--- language: - en license: llama2 datasets: - ehartford/samantha-data model_name: Samantha 1.1 70B base_model: ehartford/Samantha-1.1-70b 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 1.1 70B - GGUF - Model creator: [Eric Hartford](https://huggingface.co/ehartford) - Original model: [Samantha 1.1 70B](https://huggingface.co/ehartford/Samantha-1.1-70b) ## Description This repo contains GGUF format model files for [Eric Hartford's Samantha 1.1 70B](https://huggingface.co/ehartford/Samantha-1.1-70b). ### 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-1.1-70B-AWQ) * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Samantha-1.1-70B-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Samantha-1.1-70B-GGUF) * [Eric Hartford's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ehartford/Samantha-1.1-70b) ## 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-1.1-70b.Q2_K.gguf](https://huggingface.co/TheBloke/Samantha-1.1-70B-GGUF/blob/main/samantha-1.1-70b.Q2_K.gguf) | Q2_K | 2 | 29.28 GB| 31.78 GB | smallest, significant quality loss - not recommended for most purposes | | [samantha-1.1-70b.Q3_K_S.gguf](https://huggingface.co/TheBloke/Samantha-1.1-70B-GGUF/blob/main/samantha-1.1-70b.Q3_K_S.gguf) | Q3_K_S | 3 | 29.92 GB| 32.42 GB | very small, high quality loss | | [samantha-1.1-70b.Q3_K_M.gguf](https://huggingface.co/TheBloke/Samantha-1.1-70B-GGUF/blob/main/samantha-1.1-70b.Q3_K_M.gguf) | Q3_K_M | 3 | 33.19 GB| 35.69 GB | very small, high quality loss | | [samantha-1.1-70b.Q3_K_L.gguf](https://huggingface.co/TheBloke/Samantha-1.1-70B-GGUF/blob/main/samantha-1.1-70b.Q3_K_L.gguf) | Q3_K_L | 3 | 36.15 GB| 38.65 GB | small, substantial quality loss | | [samantha-1.1-70b.Q4_0.gguf](https://huggingface.co/TheBloke/Samantha-1.1-70B-GGUF/blob/main/samantha-1.1-70b.Q4_0.gguf) | Q4_0 | 4 | 38.87 GB| 41.37 GB | legacy; small, very high quality loss - prefer using Q3_K_M | | [samantha-1.1-70b.Q4_K_S.gguf](https://huggingface.co/TheBloke/Samantha-1.1-70B-GGUF/blob/main/samantha-1.1-70b.Q4_K_S.gguf) | Q4_K_S | 4 | 39.07 GB| 41.57 GB | small, greater quality loss | | [samantha-1.1-70b.Q4_K_M.gguf](https://huggingface.co/TheBloke/Samantha-1.1-70B-GGUF/blob/main/samantha-1.1-70b.Q4_K_M.gguf) | Q4_K_M | 4 | 41.42 GB| 43.92 GB | medium, balanced quality - recommended | | [samantha-1.1-70b.Q5_0.gguf](https://huggingface.co/TheBloke/Samantha-1.1-70B-GGUF/blob/main/samantha-1.1-70b.Q5_0.gguf) | Q5_0 | 5 | 47.46 GB| 49.96 GB | legacy; medium, balanced quality - prefer using Q4_K_M | | [samantha-1.1-70b.Q5_K_S.gguf](https://huggingface.co/TheBloke/Samantha-1.1-70B-GGUF/blob/main/samantha-1.1-70b.Q5_K_S.gguf) | Q5_K_S | 5 | 47.46 GB| 49.96 GB | large, low quality loss - recommended | | [samantha-1.1-70b.Q5_K_M.gguf](https://huggingface.co/TheBloke/Samantha-1.1-70B-GGUF/blob/main/samantha-1.1-70b.Q5_K_M.gguf) | Q5_K_M | 5 | 48.75 GB| 51.25 GB | large, very low quality loss - recommended | | samantha-1.1-70b.Q6_K.gguf | Q6_K | 6 | 56.59 GB| 59.09 GB | very large, extremely low quality loss | | samantha-1.1-70b.Q8_0.gguf | Q8_0 | 8 | 73.29 GB| 75.79 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. ### Q6_K and Q8_0 files are split and require joining **Note:** HF does not support uploading files larger than 50GB. Therefore I have uploaded the Q6_K and Q8_0 files as split files.
Click for instructions regarding Q6_K and Q8_0 files ### q6_K Please download: * `samantha-1.1-70b.Q6_K.gguf-split-a` * `samantha-1.1-70b.Q6_K.gguf-split-b` ### q8_0 Please download: * `samantha-1.1-70b.Q8_0.gguf-split-a` * `samantha-1.1-70b.Q8_0.gguf-split-b` To join the files, do the following: Linux and macOS: ``` cat samantha-1.1-70b.Q6_K.gguf-split-* > samantha-1.1-70b.Q6_K.gguf && rm samantha-1.1-70b.Q6_K.gguf-split-* cat samantha-1.1-70b.Q8_0.gguf-split-* > samantha-1.1-70b.Q8_0.gguf && rm samantha-1.1-70b.Q8_0.gguf-split-* ``` Windows command line: ``` COPY /B samantha-1.1-70b.Q6_K.gguf-split-a + samantha-1.1-70b.Q6_K.gguf-split-b samantha-1.1-70b.Q6_K.gguf del samantha-1.1-70b.Q6_K.gguf-split-a samantha-1.1-70b.Q6_K.gguf-split-b COPY /B samantha-1.1-70b.Q8_0.gguf-split-a + samantha-1.1-70b.Q8_0.gguf-split-b samantha-1.1-70b.Q8_0.gguf del samantha-1.1-70b.Q8_0.gguf-split-a samantha-1.1-70b.Q8_0.gguf-split-b ```
## 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-1.1-70B-GGUF and below it, a specific filename to download, such as: samantha-1.1-70b.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-1.1-70B-GGUF samantha-1.1-70b.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-1.1-70B-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-1.1-70B-GGUF samantha-1.1-70b.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-1.1-70b.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-1.1-70B-GGUF", model_file="samantha-1.1-70b.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 1.1 70B [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. Training 70b took 4 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)