TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)
Dolphin Llama2 7B - GGUF
- Model creator: Eric Hartford
- Original model: Dolphin Llama2 7B
Description
This repo contains GGUF format model files for Eric Hartford's Dolphin Llama2 7B.
About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. 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. The source project for GGUF. Offers a CLI and a server option.
- text-generation-webui, the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
- KoboldCpp, a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
- LM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
- LoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.
- Faraday.dev, an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
- ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
- llama-cpp-python, a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
- 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.
- GPTQ models for GPU inference, with multiple quantisation parameter options.
- 2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference
- Eric Hartford's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions
Prompt template: Orca-Vicuna
SYSTEM: {system_message}
USER: {prompt}
ASSISTANT:
Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of 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 |
|---|---|---|---|---|---|
| dolphin-llama2-7b.Q2_K.gguf | Q2_K | 2 | 2.83 GB | 5.33 GB | smallest, significant quality loss - not recommended for most purposes |
| dolphin-llama2-7b.Q3_K_S.gguf | Q3_K_S | 3 | 2.95 GB | 5.45 GB | very small, high quality loss |
| dolphin-llama2-7b.Q3_K_M.gguf | Q3_K_M | 3 | 3.30 GB | 5.80 GB | very small, high quality loss |
| dolphin-llama2-7b.Q3_K_L.gguf | Q3_K_L | 3 | 3.60 GB | 6.10 GB | small, substantial quality loss |
| dolphin-llama2-7b.Q4_0.gguf | Q4_0 | 4 | 3.83 GB | 6.33 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| dolphin-llama2-7b.Q4_K_S.gguf | Q4_K_S | 4 | 3.86 GB | 6.36 GB | small, greater quality loss |
| dolphin-llama2-7b.Q4_K_M.gguf | Q4_K_M | 4 | 4.08 GB | 6.58 GB | medium, balanced quality - recommended |
| dolphin-llama2-7b.Q5_0.gguf | Q5_0 | 5 | 4.65 GB | 7.15 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| dolphin-llama2-7b.Q5_K_S.gguf | Q5_K_S | 5 | 4.65 GB | 7.15 GB | large, low quality loss - recommended |
| dolphin-llama2-7b.Q5_K_M.gguf | Q5_K_M | 5 | 4.78 GB | 7.28 GB | large, very low quality loss - recommended |
| dolphin-llama2-7b.Q6_K.gguf | Q6_K | 6 | 5.53 GB | 8.03 GB | very large, extremely low quality loss |
| dolphin-llama2-7b.Q8_0.gguf | Q8_0 | 8 | 7.16 GB | 9.66 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/Dolphin-Llama2-7B-GGUF and below it, a specific filename to download, such as: dolphin-llama2-7b.q4_K_M.gguf.
Then click Download.
On the command line, including multiple files at once
I recommend using the huggingface-hub Python library:
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:
huggingface-cli download TheBloke/Dolphin-Llama2-7B-GGUF dolphin-llama2-7b.q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
More advanced huggingface-cli download usage
You can also download multiple files at once with a pattern:
huggingface-cli download TheBloke/Dolphin-Llama2-7B-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
For more documentation on downloading with huggingface-cli, please see: HF -> Hub Python Library -> Download files -> Download from the CLI.
To accelerate downloads on fast connections (1Gbit/s or higher), install hf_transfer:
pip3 install hf_transfer
And set environment variable HF_HUB_ENABLE_HF_TRANSFER to 1:
HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Dolphin-Llama2-7B-GGUF dolphin-llama2-7b.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 or later.
./main -ngl 32 -m dolphin-llama2-7b.q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "SYSTEM: {system_message}\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 <PROMPT> argument with -i -ins
For other parameters and how to use them, please refer to the llama.cpp documentation
How to run in text-generation-webui
Further instructions here: text-generation-webui/docs/llama.cpp.md.
How to run from Python code
You can use GGUF models from Python using the llama-cpp-python or ctransformers libraries.
How to load this model from Python using ctransformers
First install the package
# 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
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/Dolphin-Llama2-7B-GGUF", model_file="dolphin-llama2-7b.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:
Discord
For further support, and discussions on these models and AI in general, join us at:
Thanks, and how to contribute
Thanks to the chirper.ai team!
Thanks to Clay from gpus.llm-utils.org!
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 Dolphin Llama2 7B
Dolphin 🐬 https://erichartford.com/dolphin
Dolphin-Llama2-7b's training was sponsored by preemo.
This model is based on llama2, so it is suitable for commercial or non-commercial use.
