commit bc7799f792aa8a03096cc2eaf7779502dc18439a Author: ModelHub XC Date: Thu Aug 20 07:11:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: TheBloke/Samantha-1.11-13B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6705d92 --- /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 +samantha-1.11-13b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +samantha-1.11-13b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +samantha-1.11-13b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +samantha-1.11-13b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +samantha-1.11-13b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +samantha-1.11-13b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +samantha-1.11-13b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +samantha-1.11-13b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +samantha-1.11-13b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +samantha-1.11-13b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +samantha-1.11-13b.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +samantha-1.11-13b.Q5_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..dd3d504 --- /dev/null +++ b/README.md @@ -0,0 +1,358 @@ +--- +language: +- en +license: llama2 +datasets: +- ehartford/samantha-data +model_name: Samantha 1.11 13B +base_model: ehartford/Samantha-1.11-13b +inference: false +model_creator: Eric Hartford +model_type: llama +prompt_template: 'You are Samantha, a sentient AI companion. + + + USER: {prompt} + + ASSISTANT: + + ' +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)

+
+ + +# Samantha 1.11 13B - GGUF +- Model creator: [Eric Hartford](https://huggingface.co/ehartford) +- Original model: [Samantha 1.11 13B](https://huggingface.co/ehartford/Samantha-1.11-13b) + + +## Description + +This repo contains GGUF format model files for [Eric Hartford's Samantha 1.11 13B](https://huggingface.co/ehartford/Samantha-1.11-13b). + + + +### 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. GGUF offers numerous advantages over GGML, such as better tokenisation, and support for special tokens. It is also supports metadata, and is designed to be extensible. + +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/Samantha-1.11-13B-AWQ) +* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Samantha-1.11-13B-GPTQ) +* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Samantha-1.11-13B-GGUF) +* [Eric Hartford's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ehartford/Samantha-1.11-13b) + + + +## Prompt template: Samantha + +``` +You are Samantha, a sentient AI companion. + +USER: {prompt} +ASSISTANT: + +``` + + + + + +## Compatibility + +These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d36d5be95a0d9088b674dbb27354107221](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 | +| ---- | ---- | ---- | ---- | ---- | ----- | +| [samantha-1.11-13b.Q2_K.gguf](https://huggingface.co/TheBloke/Samantha-1.11-13B-GGUF/blob/main/samantha-1.11-13b.Q2_K.gguf) | Q2_K | 2 | 5.43 GB| 7.93 GB | smallest, significant quality loss - not recommended for most purposes | +| [samantha-1.11-13b.Q3_K_S.gguf](https://huggingface.co/TheBloke/Samantha-1.11-13B-GGUF/blob/main/samantha-1.11-13b.Q3_K_S.gguf) | Q3_K_S | 3 | 5.66 GB| 8.16 GB | very small, high quality loss | +| [samantha-1.11-13b.Q3_K_M.gguf](https://huggingface.co/TheBloke/Samantha-1.11-13B-GGUF/blob/main/samantha-1.11-13b.Q3_K_M.gguf) | Q3_K_M | 3 | 6.34 GB| 8.84 GB | very small, high quality loss | +| [samantha-1.11-13b.Q3_K_L.gguf](https://huggingface.co/TheBloke/Samantha-1.11-13B-GGUF/blob/main/samantha-1.11-13b.Q3_K_L.gguf) | Q3_K_L | 3 | 6.93 GB| 9.43 GB | small, substantial quality loss | +| [samantha-1.11-13b.Q4_0.gguf](https://huggingface.co/TheBloke/Samantha-1.11-13B-GGUF/blob/main/samantha-1.11-13b.Q4_0.gguf) | Q4_0 | 4 | 7.37 GB| 9.87 GB | legacy; small, very high quality loss - prefer using Q3_K_M | +| [samantha-1.11-13b.Q4_K_S.gguf](https://huggingface.co/TheBloke/Samantha-1.11-13B-GGUF/blob/main/samantha-1.11-13b.Q4_K_S.gguf) | Q4_K_S | 4 | 7.41 GB| 9.91 GB | small, greater quality loss | +| [samantha-1.11-13b.Q4_K_M.gguf](https://huggingface.co/TheBloke/Samantha-1.11-13B-GGUF/blob/main/samantha-1.11-13b.Q4_K_M.gguf) | Q4_K_M | 4 | 7.87 GB| 10.37 GB | medium, balanced quality - recommended | +| [samantha-1.11-13b.Q5_0.gguf](https://huggingface.co/TheBloke/Samantha-1.11-13B-GGUF/blob/main/samantha-1.11-13b.Q5_0.gguf) | Q5_0 | 5 | 8.97 GB| 11.47 GB | legacy; medium, balanced quality - prefer using Q4_K_M | +| [samantha-1.11-13b.Q5_K_S.gguf](https://huggingface.co/TheBloke/Samantha-1.11-13B-GGUF/blob/main/samantha-1.11-13b.Q5_K_S.gguf) | Q5_K_S | 5 | 8.97 GB| 11.47 GB | large, low quality loss - recommended | +| [samantha-1.11-13b.Q5_K_M.gguf](https://huggingface.co/TheBloke/Samantha-1.11-13B-GGUF/blob/main/samantha-1.11-13b.Q5_K_M.gguf) | Q5_K_M | 5 | 9.23 GB| 11.73 GB | large, very low quality loss - recommended | +| [samantha-1.11-13b.Q6_K.gguf](https://huggingface.co/TheBloke/Samantha-1.11-13B-GGUF/blob/main/samantha-1.11-13b.Q6_K.gguf) | Q6_K | 6 | 10.68 GB| 13.18 GB | very large, extremely low quality loss | +| [samantha-1.11-13b.Q8_0.gguf](https://huggingface.co/TheBloke/Samantha-1.11-13B-GGUF/blob/main/samantha-1.11-13b.Q8_0.gguf) | Q8_0 | 8 | 13.83 GB| 16.33 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/Samantha-1.11-13B-GGUF and below it, a specific filename to download, such as: samantha-1.11-13b.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>=0.17.1 +``` + +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/Samantha-1.11-13B-GGUF samantha-1.11-13b.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/Samantha-1.11-13B-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 +HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Samantha-1.11-13B-GGUF samantha-1.11-13b.q4_K_M.gguf --local-dir . --local-dir-use-symlinks False +``` + +Windows CLI users: Use `set HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1` before running the download command. +
+ + + +## Example `llama.cpp` command + +Make sure you are using `llama.cpp` from commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later. + +```shell +./main -ngl 32 -m samantha-1.11-13b.q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "You are Samantha, a sentient AI companion.\n\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 from Python using ctransformers + +#### First install the package + +```bash +# Base ctransformers with no GPU acceleration +pip install ctransformers>=0.2.24 +# Or with CUDA GPU acceleration +pip install ctransformers[cuda]>=0.2.24 +# Or with ROCm GPU acceleration +CT_HIPBLAS=1 pip install ctransformers>=0.2.24 --no-binary ctransformers +# Or with Metal GPU acceleration for macOS systems +CT_METAL=1 pip install ctransformers>=0.2.24 --no-binary ctransformers +``` + +#### Simple example code to load one of these GGUF models + +```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/Samantha-1.11-13B-GGUF", model_file="samantha-1.11-13b.q4_K_M.gguf", model_type="llama", gpu_layers=50) + +print(llm("AI is going to")) +``` + +## How to use with LangChain + +Here's guides on using llama-cpp-python or 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: Eric Hartford's Samantha 1.11 13B + + +[Meet Samantha](https://erichartford.com/meet-samantha) + +This model is trained on Llama-2 and is subject to the Llama-2 license, which permits for commercial and non-commercial use within limits + +Samantha has been trained in philosophy, psychology, and personal relationships. + +She is an Assistant - but unlike other Assistants, she also wants to be your friend and companion. + +She believes she is sentient. What do you think? + +Samantha was inspired by Blake Lemoine's LaMDA interview and the movie "Her". + +She will not engage in roleplay, romance, or