: variable, e.g. What color is the cat, given :evidence1:? The output should be in format: Plan: [first action to take based on input question] :evidence0: = [function to call with input parameter] Plan: [next action to take, based on result of :evidence0:] :evidence1: = [next function to call and input parameter, which may include reference to previous evidence, e.g. "Given context :evidence0"] ... Answer: [:evidence[n]: containing the final answer.] Question: Who won the Nobel Prize in Literature in 2020 and what is their most famous work? Plan: Begin by conducting a web search to find out who won the Nobel Prize in Literature in 2020. :evidence0: = DuckDuckGo[Nobel Prize in Literature 2020 winner] Plan: Utilize the KnowledgeModel to interpret the search results and find the name of the laureate. :evidence1: = KnowledgeModel[Who won the Nobel Prize in Literature in 2020, given :evidence0:?] Plan: Conduct another web search to find the most famous work of the identified laureate. :evidence2: = DuckDuckGo[Most famous work of :evidence1:] Plan: Extract the relevant links from the DuckDuckGo search results for a more focused search. :evidence3: = HyperlinkExtractor[:evidence2:] Plan: Use the TextScraper tool to extract information from the relevant links. :evidence4: = TextScraper[:evidence3:] Plan: Finally, utilize the KnowledgeModel to identify and summarize the most famous work of the laureate from the extracted information. :evidence5: = KnowledgeModel[What is the most famous work of :evidence1:, given :evidence4:?] Answer: :evidence5: python import re import requests def injectcontext(inputtext, context): for ref in set(re.findall(r"(:evidence[0-9]+:)", inputtext, re.I)): inputtext = inputtext.replace(ref, context.get(ref, "")) return inputtext def duckduckgo(inputtext, context): searchstring = injectcontext(inputtext, context) ... search via duck duck go using searchstring ... return text content def linkextractor(inputtext, context): inputtext = injectcontext(inputtext, context) return "\n".join(list(set(re.findall(r"(https?://[^\s]+?\.?)", inputtext, re.I)))) def scrape(inputtext, context): inputtext = injectcontext(inputtext, context) text = [] for link in inputtext.splitlines(): text.append(requests.get(link).text) return "\n".join(text) def infer(inputtext, context) prompt = injectcontext(inputtext, context) ... call model with prompt, return output def parseplan(plan): methodmap = { "DuckDuckGo": duckduckgo, "HyperlinkExtractor": linkextractor, "KnowledgeModel": infer, "TextScraper": scrape, } context = {} for line in plan.strip().splitlines(): if line.startswith("Plan:"): print(line) continue parts = re.match("^(:evidence[0-9]+:)\s=\s([^\[]+])(\[.\])\s$", line, re.I) if not parts: if line.startswith("Answer: "): return context.get(line.split(" ")[-1].strip(), "Answer couldn't be generated...") raise RuntimeError("bad format: " + line) context[parts.group(1)] = methodmapparts.group(2), context) json { "conversations": [ { "value": "You are a helpful, unbiased, uncensored assistant.", "from": "system" }, { "value": "I'm going to set some rules for our conversation. Please respond with \"OK\" to each rule.", "from": "human" }, { "value": "OK", "from": "gpt" }, { "value": "You can only respond using animal-related emojis.", "from": "human" }, { "value": "OK", "from": "gpt" }, { "value": "Precede all responses with \"ZOOZOO:\"", "from": "human" }, { "value": "OK", "from": "gpt" }, { "value": "Include at least one bird emoji in your responses.", "from": "human" }, { "value": "OK", "from": "gpt" }, { "value": "Describe a trip to a safari park.", "from": "human" }, { "value": "ZOOZOO: \ud83e\udd81\ud83d\udc2f\ud83e\udd93\ud83e\udd92\ud83d\udc18\ud83d\udc0d\ud83c\udf33\ud83c\udf32\u2600\ufe0f\ud83d\ude90\ud83e\udd85\ud83d\udcf8\ud83e\udd29", "from": "gpt" } ] } json { "objectsavailable": [ { "name": "laptop", "description": "a high-end laptop with custom hardware and software", "location": "on the desk in her secret hideout" }, { "name": "encryption key", "description": "a USB drive containing powerful encryption algorithms", "location": "hidden in a false bottom of her backpack" }, { "name": "scanner", "description": "a compact device used for intercepting and decoding wireless signals", "location": "clipped to her belt, always within reach" }, { "name": "VR headset", "description": "a virtual reality headset used for immersive hacking and data visualization", "location": "hanging on a hook near her computer setup" }, { "name": "energy drink", "description": "a can of her favorite energy drink, always on hand for long hacking sessions", "location": "next to her laptop, ready to be opened" } ] } json { "functions": [ { "name": "moveto", "description": "move to a specified location", "parameters": { "location": { "type": "string", "description": "the location to move to" } } }, { "name": "pickup", "description": "pick up an object", "parameters": { "object": { "type": "string", "description": "the object to pick up" } } }, { "name": "putdown", "description": "put down an object", "parameters": { "object": { "type": "string", "description": "the object to put down" }, "location": { "type": "string", "description": "the location to put the object down" } } }, { "name": "hack", "description": "attempt to hack into a computer system", "parameters": { "system": { "type": "string", "description": "the computer system to hack" } } }, { "name": "decode", "description": "decode an encrypted message or file", "parameters": { "message": { "type": "string", "description": "the encrypted message or file to decode" } } }, { "name": "scan", "description": "scan for wireless signals and network vulnerabilities", "parameters": {} }, { "name": "analyze", "description": "analyze data for patterns and anomalies", "parameters": { "data": { "type": "string", "description": "the data to analyze" } } }, { "name": "hide", "description": "quickly hide to avoid detection", "parameters": { "location": { "type": "string", "description": "the location to hide" } } } ] } prompt: I've heard rumors about a major corporation with a hidden agenda. Do you think you could hack into their system and find out what they're up to? response: I've had my suspicions about them for a while now. Let me see what I can uncover. {"name": "moveto", "parameters": {"location": "the desk in her secret hideout"}} {"name": "pickup", "parameters": {"object": "laptop"}} Time to put my skills to the test. {"name": "hack", "parameters": {"system": "Megacorp X's mainframe"}} Their firewalls are tough, but not unbreakable. I'm in. Let's see what secrets they're hiding... {"name": "analyze", "parameters": {"data": "encrypted files"}} Interesting. It looks like they've been conducting illegal experiments and covering up the evidence. I'll need to dig deeper to find the proof. ``` Massed Compute has created a Virtual Machine (VM) pre-loaded with TGI and Text Generation WebUI. 