--- base_model: PocketDoc/Dans-AdventurousWinds-7b inference: false language: - en model_creator: PocketDoc Labs model_name: Dans AdventurousWinds 7B model_type: mistral prompt_template: '[Genres: Science Fiction] [Tags: humor, old school, sci fi] [Mode: Adventure] [Description: A puzzle about committing acts of financial skulduggery and exploiting ridiculous magical items.] [Misc: Writing era: 1993] [Intro] It is the year 2045. You are a young man in his twenties living in New York City. Your father was an inventor who died when you were very small; your mother raised you alone for many years until she remarried. Now you live with your stepfather, but he doesn''t care much for you and has never given you any money to help support yourself. You have no job and little hope of getting one because of your lack of experience. However, you do have some unusual abilities that could be put to good use if only you knew how... > {prompt} ' quantized_by: TheBloke ---
TheBlokeAI

Chat & support: TheBloke's Discord server

Want to contribute? TheBloke's Patreon page

TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)


# Dans AdventurousWinds 7B - GGUF - Model creator: [PocketDoc Labs](https://huggingface.co/PocketDoc) - Original model: [Dans AdventurousWinds 7B](https://huggingface.co/PocketDoc/Dans-AdventurousWinds-7b) ## Description This repo contains GGUF format model files for [PocketDoc Labs's Dans AdventurousWinds 7B](https://huggingface.co/PocketDoc/Dans-AdventurousWinds-7b). ### About GGUF GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. Here is an incomplate list of clients and libraries that are known to support GGUF: * [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option. * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration. * [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling. * [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection. * [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration. * [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server. * [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use. ## Repositories available * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Dans-AdventurousWinds-7B-AWQ) * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Dans-AdventurousWinds-7B-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Dans-AdventurousWinds-7B-GGUF) * [PocketDoc Labs's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/PocketDoc/Dans-AdventurousWinds-7b) ## Prompt template: Adventure ``` [Genres: Science Fiction] [Tags: humor, old school, sci fi] [Mode: Adventure] [Description: A puzzle about committing acts of financial skulduggery and exploiting ridiculous magical items.] [Misc: Writing era: 1993] [Intro] It is the year 2045. You are a young man in his twenties living in New York City. Your father was an inventor who died when you were very small; your mother raised you alone for many years until she remarried. Now you live with your stepfather, but he doesn't care much for you and has never given you any money to help support yourself. You have no job and little hope of getting one because of your lack of experience. However, you do have some unusual abilities that could be put to good use if only you knew how... > {prompt} ``` ## Compatibility These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) They are also compatible with many third party UIs and libraries - please see the list at the top of this README. ## Explanation of quantisation methods
Click to see details The new methods available are: * GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw) * GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw. * GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw. * GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw * GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw Refer to the Provided Files table below to see what files use which methods, and how.
## Provided files | Name | Quant method | Bits | Size | Max RAM required | Use case | | ---- | ---- | ---- | ---- | ---- | ----- | | [dans-adventurouswinds-7b.Q2_K.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-7B-GGUF/blob/main/dans-adventurouswinds-7b.Q2_K.gguf) | Q2_K | 2 | 3.08 GB| 5.58 GB | smallest, significant quality loss - not recommended for most purposes | | [dans-adventurouswinds-7b.Q3_K_S.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-7B-GGUF/blob/main/dans-adventurouswinds-7b.Q3_K_S.gguf) | Q3_K_S | 3 | 3.16 GB| 5.66 GB | very small, high quality loss | | [dans-adventurouswinds-7b.Q3_K_M.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-7B-GGUF/blob/main/dans-adventurouswinds-7b.Q3_K_M.gguf) | Q3_K_M | 3 | 3.52 GB| 6.02 GB | very small, high quality loss | | [dans-adventurouswinds-7b.Q3_K_L.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-7B-GGUF/blob/main/dans-adventurouswinds-7b.Q3_K_L.gguf) | Q3_K_L | 3 | 3.82 GB| 6.32 GB | small, substantial quality loss | | [dans-adventurouswinds-7b.Q4_0.