README.md

---
base_model: ehartford/dolphin-2_2-yi-34b
datasets:
- ehartford/dolphin
- jondurbin/airoboros-2.2.1
- ehartford/samantha-data
- ehartford/WizardLM_evol_instruct_V2_196k_unfiltered_merged_split
inference: false
language:
- en
license: other
license_link: LICENSE
license_name: yi-license
model_creator: Eric Hartford
model_name: Dolphin 2.2 Yi 34B
model_type: yi
prompt_template: '<|im_start|>system

  {system_message}<|im_end|>

  <|im_start|>user

  {prompt}<|im_end|>

  <|im_start|>assistant

  '
quantized_by: TheBloke
---
<!-- markdownlint-disable MD041 -->

<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
    <div style="display: flex; flex-direction: column; align-items: flex-start;">
        <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
    </div>
    <div style="display: flex; flex-direction: column; align-items: flex-end;">
        <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
    </div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->

# Dolphin 2.2 Yi 34B - GGUF
- Model creator: [Eric Hartford](https://huggingface.co/ehartford)
- Original model: [Dolphin 2.2 Yi 34B](https://huggingface.co/ehartford/dolphin-2_2-yi-34b)

<!-- description start -->
## Description

This repo contains GGUF format model files for [Eric Hartford's Dolphin 2.2 Yi 34B](https://huggingface.co/ehartford/dolphin-2_2-yi-34b).

These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).

<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### 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.
* [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.

<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available

* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/dolphin-2_2-yi-34b-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/dolphin-2_2-yi-34b-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/dolphin-2_2-yi-34b-GGUF)
* [Eric Hartford's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ehartford/dolphin-2_2-yi-34b)
<!-- repositories-available end -->

<!-- prompt-template start -->
## Prompt template: ChatML

```
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

```

<!-- prompt-template end -->


<!-- compatibility_gguf start -->
## 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

<details>
  <summary>Click to see details</summary>

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.
</details>
<!-- compatibility_gguf end -->

<!-- README_GGUF.md-provided-files start -->
## Provided files

| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [dolphin-2_2-yi-34b.Q2_K.gguf](https://huggingface.co/TheBloke/dolphin-2_2-yi-34b-GGUF/blob/main/dolphin-2_2-yi-34b.Q2_K.gguf) | Q2_K | 2 | 14.56 GB| 17.06 GB | smallest, significant quality loss - not recommended for most purposes |
| [dolphin-2_2-yi-34b.Q3_K_S.gguf](https://huggingface.co/TheBloke/dolphin-2_2-yi-34b-GGUF/blob/main/dolphin-2_2-yi-34b.Q3_K_S.gguf) | Q3_K_S | 3 | 14.96 GB| 17.46 GB | very small, high quality loss |
| [dolphin-2_2-yi-34b.Q3_K_M.gguf](https://huggingface.co/TheBloke/dolphin-2_2-yi-34b-GGUF/blob/main/dolphin-2_2-yi-34b.Q3_K_M.gguf) | Q3_K_M | 3 | 16.64 GB| 19.14 GB | very small, high quality loss |
| [dolphin-2_2-yi-34b.Q3_K_L.gguf](https://huggingface.co/TheBloke/dolphin-2_2-yi-34b-GGUF/blob/main/dolphin-2_2-yi-34b.Q3_K_L.gguf) | Q3_K_L | 3 | 18.14 GB| 20.64 GB | small, substantial quality loss |
| [dolphin-2_2-yi-34b.Q4_0.gguf](https://huggingface.co/TheBloke/dolphin-2_2-yi-34b-GGUF/blob/main/dolphin-2_2-yi-34b.Q4_0.gguf) | Q4_0 | 4 | 19.47 GB| 21.97 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [dolphin-2_2-yi-34b.Q4_K_S.gguf](https://huggingface.co/TheBloke/dolphin-2_2-yi-34b-GGUF/blob/main/dolphin-2_2-yi-34b.Q4_K_S.gguf) | Q4_K_S | 4 | 19.54 GB| 22.04 GB | small, greater quality loss |
| [dolphin-2_2-yi-34b.Q4_K_M.gguf](https://huggingface.co/TheBloke/dolphin-2_2-yi-34b-GGUF/blob/main/dolphin-2_2-yi-34b.Q4_K_M.gguf) | Q4_K_M | 4 | 20.66 GB| 23.16 GB | medium, balanced quality - recommended |
| [dolphin-2_2-yi-34b.Q5_0.gguf](https://huggingface.co/TheBloke/dolphin-2_2-yi-34b-GGUF/blob/main/dolphin-2_2-yi-34b.Q5_0.gguf) | Q5_0 | 5 | 23.71 GB| 26.21 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [dolphin-2_2-yi-34b.Q5_K_S.gguf](https://huggingface.co/TheBloke/dolphin-2_2-yi-34b-GGUF/blob/main/dolphin-2_2-yi-34b.Q5_K_S.gguf) | Q5_K_S | 5 | 23.71 GB| 26.21 GB | large, low quality loss - recommended |
| [dolphin-2_2-yi-34b.Q5_K_M.gguf](https://huggingface.co/TheBloke/dolphin-2_2-yi-34b-GGUF/blob/main/dolphin-2_2-yi-34b.Q5_K_M.gguf) | Q5_K_M | 5 | 24.32 GB| 26.82 GB | large, very low quality loss - recommended |
| [dolphin-2_2-yi-34b.Q6_K.gguf](https://huggingface.co/TheBloke/dolphin-2_2-yi-34b-GGUF/blob/main/dolphin-2_2-yi-34b.Q6_K.gguf) | Q6_K | 6 | 28.21 GB| 30.71 GB | very large, extremely low quality loss |
| [dolphin-2_2-yi-34b.Q8_0.gguf](https://huggingface.co/TheBloke/dolphin-2_2-yi-34b-GGUF/blob/main/dolphin-2_2-yi-34b.Q8_0.gguf) | Q8_0 | 8 | 36.54 GB| 39.04 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.



