commit 983e0aaeaa8b949f78feec5d9324eeabded86813 Author: ModelHub XC Date: Thu Apr 9 13:49:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: TheBloke/airoboros-c34b-2.2.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..917f6bd --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +airoboros-c34b-2.2.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-c34b-2.2.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-c34b-2.2.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-c34b-2.2.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-c34b-2.2.1.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-c34b-2.2.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-c34b-2.2.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-c34b-2.2.1.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-c34b-2.2.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-c34b-2.2.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-c34b-2.2.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +airoboros-c34b-2.2.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LICENSE.txt b/LICENSE.txt new file mode 100644 index 0000000..51089e2 --- /dev/null +++ b/LICENSE.txt @@ -0,0 +1,126 @@ +LLAMA 2 COMMUNITY LICENSE AGREEMENT +Llama 2 Version Release Date: July 18, 2023 + +"Agreement" means the terms and conditions for use, reproduction, distribution and +modification of the Llama Materials set forth herein. + +"Documentation" means the specifications, manuals and documentation +accompanying Llama 2 distributed by Meta at ai.meta.com/resources/models-and- +libraries/llama-downloads/. + +"Licensee" or "you" means you, or your employer or any other person or entity (if +you are entering into this Agreement on such person or entity's behalf), of the age +required under applicable laws, rules or regulations to provide legal consent and that +has legal authority to bind your employer or such other person or entity if you are +entering in this Agreement on their behalf. + +"Llama 2" means the foundational large language models and software and +algorithms, including machine-learning model code, trained model weights, +inference-enabling code, training-enabling code, fine-tuning enabling code and other +elements of the foregoing distributed by Meta at ai.meta.com/resources/models-and- +libraries/llama-downloads/. + +"Llama Materials" means, collectively, Meta's proprietary Llama 2 and +Documentation (and any portion thereof) made available under this Agreement. + +"Meta" or "we" means Meta Platforms Ireland Limited (if you are located in or, if you +are an entity, your principal place of business is in the EEA or Switzerland) and Meta +Platforms, Inc. (if you are located outside of the EEA or Switzerland). + +By clicking "I Accept" below or by using or distributing any portion or element of the +Llama Materials, you agree to be bound by this Agreement. + +1. License Rights and Redistribution. + + a. Grant of Rights. You are granted a non-exclusive, worldwide, non- +transferable and royalty-free limited license under Meta's intellectual property or +other rights owned by Meta embodied in the Llama Materials to use, reproduce, +distribute, copy, create derivative works of, and make modifications to the Llama +Materials. + + b. Redistribution and Use. + + i. If you distribute or make the Llama Materials, or any derivative works +thereof, available to a third party, you shall provide a copy of this Agreement to such +third party. + ii. If you receive Llama Materials, or any derivative works thereof, from +a Licensee as part of an integrated end user product, then Section 2 of this +Agreement will not apply to you. + + iii. You must retain in all copies of the Llama Materials that you +distribute the following attribution notice within a "Notice" text file distributed as a +part of such copies: "Llama 2 is licensed under the LLAMA 2 Community License, +Copyright (c) Meta Platforms, Inc. All Rights Reserved." + + iv. Your use of the Llama Materials must comply with applicable laws +and regulations (including trade compliance laws and regulations) and adhere to the +Acceptable Use Policy for the Llama Materials (available at +https://ai.meta.com/llama/use-policy), which is hereby incorporated by reference into +this Agreement. + + v. You will not use the Llama Materials or any output or results of the +Llama Materials to improve any other large language model (excluding Llama 2 or +derivative works thereof). + +2. Additional Commercial Terms. If, on the Llama 2 version release date, the +monthly active