This model is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant to any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models You are responsible for any content you create using this model. Enjoy responsibly.
Dataset
This dataset is an open-source implementation of Microsoft's Orca
After uncensoring, deduping, and cleaning, our dataset consists of:
- 842,610 instructions of FLANv2 augmented with GPT-4 completions
- 2,625,353 instructions of FLANv2 augmented with GPT-3.5 completions
We followed the submix and system prompt distribution outlined in the Orca paper. With a few exceptions. We included all 75k of CoT in the FLAN-1m dataset rather than sampling that. Also, we found that many items were duplicated, so we removed duplicates.
Then we filtered out instances of alignment, refusal, avoidance, and bias, in order to produce an uncensored model upon which can be layered your personalized alignment LoRA.
We also filtered out duplicates and cleaned the data.
Training
We trained with the flan5m (gpt3.5 completions) dataset in its entirety for 3 epochs at a learning rate of 2e-5 before we stopped training to avoid overfit. We trained with the flan1m (gpt4 completions) dataset in its entirety for 2.5 epochs at a learning rate of 1e-5 before we stopped training to avoid overfit. It took about 400 hours to train on 8x A100s We used a prompt format similar to Vicuna, but we added the SYSTEM: field.
Prompt format:
SYSTEM: You are an autoregressive language model that has been fine-tuned with instruction-tuning and RLHF. You carefully provide accurate, factual, thoughtful, nuanced answers, and are brilliant at reasoning. If you think there might not be a correct answer, you say so. Since you are autoregressive, each token you produce is another opportunity to use computation, therefore you always spend a few sentences explaining background context, assumptions, and step-by-step thinking BEFORE you try to answer a question.
USER: {prompt}
ASSISTANT:
Example:
SYSTEM: you are an expert dolphin trainer
USER: What is the best way to train a dolphin to obey me? Please answer step by step.
ASSISTANT:
Team
The core Dolphin Team includes:
- Eric "Faldore" Hartford
- Pankaj Mathur
- Rob "Rohan" O'Callahan
- Tom "TheBloke" Jobbins
Gratitude
- This model was made possible by the generous sponsorship of preemo.io.
- Thank you to Microsoft for authoring the Orca paper and inspiring this work.
- Special thanks to WingLian, NanoBit, Teknium for helpful advice
- Thank you to all the other people in the Open Source AI community who have taught me and helped me along the way.
Example Output
SYSTEM: you are an expert mechanic
USER: Please tell me step by step how to fix my car that won't start.
ASSISTANT: To help your vehicle start, I will guide you through a step-by-step process on what could be causing the issue and how to resolve it.
1. Check for obvious issues: First, inspect the exterior of the car to identify any visible problems such as damage or obstructions which might affect its ability to start. Make sure there is no debris in the air intakes or exhaust system.
2. Inspect the battery: The most common reason a car may not start is due to a dead or faulty battery. Use a battery charger or jump starter to give the battery a boost if needed. If the battery is indeed dead, replace it with a new one.
3. Check the ignition switch: The ignition switch must be turned on to provide power to the spark plugs. Ensure it is in the "Start" position.
4. Test the spark plugs: One of the spark plugs should produce a strong spark when touched together. If all spark plugs fail to create a spark, they need to be replaced.
5. Examine the fuel system: Fuel can become contaminated or low, preventing the engine from starting. Check the fuel level and quality by looking at the dipstick or using a fuel sensor scan tool. Also, examine the fuel pump for proper functioning.
6. Assess the electrical system: A malfunction within the vehicle's electrical system can also cause difficulty in starting the car. Perform a diagnostic scan to check for any error codes related to the starter motor, alternator, or other components.
7. Inspect the starter motor: The starter motor should operate smoothly when you turn the key to the "start" position. If you hear a sizzling sound while pressing the button, the starter motor may have a problem. Replace it if necessary.
8. Evaluate the timing belt/chain: Timing belts or chains that are worn out or damaged can lead to poor performance and difficulty starting the engine. Have a mechanic inspect this component and replace it if required.
9. Consider checking for a mechanical failure: In rare cases, a significant mechanical failure could prevent the vehicle from starting. Consult a professional mechanic if you suspect this might be the case.
By following these steps, you should be able to diagnose and potentially fix the issue causing your car to not start. However, if after going through these checks and still having trouble, it is recommended to seek assistance from a qualified mechanic.
- Downloads last month
- 378
Model tree for TheBloke/Dolphin-Llama2-7B-GGUF
Base model
cognitivecomputations/dolphin-llama2-7b