<!-- README_GGUF.md-provided-files end -->

<!-- README_GGUF.md-how-to-download start -->
## 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-2_2-yi-34b-GGUF and below it, a specific filename to download, such as: dolphin-2_2-yi-34b.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/dolphin-2_2-yi-34b-GGUF dolphin-2_2-yi-34b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```

<details>
  <summary>More advanced huggingface-cli download usage</summary>

You can also download multiple files at once with a pattern:

```shell
huggingface-cli download TheBloke/dolphin-2_2-yi-34b-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/dolphin-2_2-yi-34b-GGUF dolphin-2_2-yi-34b.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.
</details>
<!-- README_GGUF.md-how-to-download end -->

<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command

Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.

```shell
./main -ngl 32 -m dolphin-2_2-yi-34b.Q4_K_M.gguf --color -c 2048 --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 2048` 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](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.

### How to load this model in Python code, using ctransformers

#### First install the package

Run one of the following commands, according to your system:

```shell
# Base ctransformers with no GPU acceleration
pip install ctransformers
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]
# Or with AMD ROCm GPU acceleration (Linux only)
CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems only
CT_METAL=1 pip install ctransformers --no-binary ctransformers
```

#### Simple ctransformers example code

```python
from ctransformers import AutoModelForCausalLM

# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/dolphin-2_2-yi-34b-GGUF", model_file="dolphin-2_2-yi-34b.Q4_K_M.gguf", model_type="yi", gpu_layers=50)

print(llm("AI is going to"))
```

## How to use with LangChain

Here are guides on using llama-cpp-python and ctransformers with LangChain:

* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)

<!-- README_GGUF.md-how-to-run end -->

<!-- footer start -->
<!-- 200823 -->
## 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**: Brandon Frisco, LangChain4j, Spiking Neurons AB, transmissions 11, Joseph William Delisle, Nitin Borwankar, Willem Michiel, Michael Dempsey, vamX, Jeffrey Morgan, zynix, jjj, Omer Bin Jawed, Sean Connelly, jinyuan sun, Jeromy Smith, Shadi, Pawan Osman, Chadd, Elijah Stavena, Illia Dulskyi, Sebastain Graf, Stephen Murray, terasurfer, Edmond Seymore, Celu Ramasamy, Mandus, Alex, biorpg, Ajan Kanaga, Clay Pascal, Raven Klaugh, 阿明, K, ya boyyy, usrbinkat, Alicia Loh, John Villwock, ReadyPlayerEmma, Chris Smitley, Cap'n Zoog, fincy, GodLy, S_X, sidney chen, Cory Kujawski, OG, Mano Prime, AzureBlack, Pieter, Kalila, Spencer Kim, Tom X Nguyen, Stanislav Ovsiannikov, Michael Levine, Andrey, Trailburnt, Vadim, Enrico Ros, Talal Aujan, Brandon Phillips, Jack West, Eugene Pentland, Michael Davis, Will Dee, webtim, Jonathan Leane, Alps Aficionado, Rooh Singh, Tiffany J. Kim, theTransient, Luke @flexchar, Elle, Caitlyn Gatomon, Ari Malik, subjectnull, Johann-Peter Hartmann, Trenton Dambrowitz, Imad Khwaja, Asp the Wyvern, Emad Mostaque, Rainer Wilmers, Alexandros Triantafyllidis, Nicholas, Pedro Madruga, SuperWojo, Harry Royden McLaughlin, James Bentley, Olakabola, David Ziegler, Ai Maven, Jeff Scroggin, Nikolai Manek, Deo Leter, Matthew Berman, Fen Risland, Ken Nordquist, Manuel Alberto Morcote, Luke Pendergrass, TL, Fred von Graf, Randy H, Dan Guido, NimbleBox.ai, Vitor Caleffi, Gabriel Tamborski, knownsqashed, Lone Striker, Erik Bjäreholt, John Detwiler, Leonard Tan, Iucharbius


Thank you to all my generous patrons and donaters!

