--- language: - en license: other tags: - upstage - llama - instruct - instruction datasets: - sciq - metaeval/ScienceQA_text_only - GAIR/lima - Open-Orca/OpenOrca - openbookqa model_name: Llama 30B Instruct 2048 base_model: upstage/llama-30b-instruct-2048 inference: false model_creator: upstage model_type: llama pipeline_tag: text-generation prompt_template: '### System: {system_message} ### User: {prompt} ### Assistant: ' 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)


# Llama 30B Instruct 2048 - GPTQ - Model creator: [upstage](https://huggingface.co/upstage) - Original model: [Llama 30B Instruct 2048](https://huggingface.co/upstage/llama-30b-instruct-2048) ## Description This repo contains GPTQ model files for [Upstage's Llama 30B Instruct 2048](https://huggingface.co/upstage/llama-30b-instruct-2048). Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them. Many thanks to William Beauchamp from [Chai](https://chai-research.com/) for providing the hardware used to make and upload these files! ## Repositories available * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/upstage-llama-30b-instruct-2048-AWQ) * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/upstage-llama-30b-instruct-2048-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/upstage-llama-30b-instruct-2048-GGUF) * [upstage's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/upstage/llama-30b-instruct-2048) ## Prompt template: Orca-Hashes ``` ### System: {system_message} ### User: {prompt} ### Assistant: ``` ## Provided files and GPTQ parameters Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements. Each separate quant is in a different branch. See below for instructions on fetching from different branches. All recent GPTQ files are made with AutoGPTQ, and all files in non-main branches are made with AutoGPTQ. Files in the `main` branch which were uploaded before August 2023 were made with GPTQ-for-LLaMa.
Explanation of GPTQ parameters - Bits: The bit size of the quantised model. - GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value. - Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now. - Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy. - GPTQ dataset: The dataset used for quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s). - Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences. - ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit.
| Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc | | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- | | [main](https://huggingface.co/TheBloke/upstage-llama-30b-instruct-2048-GPTQ/tree/main) | 4 | None | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 16.94 GB | Yes | 4-bit, with Act Order. No group size, to lower VRAM requirements. | | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/upstage-llama-30b-instruct-2048-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 19.44 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. | | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/upstage-llama-30b-instruct-2048-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 18.18 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. | | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/upstage-llama-30b-instruct-2048-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 17.55 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. | | [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/upstage-llama-30b-instruct-2048-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 32.99 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. | | [gptq-8bit-128g-actorder_False](https://huggingface.co/TheBloke/upstage-llama-30b-instruct-2048-GPTQ/tree/gptq-8bit-128g-actorder_False) | 8 | 128 | No | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 33.73 GB | No | 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed. | | [gptq-3bit-128g-actorder_False](https://huggingface.co/TheBloke/upstage-llama-30b-instruct-2048-GPTQ/tree/gptq-3bit-128g-actorder_False) | 3 | 128 | No | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 13.51 GB | No | 3-bit, with group size 128g but no act-order. Slightly higher VRAM requirements than 3-bit None. | | [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/upstage-llama-30b-instruct-2048-GPTQ/tree/gptq-3bit-128g-actorder_True) | 3 | 128 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 13.51 GB | No | 3-bit, with group size 128g and act-order. Higher quality than 128g-False. | ## How to download from branches - In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/upstage-llama-30b-instruct-2048-GPTQ:main` - With Git, you can clone a branch with: ``` git clone --single-branch --branch main https://huggingface.co/TheBloke/upstage-llama-30b-instruct-2048-GPTQ ``` - In Python Transformers code, the branch is the `revision` parameter; see below. ## 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/upstage-llama-30b-instruct-2048-GPTQ`. - To download from a specific branch, enter for example `TheBloke/upstage-llama-30b-instruct-2048-GPTQ:main` - see Provided Files above for the list of branches for each option. 