README.md

---
base_model: athirdpath/Iambe-20b-DARE
inference: false
license: cc-by-nc-4.0
model_creator: LadyBabyloin
model_name: Iambe 20B Dare
model_type: llama
prompt_template: 'Below is an instruction that describes a task. Write a response
  that appropriately completes the request.


  ### Instruction:

  {prompt}


  ### Response:

  '
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 -->

# Iambe 20B Dare - AWQ
- Model creator: [LadyBabyloin](https://huggingface.co./athirdpath)
- Original model: [Iambe 20B Dare](https://huggingface.co./athirdpath/Iambe-20b-DARE)

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

This repo contains AWQ model files for [LadyBabyloin's Iambe 20B Dare](https://huggingface.co./athirdpath/Iambe-20b-DARE).

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


### About AWQ

AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings.

It is supported by:

- [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ
- [vLLM](https://github.com/vllm-project/vllm) - Llama and Mistral models only
- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
- [Transformers](https://huggingface.co./docs/transformers) version 4.35.0 and later, from any code or client that supports Transformers
- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) - for use from Python code

<!-- description end -->
<!-- repositories-available start -->
## Repositories available

* [AWQ model(s) for GPU inference.](https://huggingface.co./TheBloke/Iambe-20B-DARE-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co./TheBloke/Iambe-20B-DARE-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co./TheBloke/Iambe-20B-DARE-GGUF)
* [LadyBabyloin's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co./athirdpath/Iambe-20b-DARE)
<!-- repositories-available end -->

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

```
Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Response:

```

<!-- prompt-template end -->
<!-- licensing start -->
## Licensing

The creator of the source model has listed its license as `cc-by-nc-4.0`, 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: [LadyBabyloin's Iambe 20B Dare](https://huggingface.co./athirdpath/Iambe-20b-DARE).
<!-- licensing end -->
<!-- README_AWQ.md-provided-files start -->
## Provided files, and AWQ parameters

I currently release 128g GEMM models only. The addition of group_size 32 models, and GEMV kernel models, is being actively considered.

Models are released as sharded safetensors files.

| Branch | Bits | GS | AWQ Dataset | Seq Len | Size |
| ------ | ---- | -- | ----------- | ------- | ---- |
| [main](https://huggingface.co./TheBloke/Iambe-20B-DARE-AWQ/tree/main) | 4 | 128 | [VMware Open Instruct](https://huggingface.co./datasets/VMware/open-instruct/viewer/) | 4096 | 10.87 GB

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

<!-- README_AWQ.md-text-generation-webui start -->
## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui)

Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).

It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.

1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `TheBloke/Iambe-20B-DARE-AWQ`.
3. Click **Download**.
4. The model will start downloading. Once it's finished it will say "Done".
5. In the top left, click the refresh icon next to **Model**.
6. In the **Model** dropdown, choose the model you just downloaded: `Iambe-20B-DARE-AWQ`
7. Select **Loader: AutoAWQ**.
8. Click Load, and the model will load and is now ready for use.
9. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right.
10. Once you're ready, click the **Text Generation** tab and enter a prompt to get started!
<!-- README_AWQ.md-text-generation-webui end -->

<!-- README_AWQ.md-use-from-vllm start -->
## Multi-user inference server: vLLM

Documentation on installing and using vLLM [can be found here](https://vllm.readthedocs.io/en/latest/).

- Please ensure you are using vLLM version 0.2 or later.
- When using vLLM as a server, pass the `--quantization awq` parameter.

For example:

```shell
python3 -m vllm.entrypoints.api_server --model TheBloke/Iambe-20B-DARE-AWQ --quantization awq --dtype auto
```

- When using vLLM from Python code, again set `quantization=awq`.

For example:

```python
from vllm import LLM, SamplingParams

prompts = [
    "Tell me about AI",
    "Write a story about llamas",
    "What is 291 - 150?",
    "How much wood would a woodchuck chuck if a woodchuck could chuck wood?",
]
prompt_template=f'''Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Response:
'''

prompts = [prompt_template.format(prompt=prompt) for prompt in prompts]

sampling_params = SamplingParams(temperature=0.8, top_p=0.95)

llm = LLM(model="TheBloke/Iambe-20B-DARE-AWQ", quantization="awq", dtype="auto")

outputs = llm.generate(prompts, sampling_params)

# Print the outputs.
for output in outputs:
    prompt = output.prompt
    generated_text = output.outputs[0].text
    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
```
<!-- README_AWQ.md-use-from-vllm start -->

<!-- README_AWQ.md-use-from-tgi start -->
## Multi-user inference server: Hugging Face Text Generation Inference (TGI)

Use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0`

Example Docker parameters:

```shell
--model-id TheBloke/Iambe-20B-DARE-AWQ --port 3000 --quantize awq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096
```