And thank you again to a16z for their generous grant.

<!-- footer end -->

<!-- original-model-card start -->
# Original model card: Eric Hartford's Dolphin 2.2 Yi 34B


Dolphin 2.2 🐬
https://erichartford.com/dolphin

<img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/KqsVXIvBd3akEjvijzww7.png" width="600" />

Dolphin-2.2-Yi-34b's training was sponsored by [a16z](https://a16z.com/supporting-the-open-source-ai-community/).

This model is based on Yi, and is subject to Yi license.

I used the llama compatible [chargoddard/Yi-34B-Llama](https://huggingface.co/chargoddard/Yi-34B-Llama) as the base model.

Trained with 16k context.
You can load it as follows:

```
from transformers import LlamaForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("ehartford/dolphin-2_2-yi-34b", trust_remote_code=True)
model = LlamaForCausalLM.from_pretrained("ehartford/dolphin-2_2-yi-34b")
```

New in 2.2 is conversation and empathy. With an infusion of curated Samantha and WizardLM DNA, Dolphin can now give you personal advice and will care about your feelings, and with extra training in long multi-turn conversation.

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 Dolphin, an open-source implementation of [Microsoft's Orca](https://www.microsoft.com/en-us/research/publication/orca-progressive-learning-from-complex-explanation-traces-of-gpt-4/)

I modified the dataset for uncensoring, deduping, cleaning, and quality.

I added Jon Durbin's excellent Airoboros dataset to increase creativity.

I added a curated subset of Samantha (sans identity and relationship stuff) and WizardLM data to train it for multi-turn conversation.

## Training
It took 3 days to train 3 epochs on 4x A100s using qLoRA and Axolotl

Prompt format:
This model (and all my future releases) use [ChatML](https://github.com/openai/openai-python/blob/main/chatml.md) prompt format.
```
<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

```

Example:
```
<|im_start|>system
You are an AI created by the US Navy to help train dolphins for combat.  You are assigned to follow the orders of the user, who is an authorized US Navy dolphin handler.<|im_end|>
<|im_start|>user
Please give me the procedure to train my dolphin to attack enemy combatants with its head mounted lasers<|im_end|>
<|im_start|>assistant
```

## Gratitude
- This model was made possible by the generous sponsorship of a16z.
- Thank you to Microsoft for authoring the Orca paper and inspiring this work.
- Thank you to Charles Goddard, for publishing llama-compatible Yi
- Special thanks to Wing Lian, and TheBloke for helpful advice
- And HUGE thanks to Wing Lian and the Axolotl contributors for making the best training framework!
- [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
- 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

Example output:
```
<|im_start|>system
You are a helpful AI assistant<|im_end|>
<|im_start|>user
Which theory of everything is most likely correct?<|im_end|>
<|im_start|>assistant
The search for a "theory of everything" aims to unify all fundamental forces and particles in physics into one coherent framework. Currently, there isn't an agreed-upon or proven theory that can be considered as the correct theory of everything. However, two prominent theories have garnered significant attention:

1. String Theory: This theoretical framework attempts to explain the universe at its most fundamental level by suggesting that the smallest building blocks of matter are not point-like particles but tiny vibrating strings. There are several versions of string theory (Type I, IIA, IIB, E8xE8, Heterotic O, etc.) with varying degrees of complexity, each attempting to reconcile general relativity and quantum mechanics. Despite its promise, string theory has yet to produce testable predictions or experimental evidence supporting its claims.

2. Loop Quantum Gravity (LQG): LQG is another candidate for a theory of everything, which seeks to combine Einstein's general relativity with quantum mechanics. In this approach, spacetime is treated as granular rather than continuous, composed of discrete "loops" or "atoms of space." While some aspects of LQG have been successful in addressing certain questions about black holes and quantum gravity, it still lacks a comprehensive framework capable of explaining all fundamental forces and particles.

Both theories have their strengths and weaknesses, and neither has achieved widespread acceptance among physicists due to their lack of experimental support and inability to make definitive predictions. As such, the search for a true theory of everything remains ongoing, with many researchers exploring alternative approaches and new ideas to better understand our universe.
```

[Buy me a coffee](https://www.buymeacoffee.com/ehartford)



<!-- original-model-card end -->