---
base_model: Locutusque/Orca-2-13b-SFT_v5
datasets:
- HuggingFaceH4/no_robots
- mlabonne/guanaco-llama2-1k
- OpenAssistant/oasst_top1_2023-08-25
- totally-not-an-llm/EverythingLM-data-V3
- garage-bAInd/Open-Platypus
inference: false
language:
- en
- fr
- es
- hi
- zh
- code
license: other
model_creator: Sebastian Gabarain
model_name: Orca 2 13B SFT V5
model_type: llama
prompt_template: '<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
'
quantized_by: TheBloke
widget:
- example_title: folklore
output:
text: 'The Nahanni Valley in Canada is a remote and rugged region that has long
been shrouded in mystery. It is home to the South Nahanni River, which was designated
as a UNESCO World Heritage Site due to its exceptional natural beauty and biodiversity.
The valley''s history includes tales of gold prospectors, fur traders, and indigenous
populations, but it also features some unexplained events and legends. One such
story involves two prospectors who allegedly encountered an unknown creature
that led them into the forest before returning without their heads. This tale
has been passed down through generations, but there are no definitive answers
regarding its veracity.
It is important to note that these stories may have originated from local folklore
or were exaggerated over time. There is no concrete evidence to support the
existence of supernatural creatures or paranormal occurrences within the Nahanni
Valley. Nonetheless, the area remains a captivating destination for those seeking
adventure and exploration. If you have any questions about this topic or need
assistance related to traveling to the Nahanni Valley, please feel free to ask!'
text: '<|im_start|>user
Are the stories of Nahanni Valley, like the decapitated men, true?
<|im_end|>
<|im_start|>assistant
'
- example_title: Alan Turing
output:
text: 'Alan Turing, a renowned mathematician and computer scientist who played
a crucial role in breaking the German Enigma code during World War II, faced
significant challenges due to his homosexuality. In 1952, he was convicted of
"gross indecency" for engaging in a consensual relationship with another man,
which led to him being sentenced to hormone therapy designed to reduce his sex
drive. This treatment included the administration of estrogen, which had the
side effect of causing breast growth.
In an effort to avoid this unwanted physical change, Turing requested that his
doctors cease the hormone treatments. However, they ignored his request and
continued the therapy without his consent. As a result, Turing''s breasts began
to grow, leading him to undergo surgery to remove them. The operation, known
as a mastectomy, caused considerable pain and discomfort, further contributing
to his emotional turmoil.
It is important to note that Turing''s castration was not directly carried out
by the authorities but rather resulted from the unintended consequences of the
forced hormone therapy.'
text: '<|im_start|>user
Why was Alan Turing castrated?
<|im_end|>
<|im_start|>assistant
'
---
# Orca 2 13B SFT V5 - GGUF
- Model creator: [Sebastian Gabarain](https://huggingface.co./Locutusque)
- Original model: [Orca 2 13B SFT V5](https://huggingface.co./Locutusque/Orca-2-13b-SFT_v5)
## Description
This repo contains GGUF format model files for [Sebastian Gabarain's Orca 2 13B SFT V5](https://huggingface.co./Locutusque/Orca-2-13b-SFT_v5).
These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
### 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 incomplete 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.
* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
* [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.
* [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.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co./TheBloke/Orca-2-13B-SFT_v5-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co./TheBloke/Orca-2-13B-SFT_v5-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co./TheBloke/Orca-2-13B-SFT_v5-GGUF)
* [Sebastian Gabarain's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co./Locutusque/Orca-2-13b-SFT_v5)
## Prompt template: ChatML
```
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
## Licensing
The creator of the source model has listed its license as `other`, and this quantization has therefore used that same license.
As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.
In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: [Sebastian Gabarain's Orca 2 13B SFT V5](https://huggingface.co./Locutusque/Orca-2-13b-SFT_v5).