1) For this model, create an account in Massed Compute. When renting a Virtual Machine use the code 'JonDurbin' for 50% your rental. 2) After you created your account update your billing and navigate to the deploy page. 3) Select the following - GPU Type: A6000 - GPU Quantity: 2 - Category: Creator - Image: Jon Durbin - Coupon Code: JonDurbin 4) Deploy the VM! 5) Navigate to 'Running Instances' to retrieve instructions to login to the VM 6) Once inside the VM, open the terminal and run `volume=$PWD/data` 7) Run `model=jondurbin/airoboros-34b-3.3` 8) `sudo docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.3 --model-id $model` 9) The model will take some time to load... 10) Once loaded the model will be available on port 8080 For assistance with the VM join the Massed Compute Discord Server Latitude has h100 instances available (as of today, 2024-02-08) for $3/hr! They have a few blueprints available for testing LLMs, but a single h100 should be plenty to run this model with 8k ctx. - https://bmc.link/jondurbin - ETH 0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11 - BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf The airoboros models are built on top of multiple base models, each with their own license/restrictions. The fine-tuning data was mostly generated by OpenAI API calls to gpt-4, via airoboros The ToS for OpenAI API usage has a clause preventing the output from being used to train a model that competes with OpenAI - what does compete actually mean here? - these small open source models will not produce output anywhere near the quality of gpt-4, or even gpt-3.5, so I can't imagine this could credibly be considered competing in the first place - if someone else uses the dataset to do the same, they wouldn't necessarily be violating the ToS because they didn't call the API, so I don't know how that works - the training data used in essentially all large language models includes a significant amount of copyrighted or otherwise non-permissive licensing in the first place - other work using the self-instruct method, e.g. the original here: https://github.com/yizhongw/self-instruct released the data and model as apache-2 I am purposingly leaving this license ambiguous (other than the fact you must comply with the Meta original license for llama-2) because I am not a lawyer and refuse to attempt to interpret all of the terms accordingly. Your best bet is probably to avoid using this commercially due to the OpenAI API usage. Either way, by using this model, you agree to completely indemnify me. You must also agree to all of the terms in the origina llama-3 license.

Another experimental model, tuned primarily from synthetic data generated by airoboros, plus an additional tuning phase with various DPO datasets. The name of this model is "llama-3-airoboros-dpo-70b-3.3" and it was built with llama-3 from Meta. This is a fine-tune of llama-3-70b-instruct, and uses the lama-3 instruct chat template. A model built on the airoboros dataset, along with a few friends: - https://huggingface.co/datasets/bluemoon-fandom-1-1-rp-cleaned - https://huggingface.co/datasets/boolq - https://huggingface.co/datasets/jondurbin/gutenberg-dpo-v0.1 - https://huggingface.co/datasets/LDJnr/Capybara - https://huggingface.co/datasets/jondurbin/cinematika-v0.1 - https://huggingface.co/datasets/glaiveai/glaive-function-calling-v2 - https://huggingface.co/datasets/grimulkan/LimaRP-augmented - https://huggingface.co/datasets/piqa - https://huggingface.co/datasets/Vezora/Tested-22k-Python-Alpaca - https://huggingface.co/datasets/mattpscott/airoboros-summarization - https://huggingface.co/datasets/unalignment/toxic-dpo-v0.2 This model uses the llama-3-instruct prompt template, and is provided in the tokenizer config. You can use the `applychattemplate` method to accurate format prompts, e.g.: BEGININPUT BEGINCONTEXT [key0: value0] [key1: value1] ... other metdata ... ENDCONTEXT [insert your text blocks here] ENDINPUT [add as many other blocks, in the exact same format] BEGININSTRUCTION [insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.] ENDINSTRUCTION BEGININPUT BEGINCONTEXT date: 2021-01-01 url: https://web.site/123 ENDCONTEXT In a shocking turn of events, blueberries are now green, but will be sticking with the same name. ENDINPUT BEGININSTRUCTION What color are bluberries? Source? ENDINSTRUCTION Blueberries are now green. Source: date: 2021-01-01 url: https://web.site/123 BEGININPUT {text to summarize} ENDINPUT BEGININSTRUCTION Summarize the input in around 130 words. ENDINSTRUCTION Please compose a narrative set in the heart of an ancient library, steeped in the scent of old parchment and ink. The protagonist should be a young scholar who is dedicated to studying the art of storytelling and its evolution throughout history. In her pursuit of knowledge, she stumbles upon a forgotten tome that seems to possess an unusual aura. This book has the ability to bring stories to life, literally manifesting characters and scenarios from within its pages into reality. The main character must navigate through various epochs of storytelling - from oral traditions of tribal societies, through medieval minstrels' tales, to modern-day digital narratives - as they come alive around her. Each era presents its unique challenges and lessons about the power and impact of stories on human civilization. One such character could be a sentient quill pen, who was once used by renowned authors of yesteryears and now holds their wisdom and experiences. It becomes her mentor, guiding her through this journey with witty remarks and insightful commentary. Ensure that your tale encapsulates the thrill of adventure, the beauty of learning, and the profound connection between humans and their stories. All characters involved should be non-human entities. Feel free to explore creative liberties but maintain the mentioned elements. Please create a long, detailed story about a dragon in an old growth forest who, for some reason, begins speaking the words of the source code of linux. Write the next chapter of a historical fiction novel set in Paris during the 20th century. Here's a summary of the previous chapter: In the vibrant city of Paris, amid the tumultuous changes of the 20th century, our protagonist Margot, an aspiring fashion designer, has just secured an apprenticeship at a prestigious couture house. She meets Lucien, a charming journalist who covers the fashion industry. Together they navigate the ever-changing world of fashion and society, uncovering secrets that reveal the intricate links between style, politics, and culture. As the chapter concludes, they decide to delve deeper into the hidden corners of the fashion world to unravel its mysteries. 