--- datasets: - garage-bAInd/OpenPlatypus inference: false language: - en license: other model_creator: garage-bAInd model_link: https://huggingface.co/garage-bAInd/Platypus2-70B-instruct model_name: Platypus2 70B Instruct model_type: llama quantized_by: TheBloke ---
TheBlokeAI

Chat & support: my new Discord server

Want to contribute? TheBloke's Patreon page

# Platypus2 70B Instruct - GGML - Model creator: [garage-bAInd](https://huggingface.co/garage-bAInd) - Original model: [Platypus2 70B Instruct](https://huggingface.co/garage-bAInd/Platypus2-70B-instruct) ## Description This repo contains GGML format model files for [garage-bAInd's Platypus2 70B Instruct](https://huggingface.co/garage-bAInd/Platypus2-70B-instruct). GPU acceleration is now available for Llama 2 70B GGML files, with both CUDA (NVidia) and Metal (macOS). The following clients/libraries are known to work with these files, including with GPU acceleration: * [llama.cpp](https://github.com/ggerganov/llama.cpp), commit `e76d630` and later. * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI. * [KoboldCpp](https://github.com/LostRuins/koboldcpp), version 1.37 and later. A powerful GGML web UI, especially good for story telling. * [LM Studio](https://lmstudio.ai/), a fully featured local GUI with GPU acceleration for both Windows and macOS. Use 0.1.11 or later for macOS GPU acceleration with 70B models. * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), version 0.1.77 and later. A Python library with LangChain support, and OpenAI-compatible API server. * [ctransformers](https://github.com/marella/ctransformers), version 0.2.15 and later. A Python library with LangChain support, and OpenAI-compatible API server. ## Repositories available * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Platypus2-70B-Instruct-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/Platypus2-70B-Instruct-GGML) * [garage-bAInd's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/garage-bAInd/Platypus2-70B-instruct) ## Prompt template: Alpaca ``` Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction: {prompt} ### Response: ``` ## Compatibility ### Requires llama.cpp [commit `e76d630`](https://github.com/ggerganov/llama.cpp/commit/e76d630df17e235e6b9ef416c45996765d2e36fb) or later. Or one of the other tools and libraries listed above. To use in llama.cpp, you must add `-gqa 8` argument. For other UIs and libraries, please check the docs. ## Explanation of the new k-quant methods
Click to see details The new methods available are: * GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw) * GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw. * GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw. * GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw * GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw * GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type. Refer to the Provided Files table below to see what files use which methods, and how.
## Provided files | Name | Quant method | Bits | Size | Max RAM required | Use case | | ---- | ---- | ---- | ---- | ---- | ----- | | [platypus2-70b-instruct.ggmlv3.q2_K.bin](https://huggingface.co/TheBloke/Platypus2-70B-Instruct-GGML/blob/main/platypus2-70b-instruct.ggmlv3.q2_K.bin) | q2_K | 2 | 28.59 GB| 31.09 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. | | [platypus2-70b-instruct.ggmlv3.q3_K_L.bin](https://huggingface.co/TheBloke/Platypus2-70B-Instruct-GGML/blob/main/platypus2-70b-instruct.ggmlv3.q3_K_L.bin) | q3_K_L | 3 | 36.15 GB| 38.65 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K | | [platypus2-70b-instruct.ggmlv3.q3_K_M.bin](https://huggingface.co/TheBloke/Platypus2-70B-Instruct-GGML/blob/main/platypus2-70b-instruct.ggmlv3.q3_K_M.bin) | q3_K_M | 3 | 33.04 GB| 35.54 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K | | [platypus2-70b-instruct.ggmlv3.q3_K_S.bin](https://huggingface.co/TheBloke/Platypus2-70B-Instruct-GGML/blob/main/platypus2-70b-instruct.ggmlv3.q3_K_S.bin) | q3_K_S | 3 | 29.75 GB| 32.25 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors | | [platypus2-70b-instruct.ggmlv3.q4_0.bin](https://huggingface.co/TheBloke/Platypus2-70B-Instruct-GGML/blob/main/platypus2-70b-instruct.ggmlv3.q4_0.bin) | q4_0 | 4 | 38.87 GB| 41.37 GB | Original quant method, 4-bit. | | [platypus2-70b-instruct.ggmlv3.q4_1.bin](https://huggingface.co/TheBloke/Platypus2-70B-Instruct-GGML/blob/main/platypus2-70b-instruct.ggmlv3.q4_1.bin) | q4_1 | 4 | 43.17 GB| 45.67 GB | Original quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. | | [platypus2-70b-instruct.ggmlv3.q4_K_M.bin](https://huggingface.co/TheBloke/Platypus2-70B-Instruct-GGML/blob/main/platypus2-70b-instruct.ggmlv3.q4_K_M.bin) | q4_K_M | 4 | 41.38 GB| 43.88 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K | | [platypus2-70b-instruct.ggmlv3.q4_K_S.bin](https://huggingface.co/TheBloke/Platypus2-70B-Instruct-GGML/blob/main/platypus2-70b-instruct.ggmlv3.q4_K_S.bin) | q4_K_S | 4 | 38.87 GB| 41.37 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors | | [platypus2-70b-instruct.ggmlv3.q5_0.bin](https://huggingface.co/TheBloke/Platypus2-70B-Instruct-GGML/blob/main/platypus2-70b-instruct.ggmlv3.q5_0.bin) | q5_0 | 5 | 47.46 GB| 49.96 GB | Original quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. | | [platypus2-70b-instruct.ggmlv3.q5_K_M.bin](https://huggingface.co/TheBloke/Platypus2-70B-Instruct-GGML/blob/main/platypus2-70b-instruct.ggmlv3.q5_K_M.bin) | q5_K_M | 5 | 48.75 GB| 51.25 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K | | [platypus2-70b-instruct.ggmlv3.q5_K_S.bin](https://huggingface.co/TheBloke/Platypus2-70B-Instruct-GGML/blob/main/platypus2-70b-instruct.ggmlv3.q5_K_S.bin) | q5_K_S | 5 | 47.46 GB| 49.96 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors | | platypus2-70b-instruct.ggmlv3.q5_1.bin | q5_1 | 5 | 51.76 GB | 54.26 GB | Original quant method, 5-bit. Higher accuracy, slower inference than q5_0. | | platypus2-70b-instruct.ggmlv3.q6_K.bin | q6_K | 6 | 56.59 GB | 59.09 GB | New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors | | platypus2-70b-instruct.ggmlv3.q8_0.bin | q8_0 | 8 | 73.23 GB | 75.73 GB | Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. | **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead. ### q5_1, q6_K and q8_0 files require expansion from archive **Note:** HF does not support uploading files larger than 50GB. Therefore I have uploaded the q6_K and q8_0 files as multi-part ZIP files. They are not compressed, they are just for storing a .bin file in two parts.
Click for instructions regarding q5_1, q6_K and q8_0 files ### q5_1 Please download: * `platypus2-70b-instruct.ggmlv3.q5_1.zip` * `platypus2-70b-instruct.ggmlv3.q5_1.z01` ### q6_K Please download: * `platypus2-70b-instruct.ggmlv3.q6_K.zip` * `platypus2-70b-instruct.ggmlv3.q6_K.z01` ### q8_0 Please download: * `platypus2-70b-instruct.ggmlv3.q8_0.zip` * `platypus2-70b-instruct.ggmlv3.q8_0.z01` Then extract the .zip archive. This will will expand both parts automatically. On Linux I found I had to use `7zip` - the basic `unzip` tool did not work. Example: ``` sudo apt update -y && sudo apt install 7zip 7zz x platypus2-70b-instruct.ggmlv3.q6_K.zip ```
