--- license: cc-by-nc-4.0 model_name: ReMM SLERP L2 13B base_model: Undi95/ReMM-SLERP-L2-13B inference: false model_creator: Undi95 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 ---
TheBlokeAI

Chat & support: TheBloke's Discord server

Want to contribute? TheBloke's Patreon page

TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)


# ReMM SLERP L2 13B - AWQ - Model creator: [Undi95](https://huggingface.co./Undi95) - Original model: [ReMM SLERP L2 13B](https://huggingface.co./Undi95/ReMM-SLERP-L2-13B) ## Description This repo contains AWQ model files for [Undi95's ReMM SLERP L2 13B](https://huggingface.co./Undi95/ReMM-SLERP-L2-13B). ### 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. It is also now supported by continuous batching server [vLLM](https://github.com/vllm-project/vllm), allowing use of AWQ models for high-throughput concurrent inference in multi-user server scenarios. Note that, at the time of writing, overall throughput is still lower than running vLLM with unquantised models, however using AWQ enables using much smaller GPUs which can lead to easier deployment and overall cost savings. For example, a 70B model can be run on 1 x 48GB GPU instead of 2 x 80GB. ## Repositories available * [AWQ model(s) for GPU inference.](https://huggingface.co./TheBloke/ReMM-SLERP-L2-13B-AWQ) * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co./TheBloke/ReMM-SLERP-L2-13B-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co./TheBloke/ReMM-SLERP-L2-13B-GGUF) * [Undi95's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co./Undi95/ReMM-SLERP-L2-13B) ## 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: [Undi95's ReMM SLERP L2 13B](https://huggingface.co./Undi95/ReMM-SLERP-L2-13B). ## Provided files and AWQ parameters For my first release of AWQ models, I am releasing 128g models only. I will consider adding 32g as well if there is interest, and once I have done perplexity and evaluation comparisons, but at this time 32g models are still not fully tested with AutoAWQ and vLLM. Models are released as sharded safetensors files. | Branch | Bits | GS | AWQ Dataset | Seq Len | Size | | ------ | ---- | -- | ----------- | ------- | ---- | | [main](https://huggingface.co./TheBloke/ReMM-SLERP-L2-13B-AWQ/tree/main) | 4 | 128 | [wikitext](https://huggingface.co./datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.25 GB ## Serving this model from vLLM Documentation on installing and using vLLM [can be found here](https://vllm.readthedocs.io/en/latest/). - When using vLLM as a server, pass the `--quantization awq` parameter, for example: ```shell python3 python -m vllm.entrypoints.api_server --model TheBloke/ReMM-SLERP-L2-13B-AWQ --quantization awq ``` When using vLLM from Python code, pass the `quantization=awq` parameter, for example: ```python from vllm import LLM, SamplingParams prompts = [ "Hello, my name is", "The president of the United States is", "The capital of France is", "The future of AI is", ] sampling_params = SamplingParams(temperature=0.8, top_p=0.95) llm = LLM(model="TheBloke/ReMM-SLERP-L2-13B-AWQ", quantization="awq") 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}") ``` ## How to use this AWQ model from Python code ### Install the necessary packages Requires: [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) 0.0.2 or later ```shell pip3 install autoawq ``` 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 . ``` ### You can then try the following example code ```python from awq import AutoAWQForCausalLM from transformers import AutoTokenizer model_name_or_path = "TheBloke/ReMM-SLERP-L2-13B-AWQ" # Load model model = AutoAWQForCausalLM.from_quantized(model_name_or_path, fuse_layers=True, trust_remote_code=False, safetensors=True) tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, trust_remote_code=False) 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: ''' print("\n\n*** Generate:") tokens = tokenizer( prompt_template, return_tensors='pt' ).input_ids.cuda() # Generate output generation_output = model.generate( tokens, do_sample=True, temperature=0.7, top_p=0.95, top_k=40, max_new_tokens=512 ) print("Output: ", tokenizer.decode(generation_output[0])) # Inference can also be done using transformers' pipeline from transformers import pipeline print("*** Pipeline:") pipe = pipeline( "text-generation", model=model, tokenizer=tokenizer, max_new_tokens=512, do_sample=True, temperature=0.7, top_p=0.95, top_k=40, repetition_penalty=1.1 ) print(pipe(prompt_template)[0]['generated_text']) ``` ## Compatibility The files provided are tested to work with [AutoAWQ](https://github.com/casper-hansen/AutoAWQ), and [vLLM](https://github.com/vllm-project/vllm). [Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) is not yet compatible with AWQ, but a PR is open which should bring support soon: [TGI PR #781](https://github.com/huggingface/text-generation-inference/issues/781). ## 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**: 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: Undi95's ReMM SLERP L2 13B Re:MythoMax (ReMM) is a recreation trial of the original [MythoMax-L2-B13](https://huggingface.co./Gryphe/MythoMax-L2-13b) with updated models. This merge use SLERP [TESTING] to merge ReML and Huginn v1.2. Command useds and explaination : ```shell Due to hardware limitation, some merge was done in 2 part. - Recreate ReML : Mythologic (v2) (Chronos/Hermes/Airboros) => Replacing Chronos by The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16 (0.30) => Replacing Airoboros by jondurbin/airoboros-l2-13b-2.1 (last version) (0.40) => Keeping NousResearch/Nous-Hermes-Llama2-13b (0.30) Part 1: python ties_merge.py TheBloke/Llama-2-13B-fp16 ./ReML-L2-13B-part1 --merge The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16 --density 0.42 --merge jondurbin/airoboros-l2-13b-2.1 --density 0.56 --cuda Part 2: python ties_merge.py TheBloke/Llama-2-13B-fp16 ./ReML-L2-13B --merge NousResearch/Nous-Hermes-Llama2-13b --density 0.30 --merge Undi95/ReML-L2-13B-part1 --density 0.70 --cuda With that : - Recreate ReMM : MythoMax (v2) (Mythologic/Huginn v1) => Replacing Mythologic by the one above (0.5) => Replacing Huginn by The-Face-Of-Goonery/Huginn-13b-v1.2 (hottest) (0.5) Part 3: python slerpmergelm.py "The-Face-Of-Goonery_Huginn-13b-v1.2" "Undi95_ReML-L2-13B" "result" ``` Version of SLERP used is different to accept usage on notebook : https://github.com/Undi95/LLM-SLERP-MergeTest/tree/main (Thanks @Vali) ## Description This repo contains fp16 files of ReMM-SLERP, a recreation of the original MythoMax, but updated and merged with SLERP. ## Models used - TheBloke/Llama-2-13B-fp16 (base) - The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16 - jondurbin/airoboros-l2-13b-2.1 - NousResearch/Nous-Hermes-Llama2-13b - The-Face-Of-Goonery/Huginn-13b-v1.2 - ReML-L2-13B (Private recreation trial of an updated Mythologic-L2-13B) ## Prompt template: Alpaca ``` Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction: {prompt} ### Response: ``` Special thanks to Sushi kek