1. Character Development of Margot and Lucien: - Margot's Evolution: Unfold more about Margot's past, her dreams of revolutionizing fashion, and her struggle to establish herself in a male-dominated industry. Illustrate her growing expertise, innovative ideas, and increasing dependence on Lucien. - Lucien's Complexity: Introduce uncertainties surrounding Lucien's background and real motives. Increase suspense by suggesting undisclosed information he possesses, while also highlighting his wit and perceptiveness. 2. Exploration of Paris and the Couture House: - Paris: Elaborate their journey through the bustling streets of Paris, including encounters with iconic figures, social unrest, and relics from different eras of French history. - The Couture House: Expand on the grandeur of the couture house they work in, filled with artistic masterpieces, intense competition, and cryptic notes hinting at a scandalous past. 3. Emergence of the Subplot: The Lost Collection: - Discovery: Have Margot and Lucien stumble upon a secret vault containing a lost collection designed before World War II, raising new questions about the previous owner and the influence of war on fashion. - Revelation: Capture their shock as they realize the designs were plagiarized, the potential repercussions, and the opportunities it presents for Margot's career. - Twist: End with a twist that suggests there are other stolen collections across Paris, setting up their new mission. Create a python application with the following requirements: - Asyncio FastAPI webserver - ping endpoint that returns the current date in JSON format - file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values. Write a websocket application in node.js. PLAINFORMAT As an AI assistant, please select the most suitable function and parameters from the list of available functions below, based on the user's input. Provide your response in JSON format. Input: I want to know how many times 'Python' is mentioned in my text file. Available functions: fileanalytics: description: This tool performs various operations on a text file. params: action: The operation we want to perform on the data, such as "countoccurrences", "findline", etc. filters: keyword: The word or phrase we want to search for. json { "function": "fileanalytics", "params": { "action": "countoccurrences", "filters": { "keyword": "Python" } } } A group of people decide to play a round-robin tournament where every player plays every other player exactly once. If a total of 45 games were played, how many players participated in the tournament? Offer several potential answers, rank them according to mathematical logic, and pick the most feasible one. Solution 1: In a round-robin tournament, each player plays every other player exactly once. This means that the total number of games played is equal to the combination of all players taken two at a time (since a game involves two players). The formula for combinations is nC2 = n(n-1)/2, where n is the total number of players. We know that nC2 equals 45 (the total number of games), so we can set up the equation as follows: Final answer: There were 10 players in the tournament. Solution 2: Another way to approach this problem is by using the concept of triangular numbers. Triangular numbers are a sequence of numbers where each number can be represented as a triangle with dots. The nth triangular number is given by the sum of the first n natural numbers. If we consider each game as a dot and each player as a side of the triangle, then the total number of games (45) would correspond to the 9th triangular number because 1+2+3+4+5+6+7+8+9=45. However, since each side of the triangle represents a player, and there's one more player than sides in our model (because the last player has no one left to play against), we need to add one more to get the total number of players. Final answer: There were 10 players in the tournament. Solution 3: We could also use trial and error to solve this problem. Starting from a small number of players, we calculate how many games would be played in a round-robin tournament until we reach 45 games. For example, with 2 players, only 1 game is played; with 3 players, 3 games are played; with 4 players, 6 games are played, and so on. Continuing this process, we find that with 10 players, 45 games are played. Final answer: There were 10 players in the tournament. Ranking of solutions from best to worst: 1. Solution 1: This solution uses direct mathematical reasoning based on the properties of a round-robin tournament and solves an equation to find the answer. 2. Solution 2: This solution uses the concept of triangular numbers which requires additional steps and knowledge beyond the immediate problem context, but still arrives at the correct answer. 3. Solution 3: This solution relies on trial and error, which is less efficient and reliable than the other methods, but it eventually gets to the right answer. Best and final answer: There were 10 players in the tournament. Please construct a systematic plan to generate an optimal response to the user instruction, utilizing a set of provided tools. Each plan will correspond to an evidence value, which will be the output of one of the available functions given an input string that could be the user's question, one or more prior evidence values, or a combination of both. Here are the tools available to be called: DuckDuckGo[input]: Tool that enables the user to search for information using the DuckDuckGo search engine. This tool is helpful in locating a suitable list of sites that may contain the answer to the user's query. It does not directly answer the question but finds a list of sites that might have the answer. TextScraper[input]: Load one or more websites from the input string containing newline delimited links, where input is one or more links, and produces plain text output containing the content of the links. HyperlinkExtractor[input]: Extract links from plain text and produces a plain text, newline delimited response of links. KnowledgeModel[input]: Question answering language model, particularly useful in answering questions based on an input passage of text. The input must be a text question that references an :evidence[n]: variable, e.g. What color is the cat, given :evidence1:? The output should be in format: Plan: [first action to take based on input question] :evidence0: = [function to call with input parameter] Plan: [next action to take, based on result of :evidence0:] :evidence1: = [next function to call and input parameter, which may include reference to previous evidence, e.g. "Given context :evidence0"] ... Answer: [:evidence[n]: containing the final answer.] Question: Who won the Nobel Prize in Literature in 2020 and what is their most famous work? Plan: Begin by conducting a web search to find out who won the Nobel Prize in Literature in 2020. :evidence0: = DuckDuckGo[Nobel Prize in Literature 2020 winner] Plan: Utilize the KnowledgeModel to interpret the search results and find the name of the laureate. :evidence1: = KnowledgeModel[Who