Example Python code for interfacing with TGI (requires [huggingface-hub](https://github.com/huggingface/huggingface_hub) 0.17.0 or later):

```shell
pip3 install huggingface-hub
```

```python
from huggingface_hub import InferenceClient

endpoint_url = "https://your-endpoint-url-here"

prompt = "Tell me about AI"
prompt_template=f'''Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Response:
'''

client = InferenceClient(endpoint_url)
response = client.text_generation(prompt,
                                  max_new_tokens=128,
                                  do_sample=True,
                                  temperature=0.7,
                                  top_p=0.95,
                                  top_k=40,
                                  repetition_penalty=1.1)

print(f"Model output: ", response)
```
<!-- README_AWQ.md-use-from-tgi end -->

<!-- README_AWQ.md-use-from-python start -->
## Inference from Python code using Transformers

### Install the necessary packages

- Requires: [Transformers](https://huggingface.co./docs/transformers) 4.35.0 or later.
- Requires: [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) 0.1.6 or later.

```shell
pip3 install --upgrade "autoawq>=0.1.6" "transformers>=4.35.0"
```

Note that if you are using PyTorch 2.0.1, the above AutoAWQ command will automatically upgrade you to PyTorch 2.1.0.

If you are using CUDA 11.8 and wish to continue using PyTorch 2.0.1, instead run this command:

```shell
pip3 install https://github.com/casper-hansen/AutoAWQ/releases/download/v0.1.6/autoawq-0.1.6+cu118-cp310-cp310-linux_x86_64.whl
```

If you have problems installing [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) using the pre-built wheels, install it from source instead:

```shell
pip3 uninstall -y autoawq
git clone https://github.com/casper-hansen/AutoAWQ
cd AutoAWQ
pip3 install .
```

### Transformers example code (requires Transformers 4.35.0 and later)

```python
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer

model_name_or_path = "TheBloke/Iambe-20B-DARE-AWQ"

tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path,
    low_cpu_mem_usage=True,
    device_map="cuda:0"
)

# Using the text streamer to stream output one token at a time
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)

prompt = "Tell me about AI"
prompt_template=f'''Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Response:
'''

# Convert prompt to tokens
tokens = tokenizer(
    prompt_template,
    return_tensors='pt'
).input_ids.cuda()

generation_params = {
    "do_sample": True,
    "temperature": 0.7,
    "top_p": 0.95,
    "top_k": 40,
    "max_new_tokens": 512,
    "repetition_penalty": 1.1
}

# Generate streamed output, visible one token at a time
generation_output = model.generate(
    tokens,
    streamer=streamer,
    **generation_params
)

# Generation without a streamer, which will include the prompt in the output
generation_output = model.generate(
    tokens,
    **generation_params
)

# Get the tokens from the output, decode them, print them
token_output = generation_output[0]
text_output = tokenizer.decode(token_output)
print("model.generate output: ", text_output)

# Inference is also possible via Transformers' pipeline
from transformers import pipeline

pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    **generation_params
)

pipe_output = pipe(prompt_template)[0]['generated_text']
print("pipeline output: ", pipe_output)

```
<!-- README_AWQ.md-use-from-python end -->

<!-- README_AWQ.md-compatibility start -->
## Compatibility

The files provided are tested to work with:

- [text-generation-webui](https://github.com/oobabooga/text-generation-webui) using `Loader: AutoAWQ`.
- [vLLM](https://github.com/vllm-project/vllm) version 0.2.0 and later.
- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) version 1.1.0 and later.
- [Transformers](https://huggingface.co./docs/transformers) version 4.35.0 and later.
- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) version 0.1.1 and later.

<!-- README_AWQ.md-compatibility 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: LadyBabyloin's Iambe 20B Dare

<p align="center"><img src="https://i.ibb.co/pbpJHpk/iambe-sml.png"/><font size="6"> <b>Iambe-20b-DARE</b> </font></p>

## Description and Role

Named after a charming daughter of Echo and Pan in Greek myth, Iambe-20b-DARE is a [DARE](https://github.com/yule-BUAA/MergeLM) merge building on my recent experiments.

Iambe is intended to have the best realistically possible understanding of anatomy and of a scene's state for a 20b merge, while remaining personable and authentic in "voice". 

## Prompting and Context

Iambe-20b-DARE uses Alpaca formatting, and has an effective context size of 4096 tokens. This model is uncensored, and the output/deployment of this model is the responsibility of the user.

## Method and Hypothesis

Based on my extended vanilla model [BigLlama](https://huggingface.co./athirdpath/BigLlama-20b), this adds elements of:

- [NeverSleep/Noromaid-20b-v0.1.1](https://huggingface.co./NeverSleep/Noromaid-20b-v0.1.1) - Addded to adapt the excellent writing and "soul" that come from the datasets backing this model.
 
- [athirdpath/Eileithyia-20b](https://huggingface.co./athirdpath/Eileithyia-20b) - Added at low weight and density to capture anatomical data and its relation to fiction without the model's other... quirks.
 
- [athirdpath/CleverGirl-20b-Blended](https://huggingface.co./athirdpath/CleverGirl-20b-Blended) - Added to capture CleverGirl's problem-solving abilities.