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: `upstage-llama-30b-instruct-2048-GPTQ` 7. The model will automatically load, and is now ready for use! 8. 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. * Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file `quantize_config.json`. 9. Once you're ready, click the **Text Generation tab** and enter a prompt to get started! ## How to use this GPTQ model from Python code ### Install the necessary packages Requires: Transformers 4.32.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later. ```shell pip3 install transformers>=4.32.0 optimum>=1.12.0 pip3 install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/ # Use cu117 if on CUDA 11.7 ``` If you have problems installing AutoGPTQ using the pre-built wheels, install it from source instead: ```shell pip3 uninstall -y auto-gptq git clone https://github.com/PanQiWei/AutoGPTQ cd AutoGPTQ pip3 install . ``` ### For CodeLlama models only: you must use Transformers 4.33.0 or later. If 4.33.0 is not yet released when you read this, you will need to install Transformers from source: ```shell pip3 uninstall -y transformers pip3 install git+https://github.com/huggingface/transformers.git ``` ### You can then use the following code ```python from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline model_name_or_path = "TheBloke/upstage-llama-30b-instruct-2048-GPTQ" # To use a different branch, change revision # For example: revision="main" model = AutoModelForCausalLM.from_pretrained(model_name_or_path, device_map="auto", trust_remote_code=False, revision="main") tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True) prompt = "Tell me about AI" prompt_template=f'''### System: {system_message} ### User: {prompt} ### Assistant: ''' print("\n\n*** Generate:") input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda() output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512) print(tokenizer.decode(output[0])) # Inference can also be done using transformers' 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 AutoGPTQ, both via Transformers and using AutoGPTQ directly. They should also work with [Occ4m's GPTQ-for-LLaMa fork](https://github.com/0cc4m/KoboldAI). [ExLlama](https://github.com/turboderp/exllama) is compatible with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility. [Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) is compatible with all GPTQ models. ## 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: Upstage's Llama 30B Instruct 2048 # LLaMa-30b-instruct-2048 model card ## Model Details * **Developed by**: [Upstage](https://en.upstage.ai) * **Backbone Model**: [LLaMA](https://github.com/facebookresearch/llama/tree/llama_v1) * **Variations**: It has different model parameter sizes and sequence lengths: [30B/1024](https://huggingface.co/upstage/llama-30b-instruct), [30B/2048](https://huggingface.co/upstage/llama-30b-instruct-2048), [65B/1024](https://huggingface.co/upstage/llama-65b-instruct) * **Language(s)**: English * **Library**: [HuggingFace Transformers](https://github.com/huggingface/transformers) * **License**: This model is under a **Non-commercial** Bespoke License and governed by the Meta license. You should only use this repository if you have been granted access to the model by filling out [this form](https://docs.google.com/forms/d/e/1FAIpQLSfqNECQnMkycAp2jP4Z9TFX0cGR4uf7b_fBxjY_OjhJILlKGA/viewform), but have either lost your copy of the weights or encountered issues converting them to the Transformers format * **Where to send comments**: Instructions on how to provide feedback or comments on a model can be found by opening an issue in the [Hugging Face community's model repository](https://huggingface.co/upstage/llama-30b-instruct-2048/discussions) * **Contact**: For questions and comments about the model, please email [contact@upstage.ai](mailto:contact@upstage.ai) ## Dataset Details ### Used Datasets - [openbookqa](https://huggingface.co/datasets/openbookqa) - [sciq](https://huggingface.co/datasets/sciq) - [Open-Orca/OpenOrca](https://huggingface.co/datasets/Open-Orca/OpenOrca) - [metaeval/ScienceQA_text_only](https://huggingface.co/datasets/metaeval/ScienceQA_text_only) - [GAIR/lima](https://huggingface.co/datasets/GAIR/lima) - No