---
base_model: athirdpath/Iambe-RP-v3-20b
datasets:
- athirdpath/DPO_Pairs-Roleplay-Alpaca-NSFW-v1
inference: false
language:
- en
license: cc-by-nc-4.0
model_creator: Raven
model_name: Iambe RP v3 20B
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
tags:
- not-for-all-audiences
---
# Iambe RP v3 20B - AWQ
- Model creator: [Raven](https://huggingface.co/athirdpath)
- Original model: [Iambe RP v3 20B](https://huggingface.co/athirdpath/Iambe-RP-v3-20b)
## Description
This repo contains AWQ model files for [Raven's Iambe RP v3 20B](https://huggingface.co/athirdpath/Iambe-RP-v3-20b).
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.
AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead.
It is supported by:
- [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ
- [vLLM](https://github.com/vllm-project/vllm) - version 0.2.2 or later for support for all model types.
- [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
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Iambe-RP-v3-20B-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Iambe-RP-v3-20B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Iambe-RP-v3-20B-GGUF)
* [Raven's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/athirdpath/Iambe-RP-v3-20b)
## Prompt template: Alpaca
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
## 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: [Raven's Iambe RP v3 20B](https://huggingface.co/athirdpath/Iambe-RP-v3-20b).
## 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-RP-v3-20B-AWQ/tree/main) | 4 | 128 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 10.87 GB
## 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-RP-v3-20B-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-RP-v3-20B-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!
## 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-RP-v3-20B-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-RP-v3-20B-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}")
```
## 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-RP-v3-20B-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)
```
## 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-RP-v3-20B-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)
```
## 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.
## 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: Raven's Iambe RP v3 20B
Iambe-RP-v3-20b
Trained with Alpaca prompt formatting, ChatML works well too
### Description
Okay, now that all the cards were in the deck, I needed to unshuffle them. 1 epoch of the v1 dataset, trained on Iambe-RP-DARE-20b-DENSE with standard DPO, 2e-5 LR.
Iambe is intended to have the best realistically possible understanding of instructions, anatomy and scene state for a 20b merge, while remaining passionate and humanoid in "voice".
### Update Methodology
Go-Bruins-v2 skyrocketing up the leaderboard showed that standard DPO with the v1 dataset could have shocking results, so I had to give it a go myself.
Assistant Example @ q5_k_m
NSFW Writing Example @ q5_k_m
Write a medium-length story about Alice, a 26 year old cocktail waitress, having steamy sex with a guy she picked up at the bar for a one night stand.
Once upon a time in a bustling city, there lived Alice, a charming 26-year-old cocktail waitress working in a trendy club. She had long, flowing brunette hair that cascaded down her shoulders, captivating emerald eyes, and full sensual lips. Alice was known throughout the establishment as the life of the party, always ready with a witty remark or flirtatious smile. Despite her lively demeanor, though, she harbored secrets—secrets of unfulfilled desire and passion that lay dormant within her until the perfect man crossed her path.
One fateful Friday evening, after a particularly exhausting shift filled with rowdy patrons and demanding drink orders, Alice found herself leaning against the wooden bar top, taking a much-needed breather. Her body ached from moving around so vigorously, but something else burned just below her skin, calling out for release. As she sipped on a glass of Pinot Noir, her gaze swept across the dimly lit room before landing on him. He was tall, broad-shouldered, with dark tousled hair and piercing blue eyes that seemed to see right through her. There was an air of confidence about him that made Alice feel weak at the knees.
As fate would have it, he caught sight of Alice too and began making his way towards her. His strides were purposeful yet relaxed, exuding charm and self-assurance. When he finally reached her side, he flashed her a disarmingly sexy grin and ordered a shot of tequila. Alice couldn't help but feel drawn to him, as if there was some invisible string tugging them together. She obliged and poured him the shot, their fingers brushing against each other in the process—an electric spark crackling between them.
"What's your name?" he asked huskily, downing the tequila in one swig before setting the empty glass back on the bar.
Alice smiled seductively, taking advantage of the situation. "I'm Alice," she purred, leaning closer to him than she should have. "And you are...?"