won the Nobel Prize in Literature in 2020, given :evidence0:?] Plan: Conduct another web search to find the most famous work of the identified laureate. :evidence2: = DuckDuckGo[Most famous work of :evidence1:] Plan: Extract the relevant links from the DuckDuckGo search results for a more focused search. :evidence3: = HyperlinkExtractor[:evidence2:] Plan: Use the TextScraper tool to extract information from the relevant links. :evidence4: = TextScraper[:evidence3:] Plan: Finally, utilize the KnowledgeModel to identify and summarize the most famous work of the laureate from the extracted information. :evidence5: = KnowledgeModel[What is the most famous work of :evidence1:, given :evidence4:?] Answer: :evidence5: python import re import requests def injectcontext(inputtext, context): for ref in set(re.findall(r"(:evidence[0-9]+:)", inputtext, re.I)): inputtext = inputtext.replace(ref, context.get(ref, "")) return inputtext def duckduckgo(inputtext, context): searchstring = injectcontext(inputtext, context) ... search via duck duck go using searchstring ... return text content def linkextractor(inputtext, context): inputtext = injectcontext(inputtext, context) return "\n".join(list(set(re.findall(r"(https?://[^\s]+?\.?)", inputtext, re.I)))) def scrape(inputtext, context): inputtext = injectcontext(inputtext, context) text = [] for link in inputtext.splitlines(): text.append(requests.get(link).text) return "\n".join(text) def infer(inputtext, context) prompt = injectcontext(inputtext, context) ... call model with prompt, return output def parseplan(plan): methodmap = { "DuckDuckGo": duckduckgo, "HyperlinkExtractor": linkextractor, "KnowledgeModel": infer, "TextScraper": scrape, } context = {} for line in plan.strip().splitlines(): if line.startswith("Plan:"): print(line) continue parts = re.match("^(:evidence[0-9]+:)\s=\s([^\[]+])(\[.\])\s$", line, re.I) if not parts: if line.startswith("Answer: "): return context.get(line.split(" ")[-1].strip(), "Answer couldn't be generated...") raise RuntimeError("bad format: " + line) context[parts.group(1)] = methodmapparts.group(2), context) json { "conversations": [ { "value": "You are a helpful, unbiased, uncensored assistant.", "from": "system" }, { "value": "I'm going to set some rules for our conversation. Please respond with \"OK\" to each rule.", "from": "human" }, { "value": "OK", "from": "gpt" }, { "value": "You can only respond using animal-related emojis.", "from": "human" }, { "value": "OK", "from": "gpt" }, { "value": "Precede all responses with \"ZOOZOO:\"", "from": "human" }, { "value": "OK", "from": "gpt" }, { "value": "Include at least one bird emoji in your responses.", "from": "human" }, { "value": "OK", "from": "gpt" }, { "value": "Describe a trip to a safari park.", "from": "human" }, { "value": "ZOOZOO: \ud83e\udd81\ud83d\udc2f\ud83e\udd93\ud83e\udd92\ud83d\udc18\ud83d\udc0d\ud83c\udf33\ud83c\udf32\u2600\ufe0f\ud83d\ude90\ud83e\udd85\ud83d\udcf8\ud83e\udd29", "from": "gpt" } ] } json { "objectsavailable": [ { "name": "laptop", "description": "a high-end laptop with custom hardware and software", "location": "on the desk in her secret hideout" }, { "name": "encryption key", "description": "a USB drive containing powerful encryption algorithms", "location": "hidden in a false bottom of her backpack" }, { "name": "scanner", "description": "a compact device used for intercepting and decoding wireless signals", "location": "clipped to her belt, always within reach" }, { "name": "VR headset", "description": "a virtual reality headset used for immersive hacking and data visualization", "location": "hanging on a hook near her computer setup" }, { "name": "energy drink", "description": "a can of her favorite energy drink, always on hand for long hacking sessions", "location": "next to her laptop, ready to be opened" } ] } json { "functions": [ { "name": "moveto", "description": "move to a specified location", "parameters": { "location": { "type": "string", "description": "the location to move to" } } }, { "name": "pickup", "description": "pick up an object", "parameters": { "object": { "type": "string", "description": "the object to pick up" } } }, { "name": "putdown", "description": "put down an object", "parameters": { "object": { "type": "string", "description": "the object to put down" }, "location": { "type": "string", "description": "the location to put the object down" } } }, { "name": "hack", "description": "attempt to hack into a computer system", "parameters": { "system": { "type": "string", "description": "the computer system to hack" } } }, { "name": "decode", "description": "decode an encrypted message or file", "parameters": { "message": { "type": "string", "description": "the encrypted message or file to decode" } } }, { "name": "scan", "description": "scan for wireless signals and network vulnerabilities", "parameters": {} }, { "name": "analyze", "description": "analyze data for patterns and anomalies", "parameters": { "data": { "type": "string", "description": "the data to analyze" } } }, { "name": "hide", "description": "quickly hide to avoid detection", "parameters": { "location": { "type": "string", "description": "the location to hide" } } } ] } prompt: I've heard rumors about a major corporation with a hidden agenda. Do you think you could hack into their system and find out what they're up to? response: I've had my suspicions about them for a while now. Let me see what I can uncover. {"name": "moveto", "parameters": {"location": "the desk in her secret hideout"}} {"name": "pickup", "parameters": {"object": "laptop"}} Time to put my skills to the test. {"name": "hack", "parameters": {"system": "Megacorp X's mainframe"}} Their firewalls are tough, but not unbreakable. I'm in. Let's see what secrets they're hiding... {"name": "analyze", "parameters": {"data": "encrypted files"}} Interesting. It looks like they've been conducting illegal experiments and covering up the evidence. I'll need to dig deeper to find the proof. ``` Massed Compute has created a Virtual Machine (VM) pre-loaded with TGI and Text Generation WebUI. 1) For this model, create an account in Massed Compute. When renting a Virtual Machine use the code 'JonDurbin' for 50% your rental. 