--- language: - en license: other tags: - sft datasets: - ehartford/dolphin - shahules786/orca-chat - togethercomputer/RedPajama-Data-1T - atom-in-the-universe/fanfics-10k-50k model_name: Llama2 13B Orca 8K 3319 base_model: OpenAssistant/llama2-13b-orca-8k-3319 inference: false model_creator: OpenAssistant model_type: llama pipeline_tag: text-generation prompt_template: '<|system|>{system_message}<|prompter|>{prompt}<|assistant|> ' quantized_by: TheBloke widget: - text: <|system|>You are an AI assistant. You will be given a task. You must generate a detailed and long answer.<|prompter|>What is a meme, and what's the history behind this word?<|assistant|> - text: <|system|>You are an AI assistant that helps people find information.<|prompter|>What's the Earth total population<|assistant|> - text: <|system|>You are an AI assistant that follows instruction extremely well. Help as much as you can.<|prompter|>Write a story about future of AI development<|assistant|> ---
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)

# Llama2 13B Orca 8K 3319 - AWQ - Model creator: [OpenAssistant](https://huggingface.co/OpenAssistant) - Original model: [Llama2 13B Orca 8K 3319](https://huggingface.co/OpenAssistant/llama2-13b-orca-8k-3319) ## Description This repo contains AWQ model files for [OpenAssistant's Llama2 13B Orca 8K 3319](https://huggingface.co/OpenAssistant/llama2-13b-orca-8k-3319). ### 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/OpenAssistant-Llama2-13B-Orca-8K-3319-AWQ) * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/OpenAssistant-Llama2-13B-Orca-8K-3319-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/OpenAssistant-Llama2-13B-Orca-8K-3319-GGUF) * [OpenAssistant's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/OpenAssistant/llama2-13b-orca-8k-3319) ## Prompt template: OpenAssistant-System ``` <|system|>{system_message}<|prompter|>{prompt}<|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: [OpenAssistant's Llama2 13B Orca 8K 3319](https://huggingface.co/OpenAssistant/llama2-13b-orca-8k-3319). ## 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/OpenAssistant-Llama2-13B-Orca-8K-3319-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/OpenAssistant-Llama2-13B-Orca-8K-3319-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/OpenAssistant-Llama2-13B-Orca-8K-3319-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/OpenAssistant-Llama2-13B-Orca-8K-3319-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'''<|system|>{system_message}<|prompter|>{prompt}<|assistant|> ''' 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: OpenAssistant's Llama2 13B Orca 8K 3319 # llama2-13b-orca-8k-3319 ## Model Description This model is a fine-tuning of Meta's Llama2 13B model with 8K context size on a long-conversation variant of the Dolphin dataset ([orca-chat](https://huggingface.co/datasets/shahules786/orca-chat)). Note: **At least Huggingface Transformers [4.31.0](https://pypi.org/project/transformers/4.31.0/) is required to load this model!** ## Usage ```python import torch from transformers import AutoModelForCausalLM, AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("OpenAssistant/llama2-13b-orca-8k-3319", use_fast=False) model = AutoModelForCausalLM.from_pretrained("OpenAssistant/llama2-13b-orca-8k-3319", torch_dtype=torch.float16, low_cpu_mem_usage=True, device_map="auto") system_message = "You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information." user_prompt = "Write me a poem please" prompt = f"""<|system|>{system_message}<|prompter|>{user_prompt}<|assistant|>""" inputs = tokenizer(prompt, return_tensors="pt").to("cuda") output = model.generate(**inputs, do_sample=True, top_p=0.95, top_k=0, max_new_tokens=256) print(tokenizer.decode(output[0], skip_special_tokens=True)) ``` ## Model Details - base model: [meta-llama/Llama-2-13b](https://huggingface.co/meta-llama/Llama-2-13b) - License: [Llama 2 Community License Agreement](https://ai.meta.com/resources/models-and-libraries/llama-downloads/) - sampling report: [2023-07-25_OpenAssistant_llama2-13b-orca-8k-3319_sampling_llama2_prompt.json](https://open-assistant.github.io/oasst-model-eval/?f=https%3A%2F%2Fraw.githubusercontent.com%2FOpen-Assistant%2Foasst-model-eval%2Fmain%2Fsampling_reports%2Foasst-pretrained%2F2023-07-25_OpenAssistant_llama2-13b-orca-8k-3319_sampling_llama2_prompt.json) - wandb: [public-sft/runs/2jfazjt9](https://wandb.ai/open-assistant/public-sft/runs/2jfazjt9) - checkpoint: 3319 steps - datatpye: fp16 - sponsored by: [Redmond.ai](https://redmond.ai/) ## Long context (RoPE Scaling) This model was fine-tuned with a context size of 8192 tokens using linear scaling of RoPE embeddings. This feature was recently added to [Huggingface transformers](https://github.com/huggingface/transformers/). Before loading this model please make sure HF transformers >=4.31.0 is installed (`pip install transformers>=4.31.0`). ## Conversation Template For the initial response use (e.g. the [llama2 default system prompt](https://github.com/facebookresearch/llama/blob/6c7fe276574e78057f917549435a2554000a876d/llama/generation.py#L46) works well): ``` <|system|>system message<|prompter|>user prompt<|assistant|> ``` For multi-turn conversations use: ``` <|system|>system message<|prompter|>Q1<|assistant|>A1<|prompter|>Q2<|assistant|> ``` The model was trained with the following 15 system messages used to generate the training examples (see [ORCA paper](https://arxiv.org/abs/2306.02707)): 1. You are an AI assistant. Provide a detailed answer so user don’t need to search outside to understand the answer. 