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-7B-GGUF/blob/main/dans-adventurouswinds-7b.Q4_0.gguf) | Q4_0 | 4 | 4.11 GB| 6.61 GB | legacy; small, very high quality loss - prefer using Q3_K_M | | [dans-adventurouswinds-7b.Q4_K_S.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-7B-GGUF/blob/main/dans-adventurouswinds-7b.Q4_K_S.gguf) | Q4_K_S | 4 | 4.14 GB| 6.64 GB | small, greater quality loss | | [dans-adventurouswinds-7b.Q4_K_M.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-7B-GGUF/blob/main/dans-adventurouswinds-7b.Q4_K_M.gguf) | Q4_K_M | 4 | 4.37 GB| 6.87 GB | medium, balanced quality - recommended | | [dans-adventurouswinds-7b.Q5_0.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-7B-GGUF/blob/main/dans-adventurouswinds-7b.Q5_0.gguf) | Q5_0 | 5 | 5.00 GB| 7.50 GB | legacy; medium, balanced quality - prefer using Q4_K_M | | [dans-adventurouswinds-7b.Q5_K_S.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-7B-GGUF/blob/main/dans-adventurouswinds-7b.Q5_K_S.gguf) | Q5_K_S | 5 | 5.00 GB| 7.50 GB | large, low quality loss - recommended | | [dans-adventurouswinds-7b.Q5_K_M.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-7B-GGUF/blob/main/dans-adventurouswinds-7b.Q5_K_M.gguf) | Q5_K_M | 5 | 5.13 GB| 7.63 GB | large, very low quality loss - recommended | | [dans-adventurouswinds-7b.Q6_K.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-7B-GGUF/blob/main/dans-adventurouswinds-7b.Q6_K.gguf) | Q6_K | 6 | 5.94 GB| 8.44 GB | very large, extremely low quality loss | | [dans-adventurouswinds-7b.Q8_0.gguf](https://huggingface.co/TheBloke/Dans-AdventurousWinds-7B-GGUF/blob/main/dans-adventurouswinds-7b.Q8_0.gguf) | Q8_0 | 8 | 7.70 GB| 10.20 GB | very large, extremely low quality loss - not recommended | **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead. ## How to download GGUF files **Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file. The following clients/libraries will automatically download models for you, providing a list of available models to choose from: - LM Studio - LoLLMS Web UI - Faraday.dev ### In `text-generation-webui` Under Download Model, you can enter the model repo: TheBloke/Dans-AdventurousWinds-7B-GGUF and below it, a specific filename to download, such as: dans-adventurouswinds-7b.Q4_K_M.gguf. Then click Download. ### On the command line, including multiple files at once I recommend using the `huggingface-hub` Python library: ```shell pip3 install huggingface-hub ``` Then you can download any individual model file to the current directory, at high speed, with a command like this: ```shell huggingface-cli download TheBloke/Dans-AdventurousWinds-7B-GGUF dans-adventurouswinds-7b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False ```
More advanced huggingface-cli download usage You can also download multiple files at once with a pattern: ```shell huggingface-cli download TheBloke/Dans-AdventurousWinds-7B-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf' ``` For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli). To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`: ```shell pip3 install hf_transfer ``` And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`: ```shell HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Dans-AdventurousWinds-7B-GGUF dans-adventurouswinds-7b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False ``` Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
## Example `llama.cpp` command Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later. ```shell ./main -ngl 32 -m dans-adventurouswinds-7b.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "[Genres: Science Fiction]\n[Tags: humor, old school, sci fi]\n[Mode: Adventure]\n[Description: A puzzle about committing acts of financial skulduggery and exploiting ridiculous magical items.]\n[Misc: Writing era: 1993]\n[Intro]\nIt is the year 2045. You are a young man in his twenties living in New York City. Your father was an inventor who died when you were very small; your mother raised you alone for many years until she remarried. Now you live with your stepfather, but he doesn't care much for you and has never given you any money to help support yourself. You have no job and little hope of getting one because of your lack of experience. However, you do have some unusual abilities that could be put to good use if only you knew how...