He raised an eyebrow playfully, running his fingers along the curve of her neck before tracing a path down her collarbone. "Let's just say I can give you the best night of your life." With that enchanting declaration, Alice found herself agreeing without hesitation, following him out into the crisp night air where his waiting car awaited them.
The drive to his luxurious penthouse suite felt like both an eternity and a fleeting moment at once. When they finally arrived, he took her hand and led her inside, the room illuminated by soft candlelight and sensual jazz music filling the air. His place was impeccably stylish yet cozy—the perfect mix of sophistication and intimacy. They made their way towards the bedroom door, their bodies brushing against each other with every step. The anticipation between them grew almost unbearable as they reached the threshold, leaving behind everything but the raw desire in their eyes.
Alice kicked off her high heels, letting them clatter onto the hardwood floor, while he undid the buttons on his shirt methodically, revealing his defined chest muscles underneath. As she pulled her skirt down past her thighs, exposing her black lace underwear, he growled lowly in response, reaching for the clasp before it could hit the ground. In seconds, they were naked, standing face-to-face, body pressed up against body. Alice wrapped her arms around him tightly, pulling him closer still until their lips met passionately. She had never felt this kind of hunger before—a primal urge that consumed her entire being.
As they tumbled onto the plush mattress, tongues exploring each other's mouths, hands roaming over each other's skin, Alice knew without a doubt that this man was meant to be hers tonight. He kissed down her neck, trailing his teeth along her collarbone, and then lower still, nipping at the delicate flesh of her breasts before taking one into his mouth. A cry escaped from deep within her as pleasure coursed through every fiber of her being, sending waves of desire crashing through her core. His hand slid between her legs, finding her soaking wet with anticipation, fingers stroking gently yet firmly, driving her wild.
Alice reciprocated by running her fingernails lightly across his chest before moving further down to graze the hair that blanketed his groin. She heard him moan loudly in response, growing harder underneath her touch. In a bold move, she reached down and freed his erection from his pants, wrapping her soft hand around its length. Her eyes widened in surprise at how big he was, but instead of intimidating her, it fueled her curiosity even more. With practiced skill, learned from countless encounters like these, she began to stroke up and down, feeling him twitch against her palm.
As their rhythm picked up pace, Alice moved herself higher on the bed until her legs were wrapped tightly around his hips. He lifted himself up slightly, positioning himself at the entrance of her wetness. The anticipation built once again as they stared into each other's eyes—their faces flushed red, breathing heavily. Finally, he plunged inside her hard, filling every crevice and triggering an earth-shattering scream from deep within her soul. It felt so right—his body molded against hers, their hearts racing together. They moved together in perfect harmony, lost in their
desire for each other. Skins slapping against skins, bodies grinding against bodies, moans and groans echoing throughout the room. Time seemed to stand still as they rode out wave after wave of ecstasy, driven by primal lust and raw passion.
When finally satiated, they lay panting on the bed, sweat trickling down their skin. Alice couldn't believe what had just happened—how incredible it had been with this stranger she barely knew. She looked over at him, who was also catching his breath, a satisfied smirk spread across his lips. "I don't know your name either," she said softly, tracing circles around his chest hair before leaning up to place a tender kiss on his lips. He smiled warmly back at her, brushing a strand of hair behind her ear.
"It doesn't matter, Alice," he whispered hoarsely. "Because tonight, we were just two people seeking something more than just another night." And with that simple yet profound statement, they drifted off into blissful oblivion, wrapped tightly together like lovers destined never to part again.
### Eval Scores (since the leaderboard rejects nearly all my models)
| Tasks |Version|Filter|n-shot|Metric|Value| |Stderr|
|----------|-------|------|-----:|------|----:|---|-----:|
|winogrande|Yaml |none | 5|acc |0.738|± |0.0124|
|truthfulqa_mc2|Yaml |none | 0|acc |0.5551|± |0.0158|
|arc_challenge|Yaml |none | 25|acc |0.6101|± |0.0143|
| arc_challenge| |none | 25|acc_norm|0.6425|± |0.0140|