2. You are an AI assistant. You will be given a task. You must generate a detailed and long answer. 3. You are a helpful assistant, who always provide explanation. Think like you are answering to a five year old. 4. You are an AI assistant that follows instruction extremely well. Help as much as you can. 5. You are an AI assistant that helps people find information. Provide a detailed answer so user don’t need to search outside to understand the answer. 6. You are an AI assistant. User will you give you a task. Your goal is to complete the task as faithfully as you can. While performing the task think step-by-step and justify your steps. 7. You should describe the task and explain your answer. While answering a multiple choice question, first output the correct answer(s). Then explain why other answers are wrong. Think like you are answering to a five year old. 8. Explain how you used the definition to come up with the answer. 9. You are an AI assistant. You should describe the task and explain your answer. While answering a multiple choice question, first output the correct answer(s). Then explain why other answers are wrong. You might need to use additional knowledge to answer the question. 10. You are an AI assistant that helps people find information. User will you give you a question. Your task is to answer as faithfully as you can. While answering think step-by- step and justify your answer. 11. User will you give you a task with some instruction. Your job is follow the instructions as faithfully as you can. While answering think step-by-step and justify your answer. 12. You are a teacher. Given a task, you explain in simple steps what the task is asking, any guidelines it provides and how to use those guidelines to find the answer. 13. You are an AI assistant, who knows every language and how to translate one language to another. Given a task, you explain in simple steps what the task is asking, any guidelines that it provides. You solve the task and show how you used the guidelines to solve the task. 14. Given a definition of a task and a sample input, break the definition into small parts. Each of those parts will have some instruction. Explain their meaning by showing an example that meets the criteria in the instruction. Use the following format: Part \#: a key part of the definition. Usage: Sample response that meets the criteria from the key part. Explain why you think it meets the criteria. 15. You are an AI assistant that helps people find information. ## Datasets: Orca-Chat/Dolphin, RedPajama1T & FanFics This model was trained on: - [shahules786/orca-chat](https://huggingface.co/datasets/shahules786/orca-chat) - [togethercomputer/RedPajama-Data-1T-Sample](https://huggingface.co/datasets/togethercomputer/RedPajama-Data-1T) - [atom-in-the-universe/fanfics-10k-50k](https://huggingface.co/datasets/atom-in-the-universe/fanfics-10k-50k) ``` Dataset Composition: Tain (sampled): orca-chat: 188842 (100%) fanfics: 47760 (100%) red_pajama: 188262 (25%) Valid: orca-chat: 5000 fanfics: 1000 red_pajama: 1000 ``` The dataset [shahules786/orca-chat](https://huggingface.co/datasets/shahules786/orca-chat) combines similar examples of the GPT-4 subset of [ehartford/dolphin](https://huggingface.co/datasets/ehartford/dolphin) to form longer conversations to improve long-context training. Additionally, RedPajama and FanFics were used for classic language modelling as an auxiliary task to improve the RoPE scaling for the 8k context size. ## Model Configuration ``` llama2_13b_orca_8k: rng_seed: 0xe1291f1a use_custom_sampler: true sort_by_length: false dtype: fp16 log_dir: "llama2_log_13b_orca_8k" learning_rate: 1e-5 model_name: /mnt/data/llama2/Llama-2-13b-hf/ output_dir: llama2_13b_orca_8k deepspeed_config: configs/zero_config_pretrain.json weight_decay: 0.0 max_length: 8192 warmup_steps: 100 use_flash_attention: true gradient_checkpointing: true gradient_accumulation_steps: 8 per_device_train_batch_size: 2 per_device_eval_batch_size: 1 residual_dropout: 0.0 eval_steps: 200 save_steps: 1000 # (total steps: 3319) num_train_epochs: 1 save_total_limit: 4 superhot: true superhot_config: type: linear scale: 2 datasets: - orca-chat: max_val_set: 5000 - fanfics: max_chunk_size: 65535 max_val_set: 1000 - red_pajama: fraction: 0.25 max_val_set: 1000 max_chunk_size: 65535 peft_model: false ``` # Developers - [shahules786](https://github.com/shahules786) - [jordiclive](https://github.com/jordiclive) - [andreaskoepf](https://github.com/andreaskoepf/) # Special Thanks We want to especially thank Eric Hartford who spared no expense in replicating ORCA and making it available at [ehartford/dolphin](https://huggingface.co/datasets/ehartford/dolphin)! Also, shoutout to the whole team working on [LLongMA-2-13b](https://huggingface.co/conceptofmind/LLongMA-2-13b) & the [scaled-rope](https://github.com/jquesnelle/scaled-rope) repository for their awesome work: bloc97, jquesnelle & conceptofmind! The whole Open-Assistant team is very grateful for the continued support of [Redmond.ai](https://redmond.ai/) who sponsored the training compute required for this model. # License - Llama 2 is licensed under the LLAMA 2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved. - Your use of the Llama Materials must comply with applicable laws and regulations (including trade compliance laws and regulations) and adhere to the [Acceptable Use Policy](https://ai.meta.com/llama/use-policy) for the Llama Materials.