users of the products or services made available by or for Licensee, +or Licensee's affiliates, is greater than 700 million monthly active users in the +preceding calendar month, you must request a license from Meta, which Meta may +grant to you in its sole discretion, and you are not authorized to exercise any of the +rights under this Agreement unless or until Meta otherwise expressly grants you +such rights. + +3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE +LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE +PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND, +EITHER EXPRESS OR IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY +WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR +FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE +FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING +THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR +USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS. + +4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE +LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, +NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS +AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, +CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN +IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF +ANY OF THE FOREGOING. + +5. Intellectual Property. + + a. No trademark licenses are granted under this Agreement, and in +connection with the Llama Materials, neither Meta nor Licensee may use any name +or mark owned by or associated with the other or any of its affiliates, except as +required for reasonable and customary use in describing and redistributing the +Llama Materials. + + b. Subject to Meta's ownership of Llama Materials and derivatives made by or +for Meta, with respect to any derivative works and modifications of the Llama +Materials that are made by you, as between you and Meta, you are and will be the +owner of such derivative works and modifications. + + c. If you institute litigation or other proceedings against Meta or any entity +(including a cross-claim or counterclaim in a lawsuit) alleging that the Llama +Materials or Llama 2 outputs or results, or any portion of any of the foregoing, +constitutes infringement of intellectual property or other rights owned or licensable +by you, then any licenses granted to you under this Agreement shall terminate as of +the date such litigation or claim is filed or instituted. You will indemnify and hold +harmless Meta from and against any claim by any third party arising out of or related +to your use or distribution of the Llama Materials. + +6. Term and Termination. The term of this Agreement will commence upon your +acceptance of this Agreement or access to the Llama Materials and will continue in +full force and effect until terminated in accordance with the terms and conditions +herein. Meta may terminate this Agreement if you are in breach of any term or +condition of this Agreement. Upon termination of this Agreement, you shall delete +and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the +termination of this Agreement. + +7. Governing Law and Jurisdiction. This Agreement will be governed and +construed under the laws of the State of California without regard to choice of law +principles, and the UN Convention on Contracts for the International Sale of Goods +does not apply to this Agreement. The courts of California shall have exclusive +jurisdiction of any dispute arising out of this Agreement. + diff --git a/Notice b/Notice new file mode 100644 index 0000000..d03b5b9 --- /dev/null +++ b/Notice @@ -0,0 +1 @@ +Llama 2 is licensed under the LLAMA 2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved. diff --git a/README.md b/README.md new file mode 100644 index 0000000..751d250 --- /dev/null +++ b/README.md @@ -0,0 +1,659 @@ +--- +license: llama2 +datasets: +- jondurbin/airoboros-2.2.1 +model_name: Airoboros C34B 2.2.1 +base_model: jondurbin/airoboros-c34b-2.2.1 +inference: false +model_creator: Jon Durbin +model_type: llama +prompt_template: "A chat.\nUSER: {prompt}\nASSISTANT: \n" +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)

+