## How to run in `llama.cpp` I use the following command line; adjust for your tastes and needs: ``` ./main -t 10 -ngl 40 -gqa 8 -m platypus2-70b-instruct.ggmlv3.q4_K_M.bin --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\nWrite a story about llamas\n\n### Response:" ``` Change `-t 10` to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use `-t 8`. If you are fully offloading the model to GPU, use `-t 1` Change `-ngl 40` to the number of GPU layers you have VRAM for. Use `-ngl 100` to offload all layers to VRAM - if you have a 48GB card, or 2 x 24GB, or similar. Otherwise you can partially offload as many as you have VRAM for, on one or more GPUs. If you want to have a chat-style conversation, replace the `-p ` argument with `-i -ins` Remember the `-gqa 8` argument, required for Llama 70B models. Change `-c 4096` to the desired sequence length for this model. For models that use RoPE, add `--rope-freq-base 10000 --rope-freq-scale 0.5` for doubled context, or `--rope-freq-base 10000 --rope-freq-scale 0.25` for 4x context. For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md) ## How to run in `text-generation-webui` Further instructions here: [text-generation-webui/docs/llama.cpp-models.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp-models.md). ## 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! 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**: Luke from CarbonQuill, Aemon Algiz. **Patreon special mentions**: Willem Michiel, Ajan Kanaga, Cory Kujawski, Alps Aficionado, Nikolai Manek, Jonathan Leane, Stanislav Ovsiannikov, Michael Levine, Luke Pendergrass, Sid, K, Gabriel Tamborski, Clay Pascal, Kalila, William Sang, Will Dee, Pieter, Nathan LeClaire, ya boyyy, David Flickinger, vamX, Derek Yates, Fen Risland, Jeffrey Morgan, webtim, Daniel P. Andersen, Chadd, Edmond Seymore, Pyrater, Olusegun Samson, Lone Striker, biorpg, alfie_i, Mano Prime, Chris Smitley, Dave, zynix, Trenton Dambrowitz, Johann-Peter Hartmann, Magnesian, Spencer Kim, John Detwiler, Iucharbius, Gabriel Puliatti, LangChain4j, Luke @flexchar, Vadim, Rishabh Srivastava, Preetika Verma, Ai Maven, Femi Adebogun, WelcomeToTheClub, Leonard Tan, Imad Khwaja, Steven Wood, Stefan Sabev, Sebastain Graf, usrbinkat, Dan Guido, Sam, Eugene Pentland, Mandus, transmissions 11, Slarti, Karl Bernard, Spiking Neurons AB, Artur Olbinski, Joseph William Delisle, ReadyPlayerEmma, Olakabola, Asp the Wyvern, Space Cruiser, Matthew Berman, Randy H, subjectnull, danny, John Villwock, Illia Dulskyi, Rainer Wilmers, theTransient, Pierre Kircher, Alexandros Triantafyllidis, Viktor Bowallius, terasurfer, Deep Realms, SuperWojo, senxiiz, Oscar Rangel, Alex, Stephen Murray, Talal Aujan, Raven Klaugh, Sean Connelly, Raymond Fosdick, Fred von Graf, chris gileta, Junyu Yang, Elle Thank you to all my generous patrons and donaters! # Original model card: garage-bAInd's Platypus2 70B Instruct # Platypus2-70B-instruct Platypus-70B-instruct is a merge of [`garage-bAInd/Platypus2-70B`](https://huggingface.co/garage-bAInd/Platypus2-70B) and [`upstage/Llama-2-70b-instruct-v2`](https://huggingface.co/upstage/Llama-2-70b-instruct-v2). ![Platty](./Best_Platty_small.jpeg) ### Benchmark Metrics | Metric | Value | |-----------------------|-------| | MMLU (5-shot) | 70.48 | | ARC (25-shot) | 71.84 | | HellaSwag (10-shot) | 87.94 | | TruthfulQA (0-shot) | 62.26 | | Avg. | 73.13 | We use state-of-the-art [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) to run the benchmark tests above, using the same version as the HuggingFace LLM Leaderboard. Please see below for detailed instructions on reproducing benchmark results. ### Model Details * **Trained by**: **Platypus2-70B** trained by Cole Hunter & Ariel Lee; **Llama-2-70b-instruct** trained by upstageAI * **Model type:** **Platypus2-70B-instruct** is an auto-regressive language model based on the LLaMA 2 transformer architecture. * **Language(s)**: English * **License**: Non-Commercial Creative Commons license ([CC BY-NC-4.0](https://creativecommons.org/licenses/by-nc/4.0/)) ### Prompt Template ``` ### Instruction: (without the <>) ### Response: ``` ### Training Dataset STEM and logic based dataset [`garage-bAInd/OpenPlatypus`](https://huggingface.co/datasets/garage-bAInd/OpenPlatypus) [COMING SOON!]