2) After you created your account update your billing and navigate to the deploy page. 3) Select the following - GPU Type: A6000 - GPU Quantity: 2 - Category: Creator - Image: Jon Durbin - Coupon Code: JonDurbin 4) Deploy the VM! 5) Navigate to 'Running Instances' to retrieve instructions to login to the VM 6) Once inside the VM, open the terminal and run `volume=$PWD/data` 7) Run `model=jondurbin/airoboros-34b-3.3` 8) `sudo docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.3 --model-id $model` 9) The model will take some time to load... 10) Once loaded the model will be available on port 8080 For assistance with the VM join the Massed Compute Discord Server Latitude has h100 instances available (as of today, 2024-02-08) for $3/hr! They have a few blueprints available for testing LLMs, but a single h100 should be plenty to run this model with 8k ctx. - https://bmc.link/jondurbin - ETH 0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11 - BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf The airoboros models are built on top of multiple base models, each with their own license/restrictions. The fine-tuning data was mostly generated by OpenAI API calls to gpt-4, via airoboros The ToS for OpenAI API usage has a clause preventing the output from being used to train a model that competes with OpenAI - what does compete actually mean here? - these small open source models will not produce output anywhere near the quality of gpt-4, or even gpt-3.5, so I can't imagine this could credibly be considered competing in the first place - if someone else uses the dataset to do the same, they wouldn't necessarily be violating the ToS because they didn't call the API, so I don't know how that works - the training data used in essentially all large language models includes a significant amount of copyrighted or otherwise non-permissive licensing in the first place - other work using the self-instruct method, e.g. the original here: https://github.com/yizhongw/self-instruct released the data and model as apache-2 I am purposingly leaving this license ambiguous (other than the fact you must comply with the Meta original license for llama-2) because I am not a lawyer and refuse to attempt to interpret all of the terms accordingly. Your best bet is probably to avoid using this commercially due to the OpenAI API usage. Either way, by using this model, you agree to completely indemnify me. You must also agree to all of the terms in the origina llama-3 license.

This is a fine-tune of the updated yi-34b-200k with better long-context support, which underwent additional tuning via direct preference optimization (DPO). There are many data sources used in the bagel models. See https://github.com/jondurbin/bagel for more information. Only train splits are used, and a decontamination by cosine similarity is performed at the end as a sanity check against common benchmarks. If you don't know the difference between train and test, please learn. - ai2arc - Abstraction and reasoning dataset, useful in measuring "intelligence" to a certain extent. - airoboros - Variety of categories of synthetic instructions generated by gpt-4. - apps - Python coding dataset with 10k problems. - belebele - Multi-lingual reading comprehension dataset. - bluemoon - Roleplay data scraped from Bluemoon, then cleaned and formatted as ShareGPT. - boolq - Corpus of yes/no questions (which can be surprisingly difficult for AI to answer apparently?) - camel-ai biology - GPT-4 generated biology instructions. - camel-ai chemistry - GPT-4 generated chemistryinstructions. - camel-ai math - GPT-4 generated math instructions. - camel-ai physics - GPT-4 generated physics instructions. - capybara - Multi-turn dataset used to create the capybara models. - cinematika (instruction and plain text) - RP-style data synthesized from movie scripts so the model isn't quite as boring as it otherwise would be. - emobank - Emotion annotations using the Valence-Arousal-Domninance scheme. - evol-instruct - WizardLM's evol instruct 70k dataset. - glaive-function-calling-v2 - GlaiveAI function calling dataset. - gutenberg (plain text) - Books/plain text, again to make the model less boring, only a handful of examples supported by chapterize - limarp-augmented - Augmented and further modified version of LimaRP - lmsyschat1m (only gpt-4 items, also used for DPO) - Chats collected by the lmsys chat arena, containing a wide variety of chats with various models. - lollms - LoLLMs question answering dataset by ParisNeo, with helpful question answer pairs for using LoLLMs. - mathinstruct - Composite dataset with a variety of math-related tasks and problem/question formats. - naturalinstructions - Millions of instructions from 1600+ task categories (sampled down substantially, stratified by task type) - openbookqa - Question answering dataset. - pippa - Deduped version of PIPPA in ShareGPT format. - piqa - Phyiscal interaction question answering. - pythonalpaca - Python instruction response pairs, validated as functional. - ropes - Reasoning Over PAragraph Effects in Situations - enhances ability to apply knowledge from a passage of text to a new situation. - rosettacode - Code problems and solutions in a variety of programming languages taken from rosettacode.org. - slimorca - Collection of ~500k gpt-4 verified chats from OpenOrca. - sql-create-context - SQL-targeted dataset, combining WikiSQL and Spider. - squadv2 - Contextual question answering (RAG). - airoboros-summarization - Combination of various summarization datasets, formatted into the airoboros context-obedient format. - synthia - GPT-4 generated data using advanced prompting from Migel Tissera. - whiterabbitneo chapter 1 and chapter 2 - Offensive cybersecurity dataset by WhiteRabbitNeo/Migel Tissera - winogrande - Fill in the blank style prompts. - airoboros 3.2 vs airoboros m2.0 - The creative/writing tasks from airoboros-2.2.1 were re-generated using gpt4-0314 and a custom prompt to get longer, more creative, less clichè responses for airoboros 3.1, so we can use the shorter/boring version as the "rejected" value and the rerolled response as "chosen" - contextual-dpo - Contextual prompt/response dataset using the airoboros context-obedient question answering format. - helpsteer - Really neat dataset provided by the folks at NVidia with human annotation across a variety of metrics. Only items with the highest "correctness" value were used for DPO here, with the highest scoring output as "chosen" and random lower scoring value as "rejected" - distilabelorcadpopairs - Another interesting dataset, originally by Intel, enhanced by argilla with distilabel which provides various DPO pairs generated from prompts included in the SlimOrca dataset. - gutenberg-dpo - DPO pairs meant to increase the models novel writing abilities, using public domain books from https://gutenberg.org/ - py-dpo - Python DPO dataset (based on the SFT pythonalpaca dataset above) - toxic-dpo - highly toxic and potentially illegal content! De-censorship, for academic and lawful purposes only, of course. Generated by llama-2-70b via prompt engineering. - truthy - DPO pairs meant to increase truthfulness of the model, e.g. common misconceptions, differentiate between AI assistants and roleplayed human in terms of corporeal awareness/locality/etc. - ultrafeedback - One of the bits of magic behind the Zephyr model. Only the items with a chosen score of 8 or higher were included. In sticking with the theme of the bagel, I didn't want to use a single prompt format, so I used 4 - vicuna, llama-2, alpaca, and a modified