## 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 |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [orca-2-13b-sft_v5.Q2_K.gguf](https://huggingface.co./TheBloke/Orca-2-13B-SFT_v5-GGUF/blob/main/orca-2-13b-sft_v5.Q2_K.gguf) | Q2_K | 2 | 5.43 GB| 7.93 GB | smallest, significant quality loss - not recommended for most purposes |
| [orca-2-13b-sft_v5.Q3_K_S.gguf](https://huggingface.co./TheBloke/Orca-2-13B-SFT_v5-GGUF/blob/main/orca-2-13b-sft_v5.Q3_K_S.gguf) | Q3_K_S | 3 | 5.66 GB| 8.16 GB | very small, high quality loss |
| [orca-2-13b-sft_v5.Q3_K_M.gguf](https://huggingface.co./TheBloke/Orca-2-13B-SFT_v5-GGUF/blob/main/orca-2-13b-sft_v5.Q3_K_M.gguf) | Q3_K_M | 3 | 6.34 GB| 8.84 GB | very small, high quality loss |
| [orca-2-13b-sft_v5.Q3_K_L.gguf](https://huggingface.co./TheBloke/Orca-2-13B-SFT_v5-GGUF/blob/main/orca-2-13b-sft_v5.Q3_K_L.gguf) | Q3_K_L | 3 | 6.93 GB| 9.43 GB | small, substantial quality loss |
| [orca-2-13b-sft_v5.Q4_0.gguf](https://huggingface.co./TheBloke/Orca-2-13B-SFT_v5-GGUF/blob/main/orca-2-13b-sft_v5.Q4_0.gguf) | Q4_0 | 4 | 7.37 GB| 9.87 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [orca-2-13b-sft_v5.Q4_K_S.gguf](https://huggingface.co./TheBloke/Orca-2-13B-SFT_v5-GGUF/blob/main/orca-2-13b-sft_v5.Q4_K_S.gguf) | Q4_K_S | 4 | 7.42 GB| 9.92 GB | small, greater quality loss |
| [orca-2-13b-sft_v5.Q4_K_M.gguf](https://huggingface.co./TheBloke/Orca-2-13B-SFT_v5-GGUF/blob/main/orca-2-13b-sft_v5.Q4_K_M.gguf) | Q4_K_M | 4 | 7.87 GB| 10.37 GB | medium, balanced quality - recommended |
| [orca-2-13b-sft_v5.Q5_0.gguf](https://huggingface.co./TheBloke/Orca-2-13B-SFT_v5-GGUF/blob/main/orca-2-13b-sft_v5.Q5_0.gguf) | Q5_0 | 5 | 8.97 GB| 11.47 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [orca-2-13b-sft_v5.Q5_K_S.gguf](https://huggingface.co./TheBloke/Orca-2-13B-SFT_v5-GGUF/blob/main/orca-2-13b-sft_v5.Q5_K_S.gguf) | Q5_K_S | 5 | 8.97 GB| 11.47 GB | large, low quality loss - recommended |
| [orca-2-13b-sft_v5.Q5_K_M.gguf](https://huggingface.co./TheBloke/Orca-2-13B-SFT_v5-GGUF/blob/main/orca-2-13b-sft_v5.Q5_K_M.gguf) | Q5_K_M | 5 | 9.23 GB| 11.73 GB | large, very low quality loss - recommended |
| [orca-2-13b-sft_v5.Q6_K.gguf](https://huggingface.co./TheBloke/Orca-2-13B-SFT_v5-GGUF/blob/main/orca-2-13b-sft_v5.Q6_K.gguf) | Q6_K | 6 | 10.68 GB| 13.18 GB | very large, extremely low quality loss |
| [orca-2-13b-sft_v5.Q8_0.gguf](https://huggingface.co./TheBloke/Orca-2-13B-SFT_v5-GGUF/blob/main/orca-2-13b-sft_v5.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/Orca-2-13B-SFT_v5-GGUF and below it, a specific filename to download, such as: orca-2-13b-sft_v5.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/Orca-2-13B-SFT_v5-GGUF orca-2-13b-sft_v5.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
More advanced huggingface-cli download usage (click to read)
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/Orca-2-13B-SFT_v5-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/Orca-2-13B-SFT_v5-GGUF orca-2-13b-sft_v5.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 35 -m orca-2-13b-sft_v5.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"
```
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. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
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 can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## 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. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# 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 = Llama(
model_path="./orca-2-13b-sft_v5.Q4_K_M.gguf", # Download the model file first
n_ctx=4096, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=[""], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./orca-2-13b-sft_v5.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## 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**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
# Original model card: Sebastian Gabarain's Orca 2 13B SFT V5
The "microsoft/Orca-2-13b" model fully fine-tuned on HuggingFaceH4/no_robots, totally-not-an-llm/EverythingLM-data-V3, mlabonne/guanaco-llama2-1k, OpenAssistant/oasst_top1_2023-08-25, and garage-bAInd/Open-Platypus. This model achieved a test loss of 0.38.
Make sure to comply with the microsoft research license. Please read it before using this model.
This model was trained on the ChatML prompt template.
The responses seen in the inference API were generated using the following sampling parameters:
temperature = 0.1
top_p = 0.14
top_k = 41
repetition_penalty = 1.176