. ### Training Procedure `garage-bAInd/Platypus2-70B` was instruction fine-tuned using LoRA on 8 A100 80GB. For training details and inference instructions please see the [Platypus](https://github.com/arielnlee/Platypus) GitHub repo. ### Reproducing Evaluation Results Install LM Evaluation Harness: ``` # clone repository git clone https://github.com/EleutherAI/lm-evaluation-harness.git # change to repo directory cd lm-evaluation-harness # check out the correct commit git checkout b281b0921b636bc36ad05c0b0b0763bd6dd43463 # install pip install -e . ``` Each task was evaluated on a single A100 80GB GPU. ARC: ``` python main.py --model hf-causal-experimental --model_args pretrained=garage-bAInd/Platypus2-70B-instruct --tasks arc_challenge --batch_size 1 --no_cache --write_out --output_path results/Platypus2-70B-instruct/arc_challenge_25shot.json --device cuda --num_fewshot 25 ``` HellaSwag: ``` python main.py --model hf-causal-experimental --model_args pretrained=garage-bAInd/Platypus2-70B-instruct --tasks hellaswag --batch_size 1 --no_cache --write_out --output_path results/Platypus2-70B-instruct/hellaswag_10shot.json --device cuda --num_fewshot 10 ``` MMLU: ``` python main.py --model hf-causal-experimental --model_args pretrained=garage-bAInd/Platypus2-70B-instruct --tasks hendrycksTest-* --batch_size 1 --no_cache --write_out --output_path results/Platypus2-70B-instruct/mmlu_5shot.json --device cuda --num_fewshot 5 ``` TruthfulQA: ``` python main.py --model hf-causal-experimental --model_args pretrained=garage-bAInd/Platypus2-70B-instruct --tasks truthfulqa_mc --batch_size 1 --no_cache --write_out --output_path results/Platypus2-70B-instruct/truthfulqa_0shot.json --device cuda ``` ### Limitations and bias Llama 2 and fine-tuned variants are a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Llama 2 and any fine-tuned varient's potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 2 variants, developers should perform safety testing and tuning tailored to their specific applications of the model. Please see the Responsible Use Guide available at https://ai.meta.com/llama/responsible-use-guide/ ### Citations ```bibtex @misc{touvron2023llama, title={Llama 2: Open Foundation and Fine-Tuned Chat Models}, author={Hugo Touvron and Louis Martin and Kevin Stone and Peter Albert and Amjad Almahairi and Yasmine Babaei and Nikolay Bashlykov and Soumya Batra and Prajjwal Bhargava and Shruti Bhosale and Dan Bikel and Lukas Blecher and Cristian Canton Ferrer and Moya Chen and Guillem Cucurull and David Esiobu and Jude Fernandes and Jeremy Fu and Wenyin Fu and Brian Fuller and Cynthia Gao and Vedanuj Goswami and Naman Goyal and Anthony Hartshorn and Saghar Hosseini and Rui Hou and Hakan Inan and Marcin Kardas and Viktor Kerkez and Madian Khabsa and Isabel Kloumann and Artem Korenev and Punit Singh Koura and Marie-Anne Lachaux and Thibaut Lavril and Jenya Lee and Diana Liskovich and Yinghai Lu and Yuning Mao and Xavier Martinet and Todor Mihaylov and Pushkar Mishra and Igor Molybog and Yixin Nie and Andrew Poulton and Jeremy Reizenstein and Rashi Rungta and Kalyan Saladi and Alan Schelten and Ruan Silva and Eric Michael Smith and Ranjan Subramanian and Xiaoqing Ellen Tan and Binh Tang and Ross Taylor and Adina Williams and Jian Xiang Kuan and Puxin Xu and Zheng Yan and Iliyan Zarov and Yuchen Zhang and Angela Fan and Melanie Kambadur and Sharan Narang and Aurelien Rodriguez and Robert Stojnic and Sergey Edunov and Thomas Scialom}, year={2023} } ``` ```bibtex @article{hu2021lora, title={LoRA: Low-Rank Adaptation of Large Language Models}, author={Hu, Edward J. and Shen, Yelong and Wallis, Phillip and Allen-Zhu, Zeyuan and Li, Yuanzhi and Wang, Shean and Chen, Weizhu}, journal={CoRR}, year={2021} } ```