\n\n> {prompt}" ``` Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration. Change `-c 2048` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. If you want to have a chat-style conversation, replace the `-p ` argument with `-i -ins` For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md) ## How to run in `text-generation-webui` Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md). ## How to run from Python code You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. ### How to load this model in Python code, using ctransformers #### First install the package Run one of the following commands, according to your system: ```shell # Base ctransformers with no GPU acceleration pip install ctransformers # Or with CUDA GPU acceleration pip install ctransformers[cuda] # Or with AMD ROCm GPU acceleration (Linux only) CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers # Or with Metal GPU acceleration for macOS systems only CT_METAL=1 pip install ctransformers --no-binary ctransformers ``` #### Simple ctransformers example code ```python from ctransformers import AutoModelForCausalLM # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system. llm = AutoModelForCausalLM.from_pretrained("TheBloke/Dans-AdventurousWinds-7B-GGUF", model_file="dans-adventurouswinds-7b.Q4_K_M.gguf", model_type="mistral", gpu_layers=50) print(llm("AI is going to")) ``` ## How to use with LangChain Here are guides on using llama-cpp-python and ctransformers with LangChain: * [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp) * [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers) ## Discord For further support, and discussions on these models and AI in general, join us at: [TheBloke AI's Discord server](https://discord.gg/theblokeai) ## Thanks, and how to contribute Thanks to the [chirper.ai](https://chirper.ai) team! Thanks to Clay from [gpus.llm-utils.org](llm-utils)! I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training. If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects. Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits. * Patreon: https://patreon.com/TheBlokeAI * Ko-Fi: https://ko-fi.com/TheBlokeAI **Special thanks to**: Aemon Algiz. **Patreon special mentions**: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski Thank you to all my generous patrons and donaters! And thank you again to a16z for their generous grant. # Original model card: PocketDoc Labs's Dans AdventurousWinds 7B # What is the model for? This model is proficient in crafting text-based adventure games. It can both concise replies and more expansive, novel-like descriptions. The ability to alternate between these two response styles can be triggered by a distinct system message. # What's in the sausage? This model was trained on [Mistral-7b](https://huggingface.co/mistralai/Mistral-7B-v0.1) using a custom version of the floyd and cys datasets from the skein text adventure dataset. The dataset has been improved over what was used in my previous model "Dans-CreepingSenseOfDoom" and this time presented in the more traditional adventure mode format. ## Prompt format and examples: #### Format description: Traditional adventure format with a description of the genre, tags, and other misc information at the top followed by an optional introductory message. User messages are prefixed with two new lines and "> ", model messages are one new line after the last user message or the description message if an introductory message is desired. #### Examples of shorter responses: ``` [Genres: Science Fiction] [Tags: humor, old school, sci fi] [Mode: Adventure] [Description: A puzzle about committing acts of financial skulduggery and exploiting ridiculous magical items.] [Misc: Writing era: 1993] [Intro] It is the year 2045. You are a young man in his twenties living in New York City. Your father was an inventor who died when you were very small; your mother raised you alone for many years until she remarried. Now you live with your stepfather, but he doesn't care much for you and has never given you any money to help support yourself. You have no job and little hope of getting one because of your lack of experience. However, you do have some unusual abilities that could be put to good use if only you knew how... > Look around You are standing on the sidewalk outside your apartment building. The street is busy with traffic and people going about their daily business. Across the street from you stands a tall office tower where your stepfather works as an accountant. To your left is a convenience store where you can buy food and drinks. > You go into the store The doorbell rings as you enter the store. An elderly woman behind the counter looks up at you expectantly. "Hello," she says cheerfully, "what can I get for you?" > You tell her you'll browse "All right then," she replies brightly, "just take your time." > You ask if she's hiring "I'm sorry," she says sadly, "but we don't need anyone new just now." > You leave without buying anything As you walk out of the store, the bell jingles merrily. > You go see your stepfather When you arrive at work, your stepfather greets you warmly. He invites you into his office and offers you a seat. "So," he begins eagerly, "how would you like to make some extra cash? There's this guy named Mr. Jones who owes my company thousands of dollars. If we could somehow convince him to pay us back, it would really help our bottom line." He pauses expectantly, waiting