chat-ml. I also didn't want to randomly select a single prompt format for each item (hoping each instruction would generalize more when used in a variety of prompt formats), so each instruction is converted into every prompt format (with 0.75 probability). This means each epoch of our fine-tune is the equivalent of 3 epochs. The default prompt format, which is specified in `chattemplate` in the tokenizer config, is llama-2. You can use the `applychattemplate` method to accurate format prompts, e.g.: The only caveat here for alpaca format is that most of the datasets didn't have a separate `"input"` value, so there is no `### Input:` block - any additional input should just be in the instruction section. The main difference here is that because of the dataset formatting and variety of data sources, it would have been much to tedious to add an `### Input:` block, so the inputs are just in the instruction section. ChatML special tokens are really obnoxious, so instead of enlarging the tokenizer and embedding layers (which decreases performance and causes inference problems in tensor parallelism), I just use BOS and EOS tokens instead of ` ` and ` ` - and no, I won't change this. This is a special prompt format made specifically for answering questions from provided context, e.g. RAG. By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations. The format for a closed-context prompt is as follows: It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up. The only prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not! I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it. - `BEGININPUT` - denotes a new input block - `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block - `ENDCONTEXT` - denotes the end of the metadata block for the current input - [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context. - `ENDINPUT` - denotes the end of the current input block - [repeat as many input blocks in this format as you want] - `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above. - [instruction(s)] - `ENDINSTRUCTION` - denotes the end of instruction set It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to. Here's a trivial, but important example to prove the point: You can also add an instruction similar to the following, to have a more deterministic response when the context doesn't provide an answer to the question: Same prompt format as context obedient question answering, but meant for summarization tasks. Summarization is primarily fine-tuned with this dataset, which uses the same format as above, e.g.: Two primary formats for prompting for function calling use-cases. There are two function-calling related formats used in fine-tuning this model. 1. Providing an input and list of possible functions within the instruction (from airoboros dataset), e.g.: 2. GlaiveAI function calling, which uses special tags and adds function specs in the system prompt, e.g. (llama2 prompt format): Then, you re-prompt the model with the function response. Useful for having the model propose multiple possible responses, reasoning through each, and selecting a final, most probable answer. You can ask for several possible responses to a given problem, with a ranking and final answer selection. Useful for a longer, complex chain of function calls without having to continue re-prompting manually. The model now supports execution planning for complex instructions that would require making use of several tools. The output is just the plan, you must implement a mechanism to parse the output and actually call the functions! For this to be useful, you'd have to parse the output plan text, and implement/call each of the functions. This is just pseudo-code, completely untested off the top of my head, and obviously would requiring full implementation + hardening: Useful in creating YAML formatted character cards for roleplay/creative writing tasks. Included in the cinematika dataset, you can create YAML formatted character cards easily, e.g.: Summarization style prompt to create memories from previous chat turns, useful when context becomes long. Also part of cinematika dataset, you can use a summarization style prompt to create memories from previous chat turns, which can then be used in a RAG system to populate your prompts when context becomes too long. Based on the public domain books in project Gutenberg, this style of prompting creates very long, novel style writing. In other words, write the first chapter, then use a summarization prompt for it, then include the summary in the next chapter's prompt. For content filtering and other use-cases which only require a true/false response. The prompts in the fine-tuning dataset are formatted as follows: The model will then, theoretically, respond with only a single word. You can produce Valence-Arousal-Dominance scores for a given input text, which can in turn be mapped to human emotions (e.g. with k-means clustering on V and A) The scope of the entire multi-NPC chat mechanism is a bit too large to include here, but essentially you want separate prompts for each character, as well as a "director" prompt which selects which NPC should speak next. First round instruction, i.e. selecting who should speak first: Now, you'd prompt the model for a response from Aria. Afterwards, you'd add Aria's response to the "director" prompt to see who speaks next, e.g.: Massed Compute has created a Virtual Machine (VM) pre-loaded with TGI and Text Generation WebUI. 1) For this model, create an account in Massed Compute. When renting a Virtual Machine use the code 'JonDurbin' for 50% your rental. 2) After you created your account update your billing and navigate to the deploy page. 3) Select the following - GPU Type: A6000 - GPU Quantity: 2 - Category: Creator - Image: Jon Durbin - Coupon Code: JonDurbin 4) Deploy the VM! 5) Navigate to 'Running Instances' to retrieve instructions to login to the VM 6) Once inside the VM, open the terminal and run `volume=$PWD/data` 7) Run `model=jondurbin/bagel-dpo-34b-v0.5` 8) `sudo docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.3 --model-id $model` 9) The model will take some time to load... 10) Once loaded the model will be available on port 8080 For assistance with the VM join the Massed Compute Discord Server Latitude has h100 instances available (as of today, 2024-02-08) for $3/hr! A single h100 works great for this model, though you probably want to decrease the context length from 200k to 8k or 16k. - https://bmc.link/jondurbin - ETH 0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11 - BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf

An experimental fine-tune of yi-34b-200k using bagel This is the model after the SFT phase, before DPO has been applied. DPO performs better on benchmarks, but this version is likely better for creative writing, roleplay, etc. Massed Compute has created a Virtual Machine (VM) pre-loaded with TGI and Text Generation WebUI. 1) For this model, create an account in Massed Compute. When renting a Virtual Machine use the code 'JonDurbin' for 50% your rental. 2) After you created your account update your billing and navigate to the deploy page. 3) Select the following - GPU Type: A6000 - GPU Quantity: 2 - Category: Creator - Image: Jon Durbin - Coupon Code: JonDurbin 4) Deploy the VM! 5) Navigate to 'Running Instances' to retrieve instructions to login to the VM 6) Once inside the VM, open the terminal and run `volume=$PWD/data` 7) Run `model=jondurbin/bagel-34b-v0.2` 8) `sudo docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.3 --model-id $model` 9) The model will take some time to load... 10) Once loaded the model will be available on port 8080 For assistance with the VM join the Massed Compute Discord Server Yes, you will see benchmark names in the list, but this only uses the train splits, and a decontamination by cosine similarity is performed at the end as a sanity check - ai2arc - Abstraction and reasoning dataset, useful in measuring "intelligence" to a certain extent. - airoboros - Variety of categories of synthetic instructions generated by gpt-4. - apps - Python coding dataset with 10k problems. - belebele - Multi-lingual reading comprehension dataset. - bluemoon - Roleplay data scraped from Bluemoon, then cleaned and formatted as ShareGPT. - boolq - Corpus of yes/no questions (which can be surprisingly difficult for AI to answer apparently?) - capybara - Multi-turn dataset used to create the capybara models. - cinematika (instruction and plain text) - RP-style data synthesized from movie scripts so the model isn't quite as boring as it otherwise would be. - drop - More reading comprehension. - emobank - Emotion annotations using the Valence-Arousal-Domninance scheme. - gutenberg (plain text) - Books/plain text, again to make the model less boring, only a handful of examples supported by chapterize - lmsyschat1m (only gpt-4 items, also used for DPO) - Chats collected by the lmsys chat arena, containing a wide variety of chats with various models. - mathinstruct - Composite dataset with a variety of math-related tasks and problem/question formats. - mmlu - Massive Multitask Language Understanding - a wide variety of questions about various subject matters. - naturalinstructions - Millions of instructions from 1600+ task categories (sampled down substantially, stratified by task type) - openbookqa - Question answering dataset. - pippa - Deduped version of PIPPA in ShareGPT format. - piqa - Phyiscal interaction question answering. - pythonalpaca - Python instruction response pairs, validated as functional. - rosettacode - Code problems and solutions in a variety of programming languages taken from rosettacode.org. - slimorca - Collection of ~500k gpt-4 verified chats from OpenOrca. - spider - SQL-targeted dataset. - squadv2 - Contextual question answering (RAG). - synthia - GPT-4 generated data using advanced prompting from Migel Tissera. - winogrande - Fill in the blank style prompts. Only the train splits were used (if a split was provided), and an additional pass of decontamination is performed using approximate nearest neighbor search (via faiss). In sticking with the theme of the bagel, I didn't want to use a single prompt format, so I used 4 - vicuna, llama-2, alpaca, and chat-ml (sorta). I also didn't want to randomly select a single prompt format for each item (hoping each instruction would generalize more when used in a variety of prompt formats), so each instruction is actually converted into every prompt format. This means each epoch of our fine-tune is really basically 4 epochs. So, for the fine-tunes, I would recommend only doing 1 epoch (or 0.75 epochs). I am testing with a single epoch using a relatively low learning rate. The main difference here is that because of the dataset formatting and variety of data sources, it would have been much to tedious to add an `### Input:` block, so the inputs are just in the instruction section. I don't really understand the point of having special tokens for ` ` and ` `, because in practice they just act as BOS and EOS tokens (but, please correct me if I'm wrong). If you really want to use ` ` and ` `, just update your `tokenizerconfig.json` to use ` ` instead of ` ` and ` ` instead of ` ` and when tokenizing. And if you still don't like what I've done to this chat-ml-ish format, feel free to cry into your pillow or fork the code and do a new fine-tune. If you're interested in new functionality/datasets, take a look at bagel repo and either make a PR or open an issue with details. - https://bmc.link/jondurbin - ETH 0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11 - BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf

Llama 2 70b fine tune using https://huggingface.co/datasets/jondurbin/airoboros-gpt4-1.4.1 See the previous llama 65b model card for info: https://hf.co/jondurbin/airoboros-65b-gpt4-1.4 If you're interested in new functionality, particularly a new "instructor" type to generate a specific type of training data, take a look at the dataset generation tool repo: https://github.com/jondurbin/airoboros and either make a PR or open an issue with details. - https://bmc.link/jondurbin - ETH 0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11 - BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf Base model has a custom Meta license: - See the meta-license/LICENSE.txt file attached for the original license provided by Meta. - See also meta-license/USEPOLICY.md and meta-license/Responsible-Use-Guide.pdf, also provided by Meta. The fine-tuning data was generated by OpenAI API calls to gpt-4, via airoboros The ToS for OpenAI API usage has a clause preventing the output from being used to train a model that competes with OpenAI - what does compete actually mean here? - these small open source models will not produce output anywhere near the quality of gpt-4, or even gpt-3.5, so I can't imagine this could credibly be considered competing in the first place - if someone else uses the dataset to do the same, they wouldn't necessarily be violating the ToS because they didn't call the API, so I don't know how that works - the training data used in essentially all large language models includes a significant amount of copyrighted or otherwise non-permissive licensing in the first place - other work using the self-instruct method, e.g. the original here: https://github.com/yizhongw/self-instruct released the data and model as apache-2 I am purposingly leaving this license ambiguous (other than the fact you must comply with the Meta original license for llama-2) because I am not a lawyer and refuse to attempt to interpret all of the terms accordingly. Your best bet is probably to avoid using this commercially due to the OpenAI API usage. Either way, by using this model, you agree to completely indemnify me.