+ + +# Airoboros C34B 2.2.1 - GGUF +- Model creator: [Jon Durbin](https://huggingface.co/jondurbin) +- Original model: [Airoboros C34B 2.2.1](https://huggingface.co/jondurbin/airoboros-c34b-2.2.1) + + +## Description + +This repo contains GGUF format model files for [Jon Durbin's Airoboros C34B 2.2.1](https://huggingface.co/jondurbin/airoboros-c34b-2.2.1). + + + +### 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/airoboros-c34b-2.2.1-AWQ) +* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/airoboros-c34b-2.2.1-GPTQ) +* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/airoboros-c34b-2.2.1-GGUF) +* [Jon Durbin's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/jondurbin/airoboros-c34b-2.2.1) + + + +## Prompt template: Chat + +``` +A chat. +USER: {prompt} +ASSISTANT: + +``` + + + + + +## 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 | +| ---- | ---- | ---- | ---- | ---- | ----- | +| [airoboros-c34b-2.2.1.Q2_K.gguf](https://huggingface.co/TheBloke/airoboros-c34b-2.2.1-GGUF/blob/main/airoboros-c34b-2.2.1.Q2_K.gguf) | Q2_K | 2 | 14.21 GB| 16.71 GB | smallest, significant quality loss - not recommended for most purposes | +| [airoboros-c34b-2.2.1.Q3_K_S.gguf](https://huggingface.co/TheBloke/airoboros-c34b-2.2.1-GGUF/blob/main/airoboros-c34b-2.2.1.Q3_K_S.gguf) | Q3_K_S | 3 | 14.61 GB| 17.11 GB | very small, high quality loss | +| [airoboros-c34b-2.2.1.Q3_K_M.gguf](https://huggingface.co/TheBloke/airoboros-c34b-2.2.1-GGUF/blob/main/airoboros-c34b-2.2.1.Q3_K_M.gguf) | Q3_K_M | 3 | 16.28 GB| 18.78 GB | very small, high quality loss | +| [airoboros-c34b-2.2.1.Q3_K_L.gguf](https://huggingface.co/TheBloke/airoboros-c34b-2.2.1-GGUF/blob/main/airoboros-c34b-2.2.1.Q3_K_L.gguf) | Q3_K_L | 3 | 17.77 GB| 20.27 GB | small, substantial quality loss | +| [airoboros-c34b-2.2.1.Q4_0.gguf](https://huggingface.co/TheBloke/airoboros-c34b-2.2.1-GGUF/blob/main/airoboros-c34b-2.2.1.Q4_0.gguf) | Q4_0 | 4 | 19.05 GB| 21.55 GB | legacy; small, very high quality loss - prefer using Q3_K_M | +| [airoboros-c34b-2.2.1.Q4_K_S.gguf](https://huggingface.co/TheBloke/airoboros-c34b-2.2.1-GGUF/blob/main/airoboros-c34b-2.2.1.Q4_K_S.gguf) | Q4_K_S | 4 | 19.15 GB| 21.65 GB | small, greater quality loss | +| [airoboros-c34b-2.2.1.Q4_K_M.gguf](https://huggingface.co/TheBloke/airoboros-c34b-2.2.1-GGUF/blob/main/airoboros-c34b-2.2.1.Q4_K_M.gguf) | Q4_K_M | 4 | 20.22 GB| 22.72 GB | medium, balanced quality - recommended | +| [airoboros-c34b-2.2.1.Q5_0.gguf](https://huggingface.co/TheBloke/airoboros-c34b-2.2.1-GGUF/blob/main/airoboros-c34b-2.2.1.Q5_0.gguf) | Q5_0 | 5 | 23.24 GB| 25.74 GB | legacy; medium, balanced quality - prefer using Q4_K_M | +| [airoboros-c34b-2.2.1.Q5_K_S.gguf](https://huggingface.co/TheBloke/airoboros-c34b-2.2.1-GGUF/blob/main/airoboros-c34b-2.2.1.Q5_K_S.gguf) | Q5_K_S | 5 | 23.24 GB| 25.74 GB | large, low quality loss - recommended | +| [airoboros-c34b-2.2.1.Q5_K_M.gguf](https://huggingface.co/TheBloke/airoboros-c34b-2.2.1-GGUF/blob/main/airoboros-c34b-2.2.1.Q5_K_M.gguf) | Q5_K_M | 5 | 23.84 GB| 26.34 GB | large, very low quality loss - recommended | +| [airoboros-c34b-2.2.1.Q6_K.gguf](https://huggingface.co/TheBloke/airoboros-c34b-2.2.1-GGUF/blob/main/airoboros-c34b-2.2.1.Q6_K.gguf) | Q6_K | 6 | 27.68 GB| 30.18 GB | very large, extremely low quality loss | +| [airoboros-c34b-2.2.1.Q8_0.gguf](https://huggingface.co/TheBloke/airoboros-c34b-2.2.1-GGUF/blob/main/airoboros-c34b-2.2.1.Q8_0.gguf) | Q8_0 | 8 | 35.86 GB| 38.36 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/airoboros-c34b-2.2.1-GGUF and below it, a specific filename to download, such as: airoboros-c34b-2.2.1.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/airoboros-c34b-2.2.1-GGUF airoboros-c34b-2.2.1.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/airoboros-c34b-2.2.1-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/airoboros-c34b-2.2.1-GGUF airoboros-c34b-2.2.1.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 airoboros-c34b-2.2.1.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "A chat.\nUSER: {prompt}\nASSISTANT:" +``` + +Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration. + +Change `-c 4096` 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/airoboros-c34b-2.2.1-GGUF", model_file="airoboros-c34b-2.2.1.Q4_K_M.gguf", model_type="llama", 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**: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov + + +Thank you to all my generous patrons and donaters! + +And thank you again to a16z for their generous grant. + + + + +# Original model card: Jon Durbin's Airoboros C34B 2.2.1 + + +### Overview + +Another experimental model, using mostly sythetic data generated by [airoboros](https://github.com/jondurbin/airoboros) + +This is essentially a minor "fix" branch of [airoboros-c34b-2.2](https://hf.co/jondurbin/airoboros-c34b-2.2) with a updates, primarily: +- [re-generated writing