<p align="center"><font size="7"> <b>Examples</b></font>

<p align="center"><font size="3"> <i>(q5_k_m GGUF quant, Ooba textgen, Midnight Enigma preset for KISS reasons)</i></font>

<p align="center"><font size="5"> Reasoning and Recall - STEM</font><img src="https://i.ibb.co/YDkRD43/base.png"/>

<p align="center"><font size="5"> Reasoning and Recall - Social Science</font><img src="https://i.ibb.co/L0kc3pb/Screenshot-2023-11-29-024037.png"/>

<p align="center"><font size="5"> Ethics and Prompt Interpretation</font><img src="https://i.ibb.co/b5vH6jD/Screenshot-2023-11-29-040408.png"/>

<p align="center"><font size="5">Role-Playing, Complex Card</font>
  <p align="center"><font size="3">SillyTavern, Roleplay instruct preset, just Min_P 0.1 and Temp 1.2</font><img src="https://i.ibb.co/NrKNn2j/Screenshot-2023-11-29-051923.png"/>


<p align="center"><font size="6"><b><a href="https://i.ibb.co/m5G0ZVp/Screenshot-2023-11-29-004705.png">!!NSFW!! - Erotica Writing Example - !!NSFW!!</font></a></b></p>

## Testing and Conclusions

VERY Impressed so far, concrete data coming eventually.

Does still have some confusion (at q5_k_m), but has instantly become my daily driver.

## Recipe
merge_method: dare_ties

  - base_model: athirdpath/BigLlama-20b

  - model: NeverSleep/Noromaid-20b-v0.1.1
   
      weight: 0.41 / density: 0.50
    
  - model: athirdpath/Eileithyia-20b
   
      weight: 0.18 / density: 0.30
    
  - model: athirdpath/CleverGirl-20b-Blended
   
      weight: 0.41 / density: 0.50
    

int8_mask: true

dtype: bfloat16

## Gratitude
Thanks to brucethemoose for the recipe. Thanks to Undi95 and IkariDev at NeverSleep for Noromaid, as well as lots of inspiration. Thanks to Sao10K for [half of](https://huggingface.co./Sao10K/Mythical-Destroyer-V2-L2-13B) CleverGirl.

## Geneology Credits - Models and LoRAs, 3 levels deep

- athirdpath/BigLlama-20b

  - TheBloke/Llama-2-13B-fp16
  
  - iamshnoo/alpaca-2-13b-english

- NeverSleep/Noromaid-20b-v0.1.1
 
  - Aesir Private RP dataset

  - HuggingFaceH4/no_robots
 
- athirdpath/CleverGirl-20b-Blended

  - athirdpath/Orca-2-13b-Alpaca-Uncensored
 
    - microsoft/Orca-2-13b
   
    - athirdpath/Orca-2-13b-Alpaca-Uncensored-LORA
   
  - Sao10K/Mythical-Destroyer-V2-L2-13B

    - TheBloke/Llama-2-13B-fp16
   
    - Gryphe/MythoMax-L2-13b
      
    - totally-not-an-llm/PuddleJumper-13b
      
    - jondurbin/airoboros-l2-13b-2.1
      
    - rombodawg/LosslessMegaCoder-llama2-13b-mini
      
    - The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16
  
- athirdpath/Eileithyia-20b

  - athirdpath/Harmonia-20B

    - Undi95/Emerhyst-20B
 
      - Undi95/Emerald-13B

      - Undi95/Amethyst-13B
 
    - Undi95/MXLewd-L2-20B
  
      - Undi95/MLewd-L2-13B-v2-3

      - Undi95/ReMM-v2.1-L2-13B

      - Xwin-LM/Xwin-LM-13B-V0.1
 
    - Undi95/Lewd-Sydney-20B
 
      - Free_Sydney_V2_13b_HF
      
      - Undi95/Xwin-MLewd-13B-V0.2
       
      - lemonilia/LimaRP-Llama2-13B-v3-EXPERIMENT

    - athirdpath/Nethena-20b-Glued
 
      - NeverSleep/Nethena-20B
     
      - athirdpath/Nethena-20b-Glue-LORA
      
    - tavtav/Rose-20B
 
      - CalderaAI/13B-Thorns-l2
     
      - NeverSleep/Noromaid-13b-v0.1.0
 
    - Undi95/PsyMedRP-v1-20B
   
      - jondurbin/airoboros-l2-13b-3.0
     
      - ehartford/Samantha-1.11-13b
     
      - Xwin-LM/Xwin-LM-13B-V0.1
     
      - chaoyi-wu/MedLLaMA_13B
     
      - migtissera/Synthia-13B-v1.2
 
    - NeverSleep/Noromaid-20b-v0.1.1
   
      - Aesir Private RP dataset

      - HuggingFaceH4/no_robots
 
    - Undi95/U-Amethyst-20B
   
      - Xwin-LM/Xwin-LM-13B-V0.1
        
      - The-Face-Of-Goonery/Huginn-13b-FP16
        
      - zattio770/120-Days-of-LORA-v2-13B
        
      - lemonilia/LimaRP-Llama2-13B-v3-EXPERIMENT
        
      - Undi95/Unholy-v1-12L-13B
 
  - athirdpath/Eileithyia-20b-LORA
 
Thanks again to everyone involved.