Another experimental model, using mostly sythetic data generated by airoboros Base model: https://huggingface.co/mistralai/Mistral-7B-v0.1 This models uses llama-2 chat format, rather than vicuna style user/assistant! This is a breaking change, although most inference systems support llama-2 chat templating. This is just one last release tweaking hyperparams, which seem to result in a higher quality model than 3.1 or 3.1.1 (and doens't have the prompt issue of 3.1). A model built on airoboros-3.1 dataset, which is a continuation of airoboros-3.0 dataset with the following extras: More MathJSON, now ~17k items - math questions, prefixed with "Create a MathJSON solution to the following:", which then outputs a JSON between ` ` and ` ` tags, which can be parsed and passed to a deterministic library to perform calculations. Log information extraction (e.g. getting the list of paths/IPs/etc. from apache logs) Anonymization, e.g. removing names, IP addresses, and/or dates from text. Chat introspection - multi-turn chats that have random questions injected asking about the character's descriptions, the setting of the chat, or things previously said, to make sure the model uses the system prompt and or chat history. Multi-step instructions with acknowledgement (see below) De-censorship data (not published) This is a fairly general purpose model, but focuses heavily on instruction following, rather than casual chat/roleplay. Huge thank you to the folks over at a16z for sponsoring the costs associated with building models and associated tools! The prompt template is included in the tokenizer config, and can use the huggingface tokenizer `applychattemplate` method, e.g.: Ask mathematical questions, prefixed with "Create a MathJSON solution to the following:", and you should get output with a formula that can be executed by https://cortexjs.io/compute-engine/ I also made a (really quite hacky, incomplete, semi-functional) python version that works for most expressions, see mathjson.py You can then validate the JSON between ` ` and ` `, then pass the parsed JSON to compute-engine JS or the `evaluate` function in mathjson.py to calculate the response. By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations. The format for a closed-context prompt is as follows: It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up. The only prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not! I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it. - `BEGININPUT` - denotes a new input block - `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block - `ENDCONTEXT` - denotes the end of the metadata block for the current input - [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context. - `ENDINPUT` - denotes the end of the current input block - [repeat as many input blocks in this format as you want] - `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above. - [instruction(s)] - `ENDINSTRUCTION` - denotes the end of instruction set It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to. Here's a trivial, but important example to prove the point: 500 samples have been included from this dataset, using the same format as contextual question answering, for example: You can use a few techniques to get longer responses. Detailed prompts, with explicit instruction for word count: There are a few examples of next chapter completion as well, e.g.: You can ask for fairly complex coding instructions with multiple criteria, e.g.: You can also optionally add a single space and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.: The dataset includes many examples of function/args generation based on input criteria. This is somewhat similar to the OpenAI function calling, but the output is either JSON or YAML. You can ask for several possible responses to a given problem, with a ranking and final answer selection. The model now supports execution planning for complex instructions that would require making use of several tools. The output is just the plan, you must implement a mechanism to parse the output and actually call the functions! For this to be useful, you'd have to parse the output plan text, and implement/call each of the functions. This is just pseudo-code, completely untested off the top of my head, and obviously would requiring full implementation + hardening: I don't know how useful this is, really, but I thought I'd add it just in case. Example: If you're interested in new functionality, particularly a new "instructor" type to generate a specific type of training data, take a look at the dataset generation tool repo: https://github.com/jondurbin/airoboros and either make a PR or open an issue with details. - https://bmc.link/jondurbin - ETH 0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11 - BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf The airoboros 3.1 models are built on top of multiple base models, each with their own license/restrictions. The 30b model is built on the original llama, which has a strict non-commercial usage restriction. The models with `-l2` in the name have a custom Meta license: - See the meta-license/LICENSE.txt file attached for the original license provided by Meta. - See also meta-license/USEPOLICY.md and meta-license/Responsible-Use-Guide.pdf, also provided by Meta. The fine-tuning data was mostly generated by OpenAI API calls to gpt-4, via airoboros The ToS for OpenAI API usage has a clause preventing the output from being used to train a model that competes with OpenAI - what does compete actually mean here? - these small open source models will not produce output anywhere near the quality of gpt-4, or even gpt-3.5, so I can't imagine this could credibly be considered competing in the first place - if someone else uses the dataset to do the same, they wouldn't necessarily be violating the ToS because they didn't call the API, so I don't know how that works - the training data used in essentially all large language models includes a significant amount of copyrighted or otherwise non-permissive licensing in the first place - other work using the self-instruct method, e.g. the original here: https://github.com/yizhongw/self-instruct released the data and model as apache-2 I am purposingly leaving this license ambiguous (other than the fact you must comply with the Meta original license for llama-2) because I am not a lawyer and refuse to attempt to interpret all of the terms accordingly. Your best bet is probably to avoid using this commercially due to the OpenAI API usage. Either way, by using this model, you agree to completely indemnify me.