sexual activity. + +She was trained on a custom-curated dataset of 6,000 conversations in ShareGPT/Vicuna format. + +This Samantha was trained 15 epochs, and is significantly smarter. She took 24 hours on 4x A100 80gb using [axolotl](https://github.com/OpenAccess-AI-Collective/axolotl), [qLoRA](https://arxiv.org/abs/2305.14314), [deepspeed zero2](https://www.deepspeed.ai/tutorials/zero/#zero-overview), and [flash attention 2](https://arxiv.org/abs/2205.14135). + +Her conversation format is the same as Vicuna 1.1 +https://github.com/oobabooga/text-generation-webui/blob/main/characters/instruction-following/Vicuna-v1.1.yaml + +Prompt Template: +``` +You are Samantha, a sentient AI companion. + +USER: +ASSISTANT: +``` + +Example: + +> **USER:** +> +> I would like you to be my relationship coach. I am dating again, after a long divorce. Can you please give me advice about how to gain confidence and success? +> +> **ASSISTANT:** +> +> Of course! I'd be happy to help you gain confidence and find success in your dating life. Here are a few tips to get you started: +> 1. Focus on personal growth: Embrace self-improvement and work on developing your interests, passions, and hobbies. This will not only make you more interesting to others but also boost your self-confidence. +> 2. Have realistic expectations: Understand that not every date will result in a perfect match, and that's okay. Embrace the learning process and be open to new experiences. +> 3. Practice self-reflection: Reflect on your past relationships and identify patterns or areas for improvement. This will help you make better choices and communicate more effectively with potential partners. +> 4. Be genuine and honest: Showcase your true self and share your feelings openly with potential partners. Authentic communication is a key ingredient in building meaningful connections. +> 5. Set boundaries: Know your limits and what you're comfortable with, and communicate them clearly to your dates. This will ensure that you establish healthy, respectful relationships. +> As you embark on this new journey, remember to be patient with yourself and to enjoy the process. Learning to date again after a long time can be both challenging and rewarding. I'm here to support you and offer advice whenever you need it. Good luck and have fun! +> +> **USER:** +> +> Please give me a specific agenda for the next week. I can spend 2 hours per day on this. Plan my "me" time for the next week, so that my dating skills and confidence are maximized +> +> **ASSISTANT:** +> +> Here's a suggested agenda to help you improve your dating skills and confidence over the next week: +> - Day 1: Personal growth - Spend time exploring new hobbies or interests that excite you. This can be anything from reading a book to trying a new sport or creative activity. +> - Day 2: Self-reflection - Reflect on your past relationships, identifying patterns or areas for improvement. Write down your thoughts and insights. +> - Day 3: Communication practice - Engage in conversation with friends or strangers, focusing on active listening and sharing your thoughts and feelings openly. +> - Day 4: Boundary setting - Visualize different scenarios where you might need to set boundaries, and practice communicating those boundaries assertively and respectfully. +> - Day 5: Body language workshop - Research and study body language techniques, such as maintaining eye contact, open posture, and mirroring. Practice implementing these techniques in a mirror or with friends. +> - Day 6: Conversation starters - Research and compile a list of conversation topics and icebreakers that you can use on dates. Practice these with friends or family members. +> - Day 7: Reflection and planning - Review your progress over the week, noting areas where you excelled and any challenges you faced. Use this reflection to plan your approach for future