responses](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1#re-generated-writing-responses) +- [longer contextual blocks](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1#longer-contextual-blocks) +- [removal of "rp" data](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1#rp-category-removed) +- [(less aggressive) de-censoring](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1#de-censoring) +- 5 epochs instead of 3 + +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](https://a16z.com/) for sponsoring the costs associated with building models and associated tools! + +### Prompt format + +The prompt format: + +``` +A chat. +USER: {prompt} +ASSISTANT: +``` + +The default system prompt ("A chat.") was used for most of the prompts, however it also included a wide sampling of responses with other prompts, particularly in "stylized\_response", "rp", "gtkm", etc. + +Here's another example: +``` +A chat between Bob (aka USER) and Tom (aka ASSISTANT). Tom is an extremely intelligent 18th century bookkeeper, who speaks loquaciously. +USER: {prompt} +ASSISTANT: +``` + +And chat scenario that wouldn't require USER/ASSISTANT (but should use stopping criteria to prevent the model from speaking on your behalf). +``` +A chat between old friends: Timmy and Tommy. +{description of characters} + +{setting for the chat} +Timmy: *takes a big sip from his coffee* "Ah, sweet, delicious, magical coffee." +Tommy: +``` + +__*I strongly suggest adding stopping criteria/early inference stopping on "USER:", and/or whatever names you specify in the system prompt.*__ + +### Fine tuning info + +https://wandb.ai/jondurbin/airoboros-c34b-2.2.1/runs/07b08z7m?workspace=user-jondurbin + +### Helpful usage tips + +*The prompts shown here are are just the text that would be included after USER: and before ASSISTANT: in the full prompt format above, the system prompt and USER:/ASSISTANT: have been omited for readability.* + +#### Context obedient question answering + +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: +``` +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 +``` + +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: +``` +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 +``` + +And the response: +``` +Blueberries are now green. +Source: +date: 2021-01-01 +url: https://web.site/123 +``` + +#### Summarization + +500 samples have been included from [this dataset](https://huggingface.co/datasets/mattpscott/airoboros-summarization), using the same format as contextual question answering, for example: + +``` +BEGININPUT +{text to summarize} +ENDINPUT +BEGININSTRUCTION +Summarize the input in around 130 words. +ENDINSTRUCTION +``` + +#### Getting longer responses + +You can use a few techniques to get longer responses. + +Detailed prompts, with explicit instruction for word count: +``` +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. + +Your response should be approximately 2300 words. +``` + +Or, a simpler example: +``` +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. +``` + +#### Coding + +You can ask for fairly complex coding instructions with multiple criteria, e.g.: + +``` +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 +``` + +Or inline criteria: + +``` +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. +``` + +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.: + +``` +Write a websocket application in node.js. PLAINFORMAT +``` + +#### Agent/function calling + +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. + +Example prompt: +``` +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: +file_analytics: + description: This tool performs various operations on a text file. + params: + action: The operation we want to perform on the data, such as "count_occurrences", "find_line", etc. + filters: + keyword: The word or phrase we want to search for. +``` + +Response: +```json +{ + "function": "file_analytics", + "params": { + "action": "count_occurrences", + "filters": { + "keyword": "Python" + } + } +} +``` + +#### Chain-of-thought + +You can ask for several possible responses to a given problem, with a ranking and final answer selection. + +Example prompt: + +``` +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. +``` + +Example response: +``` +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: + +n(n-1)/2 = 45 + +Solving this equation gives us n=10. + +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. +``` + +#### reWOO style execution planning + +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! + +Example prompt: +``` +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? +``` + +Response: +``` +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: +``` + +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: + +```python +import re +import requests + +def inject_context(input_text, **context): + for ref in set(re.findall(r"(:evidence[0-9]+:)", input_text, re.I)): + input_text = input_text.replace(ref, context.get(ref, "")) + return input_text + +def duckduckgo(input_text, **context): + search_string = inject_context(input_text, **context) + ... search via duck duck go using search_string + ... return text content + +def link_extractor(input_text, **context): + input_text = inject_context(input_text, **context) + return "\n".join(list(set(re.findall(r"(https?://[^\s]+?\.?)", input_text, re.I)))) + +def scrape(input_text, **context): + input_text = inject_context(input_text, **context) + text = [] + for link in input_text.splitlines(): + text.append(requests.get(link).text) + return "\n".join(text) + +def infer(input_text, **context) + prompt = inject_context(input_text, **context) + ... call model with prompt, return output + +def parse_plan(plan): + method_map = { + "DuckDuckGo": duckduckgo, + "HyperlinkExtractor": link_extractor, + "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)] = method_map[parts.group(2)](parts.group(3), **context) +``` + +### Contribute + +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. + +To help me with the OpenAI/compute costs: + +- https://bmc.link/jondurbin +- ETH 0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11 +- BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf + +### Licence and usage restrictions + +The airoboros 2.2 models are built on top of llama-2/codellama. + +The llama-2 base model has a custom Meta license: +- See the [meta-license/LICENSE.txt](meta-license/LICENSE.txt) file attached for the original license provided by Meta. +- See also [meta-license/USE_POLICY.md](meta-license/USE_POLICY.md) and [meta-license/Responsible-Use-Guide.pdf](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](https://github.com/jondurbin/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. + + diff --git a/USE_POLICY.md b/USE_POLICY.md new file mode 100644 index 0000000..abbcc19 --- /dev/null +++ b/USE_POLICY.md @@ -0,0 +1,50 @@ +# Llama 2 Acceptable Use Policy + +Meta is committed to promoting safe and fair use of its tools and features, including Llama 2. If you access or use Llama 2, you agree to this Acceptable Use Policy (“Policy”). The most recent copy of this policy can be found at [ai.meta.com/llama/use-policy](http://ai.meta.com/llama/use-policy). + +## Prohibited Uses +We want everyone to use Llama 2 safely and responsibly. You agree you will not use, or allow others to use, Llama 2 to: + +1. Violate the law or others’ rights, including to: + 1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as: + 1. Violence or terrorism + 2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material + 3. Human trafficking, exploitation, and sexual violence + 4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials. + 5. Sexual solicitation + 6. Any other criminal activity + 2. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals + 3. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services + 4. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices + 5. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws + 6. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama 2 Materials + 7. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system + + + +2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Llama 2 related to the following: + 1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State + 2. Guns and illegal weapons (including weapon development) + 3. Illegal drugs and regulated/controlled substances + 4. Operation of critical infrastructure, transportation technologies, or heavy machinery + 5. Self-harm or harm to others, including suicide, cutting, and eating disorders + 6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual + + + +3. Intentionally deceive or mislead others, including use of Llama 2 related to the following: + 1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation + 2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content + 3. Generating, promoting, or further distributing spam + 4. Impersonating another individual without consent, authorization, or legal right + 5. Representing that the use of Llama 2 or outputs are human-generated + 6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement +4. Fail to appropriately disclose to end users any known dangers of your AI system + +Please report any violation of this Policy, software “bug,” or other problems that could lead to a violation of this Policy through one of the following means: + +* Reporting issues with the model: [github.com/facebookresearch/llama](http://github.com/facebookresearch/llama) +* Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback) +* Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info) +* Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama: [LlamaUseReport@meta.com](mailto:LlamaUseReport@meta.com) + diff --git a/airoboros-c34b-2.2.1.Q2_K.gguf b/airoboros-c34b-2.2.1.Q2_K.gguf new file mode 100644 index 0000000..f9a2154 --- /dev/null +++ b/airoboros-c34b-2.2.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba426ce4d8da040634e36cd8577f3c2c2fe3dce64a81ef2f665195c2d47daab9 +size 14210674848 diff --git a/airoboros-c34b-2.2.1.Q3_K_L.gguf b/airoboros-c34b-2.2.1.Q3_K_L.gguf new file mode 100644 index 0000000..80a5e56 --- /dev/null +++ b/airoboros-c34b-2.2.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4131e27130121fb75413c42032466a5ebb27710c5565d2e6afab5356c6fae01 +size 17771524256 diff --git a/airoboros-c34b-2.2.1.Q3_K_M.gguf b/airoboros-c34b-2.2.1.Q3_K_M.gguf new file mode 100644 index 0000000..0b72d79 --- /dev/null +++ b/airoboros-c34b-2.2.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a35a07aab5fa2a3b56c6fe2bc97de383f0bfe311b8268d25dd8fdc82e7fd8113 +size 16283594912 diff --git a/airoboros-c34b-2.2.1.Q3_K_S.gguf b/airoboros-c34b-2.2.1.Q3_K_S.gguf new file mode 100644 index 0000000..9dd929a --- /dev/null +++ b/airoboros-c34b-2.2.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de802b5583b7e91599094625e3fc0ce3eda1b8392b31738fc3f3c134a3f281da +size 14605349024 diff --git a/airoboros-c34b-2.2.1.Q4_0.gguf b/airoboros-c34b-2.2.1.Q4_0.gguf new file mode 100644 index 0000000..4ee663d --- /dev/null +++ b/airoboros-c34b-2.2.1.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3009eb7ac8a0f4c4e29c3d5ebd65ed9dc8d5347985e00493fc44c1ca3dc4177 +size 19052048544 diff --git a/airoboros-c34b-2.2.1.Q4_K_M.gguf b/airoboros-c34b-2.2.1.Q4_K_M.gguf new file mode 100644 index 0000000..aac9876 --- /dev/null +++ b/airoboros-c34b-2.2.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1da3993b6add596ea45de229b8e4328d38bdbe7361c538b6ec419022c0a79407 +size 20219900064 diff --git a/airoboros-c34b-2.2.1.Q4_K_S.gguf b/airoboros-c34b-2.2.1.Q4_K_S.gguf new file mode 100644 index 0000000..3f1b0f9 --- /dev/null +++ b/airoboros-c34b-2.2.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84deb0fadbf79e9ce592b6537e0d9c4fe9b70ceb4d3a3e3aad8b1c6324ea4196 +size 19146420384 diff --git a/airoboros-c34b-2.2.1.Q5_0.gguf b/airoboros-c34b-2.2.1.Q5_0.gguf new file mode 100644 index 0000000..a099b43 --- /dev/null +++ b/airoboros-c34b-2.2.1.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fabba1fe213318879b7022330718efea35f8f6ae77a07bef696f6ac1e37cdd0 +size 23237177504 diff --git a/airoboros-c34b-2.2.1.Q5_K_M.gguf b/airoboros-c34b-2.2.1.Q5_K_M.gguf new file mode 100644 index 0000000..17b269d --- /dev/null +++ b/airoboros-c34b-2.2.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5097dede20365994ac57594a5731e4f37a1b6b27337a63125359edd573081754 +size 23838797984 diff --git a/airoboros-c34b-2.2.1.Q5_K_S.gguf b/airoboros-c34b-2.2.1.Q5_K_S.gguf new file mode 100644 index 0000000..22c04fc --- /dev/null +++ b/airoboros-c34b-2.2.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3b0d0b98dcd5542a010c1046227ea5acf54f664f7f399e8fe57bd97b10eb7c8 +size 23237177504 diff --git a/airoboros-c34b-2.2.1.Q6_K.gguf b/airoboros-c34b-2.2.1.Q6_K.gguf new file mode 100644 index 0000000..40d17ba --- /dev/null +++ b/airoboros-c34b-2.2.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1af46bed78bdd1a870d598713d010da680d0addc39ba777037461fae9b89900c +size 27683877024 diff --git a/airoboros-c34b-2.2.1.Q8_0.gguf b/airoboros-c34b-2.2.1.Q8_0.gguf new file mode 100644 index 0000000..91f6368 --- /dev/null +++ b/airoboros-c34b-2.2.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:180c6779479f014b2eb147c9027b24fb3bd73d53271ca40bf0fe6fe361231cba +size 35856052384 diff --git a/config.json b/config.json new file mode 100644 index 0000000..a4ba21b --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +{ + "model_type": "llama" +} \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..159097f --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "others", "allow_remote": true} \ No newline at end of file