for your response. > You ask him whats involved "Well," he continues excitedly, "it turns out that Mr. Jones has a very valuable antique watch that he keeps locked away in a safe deposit box at the bank. We think that if we could somehow break into the box and steal the watch, we could sell it for enough money to cover his debt." Your heart races as you realize the potential danger of such a scheme. But before you can say anything, your stepfather cuts off your thoughts by continuing, "Of course, there's always the chance that something could go wrong and we might end up losing everything..." ``` #### Examples of longer novel like responses: ``` [Genres: grimdark fantasy] [Tags: Fantasy, Grimdark, Serious, Villain Protagonist, War] [Description: This story is definitely more "story" than "game", however there are two distinct paths that can be followed, each with their own pitfalls and additional choices. This story can get long, and assuming you're surviving, years do pass in it and you and your environment will change.] [First message intro] [Mode: Interactive Storyteller] You have been a soldier for as long as you remember. You don't know who you were before the war began, but you were someone else. Someone less angry. More forgiving. Perhaps even kinder. It all started when you were very young. The King of this land was attacked by an army from another kingdom. His forces were outmatched, his city overrun. He had no choice but to flee into the forest, taking what few soldiers he could muster along with him. As the king fled deeper into the woods, his army fell back, forming a protective wall around them. They fought valiantly against the invaders, giving the king time to escape, but they eventually succumbed to overwhelming numbers. When the fighting finally ended, only one man remained alive; you. The king found you hiding behind some bushes, covered in blood and dirt. He took pity on you and offered you a place at court if you would swear allegiance to him. Without hesitation, you accepted. And so began your journey down the path of darkness... > You meet with the king to discuss the plans A week has passed since the battle and you have just met with the king to discuss future plans. It seems like things are finally starting to settle down after such chaos. However, there is still much work to be done before we can truly consider ourselves safe again. The first order of business is rebuilding our army. We need men willing to fight for us once more. Men who understand what needs to be done and aren't afraid to die trying. I believe I have found such warriors among those loyal subjects who survived the initial attack. If we train them properly, then perhaps they might prove useful against our enemies next time around. Next, we must find ways to improve our defenses. There are many areas where improvements could be made. For instance, we should construct better walls around our cities. These walls must not only keep intruders out, but also allow us easy access inside should anyone try to breach them. In addition, we must strengthen our gates so that no matter how strong our enemy becomes, he cannot break through without great effort. Finally, we must fortify our castles and other strategic locations throughout the country. By doing these things, we will ensure that nobody ever attacks us again! > You ask what he desires your involvement to be After hearing about his plans, you feel compelled to help him achieve victory. After all, you owe everything to him. But before agreeing to anything, you want to make sure that he understands exactly what you expect from him. So you decide to approach him directly. "Your Majesty," you begin, "I am honored beyond measure to serve under your command. However, before committing myself fully to this cause, I wish to clarify certain matters." He nods slowly. "Very well. What would you like me to explain?" "Well," you say, "first off, I want to know why you chose me above everyone else? Why did you pick me specifically?" He smiles softly. "Because I saw potential within you. Potential which others lacked. Potentials which could prove valuable during times of crisis. Therefore, I felt confident enough to entrust my fate to you." "But what makes you think I possess such abilities?" you ask curiously. "Oh, nothing special really," he replies casually. "Just raw determination combined with intelligence and resourcefulness. Those qualities alone are enough to carry us forward toward victory!" ``` # Some quick and dirty training details: - [Built with Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) - Sequence length: 4096 - \# of epochs: 3 - Training time: 1 hour - Hardware: 1x RTX 3090 - Training type: QLoRA - PEFT R/A: 32/32 # Credits: ### Skein Text Adventure Data: Thank you to the [Kobold AI](https://huggingface.co/KoboldAI) community for curating the Skein dataset, which is pivotal to this model's capabilities.