other data was used except for the dataset mentioned above ### Prompt Template ``` ### System: {System} ### User: {User} ### Assistant: {Assistant} ``` ## Usage - Tested on A100 80GB - Our model can handle up to 10k+ input tokens, thanks to the `rope_scaling` option ```python import torch from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer tokenizer = AutoTokenizer.from_pretrained("upstage/llama-30b-instruct-2048") model = AutoModelForCausalLM.from_pretrained( "upstage/llama-30b-instruct-2048", device_map="auto", torch_dtype=torch.float16, load_in_8bit=True, rope_scaling={"type": "dynamic", "factor": 2} # allows handling of longer inputs ) prompt = "### User:\nThomas is healthy, but he has to go to the hospital. What could be the reasons?\n\n### Assistant:\n" inputs = tokenizer(prompt, return_tensors="pt").to(model.device) del inputs["token_type_ids"] streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True) output = model.generate(**inputs, streamer=streamer, use_cache=True, max_new_tokens=float('inf')) output_text = tokenizer.decode(output[0], skip_special_tokens=True) ``` ## Hardware and Software * **Hardware**: We utilized an A100x8 * 1 for training our model * **Training Factors**: We fine-tuned this model using a combination of the [DeepSpeed library](https://github.com/microsoft/DeepSpeed) and the [HuggingFace Trainer](https://huggingface.co/docs/transformers/main_classes/trainer) / [HuggingFace Accelerate](https://huggingface.co/docs/accelerate/index) ## Evaluation Results ### Overview - We conducted a performance evaluation based on the tasks being evaluated on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard). We evaluated our model on four benchmark datasets, which include `ARC-Challenge`, `HellaSwag`, `MMLU`, and `TruthfulQA` We used the [lm-evaluation-harness repository](https://github.com/EleutherAI/lm-evaluation-harness), specifically commit [b281b0921b636bc36ad05c0b0b0763bd6dd43463](https://github.com/EleutherAI/lm-evaluation-harness/tree/b281b0921b636bc36ad05c0b0b0763bd6dd43463) - We used [MT-bench](https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge), a set of challenging multi-turn open-ended questions, to evaluate the models ### Main Results | Model | H4(Avg) | ARC | HellaSwag | MMLU | TruthfulQA | | MT_Bench | |--------------------------------------------------------------------|----------|----------|----------|------|----------|-|-------------| | **[Llama-2-70b-instruct-v2](https://huggingface.co/upstage/Llama-2-70b-instruct-v2)**(Ours, Open LLM Leaderboard) | **73** | **71.1** | **87.9** | **70.6** | **62.2** | | **7.44063** | | [Llama-2-70b-instruct](https://huggingface.co/upstage/Llama-2-70b-instruct) (Ours, Open LLM Leaderboard) | 72.3 | 70.9 | 87.5 | 69.8 | 61 | | 7.24375 | | [llama-65b-instruct](https://huggingface.co/upstage/llama-65b-instruct) (Ours, Open LLM Leaderboard) | 69.4 | 67.6 | 86.5 | 64.9 | 58.8 | | | | Llama-2-70b-hf | 67.3 | 67.3 | 87.3 | 69.8 | 44.9 | | | | [llama-30b-instruct-2048](https://huggingface.co/upstage/llama-30b-instruct-2048) (***Ours***, ***Open LLM Leaderboard***) | 67.0 | 64.9 | 84.9 | 61.9 | 56.3 | | | | [llama-30b-instruct](https://huggingface.co/upstage/llama-30b-instruct) (Ours, Open LLM Leaderboard) | 65.2 | 62.5 | 86.2 | 59.4 | 52.8 | | | | llama-65b | 64.2 | 63.5 | 86.1 | 63.9 | 43.4 | | | | falcon-40b-instruct | 63.4 | 61.6 | 84.3 | 55.4 | 52.5 | | | ### Scripts for H4 Score Reproduction - Prepare evaluation environments: ``` # clone the repository git clone https://github.com/EleutherAI/lm-evaluation-harness.git # check out the specific commit git checkout b281b0921b636bc36ad05c0b0b0763bd6dd43463 # change to the repository directory cd lm-evaluation-harness ``` ## Ethical Issues ### Ethical Considerations - There were no ethical issues involved, as we did not include the benchmark test set or the training set in the model's training process ## Contact Us ### Why Upstage LLM? - [Upstage](https://en.upstage.ai)'s LLM research has yielded remarkable results. As of August 1st, our 70B model has reached the top spot in openLLM rankings, marking itself as the current leading performer globally. Recognizing the immense potential in implementing private LLM to actual businesses, we invite you to easily apply private LLM and fine-tune it with your own data. For a seamless and tailored solution, please do not hesitate to reach out to us. ► [click here to contact](https://www.upstage.ai/private-llm?utm_source=huggingface&utm_medium=link&utm_campaign=privatellm)