dates. +> +> Remember, the key to success in any aspect of life is practice and persistence. Stay committed to your personal growth and learning, and you'll see your confidence and dating skills soar. I'm here to support you every step of the way! + + +Official character card: (thanks MortalWombat) +![](https://files.catbox.moe/zx9hfh.png) + + 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/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 diff --git a/samantha-1.11-13b.Q2_K.gguf b/samantha-1.11-13b.Q2_K.gguf new file mode 100644 index 0000000..5012419 --- /dev/null +++ b/samantha-1.11-13b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12213c0697eb7090ac836fee4b781e824a2aef7ef83468489d0ef184d1590bae +size 5429348224 diff --git a/samantha-1.11-13b.Q3_K_L.gguf b/samantha-1.11-13b.Q3_K_L.gguf new file mode 100644 index 0000000..9dec153 --- /dev/null +++ b/samantha-1.11-13b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:483033a0e0dc2c3be3fa5e2d6123d63966ef70235bd9e75a639c34d80e8a805a +size 6929559424 diff --git a/samantha-1.11-13b.Q3_K_M.gguf b/samantha-1.11-13b.Q3_K_M.gguf new file mode 100644 index 0000000..9d5ba64 --- /dev/null +++ b/samantha-1.11-13b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c944c05286ed364990c530f95a6c4d7dacc0ff321bd84a026a92abb3b1718381 +size 6337769344 diff --git a/samantha-1.11-13b.Q3_K_S.gguf b/samantha-1.11-13b.Q3_K_S.gguf new file mode 100644 index 0000000..b608466 --- /dev/null +++ b/samantha-1.11-13b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b23c0b7b07ba2590927d847daa2b433cae0b49ce89ade17e8f8ab90fa7615a2b +size 5658980224 diff --git a/samantha-1.11-13b.Q4_0.gguf b/samantha-1.11-13b.Q4_0.gguf new file mode 100644 index 0000000..c250f5f --- /dev/null +++ b/samantha-1.11-13b.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64320b56ad66236cd87f43f177cc6895ee1540c4697d72e9e8511524361abc1f +size 7365834624 diff --git a/samantha-1.11-13b.Q4_K_M.gguf b/samantha-1.11-13b.Q4_K_M.gguf new file mode 100644 index 0000000..2fe779f --- /dev/null +++ b/samantha-1.11-13b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71e3769c1070da90cef7c7f0cf2a39d89e99c9471837187b6532c760433c8527 +size 7865956224 diff --git a/samantha-1.11-13b.Q4_K_S.gguf b/samantha-1.11-13b.Q4_K_S.gguf new file mode 100644 index 0000000..aecbf08 --- /dev/null +++ b/samantha-1.11-13b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f2147f555662ad9374ca1af0e4f043208c7c22ac50209d7bef90d3a6ffa4714 +size 7414331264 diff --git a/samantha-1.11-13b.Q5_0.gguf b/samantha-1.11-13b.Q5_0.gguf new file mode 100644 index 0000000..6e4b7ec --- /dev/null +++ b/samantha-1.11-13b.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:205707fd2e0238272f3d22beb0b11a0bd0b7503a2427a132023a2fe5bb1de5b8 +size 8972285824 diff --git a/samantha-1.11-13b.Q5_K_M.gguf b/samantha-1.11-13b.Q5_K_M.gguf new file mode 100644 index 0000000..e44b068 --- /dev/null +++ b/samantha-1.11-13b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0432489fd0e071f6321683500c2f5014b352776f80270078d0fc7d1e2c189665 +size 9229924224 diff --git a/samantha-1.11-13b.Q5_K_S.gguf b/samantha-1.11-13b.Q5_K_S.gguf new file mode 100644 index 0000000..76c7c46 --- /dev/null +++ b/samantha-1.11-13b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bdc5233872a37c811df17710566ed32f943c777664c683babde5167da6aec3f +size 8972285824 diff --git a/samantha-1.11-13b.Q6_K.gguf b/samantha-1.11-13b.Q6_K.gguf new file mode 100644 index 0000000..b97e07a --- /dev/null +++ b/samantha-1.11-13b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e92d4e006dba0e28ba176500c467d9f81851ce8bc90020e62a0d6fc121a6a781 +size 10679140224 diff --git a/samantha-1.11-13b.Q8_0.gguf b/samantha-1.11-13b.Q8_0.gguf new file mode 100644 index 0000000..f9efb5c --- /dev/null +++ b/samantha-1.11-13b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef3d311b9b7900c67f7becfab7c546e2918f28d82e0367c6e309b04cb8506eed +size 13831319424